EP3676734A1 - Systems and methods for process design and analysis - Google Patents
Systems and methods for process design and analysisInfo
- Publication number
- EP3676734A1 EP3676734A1 EP18851799.9A EP18851799A EP3676734A1 EP 3676734 A1 EP3676734 A1 EP 3676734A1 EP 18851799 A EP18851799 A EP 18851799A EP 3676734 A1 EP3676734 A1 EP 3676734A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- parameterized
- processes
- resource
- storage medium
- readable storage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
Definitions
- the present disclosure relates generally to systems and methods for process design and analysis of processes that result in analytical information or products.
- Multi-stage processes are relied upon in the research and manufacture of a wide range of products including biologies, pharmaceuticals, mechanical devices, electrical devices, and food, to name a few examples.
- Such processes typically have many sources of variation. While most of these sources are minor and may be ignored, the dominant sources of variation may adversely affect the efficiency or even viability of such processes. If identified, however, resources to remove these dominant sources of variation can be engaged and, potentially, such dominant sources of variation can be removed, minimized or contained.
- a process may be considered stabilized. When a process is stable, its variation should remain within a known set of limits. That is, at least, until another assignable source of variation occurs.
- a laundry soap packaging line may be designed to fill each laundry soap box with fourteen ounces of laundry soap. Some boxes will have slightly more than fourteen ounces, and some will have slightly less.
- the data will demonstrate a distribution of net weights. If the production process, its inputs, or its environment (for example, the machines on the line) change, the distribution of the data will change. For example, as the cams and pulleys of the machinery wear, the laundry soap filling machine may put more than the specified amount of soap into each box. Although this might benefit the customer, from the manufacturer's point of view, this is wasteful and increases the cost of production.
- ENNs electronic lab notebooks
- LTMS Lab information management systems
- the disclosed embodiments address the need in the art for improved systems and methods for stabilization of processes that result in analytical information or products.
- product refers to, for example, tangible products such as materials, compositions, ingredients, medicines, bulk materials, and the like; and the term “analytical information” refers to, for example, categorical or quantitative data describing measurements of materials, equipment, or process settings.
- the disclosed systems and methods advantageously and uniquely reduce experimental noise and collaborative friction from research and development to manufacturing.
- the disclosed systems and methods facilitate visualization of data against evolving maps of experimental processes to highlight quality issues and opportunities, expose trends and causal relationships across time, experiments and teams, stimulate collaborative improvement of experimental and process quality, and stabilize processes.
- the disclosed systems and methods maintain a hypergraph data store which has one or more versions on one or more processes.
- a version of a process comprises a hypergraph with nodes, for stages of the process, and edges.
- Stages have parameterized resource inputs associated with stage input properties, and input specification limits.
- Stages have resource outputs with output properties and output specification limits.
- Edges link the outputs of nodes to the inputs of other nodes, representing the intended or actual transfer of resources from output to input.
- the disclosed systems and methods also maintain a run data store having a plurality of process runs.
- Each process run identifies a process version, values for the inputs of a first node in the hypergraph of the corresponding process, their input properties, the resource outputs of the first node, and obtained values of output properties of the resource outputs.
- a query identifies one or more inputs and/or outputs present in the run data store, they are formatted for analysis.
- Embodiment 1 - steps (edges) connecting resources (nodes).
- One aspect of the present disclosure provides a non-transitory computer readable storage medium for providing process design and analysis of one or more processes. Each process in the one or more processes results in a respective product or analytical information.
- the non-transitory computer readable storage medium stores instructions, which when executed by a first device, cause the first device to maintain a hypergraph data store comprising, for each respective process in the one or more processes, a respective plurality of versions of the respective process.
- Each respective version comprises a hypergraph comprising a plurality of nodes connected by edges in a plurality of edges.
- Each respective edge in the plurality of edges comprises a process stage label representing a respective stage in the corresponding process, and is associated with (i) a set of parameterized resource inputs to the respective stage in the corresponding process, wherein at least one parameterized resource input in the set of parameterized resource inputs is associated with one or more input properties, the one or more input properties including one or more input specification limits, and (ii) a set of parameterized resource outputs to the respective stage in the corresponding process, wherein at least one parameterized resource output in the set of parameterized resource outputs is associated with one or more output properties, the one or more output properties including one or more corresponding output specification limits.
- Each respective node in the plurality of nodes specifies that the set of parameterized resource outputs of an edge in the plurality of nodes is included in the set of parameterized resource inputs of at least one other edge in the plurality of edges.
- the first device further maintains a run data store.
- the run data store comprises a plurality of process runs.
- Each process run comprises (i) an identification of a version in the plurality of versions for a process in the one or more processes, (ii) values for the respective set of parameterized resource inputs of a first edge in the hypergraph of the respective version and their associated input properties, (iii) the respective set of parameterized resource outputs of the first edge in the hypergraph of the respective version, and (iv) obtained values of at least one output property of a parameterized resource output in the respective set of parameterized resource outputs of the first edge in the hypergraph of the respective version.
- the first device further maintains a statistics module that, responsive to receiving a query that identifies one or more first parameterized resource inputs and/or parameterized resource outputs present in one or more process runs in the run data store, formats the one or more first parameterized resource inputs and/or parameterized resource outputs for analysis.
- the query further identifies one or more second parameterized resource inputs and/or parameterized resource outputs present in one or more runs in the run data store.
- the instructions which when executed by the first device, further cause the first device to: correlate the one or more first parameterized resource inputs and/or parameterized resource outputs and the one or more second parameterized resource inputs and/or parameterized resource outputs; and format, for presentation, a numerical measure of the correlation.
- the instructions which when executed by the first device, further cause the first device to: export the one or more first parameterized resource inputs and/or parameterized resource outputs for analysis to a second device.
- the instructions which when executed by the first device, further cause the first device to: maintain a process evaluation module that generates an alert in the form of a computer data transmission when an obtained value for an output property of a parameterized resource output in a set of parameterized resource outputs for a process run in the plurality of process runs is outside the output specification limit.
- a first version and a second version in a respective plurality of versions for a process in the one or more processes differ from each other in a number of nodes, a process stage label of an edge, a parameterized resource input in a set of parameterized resource inputs, or a parameterized resource output in a set of parameterized resource outputs.
- the query further identifies one or more second parameterized resource inputs and/or parameterized resource outputs present in one or more runs in the run data store.
- the statistics module further identifies a correlation between (i) the one or more first parameterized resource inputs and/or parameterized resource outputs and (ii) the one or more second parameterized resource inputs and/or parameterized resource outputs present in one or more process runs in the run data store from among all the parameterized resource inputs and/or parameterized resource outputs present in the run data store using a multivariate analysis technique.
- the multivariate analysis comprises a feature selection technique (e.g., least angle regression, stepwise regression, etc.)
- the statistics module further provides suggested values for the one or more second parameterized resource inputs for an additional process run of a first process in the one or more processes, not present in the run data store, based on a prediction that the suggested values for the one or more second parameterized resource inputs will alter a numerical attribute of the one or more process runs.
- the numerical attribute is a reduction in variance in the one or more first parameterized resource inputs.
- the query further identifies one or more third parameterized resource inputs and/or parameterized resource outputs present in one or more runs in the run data store, and the numerical attribute is a confidence in a correlation between the one or more first parameterized resource inputs and/or
- parameterized resource outputs and the one or more third parameterized resource inputs and/or parameterized resource outputs.
- the one or more processes is a plurality of processes and the correlation is identified from process runs in a subset of the plurality of processes. In some embodiments, the one or more processes is a plurality of processes and the correlation is identified from process runs in a single process in the plurality of processes. In some embodiments, the one or more processes is a plurality of processes and the query further identifies a subset of the plurality of processes whose process runs are to be formatted by the statistics module.
- the one or more processes is a plurality of processes and the query further identifies a single process in the plurality of processes whose process runs are to be formatted by the statistics module.
- the query further identifies a subset of process runs in the one or more processes.
- the statistics module further identifies a correlation between (i) a first set comprising one or more process runs in the run data store and (ii) a second set comprising one or more process runs in the run data store, wherein process runs in the second set are not in the first set.
- the correlation is computed across a plurality of parameterized resource inputs and/or parameterized resource outputs present in the first and second sets.
- the set of parameterized resource inputs for an edge in the plurality of edges of a hypergraph for a process version in the respective plurality of process versions comprises a first and second parameterized resource input, the first parameterized resource input specifying a first resource and is associated with a first input property, and the second parameterized resource input specifying a second resource and is associated with a second input property, where the first input property is different than the second input property.
- the first input property is a viscosity value, a purity value, composition value, a temperature value, a weight value, a mass value, a volume value, or a batch identifier of the first resource.
- the first resource is a single resource or a composite resource.
- the set of parameterized resource inputs for a first edge in the plurality of nodes of a hypergraph of a process version in the respective plurality of process versions comprises a first parameterized resource input, and the first
- parameterized resource input specifies a process condition associated with the
- the process condition comprises a temperature, an exposure time, a mixing time, a type of equipment, or a batch identifier.
- the instructions further cause the first device to execute a data driver for a respective process in the one or more processes, the data driver including: instructions for receiving a dataset for the respective process, instructions for parsing the dataset to thereby obtain (i) an identification of a process run in the run data store and (ii) output property values associated with the respective set of parameterized resource outputs of a first edge in the hypergraph of the respective process for the process run, and instructions for populating the output property values of parameterized resource outputs of the first edge in the run data store with the parsed values.
- the corresponding output specification limit comprises an upper limit and a lower limit for the corresponding parameterized resource output.
- the corresponding output specification limit comprises an enumerated list of allowable types.
- the one or more processes is a plurality of processes and a first process in the plurality of processes results in a first product and a second process in the plurality of processes results in a second product, where the first product is different than the second product.
- the run data store further comprises a genealogical graph showing a relationship between (i) versions of a single process in the plurality of versions of a process or (ii) versions of two or more processes in the respective plurality of versions of two or more processes.
- Another aspect of the present disclosure provides a computer system, comprising: one or more processors, memory, and one or more programs stored in the memory for execution by the one or more processors.
- the one or more programs comprise instructions for maintaining a hypergraph data store comprising, for each respective process in a set of one or more processes, each process in the set of one or more processes resulting in a respective product or analytical information, a respective plurality of versions of the respective process.
- Each respective version comprises a hypergraph comprising a plurality of nodes connected by edges in a plurality of edges.
- Each respective edge in the plurality of edges comprising a process stage label representing a respective stage in the corresponding process, and associated with (i) a set of parameterized resource inputs to the respective stage in the corresponding process, where at least one parameterized resource input in the set of parameterized resource inputs is associated with one or more input properties, the one or more input properties including one or more input specification limits, and (ii) a set of parameterized resource outputs to the respective stage in the corresponding process, where at least one parameterized resource output in the set of parameterized resource outputs is associated with one or more output properties, the one or more output properties including one or more corresponding output specification limits.
- Each respective node in the plurality of nodes specifies that the set of parameterized resource outputs of an edge in the plurality of edges is included in the set of parameterized resource inputs of at least one other edge in the plurality of edges.
- a run data store is maintained.
- the run data store comprises a plurality of process runs, each process run comprising (i) an identification of a version in the plurality of versions for a process in the one or more processes, (ii) values for the respective set of parameterized resource inputs of a first edge in the hypergraph of the respective version and their associated input properties, (iii) the respective set of parameterized resource outputs of the first edge in the hypergraph of the respective version, and (iv) obtained values of at least one output property of a parameterized resource output in the respective set of parameterized resource outputs of each edge in the hypergraph of the respective version.
- a statistics module is maintained that, responsive to receiving a query that identifies one or more first parameterized resource inputs and/or parameterized resource outputs present in one or more process runs in the run data store, formats the one or more first parameterized inputs and/or parameterized outputs for analysis.
- Embodiment 2 - steps (edges) connecting by generic entities (nodes) with resource lists associated with those nodes.
- Another aspect of the present disclosure provides a non-transitory computer readable storage medium for providing process design and analysis of one or more processes. Each process in the one or more processes results in a respective product or analytical information, the non-transitory computer readable storage medium stores instructions, which when executed by a first device, cause the first device to maintain a hypergraph data store comprising, for each respective process in the one or more processes, a respective plurality of versions of the respective process. Each respective version comprises a hypergraph comprising a plurality of edges connected by nodes in a plurality of nodes.
