CN112201301A - Virtual reality-based drug design cloud computing flow control system and method thereof - Google Patents
Virtual reality-based drug design cloud computing flow control system and method thereof Download PDFInfo
- Publication number
- CN112201301A CN112201301A CN202011149511.1A CN202011149511A CN112201301A CN 112201301 A CN112201301 A CN 112201301A CN 202011149511 A CN202011149511 A CN 202011149511A CN 112201301 A CN112201301 A CN 112201301A
- Authority
- CN
- China
- Prior art keywords
- module
- drug design
- task
- virtual reality
- cloud computing
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 238000009510 drug design Methods 0.000 title claims abstract description 67
- 238000004364 calculation method Methods 0.000 claims abstract description 41
- 241000121629 Majorana Species 0.000 claims abstract description 19
- 230000003993 interaction Effects 0.000 claims abstract description 19
- 238000012795 verification Methods 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 238000005516 engineering process Methods 0.000 claims abstract description 17
- 238000003032 molecular docking Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000001914 filtration Methods 0.000 claims abstract description 11
- 238000000329 molecular dynamics simulation Methods 0.000 claims abstract description 10
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 6
- 230000035495 ADMET Effects 0.000 claims abstract description 5
- 238000010535 acyclic diene metathesis reaction Methods 0.000 claims abstract description 5
- 150000001875 compounds Chemical class 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 18
- 150000003384 small molecules Chemical class 0.000 claims description 15
- 238000004886 process control Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 8
- 238000013515 script Methods 0.000 claims description 8
- 239000003814 drug Substances 0.000 claims description 7
- 230000000007 visual effect Effects 0.000 claims description 7
- 238000012800 visualization Methods 0.000 claims description 5
- 238000010205 computational analysis Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 3
- 150000001413 amino acids Chemical class 0.000 claims description 2
- 239000013078 crystal Substances 0.000 claims description 2
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 230000004907 flux Effects 0.000 abstract description 2
- 150000002611 lead compounds Chemical class 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 2
- 239000003446 ligand Substances 0.000 description 2
- 239000002547 new drug Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 229940043263 traditional drug Drugs 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004166 bioassay Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000003776 cleavage reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009509 drug development Methods 0.000 description 1
- 238000007877 drug screening Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 230000002209 hydrophobic effect Effects 0.000 description 1
- 230000009456 molecular mechanism Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000007017 scission Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000003041 virtual screening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B15/00—ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
- G16B15/30—Drug targeting using structural data; Docking or binding prediction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/211—Schema design and management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Crystallography & Structural Chemistry (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biotechnology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medicinal Chemistry (AREA)
- Biophysics (AREA)
- Human Computer Interaction (AREA)
- Pharmacology & Pharmacy (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a virtual reality-based drug design cloud computing flow control system and a method thereof, wherein the drug design cloud computing flow control system comprises a drug design module group, an interaction and scheduling module and a virtual reality drug design module; the drug design module group comprises a verification module, a database module, a filtering module, a preprocessing module, a method module and an analysis module; the drug design module group is displayed in a module form, and a user freely selects and combines corresponding modules to calculate according to project requirements; the method module comprises a molecular docking module, a molecular dynamics module, a combined free energy calculation module, a free energy perturbation module, a pharmacophore module, an artificial intelligence molecule generation module and an ADMET prediction module; the interaction and scheduling module comprises a Jupyter unit and a Majorana task scheduling platform. The invention realizes the cross-platform scheduling of the drug design cloud computing task based on the virtual reality technology with high flux and high parallelism.
Description
Technical Field
The invention belongs to the field of artificial intelligence-based drug design, and particularly relates to a drug design cloud computing flow control method based on a virtual reality technology.
Background
The traditional computer-aided drug design method, mainly a structure-based drug design method, has been widely applied in the field of new drug development.
These traditional drug designs are all based on open source or commercial software, and are classified as either Linux-based or Windows-based platforms.
Typical drug design methods or software are: maestro software, MOE software, Amber molecular dynamics software, Autudock molecular docking software, Pymol display software, VMD display software, and the like.
Although these drug design methods are widely used, they have the following drawbacks:
1. the process integration is limited: open source software can generally independently complete specific computing tasks, but if the open source software needs to be integrated to complete more complex functions, multiple pieces of software need to be integrated by self-writing scripts, and different pieces of software have different input and output formats, and the integration can have certain difficulty. Commercial software is more functionally sophisticated and has a relatively sophisticated flow, but software costs are generally expensive. Because the software is commercial software, if secondary development is needed, certain access difficulty exists.