- Each respective edge in the plurality of edges comprises a process stage label representing a respective stage in the corresponding process, and is associated with one or more inputs and at least one output.
- Each respective node in the plurality of nodes is associated with a corresponding set of parameterized resources and specifies that the corresponding set of parameterized resources form an output of the at least one output of a first edge in the plurality of edges and also forms an input of the one or more inputs of at least one other edge in the plurality of edges.
- At least one parameterized resource in the set of parameterized resources is associated with one or more properties.
- the one or more properties include one or more corresponding specification limits.
- a run data store is maintained in such embodiments.
- the run data store comprises a plurality of process runs.
- Each process run comprises (i) an identification of a version in the plurality of versions for a process in the one or more processes, and (ii) values for the respective set of parameterized resources corresponding to at least one of the first output of the first node or the first input of the at least one other node of a first node in the hypergraph of the respective version and their associated one or more properties.
- the values of a resource associated with the output side of an edge may be different than the values of a resource associated with the input side of the same edge.
- a statistics module is maintained in such embodiments that, responsive to receiving a query that identifies one or more first parameterized resources present in one or more process runs in the run data store, formats the one or more first parameterized resources for analysis.
- the query further identifies one or more second parameterized resources present in one or more runs in the run data store.
- the instructions which when executed by the first device, further cause the first device to: correlate the one or more first parameterized resources and the one or more second parameterized resources and format, for presentation, a numerical measure of the correlation.
- the instructions, which when executed by the first device, further cause the first device to export the one or more first parameterized resources for analysis to a second device.
- the instructions, which when executed by the first device further cause the first device to: maintain a process evaluation module that generates an alert in the form of a computer data transmission when an obtained value for a property of a parameterized resource in a set of parameterized resources for a process run in the plurality of process runs is outside the corresponding specification limit.
- a first version and a second version in a respective plurality of versions for a process in the one or more processes differ from each other in a number of nodes, a process stage label of a node, or a parameterized resource in a set of parameterized resources.
- the query further identifies one or more second parameterized resources present in one or more runs in the run data store
- the statistics module further identifies a correlation between (i) the one or more first parameterized resources and (ii) the one or more second parameterized resources present in one or more process runs in the run data store from among all the parameterized resources present in the run data store using a multivariate analysis technique (e.g., using a feature selection technique such as least angle regression, stepwise regression, etc.).
- the statistics module further provides suggested values for one or more second
- the numerical attribute is a reduction in a variance in the one or more first parameterized resources exhibited across the one or more process runs.
- the query further identifies one or more third parameterized resources present in one or more runs in the run data store, and the numerical attribute is a confidence in a correlation between the one or more first parameterized inputs resources and the one or more third parameterized resources.
- the one or more processes is a plurality of processes and the correlation is identified from process runs in a subset of the plurality of processes.
- the one or more processes is a plurality of processes and the correlation is identified from process runs in a single process in the plurality of processes.
- the one or more processes is a plurality of processes and the query further identifies a subset of the plurality of processes whose process runs are to be formatted by the statistics module. In some embodiments, the one or more processes is a plurality of processes and the query further identifies a single process in the plurality of processes whose process runs are to be formatted by the statistics module. In some embodiments, the query further identifies a subset of process runs in the one or more processes.
- the statistics module further identifies a correlation between (i) a first set comprising one or more process runs in the run data store and (ii) a second set comprising one or more process runs in the run data store, wherein process runs in the second set are not in the first set.
- the correlation is computed across a plurality of parameterized resources present in the first and second sets.
- the set of parameterized resources for a node in the plurality of nodes of a hypergraph for a process version in the respective plurality of process versions comprises a first and second parameterized resource, the first parameterized resource specifies a first resource and is associated with a first property, and the second parameterized resource specifies a second resource and is associated with a second property, where the first property is different than the second property.
- the first property is a viscosity value, a purity value, composition value, a temperature value, a weight value, a mass value, a volume value, or a batch identifier of the first resource.
- the first resource is a single resource or a composite resource.
- the set of parameterized resources for a first node in the plurality of nodes of a hypergraph of a process version in the respective plurality of process versions comprises a first parameterized resource
- the first parameterized resource specifies a process condition associated with the corresponding stage of the process associated with the corresponding first edge.
- the process condition comprises a temperature, an exposure time, a mixing time, a type of equipment, or a batch identifier.
- the instructions further cause the first device to execute a data driver for a respective process in the one or more processes.
- the data driver includes instructions for receiving a dataset for the respective process, instructions for parsing the dataset to thereby obtain (i) an identification of a process run in the run data store and (ii) property values associated with the respective set of parameterized resources of a first node in the hypergraph of the respective process for the process run, and instructions for populating the property values of parameterized resources of the corresponding first node in the run data store with the parsed values.
- the corresponding specification limit comprises an upper limit and a lower limit for the corresponding parameterized resource.
- the corresponding specification limit comprises an enumerated list of allowable types.
- the one or more processes is a plurality of processes and a first process in the plurality of processes results in a first product and a second process in the plurality of processes results in a second product, wherein the first product is different than the second product.
- the run data store further comprises a genealogical graph showing a relationship between (i) versions of a single process in the plurality of versions of a process or (ii) versions of two or more processes in the respective plurality of versions of two or more processes.
- the one or more programs comprise instructions for maintaining a hypergraph data store.
- the hypergraph data store comprises, for each respective process in a set of one or more processes, each process in the set of one or more processes resulting in a respective product or analytical information, a respective plurality of versions of the respective process.
- Each such respective version comprise a hypergraph comprising a plurality of nodes connected by edges in a plurality of edges, each respective edge in the plurality of edges comprising a process stage label representing a respective stage in the corresponding process, and associated with one or more inputs and at least one output, and each respective node in the plurality of nodes is associated with a corresponding set of parameterized resources and specifies that the corresponding set of parametrized resources form an output of the at least one output of a first edge in the plurality of edges and also forms an input of the one or more inputs of at least one other edge in the plurality of edges, and wherein at least one parameterized resource in the set of parameterized resources is associated with one or more properties, the one or more properties including one or more corresponding specification limits.
- a run data store is further maintained.
- the run data store comprises a plurality of process runs.
- Each process run comprises (i) an identification of a version in the plurality of versions for a process in the one or more processes, and (ii) values for the respective set of parameterized resources corresponding to at least one of the first output of the first node or the first input of the at least one other node of a first node in the hypergraph of the respective version and their associated one or more properties.
- the values of a resource associated with the output side of an edge may be different than the values of a resource associated with the input side of the same edge.
- a statistics module is maintained that, responsive to receiving a query that identifies one or more first parameterized resources present in one or more process runs in the run data store, formats the one or more first parameterized resources for analysis.
- Embodiment 3 - steps (edges) connected by generic entities (nodes) with no associated lists.
- Another aspect of the present disclosure provides a non-transitory computer readable storage medium for providing process design and analysis of one or more processes. Each process in the one or more processes results in a respective product or analytical information.
- the non-transitory computer readable storage medium stores instructions, which when executed by a first device, cause the first device to maintain a hypergraph data store comprising, for each respective process in the one or more processes, a respective plurality of versions of the respective process.
- Each respective version comprises a hypergraph comprising a plurality of edges connected by nodes in a plurality of nodes.
- Each respective edge in the plurality of edges comprises a process stage label representing a respective stage in the corresponding process, and is associated with one or more inputs and at least one output.
- Each respective node in the plurality of nodes forms an output of the at least one output of a first edge in the plurality of edges and also forms an input of the one or more inputs of at least one other edge in the plurality of edges.
- a run data store is maintained.
- the run data store comprises a plurality of process runs.
- Each process run comprises an identification of a version in the plurality of versions for a process in the one or more processes.
- a statistics module is maintained that, responsive to receiving a query that identifies one or more first parameterized resources present in one or more process runs in the run data store, formats the one or more first parameterized resources for analysis.
- the method further comprises associating each respective node in the plurality of nodes with a corresponding set of parameterized resources and specifying that the corresponding set of parameterized resources form an output of the at least one output of a first edge in the plurality of edges and also forms an input of the one or more inputs of at least one other edge in the plurality of edges.
- At least one parameterized resource in the set of parameterized resources is associated with one or more properties, the one or more properties including one or more corresponding specification limits.
- the run data store also comprises, for each respective process run in the plurality of process runs, values for the respective set of parameterized resources corresponding to at least one of the first output of the first node or the first input of the at least one other node of a first node in the hypergraph of the respective version and their associated one or more properties.
- the query further identifies one or more second parameterized resources present in one or more runs in the run data store.
- the instructions which when executed by the first device, further cause the first device to: correlate the one or more first parameterized resources and the one or more second parameterized resources and format, for presentation, a numerical measure of the correlation.
- the instructions which when executed by the first device, further cause the first device to export the one or more first parameterized resources for analysis to a second device.
- the instructions which when executed by the first device, further cause the first device to maintain a process evaluation module that generates an alert in the form of a computer data transmission when an obtained value for a property of a parameterized resource in a set of parameterized resource outputs for a process run in the plurality of process runs is outside the output specification limit.
- a first version and a second version in a respective plurality of versions for a process in the one or more processes differ from each other in a number of nodes, a process stage label of a node, or a parameterized resource in a set of parameterized resources inputs.
- the query further identifies one or more second parameterized resources present in one or more runs in the run data store.
- the statistics module further identifies a correlation between (i) the one or more first parameterized resources and (ii) the one or more second parameterized resources present in one or more process runs in the run data store from among all the parameterized resources present in the run data store using a multivariate analysis technique.
- the multivariate analysis comprises a feature selection technique, such as least angle regression, or stepwise regression.
- the statistics module further provides suggested values for one or more second resources for an additional process run of a first process in the one or more processes, not present in the run data store, based on a prediction that the suggested values for the one or more second resources will alter a numerical attribute of the one or more process runs.
- the numerical attribute is a reduction in a variance in the one or more first parameterized resources exhibited across the one or more process runs.
- the query further identifies one or more third parameterized resources present in one or more runs in the run data store, and the numerical attribute is a confidence in a correlation between the one or more first resources and the one or more third resources.
- the one or more processes is a plurality of processes and the correlation is identified from process runs in a subset of the plurality of processes. In some embodiments, the one or more processes is a plurality of processes and the correlation is identified from process runs in a single process in the plurality of processes. In some embodiments, the one or more processes is a plurality of processes and the query further identifies a subset of the plurality of processes whose process runs are to be formatted by the statistics module In some embodiments, the one or more processes is a plurality of processes and the query further identifies a single process in the plurality of processes whose process runs are to be formatted by the statistics module.
- the query further identifies a subset of process runs in the one or more processes.
- the statistics module further identifies a correlation between (i) a first set comprising one or more process runs in the run data store and (ii) a second set comprising one or more process runs in the run data store, wherein process runs in the second set are not in the first set.
- the correlation is computed across a plurality of parameterized resources present in the first and second sets.
- the set of resources for a node in the plurality of nodes of a hypergraph for a process version in the respective plurality of process versions comprises a first and second parameterized resource, the first parameterized resource specifying a first resource and is associated with a first property, and the second
- the parameterized resource specifying a second resource and is associated with a second property, where the first property is different than the input property.
- the first property is a viscosity value, a purity value, composition value, a temperature value, a weight value, a mass value, a volume value, or a batch identifier of the first resource.
- the first resource is a single resource or a composite resource.
- the set of parameterized resources for a first node in the plurality of nodes of a hypergraph of a process version in the respective plurality of process versions comprises a first parameterized resource, the first parameterized resource specifying a process condition.
- the process condition comprises a temperature, an exposure time, a mixing time, a type of equipment, or a batch identifier.
- the instructions further cause the first device to execute a data driver for a respective process in the one or more processes.
- the data driver includes instructions for receiving a dataset for the respective process, instructions for parsing the dataset to thereby obtain (i) an identification of a process run in the run data store and (ii) property values associated with the respective set of parameterized resources of a first node in the hypergraph of the respective process for the process run, and instructions for populating the property values of parameterized resources of the first node in the run data store with the parsed values.
- the corresponding specification limit comprises an upper limit and a lower limit for the corresponding parameterized resource.
- the corresponding output specification limit comprises an enumerated list of allowable types.