2. Scheduling across platforms is not possible: at present, almost all software needs to be manually logged in and a task script is compiled and then submitted to respective platforms for computing if a cloud computing platform needs to be used.
3. Visualization is mainly based on 2D or pseudo-3D display of a display, and certain display difficulty exists for complex three-dimensional structures such as small molecules and target compounds.
Disclosure of Invention
In order to solve the technical problems, the invention provides a drug design cloud computing flow control method based on a virtual reality technology.
In order to achieve the purpose, the invention adopts the following scheme:
the invention mainly relates to a medicine design cloud computing flow control system based on artificial intelligence and virtual reality technology, which comprises a medicine design module group, an interaction and scheduling module and a virtual reality medicine design module;
the drug design module group comprises a verification module, a database module, a filtering module, a preprocessing module, a method module and an analysis module; the drug design module group comprises a typical drug design method and software, and specifically comprises Maestro software, MOE software, Amber molecular dynamics software, Autudock molecular docking software, Pymol display software and VMD display software, which are displayed in a module form, and a user can freely select and combine corresponding modules according to project requirements to calculate;
the method module comprises a Molecular docking module (Molecular docking), a Molecular Dynamics module (Molecular Dynamics), a combined free energy calculation module (MMGBSA/MMPBSA), a free energy perturbation module (FEP), a Pharmacophore module (Pharmacophore), an artificial intelligent molecule generation module and an ADMET prediction module.
The interaction and scheduling module comprises a Jupyter unit and a Majorana task scheduling platform;
the Jupyter unit is an interface for interacting with a user, and the user can send instructions for calling various modules to complete corresponding drug design operation according to the requirements of projects through the Jupyter unit; the virtual reality drug design module can be called to complete the whole drug design operation in a virtual reality visual operation mode and display the operation result;
the Majorana task scheduling platform is an internally developed scheduling system, and has the functions of receiving a user instruction sent by a Jupyter unit, calling a corresponding task module from a drug design module group for calculation, submitting a calculation task to a specified cloud computing platform, and checking the state of the calculation task; the checking and calculating task state mainly comprises whether the task is successfully submitted, the number of the GPUs and the state (starting, executing, completing and the like) of the task, a task log, an output file and the like.
The cloud computing platform comprises an amazon cloud, an Tencent cloud and an Ali cloud, a task execution script and a task monitoring script which are butted with each cloud computing platform are built in the Majorana task scheduling platform, and a user can easily realize the cross-platform cloud computing requirement according to the computing requirement;
the virtual reality drug design module comprises virtual reality hardware equipment: the drug design cloud computing process control method can be operated and completed in a virtual reality visual operation mode by operating virtual reality hardware equipment, and results can be displayed timely after computing is completed.
The visualization operation in the virtual reality drug design module can be operated in a 2D or 3D manner;
the display result in the virtual reality drug design module can be displayed in a 2D or 3D mode;
the virtual reality drug design module can autonomously select whether to adopt a virtual reality mode for operation according to the requirements of a user;
a drug design cloud computing flow control method based on a virtual reality technology comprises the following processes:
(a) small scale verification
The small-scale verification firstly calls a verification module which comprises four sub-modules of preprocessing, a database, a method and analysis, the required sub-module can be selected according to the actual requirement of the project, and the appropriate sub-module is selected for analysis and verification to obtain the corresponding parameter, and the corresponding parameter is recorded.
The small-scale verification is a simple version process, and mainly aims to verify the performance of a calculation method in a corresponding research system, and parameters after the verification are applied to a formal screening process; the specific verification sub-modules are mainly determined according to the actual requirements of the project.
(b) Data read-in
Calling a database module to read original data and structures, and mainly reading structural information of target spots and small molecular compounds into a workflow from the database;
(c) filtration and screening
Calling a filtering module to carry out primary filtering and screening on the small molecule database, wherein the main content is to filter out some molecules with poor druggability through five rules of druggability;
(d) pretreatment of
And calling a preprocessing module to process the target spot and the small molecule data read by the database module, and performing preprocessing work before formal calculation. Generally, the pretreatment is mainly divided into target pretreatment and micromolecule pretreatment. The pretreatment of the target mainly comprises the following steps: repairing target point deletion residues in the crystal structure, hydrogenating, charging, protonating amino acid and the like, and storing into a standard PDB format;
the pretreatment method of the small molecules comprises the following steps: each small molecule filtered by the database needs to be preprocessed, and the preprocessing mainly comprises the steps of converting a plane two-dimensional structure into a three-dimensional structure, searching the lowest energy conformation, calculating PKa, hydrogenating, adding charges and the like, and the small molecules are stored into a standard format, such as an SDF format.
(e) Computational analysis
Calling a method module, calling a corresponding module to perform computational analysis according to actual computational requirements, wherein the method module comprises a Molecular docking module (Molecular docking), a Molecular Dynamics module (Molecular Dynamics), a combined free energy computing module (MMGBSA/MMPBSA), a free energy perturbation module (FEP), a Pharmacophore module (Pharmacophore), an artificial intelligence molecule generation module, an ADMET prediction module and other main computational analysis modules;
(f) cloud computing
And calling the Majorana task scheduling platform, submitting a computing task to a specified cloud platform (Amazon cloud, Tencent cloud, Ariiyun and the like) according to the computing requirement of the method module, and checking the state of the computing task. Majorana is a scheduling system developed in the interior, and mainly comprises whether a task is successfully submitted, the number of GPUs (graphic processing units) occupied by the task, the state (starting, executing, completing and the like) of the task, a task log and an output file.
(g) Results display
And calling an analysis module to analyze the display result, and automatically writing the task data into the database module. The display result is mainly related to which methods are called in the method module, and the main contents comprise the stability of the structures of the compounds, the key interaction between small molecule targets, the energy value and the like by using a chart and animation for displaying the structures of the compounds according to a binding mode, a molecular dynamics track, the structures of the compounds, the properties of the compounds and the like. Molecular docking and free energy calculations are taken here as examples. After the molecular docking is completed, the system can display a binding mode obtained by software calculation, mark the interaction between the key small molecules and the target spot, such as hydrogen bond, hydrophobic interaction, polar interaction and the like, and output the interaction into a standard format such as PNG format picture, GIF animation and the like, so that the interaction is convenient to review and display in the future. The free energy calculation can show the calculated free energy value, error, dynamic track stability and the like, and can also be output into PNG format pictures, GIF animation and the like, which are convenient to review and show in the future.
(h) Loop execution
The steps (b) - (g) are executed circularly, whether the steps are ended or not depends on preset indexes, such as 100 compounds with better activity are predicted, molecules with energy values within a certain range are predicted, and the like, and the calculation of the next round can be stopped when the standard is met.
The complete process of the drug design cloud computing process control method based on the virtual reality technology comprises the steps (a) - (h), and the steps (a) - (h) can be freely combined by a user according to the requirements of projects.
The invention brings the following beneficial effects:
a) the cross-platform scheduling of the drug design cloud computing task based on the virtual reality technology with high flux and high parallelism is realized.
b) The functions of molecular processing, evaluation, analysis and the like of the new drug screening process are seamlessly connected.
c) The steps of creating, submitting and managing all molecular docking and virtual screening tasks, analyzing results, drawing and the like are integrated into Jupitter, and the visual operation of the molecular docking cloud computing process is realized.
d) And a virtual display technology is introduced, so that rational drug design based on structure can be more truly carried out. .
Drawings
Fig. 1 is a flow diagram of a drug design cloud computing flow control method based on virtual reality technology.
Fig. 2 is the specific content of a verification module of the drug design cloud computing process control method based on the virtual reality technology.
Fig. 3 is specific contents of modules of a drug design cloud computing process control method based on virtual reality technology.
FIG. 4 is a graph of correlation between biological assay test and calculated predicted activity in example 1.
Fig. 5 is a comparison of the CPU running time of the conventional flow and the Majorana task scheduling system in embodiment 2.
FIG. 6 is a graph showing the results of the drug design method in example 3.
FIG. 7 is a graph showing the results of molecular characterization in example 4.
FIG. 8 is a graph showing the results of the combination mode in example 4.