- the one or more processes is a plurality of processes and a first process in the plurality of processes results in a first product and a second process in the plurality of processes results in a second product, wherein the first product is different than the second product.
- the run data store further comprises a genealogical graph showing a relationship between (i) versions of a single process in the plurality of versions of a process or (ii) versions of two or more processes in the respective plurality of versions of two or more processes.
- Another aspect of the present disclosure provides a computer system, comprising one or more processors, memory, and one or more programs stored in the memory for execution by the one or more processors.
- the one or more programs comprise instructions for maintaining a hypergraph data store comprising, for each respective process in a set of one or more processes, each process in the set of one or more processes resulting in a respective product or analytical information, a respective plurality of versions of the respective process.
- Each such respective version comprises a hypergraph comprising a plurality of edges connected by nodes in a plurality of nodes.
- Each respective edge in the plurality of edges comprises a process stage label representing a respective stage in the corresponding process, and is associated with one or more inputs and at least one output.
- Each respective node in the plurality of nodes forms an output of the at least one output of a first edge in the plurality of edges and also forms an input of the one or more inputs of at least one other edge in the plurality of edges.
- a run data store is maintained.
- the run data store comprises a plurality of process runs.
- Each process run comprises an identification of a version in the plurality of versions for a process in the one or more processes.
- a statistics module is maintained that, responsive to receiving a query that identifies one or more first parameterized resources present in one or more process runs in the run data store, formats the one or more resources for analysis.
- Figure 1 illustrates a system topology in accordance with the present disclosure that includes a device, namely a computer system 200, and a plurality of stages 20 of a process.
- Figure 2 illustrates a computer system in accordance with an embodiment of the present disclosure.
- Figure 3 illustrates a process version in accordance with an embodiment of the present disclosure.
- Figure 4 illustrates a run data store in accordance with an embodiment of the present disclosure.
- Figure 5 illustrates a process evaluation module in accordance with an embodiment of the present disclosure.
- Figures 6A, 6B, 6C, 6D, and 6E collectively illustrate a flow chart providing process design and analysis of one or more processes in which steps (edges) connect resources (nodes) in accordance with an embodiment of the present disclosure.
- Figure 7 illustrates a hypergraph comprising a plurality of nodes connected by edges in which a fermenter setup stage is highlighted in accordance with an embodiment of the present disclosure.
- Figure 8 illustrates the hypergraph of Figure 7 in which a grow inoculum stage is highlighted in accordance with an embodiment of the present disclosure.
- Figure 9 illustrates the hypergraph of Figure 7 in which a inoculate fermenter stage is highlighted in accordance with an embodiment of the present disclosure.
- Figure 10 illustrates the hypergraph of Figure 7 in which a fed-batch fermentation stage is highlighted in accordance with an embodiment of the present disclosure.
- Figure 11 illustrates the hypergraph of Figure 7 in which a new stage is being added to the hypergraph of Figure 7 in accordance with an embodiment of the present disclosure.
- Figure 12 illustrates the hypergraph of Figure 1 1 in which a DW Assay stage and Off-Gas Assay stage are added to the hypergraph of Figure 7 in accordance with an embodiment of the present disclosure.
- Figure 13 illustrates the hypergraph of Figure 12 in which a new group of stages is added to the hypergraph of Figure 7 in accordance with an embodiment of the present disclosure.
- Figure 14 illustrates the hypergraph of Figure 13 in which the new group of stages is defined in accordance with an embodiment of the present disclosure.
- Figure 15 illustrates how the new group of stages defined in the hypergraph of Figures 13 and 14 is defined in accordance with an embodiment of the present disclosure.
- Figure 16 illustrates how the new standards prep stage in the new group of stages defined in the hypergraph of Figures 13 and 14 is defined in accordance with an embodiment of the present disclosure.
- Figure 17 illustrates how the new instrument calibration stage in the new group of stages defined in the hypergraph of Figures 13 and 14 is defined in accordance with an embodiment of the present disclosure.
- Figure 18 further illustrates how the new instrument calibration stage in the new group of stages defined in the hypergraph of Figures 13 and 14 is defined in accordance with an embodiment of the present disclosure.
- Figure 19 illustrates how the new run samples stage in the new group of stages defined in the hypergraph of Figures 13 and 14 is defined in accordance with an embodiment of the present disclosure.
- Figure 20 illustrates setting up process runs using the new group of stages defined in the hypergraph of Figures 13 and 14 in accordance with an embodiment of the present disclosure.
- Figure 21 further illustrates setting up process runs using the new group of stages defined in the hypergraph of Figures 13 and 14 in accordance with an embodiment of the present disclosure.
- Figure 22 further illustrates setting up process runs using the new group of stages defined in the hypergraph of Figures 13 and 14 in accordance with an embodiment of the present disclosure.
- Figure 23 further illustrates the raw data for three different process runs of the new run samples stage in the new group of stages defined in the hypergraph of Figures 13 and 14 in accordance with an embodiment of the present disclosure.
- Figure 24 further illustrates selecting to analyze the data illustrated in Figure
- Figure 25 illustrates analysis of the data illustrated in Figure 23 in accordance with an embodiment of the present disclosure.
- Figure 26 illustrates further analysis of the data illustrated in Figure 23 in accordance with an embodiment of the present disclosure.
- Figures 27A, 27B, 27C, 27D, and 27E collectively illustrate a flow chart providing process design and analysis of one or more processes in which steps (edges) are connected by generic entities (nodes) with resource lists associated with those nodes in accordance with another embodiment of the present disclosure.
- Figures 28A, 28B, 28C, 28D, and 28E collectively illustrate a flow chart providing process design and analysis of one or more processes in which steps (edges) are connected by generic entities (nodes) with no associated lists in accordance with another embodiment of the present disclosure.
- first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another.
- a first subject could be termed a second subject, and, similarly, a second subject could be termed a first subject, without departing from the scope of the present disclosure.
- the first subject and the second subject are both subjects, but they are not the same subject.
- the phrase “if it is determined” or “if [a stated condition or event] is detected” may be construed to mean “upon determining” or “in response to determining” or “upon detecting [the stated condition or event]” or “in response to detecting [the stated condition or event],” depending on the context.
- Figure 1 illustrates a process or pipeline having a plurality of stages 20.
- Each respective stage 20 in Figure 1 is illustrated by an exemplary reaction chamber to indicate that a form of material transformation takes place. However, there is no requirement that this material transformation take place in a reaction chamber.
- each stage 20 includes a set of parameterized inputs 308 and a set of parameterized outputs 314. More generally, in some embodiments, each respective stage in the plurality of stages is associated with one or more inputs and at least one output.
- inputs 308 and outputs 314 is provided to computer system 200, possibly over communications network 106.
- a file that includes the parameterized outputs of this stage is stored in a directory associated with this stage.
- a sweeping or monitoring process takes this new file and sends it to computer system 200 where it is uploaded into a corresponding process run stored in the computer system 200.
- inputs 308 or outputs 314 are electronically measured by measuring devices.
- a software component such as a sync engine that runs as a background process (like Google Drive or Dropbox Sync) on any computer attached to an instrument or other component of a stage 20 monitors a synced folder.
- a hardware solution is used to communicate the set of inputs 308 and outputs 314 of the stages 20 of a process.
- data acquisition and transfer is performed by direct interface with instruments or other components of stages 20.
- a BeagleBone black microcontroller http://beagleboard.org/BLACK
- BLACK BeagleBone black microcontroller
- data e.g., values for a set of parameterized resource inputs 310 and/or values for a set of parameterized resource outputs 314 associated with a stage 20 of a process
- data is communicated from the respective stages 20 to the computer system via HTTPS port 443 via HTTP POSTs or representational state transfer.
- computer system 200 can in fact constitute several computers that are linked together in a network or be a virtual machine in a cloud computing context.
- the exemplary topology shown in Figure 1 merely serves to describe the features of an embodiment of the present disclosure in a manner that will be readily understood to one of skill in the art.
- a computer system 200 for providing process design and analysis of one or more processes comprises one or more computers.
- the computer system 200 is represented as a single computer that includes all of the functionality of the computer system 200.
- the functionality of the computer system 200 may be spread across any number of networked computers and/or reside on each of several networked computers and/or by hosted on one or more virtual machines at a remote location accessible across the communications network 106.
- One of skill in the art will appreciate that a wide array of different computer topologies is possible for the computer system 200 and all such topologies are within the scope of the present disclosure.
- the computer system 200 is uniquely structured to record and store data in a computable way with minimal effort, quantitatively search all experimental designs, and data, or any subset thereof, apply real-time statistical analysis, achieve quality by design, update experimental processes and data collection systems, identify meaningful variables via automated critical-to-quality analysis, routinely obtain results that are true and unequivocal, access transparent data and results, make results open and accessible (and securely control access to anyone or any team), build quantitatively and directly on others' designs and results, and unambiguously communicate evidence supporting a conclusion to team members or partners.
- a computer system 200 comprises one or more processing units (CPU's) 274, a network or other communications interface 284, a memory 192 (e.g., random access memory), one or more magnetic disk storage and/or persistent devices 290 optionally accessed by one or more controllers 288, one or more communication busses 112 for interconnecting the aforementioned components, and a power supply 276 for powering the aforementioned components.
- Data in memory 192 can be seamlessly shared with non -volatile memory 290 using known computing techniques such as caching.
- Memory 192 and/or memory 290 can include mass storage that is remotely located with respect to the central processing unit(s) 274.
- memory 192 and/or memory 290 may in fact be hosted on computers that are external to computer system 200 but that can be electronically accessed by the computer system over an Internet, intranet, or other form of network or electronic cable (illustrated as element 106 in Figure 2) using network interface 284.
- the memory 192 of computer system 200 stores:
- a hypergraph data store 204 store comprising, for each respective process 206 in the one or more processes, a respective plurality of versions 208 of the respective process 206;
- each data driver for a respective process in the one or more processes including instructions for receiving a dataset for the respective process and instructions for processing the dataset.
- one or more of the above identified data elements or modules of the computer system 200 are stored in one or more of the previously mentioned memory devices, and correspond to a set of instructions for performing a function described above.
- the above identified data, modules or programs (e.g., sets of instructions) need not be implemented as separate software programs, procedures or modules, and thus various subsets of these modules may be combined or otherwise rearranged in various implementations.
- the memory 192 and/or 290 optionally stores a subset of the modules and data structures identified above.
- the memory 192 and/or 206 stores additional modules and data structures not described above.
- the process version comprises a hypergraph 302.
- the hypergraph 302 comprises a plurality of nodes, is directional, causal, and sequential based.
- each respective node 322 in the plurality of nodes is connected to at least one other node in the plurality of nodes by an edge 304 in a plurality of edges.
- each respective edge 304 in the plurality of edges comprises a process stage label 306 representing a respective stage in the corresponding process.
- each respective node 322 in the plurality of nodes, rather than an edge 304 in the plurality of edges comprises a process stage label 306 representing a respective stage in the corresponding process.
- a node 322 is a complete and self-contained description of a transformative event that can be used to build larger processes. In some embodiments a node 322 is sufficiently general to serve in a wide array of processes, such as chemical processes, life science processes, and food preparation process.
- nodes 322 do not lose their meaning or utility when copied into other process.
- the definition of a particular node 322 does not depend on the definition of another node in a hypergraph 302 in preferred embodiments.
- edges 322 are structured to be associated with data in a unique way, in order to facilitate subsequent data mining and reasoning engines to analyze process runs based on process versions 208.
- each respective edge 304 in the plurality of edges is associated with a set of parameterized resource inputs 308 to the respective stage in the corresponding process.
- At least one parameterized resource input 310 in the set of parameterized resource inputs 308 is associated with one or more input properties 312, the one or more input properties including an input specification limit 314.
- Examples of input properties 312 are the attributes (e.g., measurements, quantities, etc.) of things such as people, equipment, materials, and data.
- There can be multiple input properties for a single parameterized resource input e.g., temperature, flow rate, viscosity, pH, purity, etc.).
- each respective edge 304 in the plurality of edges is also associated with a set of parameterized resource outputs 314 to the respective stage in the corresponding process.
- At least one parameterized resource output 316 in the set of parameterized resource outputs 314 is associated with one or more output properties 318, the one or more output properties including a corresponding output specification limit 320.