Detailed Description
Preferred embodiments of the present invention will be described in further detail below with reference to the accompanying drawings:
example 1
As shown in fig. 1-3, the drug design cloud computing process control system based on artificial intelligence and virtual reality technology comprises a drug design module group, an interaction and scheduling module and a virtual reality drug design module;
the drug design module group comprises a verification module, a database module, a filtering module, a preprocessing module, a method module and an analysis module; the drug design module group comprises a typical drug design method and software, and specifically comprises Maestro software, MOE software, Amber molecular dynamics software, Autudock molecular docking software, Pymol display software and VMD display software, which are displayed in a module form, and a user can freely select and combine corresponding modules according to project requirements to calculate;
the method module comprises a Molecular docking module (Molecular docking), a Molecular Dynamics module (Molecular Dynamics), a combined free energy calculation module (MMGBSA/MMPBSA), a free energy perturbation module (FEP), a Pharmacophore module (Pharmacophore), an artificial intelligent molecule generation module and an ADMET prediction module.
The interaction and scheduling module comprises a Jupyter unit and a Majorana task scheduling platform;
the Jupyter unit is an interface for interacting with a user, and the user can send instructions for calling various modules to complete corresponding drug design operation according to the requirements of projects through the Jupyter unit; the virtual reality drug design module can be called to complete the whole drug design operation in a virtual reality visual operation mode and display the operation result;
the Majorana task scheduling platform is an internally developed scheduling system, and has the functions of receiving a user instruction sent by a Jupyter unit, calling a corresponding task module from a drug design module group for calculation, submitting a calculation task to a specified cloud computing platform, and checking the state of the calculation task; the checking and calculating task state mainly comprises whether the task is successfully submitted, the number of the GPUs and the state (starting, executing, completing and the like) of the task, a task log, an output file and the like.
The cloud computing platform comprises an amazon cloud, an Tencent cloud and an Ali cloud, a task execution script and a task monitoring script which are butted with each cloud computing platform are built in the Majorana task scheduling platform, and a user can easily realize the cross-platform cloud computing requirement according to the computing requirement;
the invention is different from the prior art in that: the virtual reality drug design module comprises virtual reality hardware equipment: the drug design cloud computing process control method can be operated and completed in a virtual reality visual operation mode by operating virtual reality hardware equipment, and results can be displayed timely after computing is completed. This may give the user a better visual effect than traditional drug design software, as well as understanding the molecular mechanisms therein, with less requirements on the user's professional background knowledge.
Example 2
Screening of shoot-head compounds against a target
The method comprises the steps of firstly carrying out small-scale verification, calling small molecules in a database from a database module, wherein the number of the small molecules is about 1 million, then calling a pretreatment module to carry out pretreatment on the molecules, and selecting a calling method module to carry out method verification on a molecule docking method in consideration of the fact that the target of a project is to screen a seedling-end compound, so that a proper screening parameter is found.
And then calling a database module to read original data and structures, calling a Majorana task scheduling platform to submit a screening task by using parameters obtained by small-scale verification, and tracking a calculation result in real time. And after the calculation is finished, calling an analysis module to analyze the calculation result. And recommending the screened seedling compounds to a biological test team according to the calculation result, thereby completing the calculation task. FIG. 4 is a graph showing the correlation between the activity of a small molecule predicted by the calculation module of this example and the activity of an experiment after the activity is recommended to a biological test team. As can be seen from FIG. 4, the calculated predicted activity and the experimental activity have a high correlation, indicating the reliability of the calculation method of this example.
Compared with other traditional methods, the method firstly adopts the flow and modularization operation, thereby facilitating the screening work and improving the efficiency. Meanwhile, due to the use of the Majorana task scheduling system, the tracking and analysis of calculation are more convenient, and the efficiency is further improved. Fig. 5 shows the comparison of the CPU running time of the conventional drug design process and the Majorana task scheduling system, and it can be seen that the Majorana task scheduling system only accounts for 40% of the running time of the conventional process, which means that the flow and modularization operation can significantly improve the working efficiency.
Example 3
Lead compound for developing new medicine aiming at target point
Some candidate shoot-head compounds with good experimental properties are screened out in the embodiment 1, the batch of shoot-head compounds are optimized by using a drug design cloud computing process control method based on a virtual reality technology again, and finally the lead compounds are obtained.
Firstly, the designed molecules and target structures are led into a system, a virtual reality drug design module is called, and drug design based on virtual reality is carried out according to a combination mode. Analyzing key combination modes between target spots and the seedling compounds directly according to the combination modes displayed in virtual reality, calling corresponding method modules according to actual calculation requirements, then calling a Majorana task scheduling platform, submitting calculation tasks to a cloud platform according to the calculation requirements of the method modules, performing cloud calculation evaluation on the background by using the calculation platform, and feeding back the calculation tasks to team members in time. The team members evaluate the feedback according to the calculation, watch the combination mode again with the help of the virtual reality technology, redesign the molecules, and submit the background calculation evaluation again. Through multiple rounds of iteration, a reasonable candidate lead compound is found. All data, scheduling, in the process can be recorded in the database, so that the disk can be conveniently backtracked in the future.
As shown in fig. 6, a visualization of the drug design flow of the present embodiment is shown. Through this process, the process of fragment cleavage and growth of the molecule, as well as the transition path between different backbones, can be observed. From this visualization process, a stepwise optimization process of the target molecule can be understood. Compared with other traditional methods, the method firstly adopts the flow and modularization operation, thereby facilitating the optimization work of the lead compound and improving the efficiency. In the case, a virtual reality drug design module is also used, so that the analysis and interpretation of results are facilitated; meanwhile, due to the use of the Majorana task scheduling system, the tracking and analysis of calculation are more convenient, and the efficiency is further improved.
Example 4
Develops a new medicine aiming at a target point and externally displays the research and development result
Some candidate lead compounds with good experimental properties were obtained from the procedures of example 1 and example 2. The cloud computing process control method is designed by utilizing the medicine based on the virtual reality technology, the batch of computing results are called, analyzed and displayed, and relevant results including a combination mode, interaction, an energy value, stability, principal component analysis and the like of the lead compounds are displayed.
As shown in fig. 7 and 8, fig. 7 illustrates the description of the molecular structure by the calculation method of the present embodiment, and mainly by means of molecular fingerprints and key value pairs, the structural features of a large number of molecules can be rapidly obtained and represented and stored in a digital manner. FIG. 8 shows the binding pattern of molecules to proteins, and it can be seen that not only the basic protein-ligand interactions are shown, but also the interaction types are further clustered to obtain a pharmacophore-like analysis, which can gain more insight into the protein-ligand binding interactions and the driving force. Compared with other traditional methods, the method is firstly a flow and modularization operation, and results are conveniently displayed.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (9)
1. A virtual reality-based drug design cloud computing flow control system is characterized by comprising a drug design module group, an interaction and scheduling module and a virtual reality drug design module;
the drug design module group comprises a verification module, a database module, a filtering module, a preprocessing module, a method module and an analysis module;
the drug design module group comprises Maestro software, MOE software, Amber molecular dynamics software, Autudock molecular docking software, Pymol display software and VMD display software, and is displayed in a module form, and a user can freely select and combine corresponding modules according to project requirements to calculate;
the method module comprises a molecular docking module, a molecular dynamics module, a combined free energy calculation module, a free energy perturbation module, a pharmacophore module, an artificial intelligence molecule generation module and an ADMET prediction module;
the interaction and scheduling module comprises a Jupyter unit and a Majorana task scheduling platform.
2. The system of claim 1, wherein the Jupyter unit is an interface for interacting with a user, and the Jupyter unit sends instructions for calling various modules according to project requirements to complete corresponding drug design operations; or the virtual reality drug design module is called to complete the whole drug design operation in a virtual reality visual operation mode and display the operation result.
3. The system of claim 1, wherein a task execution script and a task monitoring script which are butted with each cloud computing platform are built in the Majorana task scheduling platform, and a user can easily realize cross-platform cloud computing requirements according to computing requirements; and calling a corresponding task module in the medicine design module group for calculation by receiving a user instruction sent by the Jupyter unit, submitting the calculation task to a specified cloud computing platform, and checking the state of the calculation task.
4. The system of claim 3, wherein said checking the status of the computing task comprises whether the task was successfully submitted, the task occupied CPU, the number of GPUs, the status of the task, a task log, and an output file.
5. The system of claim 1, wherein the visualization operation in the virtual reality drug design module can operate in 2D or 3D; the display result in the virtual reality drug design module can be displayed in a 2D or 3D mode.