- Examples of output properties 318 include attributes (e.g., measurements, quantities, etc.) of things such as people, equipment, materials, and data.
- Figures 17 and 18 illustrate the above concepts.
- Figure 17 illustrates a portion of a hypergraph 302 and illustrates the nodes 322 in the portion of the hypergraph.
- the node "Instrument Calibration" 322-14 is highlighted.
- the set of parameterized resource inputs 308 and the set of parameterized resource outputs 314 for an edge connected to this node are shown on the right side of Figure 17.
- the set of parameterized resource inputs 308 for an edge connected to this node includes sulfuric acid 310-1, column 310-2, citric acid 310-3, glucose 310-4, glycerol 310-5, and UPLC 310-6.
- the exemplary set of parameterized resource inputs 308 illustrates that two of the many possible types of parameterized inputs are (i) compositions (e.g., sulfuric acid, citric acid, glucose, glycerol, etc.) and (ii) type of equipment (e.g., column, ULLC, etc.).
- compositions e.g., sulfuric acid, citric acid, glucose, glycerol, etc.
- type of equipment e.g., column, ULLC, etc.
- the set of parameterized resource outputs 314 for an edge connected to the node "Instrument Calibration" consists of HPLC 316.
- the parameterized resource input 310-3 "citric acid” is associated with one or more input properties 312 including an input specification limit 314.
- one input property for parameterized resource input 310-3 "citric acid” is "pH" 312-3-1 and this property includes an input specification limit 314-3-1.
- the input specification limit 314-3-1 is expressed as a lower limit (pH 3.5), a target limit (pH 4), and an upper limit (pH 4.5).
- concentration 312-3-2 and this property includes an input specification limit 314-3-2.
- the input specification limit 314-3-2 is expressed as a lower limit (9.75 g/L Units), a target limit (10 g/L Units), and an upper limit (10.25 g/L Units).
- each hypergraph 302 includes a plurality of nodes.
- Each respective node 322 in the plurality of nodes specifies that the set of parameterized resource outputs 314 of a source edge 304 in the plurality of edges is included in the set of parameterized resource inputs 308 of at least one other destination edge 304 in the plurality of edges.
- a node specifies that the state of a material, equipment, people or other thing inputted into one edge (destination edge) in a given process is identical to the state of material, equipment, people, or other thing that has been outputted from another edge (source edge) in the hypergraph for that process.
- a node specifies that the state of a material, equipment, people or other thing inputted into a plurality of edges (destination node) is identical in a given process to the state of material, equipment, people, or other thing that has been outputted from another edge (source edge) in the hypergraph for that process.
- a destination edge may be connected to two or more source edges meaning that the input the destination edge includes material, equipment, people or other thing in the same state as it was in the output of the two or more source edges for a given process.
- Process versioning 208 is an advantageous feature of the disclosed systems and methods. For example, when the input or output of a particular edge is identified through correlation analysis across various process runs of a process to be a cause of poor reproducibility of the overall process, additional edges before and after the problematic edge can be added in successive versions of the process and process runs of these new versions of the process can then be executed. Moreover, advantageously, data from older versions and newer versions of the process can be used together in correlation analysis, in some embodiments, across all the process runs of all of the process versions to determine the root cause of the variability or other unfavorable attribute associated with the problematic edge and hereby develop a process version that adequately addresses the problem. In fact, process runs from multiple processes that make similar but not identical products or produce similar but not identical analytical information can be analyzed to identify such problems.
- each edge 304 has inputs (set of parameterized resource inputs 308), and each of these parameterized resource inputs 310 has one or more input properties 312, and each these input properties has input specification limits 314. Further, each edge 304 has one or more parameterized resource outputs (set of
- each of these parameterized resource outputs 316 has one or more output properties 318. Moreover, each of these output properties has output specification limits 320.
- the set of parameterized resource outputs serve as the inputs to other edges and such relationships are denoted by node. Moreover, the set of parameterized resource outputs 314 of a particular edge can serve as the inputs to more than one edge, thus the nodes and edges constitute a hypergraph.
- the set of parameterized inputs 308 to an edge to this node that includes one or more inputs to this node include a description of the fermenter broth and the thermocouple that makes the temperature measurement.
- the thermocouple will include input properties that include its cleanliness state, calibration state and other properties of the thermocouple.
- the set of parameterized outputs of an edge connected to one or more outputs for this node include the temperature of the fermenter broth, and output specification limits for this temperature (e.g., an acceptable range for the temperature).
- thermocouple Another possible parameterized resource output 316 of an edge of the node 322 is the thermocouple itself along with properties 316 of the thermocouple after the temperature has been taken, such as its cleanliness state and calibration state. For each of these properties 316 there is again corresponding output specification limits.
- a destination node 326 includes multiple edges 304, each such edge from a different source node 324.
- the set of parameterized resource outputs 314 for each such edge collectively constitute the set of parameterized resource inputs 308 for the edges leading to the destination node 326.
- the run data store 210 comprises a plurality of process runs. That is to say, when a node of a process is run, actual material lots or pieces of equipment, etc., are obtained and/or used as real world instances of a particular process version 406.
- each process run 402 comprises an identification of a node 406 of an identified 404 process version 208 in the plurality of versions for a process 206 in the one or more processes.
- the process run 402 further comprises values for the respective set of parameterized resource inputs 308 of a first edge 304 in the hypergraph 302 of the respective process version 208 and their associated input properties 312.
- the process run 402 also comprises the respective set of parameterized resource outputs 314 of the first edge 304. Further, for the identified process version 208, the process run 402 also comprises obtained values of at least one output property 318 of a parameterized resource output 316 in the respective set of parameterized resource outputs 314 of the first edge 304 in the hypergraph 302 of the respective process version.
- Figures 19 through 24 illustrate three process runs 402 for a particular process version, with each process run 402 characterized by different conditions (e.g., different amounts for one or more input properties of one or more parameterized inputs to one or more nodes in the hypergraph of the process version).
- run data store 210 includes a genealogical graph 420 comprising one or more process sets 422.
- Each process set 422 comprises the identities 424 of related process versions 424.
- a first process version 404 in a process set 420 and a second process version 404 in the process set 420 have the same hypergraph but an output property, output specification limit, input property, or input specification limit to one of the edges in the hypergraph is different.
- a first process version 404 in a process set 420 and a second process version 404 in the process set 420 have hypergraphs that have all but one, all but two, all but three, or all but four nodes and/or edges in common.
- the process versions in a process set are related to each other in the sense that a process gets refined over time, and various versions of the process are saved as process versions.
- Refinement of a process includes any combination of adding or removing nodes from a hypergraph, adding or removing edges from the hypergraph, adding or removing parameterized resource inputs to one or more edges in the hypergraph, adding or removing parameterized resource outputs to one or more edges in the hypergraph, adding, removing or changing an input property or input specification limit of a parameterized resource input of one or more edges in the hypergraph, and/or adding, removing or changing an output property or output specification limit of a parameterized resource output of one or more edges in the hypergraph.
- the process evaluation module 216 takes advantage of the unique architecture of the disclosed processes. In particular, when assessing whether a parameterized resource output 316 for a particular edge 304 satisfies a particular associated output specification limit 320, it is only necessary to evaluate the values in process runs for the corresponding parameterized resource output of that edge. The inputs and outputs of other edges do not need to be evaluated for this purpose. So it is possible to generate an alert in the form of a computer data transmission when an obtained value for an output property of a
- parameterized resource output in a set of parameterized resource outputs for a run of an edge in a hypergraph for a process version is outside the output specification limit.
- a process evaluation module is organized by process version 502. For each process version, edges 504 for which process alerts are needed are identified. For each such edge 504, one or more parameterized resource outputs 506 to the edge are identified. For each of the one or more parameterized resource outputs, one or more alert values 508 are identified for the parameterized resource outputs. If an alert value is triggered for a property of a parameterized resource output of a particular edge of a particular process version, then a computer data transmission 510 corresponding to the alert is communicated. In some embodiments, the computer data transmission 510 is a message sent to a user interface or a client computer indicating that the alert has been triggered.
- the computer data transmission is in the form of a text message, an E- mail, an SMS message, or an audible alarm.
- the output specification limit 320 of an output property 318 of a parameterized resource output 316 of an edge 304 specifies that output pH should not exceed 7.
- an alert 508 is set up for this output property. If, in a process run 502, the pH of the resource output does in fact exceed 7.0, then a computer data transmission 510 corresponding to this alert is communicated.
- System 48 provides a unique design for processes through unambiguous definition of state ⁇ e.g., the state of edge inputs and edge outputs) at whatever level of resolution needed to achieve the performance goals of a process ⁇ e.g., to satisfactorily stabilize the process).
- states include, for example, the "what” and “how much” for each of the edge inputs and outputs. Examples of "what” can be a piece of equipment, human resource, type material or composition of matter, to name a few examples.
- System 48 advantageously provides a way to unite multiple disparate functional areas (e.g., chemistry, biology, fermentation, analytical, different control systems, etc.) into a seamless process of repeatable material transformations (nodes) that can be versioned and for which the data from process runs can be evaluated using statistical techniques to achieve product control (e.g., identify root causes of unwanted variability).
- functional areas e.g., chemistry, biology, fermentation, analytical, different control systems, etc.
- nodes repeatable material transformations
- the disclosed data structures fully define nodes and edges (their input, their output, and hence the transformation that takes place at each node) without any ambiguity in the pertinent properties of each edge input and each edge output.
- the actual transformation that takes place within a node does not necessarily need to be defined beyond a basic description (stage label) for record keeping and identification purposes.
- process runs in which the inputs of a node and/or edge in a process are varied, are run and the outputs or final product of the process is statistically analyzed in view of these varied inputs to determine if the change in the inputs improves an aspect of the final product of the process (e.g., reproducibility, yield, etc.).
- One benefit of the disclosed systems and methods is that they provide mechanisms to truly understand the dynamics of a process (e.g., how variance in certain edge inputs or properties of edge inputs affect final product) and therefore allows the process to be successfully scaled up in size more easily. Because of the way processes are defined in the disclosed systems and methods, it is possible to find sources of error that cause undesirable results (e.g. bad yield, poor reproducibility, etc.) in defined processes or, for that matter, desirable results. Examples of unwanted error in processes is application dependent and depends, for example on the type of edge input or output, but can be for instance, measurement error or failure to quantify or even identify a relevant property of an edge input or edge output.
- an edge input is sugar
- a measurement error may arise because the process by which the weight of the sugar input to the edge is measured is not sufficiently accurate.
- a relevant property of the sugar may be lot number, because in the particular process, sugar lot number happens to have a profound impact on overall product yield.
- a hypergraph data store 204 is maintained.
- the hypergraph data store 204 comprises, for each respective process 206 of one or more processes, a respective plurality of versions of the respective process.
- Each respective version 208 comprises a hypergraph 302 comprising a plurality of nodes 322 connected by edges 304 in a plurality of edges.
- Each respective node 304 in the plurality of nodes comprises a process stage label representing a respective stage in the corresponding process.
- Figure 7 illustrates a process version 208.
- the process version includes a hypergraph that includes a plurality of nodes 322 corresponding to respective stages of a process (e.g., "Fermenter Prep,” “Fermenter Setup,” “Media Prep,” “Grow Inoculum,” “Innoculate Fermenter,” “Fed-Batch Fermentation,” and “Measure T, Ph, D, DO”).
- concurrency is supported. That is, multiple users, each operating at a different client computer in communication with computer system 200, can view an instance of the process version displayed in Figure 7, make changes to it, and view and analyze data from process runs that make use of it.
- Each edge 304 is associated with a set of parameterized resource inputs 308. At least one parameterized resource input 310 in the set of parameterized resource inputs 308 is associated with one or more input properties 312. The one or more input properties include an input specification limit 314. Each edge 304 is also associated with a set of parameterized resource outputs 314. At least one parameterized resource output 316 in the set of parameterized resource outputs is associated with one or more output properties. The one or more output properties include a corresponding output specification limit.
- Figure 7 illustrates the set of parameterized resource inputs 308 and the set of parameterized resource outputs 314 for an edge connected to node 304-4 "Fermenter Setup.”
- Figure 8 illustrates the set of parameterized resource inputs 308 and the set of parameterized resource outputs 314 for an edge connected to the node 304-3 "Grow Inoculum.”