6. A drug design cloud computing process control method based on a virtual reality technology is characterized by comprising the following steps:
step (a) small-scale verification:
calling a verification module, which comprises four sub-modules of preprocessing, a database, a method and analysis, selecting a required sub-module according to actual requirements, and selecting a proper sub-module for analysis and verification to obtain a corresponding parameter;
reading data in the step (b):
calling a database module to read original data and structures, and mainly reading structural information of target spots and small molecular compounds into a workflow from the database;
step (c) filtering and screening:
calling a filtering module to carry out primary filtering and screening on the small molecule database, and filtering out some molecules with poor druggability through five rules of druggability;
step (d) pretreatment:
calling a preprocessing module to process the target spot and the small molecule data read by the database module, and performing preprocessing work before formal calculation;
step (e) computational analysis:
calling a method module, calling a corresponding module to perform calculation analysis according to actual calculation requirements, and (f) performing cloud calculation:
calling the Majorana task scheduling platform, submitting a computing task to a specified cloud platform according to the computing requirement of the method module, and checking the state of the computing task;
and (g) displaying a result:
calling an analysis module to analyze the display result, and automatically writing the task data into a database module;
step (h) is executed in a loop:
and (c) performing steps (b) - (g) in a circulating manner, wherein the complete process of the drug design cloud computing process control method based on the virtual reality technology comprises the steps (a) - (h), and whether the process is ended depends on preset indexes.
7. The method of claim 6, wherein in step (d), the pretreatment is divided into target pretreatment and small molecule pretreatment; the pretreatment of the target site comprises the following steps: repairing target point deletion residues in the crystal structure, hydrogenating, charging, protonating amino acid, and storing into a standard PDB format; each small molecule filtered by the database needs to be preprocessed, and the preprocessing mainly comprises the steps of converting a plane two-dimensional structure into a three-dimensional structure, searching the lowest energy conformation, calculating PKa, hydrogenating, adding charges and storing into a standard format.
8. The method of claim 6, wherein in the step (g) result presentation, the primary content comprises at least one of: the method comprises the following steps of combining modes, molecular dynamics tracks, compound structures, compound properties, displaying the stability of the compound structures, the key interaction between small molecular targets and energy values by using charts and animation.
9. The method of claim 6, wherein in step (h), the indicator comprises at least one of: 100 compounds with better activity are obtained through prediction, molecules with energy values within a certain range interval and the like are obtained through prediction, and the calculation in the next round can be stopped when the standard is met.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011149511.1A CN112201301A (en) | 2020-10-23 | 2020-10-23 | Virtual reality-based drug design cloud computing flow control system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011149511.1A CN112201301A (en) | 2020-10-23 | 2020-10-23 | Virtual reality-based drug design cloud computing flow control system and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112201301A true CN112201301A (en) | 2021-01-08 |
Family
ID=74011066
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011149511.1A Pending CN112201301A (en) | 2020-10-23 | 2020-10-23 | Virtual reality-based drug design cloud computing flow control system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112201301A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113012781A (en) * | 2021-02-07 | 2021-06-22 | 重庆三峡医药高等专科学校 | Pharmacological digital human system |
| CN114240173A (en) * | 2021-12-20 | 2022-03-25 | 吉斯凯(苏州)制药有限公司 | New drug development nonlinear task scheduling method based on drug design |
| CN114464269A (en) * | 2022-04-07 | 2022-05-10 | 国家超级计算天津中心 | Virtual medicine generation method and device and computer equipment |
| WO2022188653A1 (en) * | 2021-03-10 | 2022-09-15 | 腾讯科技（深圳）有限公司 | Molecular scaffold hopping processing method and apparatus, medium, electronic device and computer program product |
| WO2024063585A1 (en) * | 2022-09-21 | 2024-03-28 | (주)신테카바이오 | Cloud platform system and service method capable of distributed and parallel processing for large-scale workflows |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103294933A (en) * | 2013-05-10 | 2013-09-11 | 司宏宗 | Drug screening method |