- Figure 9 illustrates the set of parameterized resource inputs 308 and the set of parameterized resource outputs 314 for an edge connected to the node 304-5 "Inoculate Fermenter.”
- Figure 10 illustrates the set of parameterized resource inputs 308 and the set of parameterized resource outputs 314 for an edge connected to the node 304-6 "Fed-Batch Fermentation.”
- a user can simply click on a node 322 and/or edge 304 to see their inputs and outputs.
- unstructured data in the form of videos, pictures, or comments can be added to nodes 322 and/or edges 304.
- a video showing the proper way to perform a procedure associated with a node can be linked to a node by simply dragging an icon link to the video onto the representation of node 322.
- a video on the proper way perform a fermenter setup can be dragged onto the "Fermenter Setup" node 322-4 of Figure 7.
- Each respective node 322 in the plurality of nodes specifies that the set of parameterized resource outputs of an edge in the plurality of edges is included in the set of parameterized resource inputs of at least one other edge in the plurality of edges.
- Figures 11 and 12 illustrate adding new nodes 322-8 "DW Assay” and 322-9
- FIG. 13 and 14 illustrate adding a group of nodes entitled “HPLC Assay” to the hypergraph.
- the HPLC Assay group is an extension of the existing hypergraph of Figure 7 and includes nodes and edges of this extension.
- HPLC Assay begins with three initial nodes, node 322-10 "Solvent Prep,” node 322-1 1 "Column Prep,” and node 322-12 “Standards Prep.”
- the names of nodes are chosen by a user from a database of allowed node names in order to ensure conformity in node names.
- the names of edge inputs 310 and 316 are also chosen by a user from a database of allowed edge input and output names in order to ensure conformity in edge input and output names.
- the names of edge input properties 312 and edge output properties 318 are also chosen by a user from a database of allowed edge input property names and edge output property names in order to ensure their conformity.
- Figure 17 illustrates the portion of the hypergraph 302 encompassed by "HPLC Assay” after more nodes have been defined in this portion of the hypergraph.
- the node "Instrument Calibration" 304-14 is selected in Figure 17. Accordingly, a set of parameterized resource inputs 308 and the set of parameterized resource outputs 314 for an edge connected to node 304-14 are shown on the right side of Figure 17.
- versions 208 of a process 206 are related to each other.
- each version 208 of a process 604 produces the same product.
- a first version and a second version in a respective plurality of versions for a process differ from each other in some way, such as in a number of nodes, a number of edges, a process stage label of an edge, a parameterized resource input in a set of parameterized resource inputs, a parameterized resource output in a set of parameterized resource outputs, a parameterized resource input specification limit, or a parameterized resource output specification limit, to name some possibilities (604).
- the set of parameterized resource inputs 308 for an edge 304 in the plurality of edges of a hypergraph 302 for a process version 208 in the respective plurality of process versions comprises a first 310-1 and second parameterized resource input 3 10-2.
- the first parameterized resource input specifies a first resource and is associated with a first input property 312-1 (606).
- the second parameterized resource input 310-2 specifies a second resource and is associated with a second input property 312-2.
- the first input property is a viscosity value, a purity value, composition value, a temperature value, a weight value, a mass value, a volume value, or a batch identifier of the first resource (608).
- Figure 7 illustrates.
- An edge connected to node 322-4 "Fermenter Setup" includes in its associated set of parameterized resource inputs 308 a fermenter 310-3 and a waste bottle 310-5 among other resource inputs.
- the fermenter 310-3 is associated with a first input property, such as a size of the fermenter or a fermenter make/model number.
- waste bottle 310-5 is associated with a second input property, such as a size of the waste bottle 310-5 or a waste bottle 310-5 make and model number.
- a resource input 310 is a single resource.
- resources 310-1 through 310-10 are all examples of single resources.
- a resource input 310 is a composite resource. Examples of composite resources include, but are not limited, to mixtures of compositions (e.g., media, broth, etc.) and multi -component equipment.
- the set of parameterized resource inputs 308 for a first edge 304 in the plurality of edges of a hypergraph 302 of a process version 208 in the respective plurality of process versions comprises a first parameterized resource input 310 and this first parameterized resource input specifies a process condition associated with the corresponding stage of the process associated with the first edge 304 (612).
- this process condition is a temperature, an exposure time, a mixing time, a concentration, a type of equipment or a batch identifier (614).
- At least one of the parameterized resource outputs in the set of parameterized resource outputs for the edge is associated with one or more output properties, and the one or more output properties includes a corresponding output specification limit.
- this corresponding output specification limit comprises an upper limit and a lower limit for the corresponding parameterized resource output (616).
- an example of an output property is pH of a composition.
- the output specification limit specifies the allowed upper limit for the pH of the composition and the allowed lower limit for the pH of the composition.
- this corresponding output specification limit comprises an enumerated list of allowable types (618).
- an example of an output property is a crystallographic orientation of a material. In such an example, the output specification limit specifies an enumerated list of allowed crystallographic orientations for the material.
- the one or more processes in a hypergraph data store is, in fact, a plurality of processes. Further, a first process in the plurality of processes results in a first product and a second process in the plurality of processes results in a different second product (620). For instance, a first process in the hypergraph data store may result in the manufacture of one type of composition and another process in the hypergraph data store may result in the manufacture of another composition.
- a run data store 210 is also maintained.
- the run data store comprises a plurality of process runs 402.
- a process version 208 is locked before a process run 402 for the process version 208 is executed so that no further changes can be made to the process version 208. If changes to underlying process 206 are desired, a new process version 208 is defined in such embodiments.
- Each process run 402 comprises an identification of a process version 404
- query 2502 and toggles 2504 can be used to select which properties (e.g., input or output properties of the edges of the underlying process versions) of which process runs are viewed.
- calculated properties e.g., amount of final product divided a quantity of input material
- correlations between calculated properties can be viewed.
- predefined process calculations e.g. a process yield calculation
- Each process run 402 comprises the respective set of parameterized resource outputs 412 of the subject edge 304 in the hypergraph 302 of the respective version 208.
- the process run 402 further comprises obtained values of at least one output property of a parameterized resource output in the respective set of parameterized resource outputs of the node.
- the run data store 210 further comprises a genealogical graph 420 showing a relationship between (i) versions of a single process in the plurality of versions of a process that are in the plurality of process runs or (ii) versions of two or more processes in the respective plurality of versions of two or more processes that are in the plurality of process runs (624).
- a first process version 404 in a process set 420 and a second process version 404 in the process set 420 have the same hypergraph but an output property, output specification limit, input property, or input specification limit to one of the edges in the hypergraph is different.
- a first process version 404 in a process set 420 and a second process version 404 in the process set 420 have hypergraphs that have all but one, all but two, all but three, or all but four edge and/or node, and so forth, in common.
- the genealogical graph provides an advantageous way of discerning the relationship between the various process versions of a given process.
- a statistics module 212 is also maintained (626).
- the statistics module 212 leverages the structure of run data store 210 and hypergraph data store 204 to enable analytics of process runs.
- the statistics module 212 combined with the unique structure of run data store 210 and hypergraph data store 204 provides an advantageous platform for supporting statistical process control (SPC) over the many disparate components of a process 206 and thus provides powerful tools for analyzing and stabilizing such processes.
- SPC is a method of quality control which uses statistical methods. It is applied in order to monitor and control processes. Monitoring and controlling processes ensures that they operate at their full potential. For instance, at its full potential, a process 206 can make as much conforming product as possible with a minimization of waste.
- SPC can be applied to any process 206 where the "conforming product" (product meeting specifications) output can be measured.
- SPC makes use of control charts, a focus on continuous improvement and the design of process runs 402 (e.g., experiments). See, for example, Barlow and Irony, 1992, “Foundations of statistical quality control” in Ghosh, M. & Pathak, P.K. (eds.) Current Issues in Statistical Inference: Essays in Honor of D. Basu, Hayward, California, Institute of Mathematical Statistics, pp. 99-112, which is hereby incorporated by reference.
- the statistics module 212 responsive to receiving a query that identifies one or more first parameterized resource inputs and/or parameterized resource outputs present in one or more process runs in the run data store, is able to easily retrieve and format the one or more first parameterized resource inputs and/or parameterized resource outputs for analysis.
- the data is formatted as one or more tab delimited files, CSV files, EXCEL spreadsheets, GOOGLE Sheets, and/or in a form suitable for relational databases.
- the data is structured to ensure that such data can be efficiently analyzed so that potential correlations are not overlooked in subsequent analysis.
- An example of such analysis that is performed as part of SPC is correlation analysis such as the root cause analysis illustrated in Figure 26. Root cause analysis is described, for example, in Wilson et ⁇ , 1993, Root Cause Analysis: A Tool for Total Quality Management, Milwaukee, Wisconsin, ASQ Quality Press, pp. 8-17, which is hereby incorporated by reference.
- a query identifies one or more first parameterized resource inputs ⁇ e.g., amino acid type) and/or parameterized resource outputs ⁇ e.g., citrate concentration) present in one or more process runs in the run data store.
- Data for the one or more first parameterized resource inputs and/or parameterized resource is then formatted and outputted for analysis.
- an analysis such as the root cause analysis of Figure 26, is conducted.
- the query results are formatted for a third party statistical analysis package such as JMP (SAS,
- the query can be of any of the resource inputs or outputs available for any combination of process versions of any combination of the one or more processes in the run data store 210 or properties of these inputs or outputs.
- the query further identifies one or more second parameterized resource inputs and/or parameterized resource outputs present in one or more runs in the run data store (or properties thereof) and the one or more first parameterized resource inputs and/or parameterized resource outputs and the one or more second parameterized resource inputs and/or parameterized resource outputs are correlated and a numerical measure of this correlation is formatted for presentation (628).
- the numerical measure of correlation is on a scale between a low number and a high number, where the low number ⁇ e.g., zero) is indicative of no correlation and the high number ⁇ e.g., one) is indicative of complete correlation across the one or more first parameterized resource inputs and/or parameterized resource outputs and the one or more second parameterized resource inputs and/or parameterized resource outputs.
- the query further identifies one or more second parameterized inputs and/or parameterized outputs present (or their properties) in one or more runs in the run data store
- the statistics module further identifies a correlation between (i) the one or more first parameterized inputs and/or parameterized outputs and (ii) the one or more second parameterized inputs and/or parameterized outputs present in one or more process runs in the run data store from among all the parameterized inputs and/or parameterized outputs present in the run data store using a multivariate analysis technique (630).
- the query identifies (i) one or more properties of one or more first parameterized inputs and/or parameterized outputs and (ii) one or more properties of one or more second parameterized inputs and/or parameterized outputs present in one or more runs in the run data store
- the statistics module further seeks a correlation between (i) the identified properties of the one or more first parameterized inputs and/or parameterized outputs and (ii) the identified one or more properties of the one or more second parameterized inputs and/or parameterized outputs present in one or more process runs in the run data store from among all the parameterized inputs and/or parameterized outputs present in the run data store using a multivariate analysis technique.
- the above processes invoke a multivariate analysis technique that comprises a feature selection technique (632) (e.g., least angle regression, stepwise regression).
- Feature selection techniques are particularly advantageous in identifying, from among the multitude of variables (e.g., values for input properties of inputs and values for output properties of outputs of nodes) present across sets of process runs, which variables (e.g., which input properties of inputs of which nodes and/or which output properties of outputs of which nodes) have a significant causal effect on a property of the product of the process (e.g., which of the variables are causal for poor reproducibility, poor yield, or conversely which of the variables are causal for excellent reproducibility, higher yield).
- the one or more processes are a plurality of processes and the correlation is identified from process runs in a subset of the plurality of processes (634). There is no requirement that each of the processes across which this correlation is identified make the same product in such embodiments.
- Such embodiments are highly advantageous because they allow for the investigation of undesirable process variability across process runs used in the manufacture of different products.
- some of the process runs used in a correlation analysis may manufacture biologic A and other process runs used in the same correlation analysis may manufacture biologic B.
- Correlation analysis that uses data from process runs for biologies A and B allows for the investigation of causes of variation that are product independent, such as, for example, a poorly defined fermentation step.
- the sugar input into this fermentation step in the process runs for both biologies A and B may not be adequately defined to ensure process stabilization.
- Another example of a source of variation common to these process versions could be, for example, identified through correlation analysis across process runs for both biologies A and B, to a piece of equipment that is beginning to fail due to age. This is all possible because the disclosed systems and methods advantageously impose a consistent framework to the process runs that make different products.
- the one or more processes are a plurality of processes and the correlation is identified from process runs in a single process in the plurality of processes (636).
- each of the processes across which this correlation is identified makes the same product or produce the same analytical information.
- Such embodiments are used, for example, to precisely identify key sources of variability in the manufacture of the product or production of the analytical information through the process.
- the one or more processes is a plurality of processes and the query further identifies a subset of the plurality of processes whose process runs are to be formatted by the statistics module (638).
- the statistics module 212 further provides suggested values for the one or more second parameterized inputs for one or more additional process runs of a first process in the one or more processes, not present in the run data store 210, based on a prediction that the suggested values for the one or more second parameterized inputs will alter a numerical attribute of the product of such process runs (640).
- the numerical attribute is a reduction in variance in the one or more first parameterized inputs (642).
- Such an embodiment is utilized, for example, to identify situations in which the input space covered by the parameterized resource inputs 310 of the edges in the process runs is insufficient to find a correlation between certain process variables across the process runs previously executed with a sufficiently high degree of confidence, or any correlation at all. In these instances, suggested values for the input space that is covered by the parameterized resource inputs 310 are provided in order to test for a correlation. Such an embodiment is utilized, in other examples, when a potential problem is identified from analysis of existing process runs. In such
- proposed additions to the input space not present in the process runs in the run data store are made that will facilitate determining whether the potential problem is real. If the potential problem is real, a new version of the process can be developed that further defines a state (property) of an input or output to an existing or new edge in the process in order to attempt to remove process state ambiguity and thereby stabilize the process.
- the query identifies one or more third parameterized inputs and/or parameterized outputs present in runs in the run data store, and the above- described numerical attribute is a confidence in a correlation between the first
- the one or more processes is a plurality of processes and the query further identifies a single process in the plurality of processes whose process runs are to be formatted by the statistics module (646). In such embodiments, all the process runs identified by the query make the same product or produce the same form of analytical information.
- the query further identifies a subset of process runs in the one or more processes (648).
- some of the process runs responsive to the query may make different products or produce different types of analytical information.
- the statistics module further identifies a correlation between (i) a first set comprising one or more process runs in the run data store and (ii) a second set comprising one or more process runs in the run data store, where process runs in the second set are not in the first set (650). For instance, in some embodiments, the correlation is computed across a plurality of parameterized inputs and/or parameterized outputs present in the first and second sets (652).
- the one or more first parameterized resource inputs and/or parameterized resource outputs are exported for analysis to another device (654), e.g., as one or more tab delimited files, CSV files, EXCEL spreadsheets, GOOGLE Sheets, or in a form suitable for an SQL database.
- another device e.g., as one or more tab delimited files, CSV files, EXCEL spreadsheets, GOOGLE Sheets, or in a form suitable for an SQL database.
- a process evaluation module is maintained that generates an alert in the form of a computer data transmission when an obtained value for an output property of a parameterized resource output in a set of parameterized resource outputs for an edge in a hypergraph of a process version is outside the output specification limit (656).
- a data driver 218 is executed for a respective process in the one or more processes (658).
- the data driver includes instructions for receiving a dataset for the respective process and further includes instructions for parsing the dataset to thereby obtain (i) an identification of a process run in the run data store and (ii) output property values associated with the respective set of parameterized resource outputs of a first edge in the hypergraph of the respective process for the process run.
- the data driver further includes instructions for populating the output property values of parameterized resource outputs of the first edge in the run data store with the parsed values. For instance, in some embodiments, a sync engine associated with an edge in the process monitors an associated synced folder.
- the sync engine associated with the edge runs as a background process (like Google Drive or Dropbox Sync) on any PC attached to an instrument associated with the node.
- a background process like Google Drive or Dropbox Sync
- the software parses and sends the data to the data driver 218.
- association of the data sets to the correct protocol variables like Google Drive or Dropbox Sync
- the data driver 218 already contains the associations between values in the data sets and the correct protocol variables (parameterized resource inputs and/or outputs) of process runs
- data in the set of parameterized resource outputs 314 that is communicated to the computer system for a node 504 of a process run 502 comprises a node identifier 406 (e.g., an instrument identifier such as a Bluetooth UUID), an identification of a process version 404, and a value for a parameterized resource input 410.
- the data is in the form of a JSON structure. See the Internet at j son.org.
- Another aspect of the present disclosure provides a computer system 200 comprising one or more processors 274, memory 192/290, and one or more programs stored in the memory for execution by the one or more processors.
- the one or more programs comprise instructions for maintaining a hypergraph data store 204.
- the hypergraph data store 204 comprises, for each respective process 206 in the one or more processes, a respective plurality of versions 208 of the respective process.
- Each respective version 208 comprises a hypergraph 302 comprising a plurality of nodes 322 connected by edges 304 in a plurality of edges.
- Each respective edge 304 in the plurality of edges comprises a process stage label 306 representing a respective stage in the corresponding process 206.
- Each respective edge 304 in the plurality of edges is associated with a set of parameterized resource inputs 308 to the respective stage 306 in the corresponding process 206.
- At least one parameterized resource input 310 in the set of parameterized resource inputs 308 is associated with one or more input properties 312.
- the one or more input properties include an input specification limit 314.
- Each respective edge 304 in the plurality of edges is also associated with a set of parameterized resource outputs 314 to the respective stage 306 in the corresponding process 206.
- At least one parameterized resource output 316 in the set of parameterized resource outputs 314 is associated with one or more output properties 318.
- the one or more output properties 318 include a corresponding output specification limit 320.
- Each respective node 322 in the plurality of nodes specifies that the set of
- the one or more programs further comprise instructions for maintaining a run data store 210.
- the run data store 210 comprises a plurality of process runs 402.
- Each process run 402 comprises (i) an identification of a process version 404 in the plurality of versions for a process 206 in the one or more processes, (ii) values for the respective set of parameterized inputs 408 ( Figure 4) of a first edge 304 in the hypergraph 302 of the respective version 208 and their associated input properties 410, (iii) the respective set of parameterized resource outputs 412 of the first edge 304, and (iv) obtained values of at least one output property 416 of a parameterized resource output 414 in the respective set of parameterized resource outputs of the first edge.
- the one or more programs further comprise instructions for maintaining a statistics module 212 that, responsive to receiving a query that identifies one or more first parameterized inputs and/or parameterized outputs present in one or more process runs 402 in the run data store, formats the one or more first parameterized inputs and/or parameterized outputs for statistical analysis. In this way instances (process runs) of a process can be performed with satisfactory reproducibility.
- a hypergraph data store 204 is maintained.
- the hypergraph data store 204 comprises, for each respective process 206 of one or more processes, a respective plurality of versions of the respective process.
- Each respective version 208 comprises a hypergraph 302 comprising a plurality of nodes 322 connected by edges 304 in a plurality of edges.
- Each respective edge 304 in the plurality of edges comprises a process stage label representing a respective stage in the corresponding process.
- each respective node 322 in the plurality of nodes is associated with a corresponding set of parameterized resources and the corresponding set of parameterized resources specifies that each respective parameterized resource in the corresponding set of parameterized resources is associated with at least a corresponding output of the at least one output of a first edge in the plurality of edges and also is associated with at least a corresponding input of the one or more inputs of at least one other edge in the plurality of edges.
- the values of a resource associated with the output side of a node may be different than the values of a resource associated with the input side of the same node.
- a user can simply click on an edge 304 to see their inputs and outputs.
- unstructured data in the form of videos, pictures, or comments can be added to nodes 322 or edges 304.
- a video showing the proper way to perform a procedure associated with a node or edge can be linked to the node or edge by simply dragging an icon link to the video onto the representation of the node 322 or edge 204.
- a video on the proper way perform a fermenter setup can be dragged onto the "Fermenter Setup" node 322-4 of Figure 7. Thereafter, when a user clicks on node 322-4, the video is played.
- versions 208 of a process 206 are related to each other.
- each version 208 of a process 604 produces the same product.
- a first version and a second version in a respective plurality of versions for a process differ from each other in some way, such as in a number of nodes, a number of edges, a process stage label of an edge, a parameterized resource in a set of parameterized resources, to name some possibilities (2704).
- a resource 310 is a single resource.
- a resource is a composite resource.
- composite resources include, but are not limited, to mixtures of compositions (e.g., media, broth, etc.) and multi- component equipment (2710).
- the set of parameterized resources for a first node in the plurality of nodes of a hypergraph 302 of a process version 208 in the respective plurality of process versions comprises a first parameterized resource and this first parameterized resource specifies a process condition associated with the corresponding stage of the process associated with the corresponding edge (2712).
- this process condition is a temperature, an exposure time, a mixing time, a concentration, a type of equipment or a batch identifier (2714).
- this corresponding specification limit comprises an upper limit and a lower limit for the corresponding parameterized resource (2716).
- an example of a property is pH of a composition.
- the specification limit specifies the allowed upper limit for the pH of the composition and the allowed lower limit for the pH of the composition.
- this corresponding specification limit comprises an enumerated list of allowable types (2718).
- an example of a property is a crystallographic orientation of a material. In such an example, the specification limit specifies an enumerated list of allowed crystallographic orientations for the material.
- the one or more processes in a hypergraph data store is, in fact, a plurality of processes. Further, a first process in the plurality of processes results in a first product and a second process in the plurality of processes results in a different second product (2720). For instance, a first process in the hypergraph data store may result in the manufacture of one type of composition and another process in the hypergraph data store may result in the manufacture of another composition.
- a run data store 210 is also maintained.
- the run data store comprises a plurality of process runs 402.
- a process version 208 is locked before a process run 402 for the process version 208 is executed so that no further changes can be made to the process version 208. If changes to underlying process 206 are desired, a new process version 208 is defined in such embodiments.
- each process run 402 comprises an identification of a first edge of a process version 404 (208) in the plurality of versions for a process 206 in the one or more processes, as illustrated in Figure 4. Furthermore, values for the respective set of parameterized resources and their associated one or more properties corresponding to at least one node in the plurality of nodes in the hypergraph 302 of the respective version are provided in a process run.
- the run data store 210 further comprises a genealogical graph 420 showing a relationship between (i) versions of a single process in the plurality of versions of a process that are in the plurality of process runs or (ii) versions of two or more processes in the respective plurality of versions of two or more processes that are in the plurality of process runs (2724).
- a first process version 404 in a process set 420 and a second process version 404 in the process set 420 have the same hypergraph but a property or specification limit to one of the nodes in the hypergraph is different.
- a first process version 404 in a process set 420 and a second process version 404 in the process set 420 have hypergraphs that have all but one, all but two, all but three, all but four nodes or edges, and so forth, in common.
- the genealogical graph provides an advantageous way of discerning the relationship between the various process versions of a given process.
- a statistics module 212 is also maintained (2726).
- the statistics module 212 leverages the structure of run data store 210 and hypergraph data store 204 to enable analytics of process runs.
- the statistics module 212 combined with the unique structure of run data store 210 and hypergraph data store 204 provides an advantageous platform for supporting statistical process control (SPC) over the many disparate components of a process 206 and thus provides powerful tools for analyzing and stabilizing such processes.
- SPC is a method of quality control which uses statistical methods. It is applied in order to monitor and control processes. Monitoring and controlling processes ensures that they operate at their full potential. For instance, at its full potential, a process 206 can make as much conforming product as possible with a minimization of waste.
- SPC can be applied to any process 206 where the "conforming product" (product meeting specifications) output can be measured.
- the statistics module 212 responsive to receiving a query that identifies one or more first parameterized resources present in one or more process runs in the run data store, is able to easily retrieve and format the one or more resources for analysis.
- the data is formatted as one or more tab delimited files, CSV files, EXCEL spreadsheets, GOOGLE Sheets, and/or in a form suitable for relational databases.
- the data is structured to ensure that such data can be efficiently analyzed so that potential correlations are not overlooked in subsequent analysis.
- Root cause analysis is described, for example, in Wilson et al, 1993, Root Cause Analysis: A Tool for Total Quality Management, Milwaukee, Wisconsin, ASQ Quality Press, pp. 8-17, which is hereby incorporated by reference.
- a query identifies one or more first parameterized resources (e.g., amino acid type) present in one or more process runs in the run data store. Data for the one or more first parameterized resources is then formatted and outputted for analysis. With this formatted data, an analysis, such as the root cause analysis of Figure 26, is conducted.
- the query results are formatted for a third party statistical analysis package such as JMP (SAS, Buckinghamshire, England, see the Internet at
- the query can be of any of the resources available for any combination of process versions of any combination of the one or more processes in the run data store 210 or properties of these resources.
- the query further identifies one or more second parameterized resources present in one or more runs in the run data store (or properties thereof) and the one or more first resources and the one or more second resources are correlated and a numerical measure of this correlation is formatted for presentation (2728).
- the numerical measure of correlation is on a scale between a low number and a high number, where the low number (e.g., zero) is indicative of no correlation and the high number (e.g., one) is indicative of complete correlation across the one or more first parameterized resources and the one or more second parameterized resources.
- the query further identifies one or more second resources present (or their properties) in one or more runs in the run data store
- the statistics module further identifies a correlation between (i) the one or more first parameterized resources and (ii) the one or more second parameterized resources present in one or more process runs in the run data store from among all the parameterized resources present in the run data store using a multivariate analysis technique (2730).
- the query identifies (i) one or more properties of one or more first resources and (ii) one or more properties of one or more second resources present in one or more runs in the run data store
- the statistics module further seeks a correlation between (i) the identified properties of the one or more first resources and (ii) the identified one or more properties of the one or more second resources present in one or more process runs in the run data store from among all the parameterized resources present in the run data store using a multivariate analysis technique.
- the above processes invoke a multivariate analysis technique that comprises a feature selection technique (2732) (e.g., least angle regression, stepwise regression).
- Feature selection techniques are particularly advantageous in identifying, from among the multitude of variables (e.g., values for properties of resources in sets of resources associated with edges) present across sets of process runs, which variables (e.g., which properties of resources of which nodes) have a significant causal effect on a property of the product of the process (e.g., which of the variables are causal for poor reproducibility, poor yield, or conversely which of the variables are causal for excellent reproducibility, higher yield).
- the one or more processes are a plurality of processes and the correlation is identified from process runs in a subset of the plurality of processes (2734). There is no requirement that each of the processes across which this correlation is identified make the same product in such embodiments.
- Such embodiments are highly advantageous because they allow for the investigation of undesirable process variability across process runs used in the manufacture of different products.
- some of the process runs used in a correlation analysis may manufacture biologic A and other process runs used in the same correlation analysis may manufacture biologic B.
- Correlation analysis that uses data from process runs for biologies A and B allows for the investigation of causes of variation that are product independent, such as, for example, a poorly defined fermentation step.
- the sugar input into this fermentation step in the process runs for both biologies A and B may not be adequately defined to ensure process stabilization.
- Another example of a source of variation common to these process versions could be, for example, identified through correlation analysis across process runs for both biologies A and B, to a piece of equipment that is beginning to fail due to age. This is all possible because the disclosed systems and methods advantageously impose a consistent framework to the process runs that make different products.
- the one or more processes are a plurality of processes and the correlation is identified from process runs in a single process in the plurality of processes (2736). In such embodiments, each of the processes across which this correlation is identified makes the same product or produce the same analytical information. Such embodiments are used, for example, to precisely identify key sources of variability in the manufacture of the product or production of the analytical information through the process.
- the one or more processes is a plurality of processes and the query further identifies a subset of the plurality of processes whose process runs are to be formatted by the statistics module (2738).
- the statistics module 212 further provides suggested values (e.g., limits) for the one or more second parameterized resources for one or more additional process runs of a first process in the one or more processes, not present in the run data store 210, based on a prediction that the suggested values (e.g., limits) for the one or more second parameterized resources will alter a numerical attribute of the product of such process runs (2740).
- the numerical attribute is a reduction in variance in the one or more first parameterized resources (2742).
- Such an embodiment is utilized, for example, to identify situations in which the resource space covered by the parameterized resources of the nodes in the process runs is insufficient to find a correlation between certain process variables across the process runs previously executed with a sufficiently high degree of confidence, or any correlation at all. In these instances, suggested values for the space that is covered by the parameterized resources are provided in order to test for a correlation.
- Such an embodiment is utilized, in other examples, when a potential problem is identified from analysis of existing process runs. In such embodiments, proposed additions to the resource space not present in the process runs in the run data store are made that will facilitate determining whether the potential problem is real. If the potential problem is real, a new version of the process can be developed that further defines a state (property) of a resource of an existing or new node in the process in order to attempt to remove process state ambiguity and thereby stabilize the process.
- the query identifies one or more third parameterized resources present in runs in the run data store, and the above-described numerical attribute is a confidence in a correlation between the first resources and the third parameterized resources (2744).
- the one or more processes is a plurality of processes and the query further identifies a single process in the plurality of processes whose process runs are to be formatted by the statistics module (2746) In such
- all the process runs identified by the query make the same product or produce the same form of analytical information.
- the query further identifies a subset of process runs in the one or more processes (2748).
- some of the process runs responsive to the query may make different products or produce different types of analytical information.
- the statistics module further identifies a correlation between (i) a first set comprising one or more process runs in the run data store and (ii) a second set comprising one or more process runs in the run data store, where process runs in the second set are not in the first set (2750). For instance, in some embodiments, the correlation is computed across a plurality of parameterized resources present in the first and second sets (2752).
- the one or more first parameterized resources are exported for analysis to another device (2754), e.g., as one or more tab delimited files, CSV files, EXCEL spreadsheets, GOOGLE Sheets, or in a form suitable for an SQL database.
- another device e.g., as one or more tab delimited files, CSV files, EXCEL spreadsheets, GOOGLE Sheets, or in a form suitable for an SQL database.
- a process evaluation module is maintained that generates an alert in the form of a computer data transmission when an obtained value for a property of a parameterized resource in a set of parameterized resources for a node in a hypergraph of a process version is outside the specification limit of the resource (2756).
- a data driver 218 is executed for a respective process in the one or more processes (2758).
- the data driver includes instructions for receiving a dataset for the respective process and further includes instructions for parsing the dataset to thereby obtain (i) an identification of a process run in the run data store and (ii) property values associated with the respective set of
- the data driver further includes instructions for populating the property values of parameterized resources of the first node in the run data store with the parsed values.
- a sync engine associated with a node in the process monitors an associated synced folder.
- the sync engine associated with the node runs as a background process (like Google Drive or Dropbox Sync) on any PC attached to an instrument associated with the node.
- the software parses and sends the data to the data driver 218.
- association of the data sets to the correct protocol variables (parameterized resources) of process runs is done via interaction with a user who is presented with a notification containing choices of process runs to which they have access.
- the data driver 218 already contains the associations between values in the data sets and the correct protocol variables (parameterized resources) of process runs.
- a hypergraph data store 204 is maintained.
- the hypergraph data store 204 comprises, for each respective process 206 of one or more processes, a respective plurality of versions of the respective process.
- Each respective version 208 comprises a hypergraph 302 comprising a plurality of edges 304 connected by nodes 322 in a plurality of nodes.
- Each respective edge 304 in the plurality of edges comprises a process stage label representing a respective stage in the corresponding process.
- each respective node 322 in the plurality of nodes comprises an output at the at least one output of a first edge in the plurality of edges and also comprises a first input of the one or more inputs of at least one other edge in the plurality of edges.
- a user can simply click on an edge 304 to see their inputs and outputs.
- unstructured data in the form of videos, pictures, or comments can be added to edges 304. For example, a video showing the proper way to perform a procedure associated with an edge can be linked to an edge by simply dragging an icon link to the video onto the representation of the edge 304.
- a run data store 210 is also maintained.
- the run data store comprises a plurality of process runs 402.
- a process version 208 is locked before a process run 402 for the process version 208 is executed so that no further changes can be made to the process version 208. If changes to underlying process 206 are desired, a new process version 208 is defined in such embodiments.
- each respective node in the plurality of nodes is associated with a corresponding set of parameterized resources.
- the corresponding set of parameterized resources comprises a first output of the at least one output of a first edge in the plurality of edges and also comprises a first input of the one or more inputs of at least one other edge in the plurality of edges.
- At least one parameterized resource in the set of parameterized resources is associated with one or more properties.
- the one or more properties include one or more corresponding specification limits.
- the run data store further comprises, for each respective process run in the plurality of process runs, values for the respective set of parameterized resources corresponding to at least one of the first output of the first edge or the first input of the at least one other edge associated with a first node in the hypergraph of the respective version and their associated one or more properties.
- versions 208 of a process 206 are related to each other.
- each version 208 of a process 604 produces the same product.
- a first version and a second version in a respective plurality of versions for a process differ from each other in some way, such as in a number of nodes or edges, a process stage label of an edge, a parameterized resource in a set of parameterized resources, to name some possibilities (2808).
- the set of parameterized resources for a node in the plurality of nodes of a hypergraph for a process version in the respective plurality of process versions comprises a first and second parameterized resource.
- the first parameterized resource specifies a first resource and is associated with a first property
- the second parameterized resource specifies a second resource and is associated with a second property.
- the first property is a viscosity value, a purity value, composition value, a temperature value, a weight value, a mass value, a volume value, or a batch identifier of the first resource.
- a resource 310 is a single resource.
- a resource is a composite resource. Examples of composite resources include, but are not limited, to mixtures of compositions ⁇ e.g., media, broth, etc.) and multi- component equipment (2814).
- the set of parameterized resources for a first node in the plurality of nodes of a hypergraph 302 of a process version 208 in the respective plurality of process versions comprises a first parameterized resource and this first parameterized resource specifies a process condition (2816).
- this process condition is a temperature, an exposure time, a mixing time, a concentration, a type of equipment or a batch identifier (2818).
- at least one of resource in a set of parameterized resources is associated with one or more properties, and the one or more properties includes a corresponding specification limit.
- this corresponding specification limit comprises an upper limit and a lower limit for the corresponding parameterized resource (2820).
- an example of a property is pH of a composition.
- the specification limit specifies the allowed upper limit for the pH of the composition and the allowed lower limit for the pH of the composition.
- this corresponding specification limit comprises an enumerated list of allowable types (2822).
- an example of a property is a crystallographic orientation of a material. In such an example, the specification limit specifies an enumerated list of allowed crystallographic orientations for the material.
- the one or more processes in a hypergraph data store is, in fact, a plurality of processes. Further, a first process in the plurality of processes results in a first product and a second process in the plurality of processes results in a different second product (2824). For instance, a first process in the hypergraph data store may result in the manufacture of one type of composition and another process in the hypergraph data store may result in the manufacture of another composition.
- the run data store 210 further comprises a
- genealogical graph 420 showing a relationship between (i) versions of a single process in the plurality of versions of a process that are in the plurality of process runs or (ii) versions of two or more processes in the respective plurality of versions of two or more processes that are in the plurality of process runs (2826).
- a first process version 404 in a process set 420 and a second process version 404 in the process set 420 have the same hypergraph but a property or specification limit to one of the nodes in the hypergraph is different.
- a first process version 404 in a process set 420 and a second process version 404 in the process set 420 have hypergraphs that have all but one, all but two, all but three, all but four nodes or edges, and so forth, in common.
- the genealogical graph provides an advantageous way of discerning the relationship between the various process versions of a given process.
- a statistics module 212 is also maintained (2828).
- the statistics module 212 leverages the structure of run data store 210 and hypergraph data store 204 to enable analytics of process runs.
- the statistics module 212 combined with the unique structure of run data store 210 and hypergraph data store 204 provides an advantageous platform for supporting statistical process control (SPC) over the many disparate components of a process 206 and thus provides powerful tools for analyzing and stabilizing such processes.
- SPC is a method of quality control which uses statistical methods. It is applied in order to monitor and control processes. Monitoring and controlling processes ensures that they operate at their full potential. For instance, at its full potential, a process 206 can make as much conforming product as possible with a minimization of waste.
- SPC can be applied to any process 206 where the "conforming product" (product meeting specifications) output can be measured.
- the statistics module 212 responsive to receiving a query that identifies one or more first parameterized resources present in one or more process runs in the run data store, is able to easily retrieve and format the one or more resources for analysis.
- the data is formatted as one or more tab delimited files, CSV files, EXCEL spreadsheets, GOOGLE Sheets, and/or in a form suitable for relational databases.
- the data is structured to ensure that such data can be efficiently analyzed so that potential correlations are not overlooked in subsequent analysis.
- Root cause analysis is described, for example, in Wilson et ah , 1993, Root Cause Analysis: A Tool for Total Quality Management, Milwaukee, Wisconsin, ASQ Quality Press, pp. 8-17, which is hereby incorporated by reference.
- a query identifies one or more first parameterized resources (e.g., amino acid type) present in one or more process runs in the run data store. Data for the one or more first parameterized resources is then formatted and outputted for analysis. With this formatted data, an analysis, such as the root cause analysis of Figure 26, is conducted.
- first parameterized resources e.g., amino acid type
- the query results are formatted for a third party statistical analysis package such as IMP (SAS, Buckinghamshire, England, on the Internet at jrap.com/en_dk/sofUvaxe.htmi).
- IMP SAS, Buckinghamshire, England
- Analysis using such a third party statistical analysis package typically results in proposals for new process versions, in which nodes and/or edges are added or removed, or the sets of resources associated with nodes are further defined or redefined, in order to identify and remove unwanted process variability (e.g., to stabilize the process).
- the query can be of any of the resources available for any combination of process versions of any combination of the one or more processes in the run data store 210 or properties of these resources.
- the query further identifies one or more second parameterized resources present in one or more runs in the run data store (or properties thereof) and the one or more first resources and the one or more second resources are correlated and a numerical measure of this correlation is formatted for presentation (2830).
- the numerical measure of correlation is on a scale between a low number and a high number, where the low number (e.g., zero) is indicative of no correlation and the high number (e.g., one) is indicative of complete correlation across the one or more first parameterized resources and the one or more second parameterized resources.
- the query further identifies one or more second resources present (or their properties) in one or more runs in the run data store
- the statistics module further identifies a correlation between (i) the one or more first parameterized resources and (ii) the one or more second parameterized resources present in one or more process runs in the run data store from among all the parameterized resources present in the run data store using a multivariate analysis technique (2830).
- the query identifies a correlation between (i) one or more first parameterized resources and (ii) one or more second parameterized resources present in one or more process runs in the run data store from among all the parameterized resources present in the run data store using a multivariate analysis technique (2832).
- a multivariate analysis technique that comprises a feature selection technique (2834) (e.g., least angle regression, stepwise regression).
- Feature selection techniques are particularly advantageous in identifying, from among the multitude of variables (e.g., values for properties of resources in sets of resources associated with edges) present across sets of process runs, which variables (e.g., which properties of resources) have a significant causal effect on a property of the product of the process (e.g., which of the variables are causal for poor reproducibility, poor yield, or conversely which of the variables are causal for excellent reproducibility, higher yield).
- variables e.g., which properties of resources
- Feature selection techniques are described, for example, in Saeys et al, 2007, “A review of feature selection techniques in bioinformatics," Bioinformatics 23, 2507-2517, and Tibshirani, 1996, “Regression and Shrinkage and Selection via the Lasso,” J. R. Statist. Soc B, pp. 267-288, each of which is hereby incorporated by reference.
- the one or more processes are a plurality of processes and the correlation is identified from process runs in a subset of the plurality of processes (2836). There is no requirement that each of the processes across which this correlation is identified make the same product in such embodiments.
- Such embodiments are highly advantageous because they allow for the investigation of undesirable process variability across process runs used in the manufacture of different products.
- some of the process runs used in a correlation analysis may manufacture biologic A and other process runs used in the same correlation analysis may manufacture biologic B.
- Correlation analysis that uses data from process runs for biologies A and B allows for the investigation of causes of variation that are product independent, such as, for example, a poorly defined fermentation step.
- the sugar input into this fermentation step in the process runs for both biologies A and B may not be adequately defined to ensure process stabilization.
- Another example of a source of variation common to these process versions could be, for example, identified through correlation analysis across process runs for both biologies A and B, to a piece of equipment that is beginning to fail due to age. This is all possible because the disclosed systems and methods advantageously impose a consistent framework to the process runs that make different products.
- the one or more processes are a plurality of processes and the correlation is identified from process runs in a single process in the plurality of processes (2838). In such embodiments, each of the processes across which this correlation is identified makes the same product or produce the same analytical information. Such embodiments are used, for example, to precisely identify key sources of variability in the manufacture of the product or production of the analytical information through the process.
- the one or more processes is a plurality of processes and the query further identifies a subset of the plurality of processes whose process runs are to be formatted by the statistics module (2839).
- the statistics module 212 further provides suggested values (e.g., limits) for the one or more second parameterized resources for one or more additional process runs of a first process in the one or more processes, not present in the run data store 210, based on a prediction that the suggested values (e.g., limits) for the one or more second parameterized resources will alter a numerical attribute of the product of such process runs (2840).
- the numerical attribute is a reduction in variance in the one or more first parameterized resources exhibited across the plurality of runs (2742).
- Such an embodiment is utilized, for example, to identify situations in which the resource space covered by the parameterized resources in the process runs is insufficient to find a correlation between certain process variables across the process runs previously executed with a sufficiently high degree of confidence, or any correlation at all. In these instances, suggested values for the space that is covered by the parameterized resources are provided in order to test for a correlation.
- Such an embodiment is utilized, in other examples, when a potential problem is identified from analysis of existing process runs. In such embodiments, proposed additions to the resource space not present in the process runs in the run data store are made that will facilitate determining whether the potential problem is real. If the potential problem is real, a new version of the process can be developed that further defines a state (property) of a resource of an existing or new edge in the process in order to attempt to remove process state ambiguity and thereby stabilize the process.
- the query identifies one or more third parameterized resources present in runs in the run data store, and the above-described numerical attribute is a confidence in a correlation between the first resources and the third parameterized resources (2844).
- the one or more processes is a plurality of processes and the query further identifies a single process in the plurality of processes whose process runs are to be formatted by the statistics module (2846). In such
- all the process runs identified by the query make the same product or produce the same form of analytical information.
- the query further identifies a subset of process runs in the one or more processes (2848). In such embodiments, there is no requirement that all the process runs identified by the query make the same product or produce the same form of analytical information. In fact, some of the process runs responsive to the query may make different products or produce different types of analytical information.
- the statistics module further identifies a correlation between (i) a first set comprising one or more process runs in the run data store and (ii) a second set comprising one or more process runs in the run data store, where process runs in the second set are not in the first set (2850). For instance, in some embodiments, the correlation is computed across a plurality of parameterized resources present in the first and second sets (2852).
- the one or more first parameterized resources are exported for analysis to another device (2754), e.g., as one or more tab delimited files, CSV files, EXCEL spreadsheets, GOOGLE Sheets, or in a form suitable for an SQL database.
- another device e.g., as one or more tab delimited files, CSV files, EXCEL spreadsheets, GOOGLE Sheets, or in a form suitable for an SQL database.
- a process evaluation module is maintained that generates an alert in the form of a computer data transmission when an obtained value for a property of a parameterized resource in a set of parameterized resources for a node in a hypergraph of a process version is outside the specification limit of the resource (2856).
- a data driver 218 is executed for a respective process in the one or more processes (2858).
- the data driver includes instructions for receiving a dataset for the respective process and further includes instructions for parsing the dataset to thereby obtain (i) an identification of a process run in the run data store and (ii) property values associated with a respective set of parameterized resources for a first node in the hypergraph of the respective process for the process run.
- the data driver further includes instructions for populating the property values of parameterized resources of the first node in the run data store with the parsed values. For instance, in some embodiments, a sync engine associated with the process monitors an associated synced folder.
- the sync engine runs as a background process (like Google Drive or Dropbox Sync) on any PC attached to an instrument associated with the edge.
- the software parses and sends the data to the data driver 218.
- association of the data sets to the correct protocol variables (parameterized resources) of process runs is done via interaction with a user who is presented with a notification containing choices of process runs to which they have access.
- the data driver 218 already contains the associations between values in the data sets and the correct protocol variables (parameterized resources) of process runs.
- the present invention can be implemented as a computer program product that comprises a computer program mechanism embedded in a nontransitory computer readable storage medium.
- the computer program product could contain the program modules shown in any combination of Figures 1, 2, 3, 4, and/or 5. These program modules can be stored on a CD-ROM, DVD, magnetic disk storage product, or any other tangible computer readable data or program storage product.
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/690,134 US10586015B2 (en) | 2014-08-01 | 2017-08-29 | Systems and methods for process design and analysis |
PCT/US2018/048179 WO2019046210A1 (en) | 2017-08-29 | 2018-08-27 | Systems and methods for process design and analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3676734A1 true EP3676734A1 (en) | 2020-07-08 |
Family
ID=65527887
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP18851799.9A Withdrawn EP3676734A1 (en) | 2017-08-29 | 2018-08-27 | Systems and methods for process design and analysis |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP3676734A1 (en) |
CN (1) | CN111279347A (en) |
WO (1) | WO2019046210A1 (en) |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1992003905A2 (en) * | 1990-08-31 | 1992-03-19 | Ab Volvo | A method and apparatus for optimally allocating resources |
US9298771B2 (en) * | 2013-01-30 | 2016-03-29 | Ias Solutions, Inc. | Resource estimation for a query optimization process |
US9910936B2 (en) * | 2014-08-01 | 2018-03-06 | Riffyn, Inc. | Systems and methods for process design and analysis |
-
2018
- 2018-08-27 EP EP18851799.9A patent/EP3676734A1/en not_active Withdrawn
- 2018-08-27 CN CN201880070170.3A patent/CN111279347A/en active Pending
- 2018-08-27 WO PCT/US2018/048179 patent/WO2019046210A1/en unknown
Also Published As
Publication number | Publication date |
---|---|
CN111279347A (en) | 2020-06-12 |
WO2019046210A1 (en) | 2019-03-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9910936B2 (en) | Systems and methods for process design and analysis | |
US10586015B2 (en) | Systems and methods for process design and analysis | |
US11625512B2 (en) | Systems and methods for process design and analysis | |
Gkoutos et al. | The Units Ontology: a tool for integrating units of measurement in science | |
Visser et al. | BioAssay Ontology (BAO): a semantic description of bioassays and high-throughput screening results | |
Bereman et al. | An automated pipeline to monitor system performance in liquid chromatography–tandem mass spectrometry proteomic experiments | |
Loh et al. | Recommendations for laboratory informatics specifications needed for the application of patient-based real time quality control | |
US20210034620A1 (en) | Systems and methods for querying time series data | |
Morrell et al. | The experiment data depot: a web-based software tool for biological experimental data storage, sharing, and visualization | |
US10467226B2 (en) | Method for in-database feature selection for high-dimensional inputs | |
US20170060972A1 (en) | Systems and methods for processing process data | |
Favaloro et al. | An update on quality control for the PFA-100/PFA-200 | |
Bittremieux et al. | iMonDB: mass spectrometry quality control through instrument monitoring | |
US10817494B2 (en) | Systems and methods for parsing data in order to form structured data tables | |
Bauer et al. | Interdisciplinary approach towards a systems medicine toolbox using the example of inflammatory diseases | |
Kasalica et al. | APE in the Wild: Automated Exploration of Proteomics Workflows in the bio. tools Registry | |
US8352050B2 (en) | System and method for displaying status of field devices | |
Kricka | Emerging and disruptive technologies | |
Neely | Cloudy with a chance of peptides: accessibility, scalability, and reproducibility with cloud-hosted environments | |
CN111213149B (en) | System and method for process design and analysis | |
US20180181889A1 (en) | Systems and methods for formulation of experiments for analysis of process performance | |
Handler et al. | Statistics in proteomics: A meta-analysis of 100 proteomics papers published in 2019 | |
Martínez-Bartolomé et al. | PACOM: A versatile tool for integrating, filtering, visualizing, and comparing multiple large mass spectrometry proteomics data sets | |
EP3676734A1 (en) | Systems and methods for process design and analysis | |
Sparkes et al. | AutoLabDB: a substantial open source database schema to support a high-throughput automated laboratory |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20200324 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN WITHDRAWN |
|
18W | Application withdrawn |
Effective date: 20200702 |