| WO2019009451A1 (en) * | 2017-07-06 | 2019-01-10 | 부경대학교 산학협력단 | Method for screening new targeted drugs through numerical inversion of quantitative structure-performance relationship and molecular dynamics computer simulation |
| CN109885390A (en) * | 2019-02-21 | 2019-06-14 | 深圳晶泰科技有限公司 | Molecular docking cloud computing flow control method |
| CN110867256A (en) * | 2019-10-17 | 2020-03-06 | 湖南中医药大学 | Optimized Ganfule anti-liver cancer formula pharmacological analysis method and system |
| KR20200080082A (en) * | 2018-12-26 | 2020-07-06 | 주식회사 유클리드소프트 | System for Molecular Dynamics Simulation based on web |
-
2020
- 2020-10-23 CN CN202011149511.1A patent/CN112201301A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103294933A (en) * | 2013-05-10 | 2013-09-11 | 司宏宗 | Drug screening method |
| WO2019009451A1 (en) * | 2017-07-06 | 2019-01-10 | 부경대학교 산학협력단 | Method for screening new targeted drugs through numerical inversion of quantitative structure-performance relationship and molecular dynamics computer simulation |
| KR20200080082A (en) * | 2018-12-26 | 2020-07-06 | 주식회사 유클리드소프트 | System for Molecular Dynamics Simulation based on web |
| CN109885390A (en) * | 2019-02-21 | 2019-06-14 | 深圳晶泰科技有限公司 | Molecular docking cloud computing flow control method |
| CN110867256A (en) * | 2019-10-17 | 2020-03-06 | 湖南中医药大学 | Optimized Ganfule anti-liver cancer formula pharmacological analysis method and system |
Non-Patent Citations (1)
| Title |
|---|
| 雷国华: "《计算机辅助医学技术导论》", vol. 2011, 30 September 2011, 中国石油大学出版社, pages: 96 - 98 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113012781A (en) * | 2021-02-07 | 2021-06-22 | 重庆三峡医药高等专科学校 | Pharmacological digital human system |
| WO2022188653A1 (en) * | 2021-03-10 | 2022-09-15 | 腾讯科技（深圳）有限公司 | Molecular scaffold hopping processing method and apparatus, medium, electronic device and computer program product |
| CN114240173A (en) * | 2021-12-20 | 2022-03-25 | 吉斯凯(苏州)制药有限公司 | New drug development nonlinear task scheduling method based on drug design |
| CN114464269A (en) * | 2022-04-07 | 2022-05-10 | 国家超级计算天津中心 | Virtual medicine generation method and device and computer equipment |
| WO2024063585A1 (en) * | 2022-09-21 | 2024-03-28 | (주)신테카바이오 | Cloud platform system and service method capable of distributed and parallel processing for large-scale workflows |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112201301A (en) | Virtual reality-based drug design cloud computing flow control system and method thereof | |
| US10255409B2 (en) | Systems and methods for in silico evaluation of polymers | |
| CA2336608C (en) | Method for defining durable data for regression testing | |
| CN110249300B (en) | Test case generator built in data integration workflow editor | |
| US8296117B2 (en) | Business process optimizer | |
| CA2693244A1 (en) | Methods for similarity searching of chemical reactions | |
| Savran et al. | pyCSEP: a Python toolkit for earthquake forecast developers | |
| Ermakov et al. | A survey of software tool utilization and capabilities for quantitative systems pharmacology: what we have and what we need | |
| Rantanen et al. | An analytic and systematic framework for estimating metabolic flux ratios from 13 C tracer experiments | |
| Koehler Leman et al. | Ensuring scientific reproducibility in bio-macromolecular modeling via extensive, automated benchmarks | |
| CN109885390B (en) | Molecular docking cloud computing flow control method | |
| Li et al. | Multi-programming-language commits in oss: An empirical study on apache projects | |
| Navas et al. | Models as enablers of agility in complex systems engineering | |
| WO2022082740A1 (en) | Drug design cloud computing flow control system based on virtual reality and method thereof | |
| Wiechert et al. | A primer to 13C metabolic flux analysis | |
| Ieong et al. | Progress towards automated Kepler scientific workflows for computer-aided drug discovery and molecular simulations | |
| Schulz et al. | Visual analytics for stochastic simulation in cell biology | |
| Chauhan et al. | DocVSP (Docking-based Virtual Screening Perl-script) for Automating and Integrating AutoDock and SBDD | |
| Bockelman | IRIS-HEP Strategic Plan for the Next Phase of Software Upgrades for HL-LHC Physics | |
| Pinto et al. | Cognitive Driven Development helps software teams to keep code units under the limit! | |
| Diaz et al. | A collaborative approach to complex systems engineering using a web-based visual analytics framework | |
| Bockelman et al. | arXiv: IRIS-HEP Strategic Plan for the Next Phase of Software Upgrades for HL-LHC Physics | |
| US11609807B2 (en) | Computing task management and analysis system for molecular force field parameter building and operation method thereof | |
| Salam et al. | Quantum computing challenges and solutions in software industry—A multivocal literature review | |
| Salomon et al. | Course Friction Explorer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |