CN109642258A - A kind of method and system of tumor prognosis prediction - Google Patents
A kind of method and system of tumor prognosis prediction Download PDFInfo
- Publication number
- CN109642258A CN109642258A CN201880002164.4A CN201880002164A CN109642258A CN 109642258 A CN109642258 A CN 109642258A CN 201880002164 A CN201880002164 A CN 201880002164A CN 109642258 A CN109642258 A CN 109642258A
- Authority
- CN
- China
- Prior art keywords
- tumor
- information
- prognosis
- gene
- prognosis prediction
- 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.)
- Granted
Links
Classifications
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
- C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
- C12Q1/6876—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes
- C12Q1/6883—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material
- C12Q1/6886—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material for cancer
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q2600/00—Oligonucleotides characterized by their use
- C12Q2600/118—Prognosis of disease development
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q2600/00—Oligonucleotides characterized by their use
- C12Q2600/156—Polymorphic or mutational markers
Abstract
The embodiment of the present application discloses a kind of method and system of tumor prognosis prediction.The tumor prognosis prediction technique includes: the characteristic information for obtaining tumor patient, and the characteristic information at least reflects the tumor patient in the gene mutation information of tumor locus；The prognosis prediction result of the tumor patient is determined according to tumor prognosis prediction model based on the characteristic information of the tumor patient.The application is based on tumor patient data and establishes tumor prognosis prediction model, and the accuracy rate to tumor prognosis prediction can be improved.
Description
Technical field
This application involves medical domain, in particular to a kind of method and system of tumor prognosis prediction.
Background technique
Tumour (e.g., osteosarcoma etc.) is world's second largest Death causes, and tumor mortality rate and disease incidence are also constantly increasing.
Although the diagnosing and treating measure of tumour is continuously improved, the death rate of patient still cannot be controlled effectively, recurred and shifted
It is the main reason for causing tumor patient dead, such as osteosarcoma can be seriously threatened to the Various Tissues organ metastasis such as lung, spinal cord
The life of patient.
Currently, clinical mainly assess tumour by pathology and iconography metamorphosis, specifies patient age, swells
The indexs such as tumor histological type, Surgical staging and residual tumor.With the technologies such as molecular biology and Molecular Epidemic Neo-Confucianism
Development, the screening study of progress tumor-related gene and molecular marker is the hot spot of current tumor research on a molecular scale,
Such method can provide with reference to indication, prediction postoperative recurrence or turn for tumor patient operation from the molecular level of tumour cell
It moves, eradicate the objective indication of tumour and provide target spot etc. for anti-metastatic therapy.
Therefore, differential expression of the research gene in tumour formation, development, drug resistance etc. analyzes gene in tumour
Activation and inhibition situation, so that more comprehensive and accurate assessment conditions of patients and prognosis, implement individual to tumor patient to realize
Change treatment is of great significance and those skilled in the art's focus of attention.
Summary of the invention
One of the embodiment of the present application provides a kind of tumor prognosis prediction technique, comprising: the characteristic information of tumor patient is obtained,
The characteristic information at least reflects the gene mutation information of the tumor patient；Based on the characteristic information of the tumor patient, root
According to tumor prognosis prediction model, the prognosis prediction result of the tumor patient is determined.
In some embodiments, the gene mutation information include the gene to mutate on DNA and its mutation abundance,
And/or tumor prognosis prediction related gene and its mutation abundance on DNA.
In some embodiments, the characteristic information for obtaining tumor patient further comprises: obtaining the tumor patient
Tissue samples；Extract the DNA of the tissue samples；Prepare the library of the DNA；Gene sequencing is carried out according to the library,
Obtain sequencing result；The sequencing result is analyzed, determines the gene mutation information of the tumor patient.
In some embodiments, the characteristic information further includes at least one in the following information of the tumor patient:
Age, gender, smoking history, the length of education enjoyed, length of service, therapeutic scheme and Sample preservation time.
In some embodiments, the tumor prognosis prediction model is supporting vector machine model or neural network model.
In some embodiments, the tumor prognosis prediction technique further include: utilize the characteristic information of several tumor patients
And its prognosis information training initial model obtains the tumor prognosis prediction model.
In some embodiments, characteristic information and its prognosis information the training initial model using several tumor patients
Obtaining the tumor prognosis prediction model includes: to be mutated abundance in the gene mutation information for remove the several tumor patients to be less than
The mutated gene information of certain given threshold.
In some embodiments, characteristic information and its prognosis information the training initial model using several tumor patients
Obtaining the tumor prognosis prediction model includes: that the redundancy gene in the gene mutation information for remove the several tumor patients is dashed forward
Become information.
In some embodiments, the tumor prognosis prediction model is supporting vector machine model；It is described to utilize several tumours
It includes: according to several swollen that characteristic information and its prognosis information the training initial model of patient, which obtains the tumor prognosis prediction model,
Each gene mutation information determines that at least partly gene is swollen to the contribution margin of supporting vector machine model in the characteristic information of tumor patient
Tumor prognosis prediction related gene；Using several tumor patients the tumor prognosis prediction related gene gene mutation information and
Its prognosis information training initial model obtains the tumor prognosis prediction model.
In some embodiments, the tumor prognosis prediction model is supporting vector machine model；The trained initial model
Obtain the tumor prognosis prediction model further include: optimize the support vector machines mould using particle swarm algorithm or grid dividing method
The parameter of type.
In some embodiments, the prognosis prediction result include: progression of disease, stable disease, part alleviate and completely
Alleviate；Alternatively, the prognosis prediction result includes: that therapeutic effect is good and therapeutic effect is bad.
In some embodiments, the tumour is osteosarcoma.
In some embodiments, the characteristic information at least reflects the mutation letter of at least one following gene of Patients with Osteosarcoma
Breath: KMT2C, SOX9, LRP1B, NF-1, PRKDC, FAT1, STAG2, SLIT2, NOTCH1, EPHA7, ATRX, KDM6A, APC,
RANBP2、RARA.AS1、C11orf30、ROS1、ARID2、TAF1、DICER1、MSH2、MSH6、TP53、KDM5A、JAK2、
ALK, RB1, NOTCH2 and RICTOR.
In some embodiments, the tumor patient gene mutation information is that the gene mutation of osteosarcoma diseased region is believed
Breath.
One of the embodiment of the present application provides a kind of tumor prognosis forecasting system, including obtains module and prediction module, wherein
The characteristic information for obtaining module and being used to obtain tumor patient, the characteristic information at least reflect the gene of the tumor patient
Abrupt information；The prediction module is used for the characteristic information based on the tumor patient, according to tumor prognosis prediction model, determines
The prognosis prediction result of the tumor patient.
In some embodiments, the gene mutation information include the gene to mutate on DNA and its mutation abundance,
And/or tumor prognosis prediction related gene and its mutation abundance on DNA.
In some embodiments, the characteristic information further includes at least one in the following information of the tumor patient:
Age, gender, smoking history, the length of education enjoyed, length of service, therapeutic scheme and Sample preservation time.
In some embodiments, the tumor prognosis prediction model is supporting vector machine model or neural network model.
In some embodiments, the tumor prognosis forecasting system further includes training module, and the training module is for benefit
The tumor prognosis prediction model is obtained with characteristic information and its prognosis information the training initial model of several tumor patients.
In some embodiments, the training module is also used to remove in the gene mutation information of the several tumor patients
It is mutated the mutated gene information of the small Mr. Yu's given threshold of abundance.
In some embodiments, the training module is also used to remove in the gene mutation information of the several tumor patients
Redundancy gene mutation information.
In some embodiments, the tumor prognosis prediction model is supporting vector machine model；The training module is also used
In: according to gene mutation information each in the characteristic information of several tumor patients to the contribution margin of supporting vector machine model, determine extremely
Small part gene is that tumor prognosis predicts related gene；Related gene is predicted using the tumor prognosis of several tumor patients
Gene mutation information and its prognosis information training initial model obtain the tumor prognosis prediction model.
In some embodiments, the tumor prognosis prediction model is supporting vector machine model；The training module is also used
In the parameter for optimizing the supporting vector machine model using particle swarm algorithm or grid dividing method.
In some embodiments, the prognosis prediction result include: progression of disease, stable disease, part alleviate and completely
Alleviate；Alternatively, the prognosis prediction result includes: that therapeutic effect is good and therapeutic effect is bad.
In some embodiments, the tumour is osteosarcoma.
In some embodiments, the characteristic information at least reflects the mutation letter of at least one following gene of Patients with Osteosarcoma
Breath: KMT2C, SOX9, LRP1B, NF-1, PRKDC, FAT1, STAG2, SLIT2, NOTCH1, EPHA7, ATRX, KDM6A, APC,
RANBP2、RARA.AS1、C11orf30、ROS1、ARID2、TAF1、DICER1、MSH2、MSH6、TP53、KDM5A、JAK2、
ALK, RB1, NOTCH2 and RICTOR.
In some embodiments, the tumor patient gene mutation information is that the gene mutation of osteosarcoma diseased region is believed
Breath.
One of the embodiment of the present application provides a kind of tumor prognosis prediction meanss, described device include at least one processor with
And at least one processor；At least one processor is for storing computer instruction；At least one described processor is used for
At least partly instruction in the computer instruction is executed to realize the tumor prognosis prediction technique.
One of the embodiment of the present application provides a kind of computer readable storage medium, and the storage medium storage computer refers to
It enables, when the computer instruction is executed by processor, realizes the tumor prognosis prediction technique.
One of the embodiment of the present application provides a kind of tumor prognosis forecasting system, comprising: at least one computer-readable storage
Medium, including the one group of instruction predicted for tumor prognosis；And at least one communicated at least one described storage medium
Processor, when executing one group of instruction, at least one described processor is configured as: obtaining the feature letter of tumor patient
Breath, the characteristic information at least reflect the gene mutation information of tumor patient；And the characteristic information based on the tumor patient,
According to tumor prognosis prediction model, the prognosis prediction result of the tumor patient is determined.
Detailed description of the invention
The application will further illustrate that these exemplary embodiments will be carried out by attached drawing in a manner of exemplary embodiment
Detailed description.These embodiments are simultaneously unrestricted, and in these embodiments, being identically numbered indicates identical structure, in which:
Fig. 1 is the application scenarios schematic diagram of the tumor prognosis forecasting system according to shown in the application some embodiments；
Fig. 2 is the configuration diagram that equipment is calculated according to shown in some embodiments of the application；
Fig. 3 is the module map of the tumor prognosis forecasting system according to shown in the application some embodiments；
Fig. 4 is the exemplary process diagram of the tumor prognosis prediction technique according to shown in the application some embodiments；
Fig. 5 is the exemplary flow that tumor patient gene mutation information is determined according to shown in some embodiments of the application
Figure；
Fig. 6 is the exemplary flow that training obtains tumor prognosis prediction model according to shown in the application some embodiments
Figure；
Fig. 7 is the gene mutation thermal map of the Patients with Osteosarcoma according to shown in the application exemplary embodiment；
Fig. 8 is the gene mutation heat of the good Patients with Osteosarcoma of the therapeutic effect according to shown in the application exemplary embodiment
Figure；
Fig. 9 is the gene mutation heat of the bad Patients with Osteosarcoma of the therapeutic effect according to shown in the application exemplary embodiment
Figure；And
Figure 10 is the prediction result verifying signal of the tumor prognosis prediction model according to shown in the application exemplary embodiment
Figure.
Specific embodiment
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to required use in embodiment description
Attached drawing be briefly described.It should be evident that the accompanying drawings in the following description is only some examples or embodiment of the application,
For those of ordinary skill in the art, without creative efforts, can also according to these attached drawings by
The application is applied to other similar scenes.Unless explaining obviously or separately from language environment, identical label is represented in figure
Identical structure or operation.
It should be appreciated that " system " used herein, " device ", " unit " and/or " mould group " is for distinguishing different stage
Different components, component, assembly unit, part or a kind of method of assembly.However, if other words can realize identical purpose,
Then the word can be replaced by other expression.
As shown in the application and claims, unless context clearly prompts exceptional situation, " one ", "one", " one
The words such as kind " and/or "the" not refer in particular to odd number, may also comprise plural number.It is, in general, that term " includes " only prompts to wrap with "comprising"
Include clearly identify the step of and element, and these steps and element do not constitute one it is exclusive enumerate, method or apparatus
It may also include other step or element.
Flow chart used herein is used to illustrate operation performed by system according to an embodiment of the present application.It should
Understand, above or below operates not necessarily to be accurately carried out in sequence.On the contrary, can be handled according to inverted order or simultaneously
Each step.It is also possible to during other operations are added to these, or remove a certain step from these processes or count step behaviour
Make.
Fig. 1 show the application scenarios signal of the tumor prognosis forecasting system 100 according to shown in the application some embodiments
Figure.As shown in Figure 1, tumor prognosis forecasting system 100 may include server 110, network 120 and database 130.In some realities
It applies in example, database 130 can store the basic information, history of disease, therapeutic scheme data of patient, can also store the base of patient
Because of information, such as tumor patient 140 is in the gene mutation information of tumor locus, the gene information and ginseng of tumor patient normal tissue
Examine gene information etc..The biological organization sample or fluid sample of patient, such as the tissue samples 145, Ke Yibao of tumor patient 140
There are in special storage equipment in case be further processed, such as gene sequencing processing etc..Specifically, tissue samples 145 can be with
The tissue samples of tumor tissues sample or other positions of patient body including patient.Server 110 can be used for believing correlation
Breath is handled, is analyzed to generate prognosis prediction result.In some embodiments, server 110 can be to obtain in database 130
Relevant information and/or data (for example, tumor patient the gene mutation information of tumor locus, tumor patient basic information,
With reference to gene data etc.), staff or other equipment instrument can also be directly acquired to the tissue samples of tumor patient 140
145 relevant informations and/or data handled.
Server 110 can be a server, be also possible to a server farm.Server farm can be concentration
Formula, such as data center.Server farm is also possible to distributed, a such as distributed system.Server 110 can be with
Be it is local, be also possible to long-range.In some embodiments, server 110 can be realized in cloud platform.It is only used as and shows
Example, cloud platform may include private clound, public cloud, mixed cloud, community cloud, distributed cloud, intermediate cloud, cloudy etc. or its any group
It closes.In some embodiments, server 110 can be real in the calculating equipment 200 at least one component shown in Fig. 2
It is existing.
In some embodiments, server 110 may include processing engine 112.Processing engine 112 can be used for executing clothes
The instruction (program code) of business device 110.For example, processing engine 112 is able to carry out the finger of analysis 140 characteristic information of tumor patient
It enables, and then obtains tumor prognosis prediction result.The instruction for analyzing 140 characteristic information of tumor patient can be with the shape of computer instruction
Formula is stored in computer readable storage medium (not shown).In some embodiments, processing engine 112 may include one or more
A sub- processing equipment (such as: single processing equipment or multicore multicore processing equipment).As just example, handling engine 112 can be wrapped
Containing central processing unit (CPU), specific integrated circuit (ASIC), dedicated instruction processor (ASIP), graphics processor (GPU), object
Manage processor (PPU), digital signal processor (DSP), field programmable gate array (FPGA), Programmadle logic circuit (PLD),
Controller, micro controller unit, reduced instruction set computer (RISC), microprocessor etc. or any of the above combination.
Network 120 can provide the channel of information exchange.In some embodiments, between server 110 and database 130
Information can be exchanged by network 120.For example, server 110 can receive the reference base in database 130 by network 120
Because of data.In some embodiments, the relevant information of tumor patient 140 and/or tissue samples 145 can be passed by network 120
It is defeated by server 110 and/database 130.For example, characteristic information (such as the gene mutation information, basic information of tumor patient 140
Deng) server 110 can be transferred to by network 120.In some embodiments, network 120 can be any type of wired
Or wireless network.For example, network 120 may include a cable network, cable network, fiber optic network, telecommunication network, internal network,
World-wide web, Local Area Network (LAN), Wide Area Network (WAN), radio area network (WLAN), metropolitan region network (MAN), public affairs
Telephone-switching network (PSTN), blueteeth network, ZigBee-network, near-field communication (NFC) network etc. or any of the above combination altogether.
Database 130 can be used for storing data and/or instruction set.In some embodiments, database 130 can store
The data obtained from server 110.In some embodiments, database 130 can store the letter for executing or using for server 110
Breath and/or instruction, to execute illustrative methods described in this application.In some embodiments, it can store in database 130
With reference to gene data.Specifically, database 130 can store gene data and/or existing text in all kinds of genome databases
That offers middle report occurs the gene data etc. with influence (or significantly affecting) to tumour.Wherein, genome database can wrap
Include but be not limited to COSMIC database, ClinVar database, HGMD database, omim database, TCGA database,
GeneCards database etc..In some embodiments, database 130 may include mass storage, removable memory,
Volatile read-write memory, read-only memory (ROM) etc. or any combination thereof.In some embodiments, database 130 can be
It is realized in cloud platform.Only as an example, cloud platform may include private clound, public cloud, mixed cloud, community cloud, distributed cloud, in
Between cloud, cloudy etc. or any combination thereof.In some embodiments, database 130 can be a part of server 110.
In some embodiments, tumor patient 140 can be the patient with one or more tumor diseases.Wherein, it swells
Tumor disease may include cancer, sarcoma, benign tumour etc. or any combination thereof.Specifically, cancer may include squamous cell carcinoma, gland
Cancer, undifferentiated carcinoma etc..For example, squamous cell carcinoma may include betiding skin, oesophagus, lung, cervix, vagina, vulva, penis
The cancer at equal positions.Gland cancer may include betide digest tube, lung, corpus uteri, mammary gland, ovary, prostate, thyroid gland, liver,
The cancer at the positions such as kidney, pancreas, gall-bladder.Sarcoma can include but is not limited to: soft tissue sarcoma, osteosarcoma, malignant fibrous histiocytoma
Cytoma, both sides sarcoma, rhabdomyosarcoma, lymphosarcoma, synovial sarcoma, liomyoma etc..Benign tumour may include but not
It is fine to be limited to the flat bone myomata of hamartoma, Pancreatic benign tumour, thyroid adenoma, mammary gland fibroma, hysteroma, gastrointestinal tract, soft tissue
Tie up tumor, synovialoma, ligament fibers tumor etc..In one specific embodiment of the application, tumor patient 140 can be Patients with Osteosarcoma.
In some embodiments, tumor patient 140 can be tumour in the patient in each stage (such as early stage, mid-term, advanced stage).Tumour
Patient 140 is also possible to treating each stage the patient (before such as treating, in treatment, after treatment).
In some embodiments, tissue samples 145 can be used for reflecting the relevant information of 140 tumour of tumor patient.Specifically
, tissue samples 145 can be from the tumor locus (such as target lesion) of tumor patient 140 and/or non-tumor locus (as except lesion
Outer position) in extract biological tissue or fluid sample.For example, tissue samples can include but is not limited to: sputum, blood sample
Sheet, flesh tissue (such as surgical tissue, puncturing tissue), paraffin-embedded tissue, urine, dropsy of serous cavity (e.g., ascites, thoracic cavity
Hydrops, pericardial effusion etc.) or tissue, cell etc. for being extracted from tumor locus or any of the above combination.In some embodiments
In, tissue samples 145 may include tissue, cell of the tumor patient 140 at tumor locus and the position in addition to tumour.?
In some embodiments, tissue samples 145 can only include tissue, cell of the tumor patient 140 in tumor locus.
In some embodiments, the relevant information of tumor patient 140 and/or tissue samples 145 can pass through artificial (such as work
Make personnel) or machine (such as instrument and equipment) be transferred to one or more components (such as server of tumor prognosis forecasting system 100
110, database 130).
Fig. 2 is the schematic diagram that the framework of equipment 200 is calculated according to shown in some embodiments of the application.As shown in Fig. 2, meter
Calculating equipment 200 may include processor 210, memory 220, input/output interface 230 and communication port 240.It is set in the calculating
Server 110 and/or database 130 may be implemented on standby 200.For example, processing engine 112 can be real on calculating equipment 200
Function that is existing and being configured as executing processing engine 112 in the application.
Processor 210 can execute computations (program code) and execute the function of server 110 described herein.
Computations may include that (function refers to described in this application for programs, objects, component, data structure, process, module and function
Specific function).For example, processor 210 can handle the instruction for predicting tumor prognosis effect in tumor prognosis forecasting system 100.
In some embodiments, processor 210 may include microcontroller, microprocessor, it is Reduced Instruction Set Computer (RISC), dedicated
Integrated circuit (ASIC), using specific instruction set processor (ASIP), central processing unit (CPU), graphics processing unit (GPU),
Physical processing unit (PPU), micro controller unit, digital signal processor (DSP), field programmable gate array (FPGA), height
Grade RISC machine (ARM), programmable logic device and any circuit and the processor that are able to carry out one or more functions etc., or
Any combination thereof.Only for explanation, a processor 210 is only described in Fig. 2, but should be noted that the application may include
Multiple processors.
Memory 220 can store the data/information that any component obtains from tumor prognosis forecasting system 100.One
In a little embodiments, memory 220 may include that mass storage, removable memory, volatibility read and write memory
With read-only memory (ROM) etc., or any combination thereof.Exemplary mass storage may include that disk, CD and solid-state are driven
Dynamic device etc..Removable memory may include flash drive, floppy disk, CD, storage card, USB flash disk, compact disk and mobile hard disk
Deng.It may include random access memory (RAM) that volatibility, which reads and writees memory,.RAM may include dynamic ram
(DRAM), Double Data Rate synchronous dynamic ram (DDRSDRAM), static state RAM (SRAM), thyristor RAM (T-RAM) and zero capacitance
(Z-RAM) etc..ROM may include mask rom (MROM), programming ROM (PROM), erasable programmable ROM (PEROM), electricity
Erasable programmable ROM (EEPROM), CD ROM (CD-ROM) and digital versatile disc ROM etc..
Input/output interface 230 can be used for inputting or output signal, data or information.In some embodiments, defeated
Enter/output interface 230 can be used for user (for example, tumor patient 140, user of tumor prognosis forecasting system 100 etc.) with
The connection of server 110.In some embodiments, user can input the feature of tumor patient by input/output interface 230
Information.In some embodiments, input/output interface 230 may include input unit and output device.Exemplary input device
It may include keyboard, mouse, touch screen and microphone etc., or any combination thereof.Exemplary output device may include that display is set
Standby, loudspeaker, printer, projector etc., or any combination thereof.Exemplary display devices may include liquid crystal display (LCD),
Display, flat-panel monitor, flexible displays, television equipment, cathode-ray tube (CRT) based on light emitting diode (LED) etc.,
Or any combination thereof.
Communication port 240 may be coupled to network 120 so as to data communication.Connection can be wired connection, be wirelessly connected
Or both combination.Wired connection may include cable, optical cable or telephone wire etc., or any combination thereof.Wireless connection can wrap
Bluetooth, WiFi, WiMax, WLAN, ZigBee, mobile network (for example, 3G, 4G or 5G etc.) etc. are included, or any combination thereof.One
In a little embodiments, communication port 240 can be standardized port, such as RS232, RS485.In some embodiments, communication ends
Mouth 240 can be the port specially designed.
Fig. 3 is the module map of the tumor prognosis forecasting system according to shown in the application some embodiments.As shown in figure 3, should
Tumor prognosis forecasting system may include obtaining module 310, prediction module 320 and training module 330.
Obtaining module 310 can be used for obtaining the characteristic information of tumor patient 140.In some embodiments, this feature is believed
Breath can at least reflect the gene mutation information of tumor patient.In some embodiments, the characteristic information of tumor patient 140 can be with
It include: the gene mutation information of tumor patient, one or more any combination such as basic information of tumor patient.
Prediction module 320 can be used for predicting the prognosis prediction result of tumor patient.For example, prediction module 320 can be with base
The prognosis prediction result of tumor patient is determined according to tumor prognosis prediction model in the characteristic information of tumor patient.
Training module 330 can be used for training and obtain tumor prognosis prediction model.Specifically, training module 330 can obtain
Take the characteristic information and its prognosis information of several tumor patients.Training module 330 can use the feature letter of several tumor patients
Breath and its prognosis information, training initial model obtain tumor prognosis prediction model.In some embodiments, training module 330 can
To remove the mutated gene information for being mutated the small Mr. Yu's given threshold of abundance in gene mutation information.In some embodiments, training
Module 330 can remove the redundancy gene mutation information in gene mutation information.In some embodiments, training module 330 can
With the contribution margin according to gene mutation information each in the characteristic information of several tumor patients to supporting vector machine model, determine at least
Portion gene is that tumor prognosis predicts related gene.In some embodiments, training module 330 can use several tumor patients
Tumor prognosis prediction related gene gene mutation information and its prognosis information training initial model obtain the tumor prognosis
Prediction model.In some embodiments, training module 330 can also using particle swarm algorithm or grid dividing method optimization support to
The parameter of amount machine model.
It should be appreciated that system shown in Fig. 3 and its module can use various modes to realize.For example, in some implementations
In example, system and its module can be realized by the combination of hardware, software or software and hardware.Wherein, hardware components can
To be realized using special logic；Software section then can store in memory, by instruction execution system appropriate, for example (,) it is micro-
Processor or special designs hardware execute.It will be appreciated by those skilled in the art that meter can be used in above-mentioned method and system
It calculation machine executable instruction and/or is included in the processor control code to realize, such as in such as disk, CD or DVD-ROM
The programmable memory of mounting medium, such as read-only memory (firmware) or the data of such as optics or electrical signal carrier
Such code is provided on carrier.The system and its module of the application can not only have such as super large-scale integration or door
The semiconductor or field programmable gate array of array, logic chip, transistor etc., programmable logic device etc.
The hardware circuit of programmable hardware device realize, can also be real with such as software as performed by various types of processors
It is existing, it can also be by combination (for example, firmware) Lai Shixian of above-mentioned hardware circuit and software.
It should be noted that the description of system and its module is shown, determined for candidate item above, only for convenience of description,
The application can not be limited within the scope of illustrated embodiment.It is appreciated that for those skilled in the art,
After the principle for solving the system, any combination may be carried out to modules, or constitute without departing substantially from this principle
Subsystem is connect with other modules.For example, in some embodiments, obtaining module 310, prediction module 320 and training module 330
It can be the disparate modules in a system, be also possible to the function that a module realizes two or more above-mentioned modules
Energy.For example, acquisition module 310 and prediction module 320 are also possible to a module while having acquisition and forecast function.Example again
Such as, modules can share a memory module, and modules can also be respectively provided with respective memory module.It is such
Deformation, within the scope of protection of this application.
Fig. 4 is the exemplary process diagram of the tumor prognosis prediction technique according to shown in the application some embodiments.Such as Fig. 4 institute
Show, which may include:
Step 410, the characteristic information of tumor patient is obtained, this feature information can at least reflect that the gene of tumor patient is prominent
Become information.Specifically, step 410 can be executed by acquisition module 310.
In some embodiments, the characteristic information of tumor patient 140 may include: tumor patient gene mutation information,
One or more any combination such as the basic information of tumor patient.In some embodiments, the characteristic information of tumor patient can
Only to include the gene mutation information of tumor patient.Specifically, the gene mutation information of tumor patient may include occurring on DNA
The gene of mutation and its tumor prognosis prediction related gene on mutation abundance and/or DNA and its mutation abundance.Tumor patient
Basic information can reflect the other information other than gene mutation information relevant to tumor patient.For example, tumour is suffered from
When the basic information of person may include the age of tumor patient, gender, smoking history, the length of education enjoyed, length of service, Sample preservation
Between (such as blood storage time, tumor tissues holding time, other normal tissue holding times of patient), therapeutic scheme or its
Any combination.In certain embodiments, therapeutic scheme may include that (such as radiotherapy, is exempted from chemotherapy for the type of therapeutic scheme
Epidemic disease therapy etc.), duration for the treatment of, use the dosage of ray, drug dose, the title of drug or type etc..In some tools
In body embodiment, the gene mutation information of tumor patient can be gene mutation of the tumor patient in tumor locus (such as target lesion)
Information.For example, the gene mutation information of Patients with Osteosarcoma can be the gene mutation information of osteosarcoma diseased region.In some realities
It applies in example, tumor patient 140 can be the patient in tumour each stage (such as early stage, mid-term, advanced stage), and/or each in treatment
The patient of a stage (before such as treating, in treatment, after treatment).For example, the osteosarcoma before available treatment (such as chemotherapy) is suffered from
The characteristic information of person with the outcome for predicted treatment, and then can provide ginseng for formulation, the selection etc. of therapeutic scheme
It examines.
In some embodiments, the gene mutation information for obtaining/determining tumor patient 140 may include: to obtain tumour to suffer from
The tissue samples 145 of person 140, the DNA for extracting tissue samples, the library for preparing the DNA, carried out according to the library gene sequencing with
Sequencing result, analysis sequencing result are obtained to determine the gene mutation information of tumor patient.About determining tumor patient
The more details of 140 gene mutation information may refer to Fig. 5 and its associated description.
Step 420, the tumor patient is determined according to tumor prognosis prediction model based on the characteristic information of tumor patient
Prognosis prediction result.Specifically, the step 420 can be executed by prediction module 320.
In some embodiments, the characteristic information of tumor patient can be input to trained tumor prognosis prediction model
In, to obtain the prognosis prediction result of tumor patient.In some embodiments, tumor prognosis prediction model can be supervised learning
Model.Specifically, supervised learning model may include: supporting vector machine model, decision-tree model, neural network model, recently
The combination of one or more of adjacent classifier etc..Training process about tumor prognosis prediction model may refer to Fig. 6 and its
Associated description.
In some embodiments, prognosis prediction result can be the prognosis situation of a period of time (such as 5 years) after treatment.Example
Such as, prognosis prediction result can be divided into progression of disease (PD, progressive disease), disease according to the variation of target lesion
Stablize (SD, stable disease), (PR, partial response) and complete incidence graph (CR, complete are alleviated in part
Response) four class.Specifically, PD can refer to that the sum of target lesion maximum diameter increases by 20% or more, or occur new lesion (such as
The new lesion occurred due to metastases)；SD can refer to that the sum of target lesion maximum diameter reduces not up to PR, or increase and do not reach PD；PR
It can refer to that the sum of target lesion maximum diameter reduces 30% or more, at least maintain 4 weeks；CR can refer to that all target lesion disappear, without new
Lesion occurs, and tumor markers are normal, at least maintains 4 weeks.In some embodiments, prognosis prediction result may include: to control
Therapeutic effect is good and bad two class of therapeutic effect.Specifically, therapeutic effect is good can be determined with bad according to clinical criteria.For example,
Indicate that therapeutic effect is bad if tumor patient disease relapse in 5 years after treatment, if the tumor patient state of an illness is not multiple in 5 years after treatment
Hair then indicates that therapeutic effect is good.In another example PD and SD can be classified as, therapeutic effect is bad, and PR and CR can be classified as therapeutic effect
It is good.In another example if the life span of patient is more than to indicate within 5 years that therapeutic effect is good after treating for the first time；If patient after treating for the first time
Life span then indicated that therapeutic effect was bad less than 5 years.
In some alternate embodiments, prognosis prediction result is also divided into other classifications, the embodiment of the present application pair
This is with no restrictions.For example, prognosis prediction result can be divided into, therapeutic effect is good, therapeutic effect is general and the poor three classes of therapeutic effect.
In some embodiments, prognosis prediction result can also be the prediction numerical value of some specific index.For example, prognosis prediction result can
With include but is not limited to remission rate, recurrence rate, disease recurred in several years, disease survival rate, life span, in the recent period
Case fatality rate, case fatality rate at a specified future date, hospital mortality, case fatality rate, operative mortality rate etc. outside institute.
It should be noted that the above-mentioned description in relation to process 400 is used for the purpose of example and explanation, without limiting the application
The scope of application.To those skilled in the art, process 400 can be carried out under the guidance of the application it is various amendment and
Change.However, these modifications and variations are still within the scope of the present application.
Fig. 5 is the exemplary flow that tumor patient gene mutation information is determined according to shown in some embodiments of the application
Figure.Specifically, each step shown in Fig. 5 can be by staff (such as doctor, experimenter, operator) and/or instrument and equipment
(such as detector, analyzer) etc. executes.As shown in figure 5, determining that the process of tumor patient gene mutation information may include:
Step 510, the tissue samples of tumor patient are obtained.
In some embodiments, tissue samples 145 can be used for reflecting the relevant information of tumour.Specifically, tissue samples
145 can be from the tumor locus (such as target lesion) of tumor patient 140 and/or non-tumor locus (position such as in addition to lesion)
The biological tissue of extraction or fluid sample.For example, tissue samples can include but is not limited to: sputum, blood sample, flesh tissue
(such as surgical tissue, puncturing tissue), paraffin-embedded tissue, urine, dropsy of serous cavity (e.g., ascites, pleural effusion, cavum pericardiale
Hydrops etc.) or tissue, cell etc. for being extracted from tumor locus or any of the above combination.In some embodiments, tissue samples
145 may include tissue, cell of the tumor patient 140 at tumor locus or the position in addition to tumour.In some embodiments,
Tissue samples 145 can only include tissue, cell of the tumor patient 140 in tumor locus.It in some embodiments, can be to group
It knits sample 145 and formulates inclusion criteria.For example, the requirement of acquisition tissue samples can be formulated, it is desirable that be surgical tissue, fresh group
It knits, puncturing tissue, 10% your the neutral fixed, tissue of paraffin embedding of Malin etc..In another example paraffin white tiles can be 10, (5 is micro-
Rice) or the white tiles of 5 (10 microns) can be with and to guarantee the tumour cell (as > 70%) in biopsy tissues containing enough ratios
Add same HE staining section (or mail informs tumour cell amount after inspection sample HE dyeing).In another example for surgical tissue or
Puncturing tissue can require sample size > 0.3cm of acquisition3, and be quickly put into EP pipe.In another example sample fortune can be formulated
Defeated standard: paraffin white tiles after cutting can room temperature inspection within 2 weeks, such as managed with EP, and nozzle is sealed with sealed membrane, to prevent fortune
It leaks, and the pathological number of inspection sample need to be written on request slip during defeated.In another example screening tissue samples can be formulated
Standard, as sample rejects standard: non-10% neutral formalin fixer tissue, inspection sample information and request slip be not inconsistent, group
Knit self-dissolving or regression etc..
Step 520, the DNA of tissue samples is extracted.
In some embodiments, the method for extracting the DNA of tissue samples may include cetyl trimethylammonium bromide method
(CTAB method), glass bead method, supercritical ultrasonics technology, polishing, freeze-thaw method, guanidine isothiocyanate method, alkaline lysis, enzyme process etc. or to take up an official post
Meaning combination.In some embodiments, the DNA for extracting tissue samples by any known method, the embodiment of the present application can also be adopted
It is without limitation.
Step 530, the library of the DNA is prepared.
In some embodiments, library preparation process may include that DNA is interrupted, end is repaired, the screening of paramagnetic particle method segment, end
Hold the part or all of steps such as tailing, connector connection, PCR enrichment, sequencing by hybridization library.Further, it is also possible to using any known
Method prepare tissue samples DNA library, the embodiment of the present application is without limitation.
Step 540, gene sequencing is carried out according to the library, obtains sequencing result.
In some embodiments, gene sequencing can be carried out to prepared library, to obtain sequencing data.Wherein, base
Because sequencing technologies can be high throughput sequencing technologies.High throughput sequencing technologies (" Next-generation " sequencing
Technology, NGS) it may include: that (Pacific Bio), ionic semiconductor (Ion Torrent is sequenced in unimolecule in real time
Sequencing), pyrosequencing (454), Bian Hecheng connect sequencing (SOLiD in side when (Illumina) is sequenced
Sequencing), one or more any combination such as chain termination method (Sanger sequencing).Further, it is also possible to using
Any of method carries out gene sequencing, and the embodiment of the present application is without limitation.
Step 550, sequencing result is analyzed, determines the gene mutation information of tumor patient.
In some embodiments, data analysis can be carried out to the sequencing data of acquisition, to obtain the gene of tumor patient
Abrupt information (predicts dependency basis including the gene to mutate on DNA and its tumor prognosis being mutated on abundance and/or DNA
Cause, mutational site mutation abundance, gene mutation abundance etc.).In some embodiments, gene mutation abundance can be statistics sequencing
As a result the site of the big Mr. Yu's setting value of single nucleotide variations (Single Nucleotide Variation, SNV) non-synonymous in
Be mutated the cumulative of abundance and.The setting value can be 0.05%, 0.1%, 0.2%, 1%, 2%, 3% or 10% etc..It is prominent
Displacement point mutation abundance can refer to a base mutation proportion.Specifically, mutational site is mutated abundance=saltant type reads
Quantity/(saltant type reads quantity+wild type reads quantity), wherein reads indicates a bit of sequencing fragment.For example, passing through
The mutated gene KMT2C that sequencing obtains certain patient shares 5 mutational sites, the mutation abundance in 5 mutational sites is respectively as follows: 1%,
3%, 4%, 6%, 8%, threshold value is set as 2%.Then the mutation abundance of mutated gene KMT2C is that 4 mutational sites greater than 2% are prominent
Become the cumulative of abundance and.In some embodiments, data analysis may include the joint sequence in (1) removal sequencing data；(2)
It carries out quality control and removes low quality sequencing data (e.g., low quality base, too short sequencing data etc.)；(3) by above-mentioned place
Sequencing data after reason is compared with reference to gene data to identify mutated gene；(4) gene normal variant situation is rejected
(such as polymorphic variation, synonymous variation)；(5) above sections or the Overall Steps such as the gene mutation information of tumor patient are obtained.
In some embodiments, normal gene data be can be (for example, the non-tumor locus of tumor patient is normal thin with reference to gene data
Gene data, the gene data of non-tumor patient in born of the same parents etc.), the gene data of corresponding tumor disease is (for example, each tumour is pre-
After predict related gene) etc..93 patients are sequenced by the sequencing approach of the application, statistics show that target area is covered
Cover degree is 98.2%~99.6%, mean value 99.41%；Target area average sequencing depth is 462.7~1252.89, mean value
It is 705.51；Target area capture rate is 75.6%~84.6%, mean value 80.01%.In some embodiments, with reference to base
Because data can store in database 130, can be transferred from the database 130 when in use.In some embodiments, also
The mutation abundance for measuring gene by any known method can be adopted.For example, the technologies such as the sequencing of two generations, BEAMING, PARE.
By sequencing, it is found that different mutated genes is distributed difference in different clinical samples.Fig. 7-9 is according to the application
The gene mutation thermal map of Patients with Osteosarcoma shown in some embodiments；Wherein, Fig. 7 is according to shown in the application exemplary embodiment
The gene mutation thermal map of all Patients with Osteosarcoma；Fig. 8 is the good bone of the therapeutic effect according to shown in the application exemplary embodiment
The gene mutation thermal map of sarcoma patients；Fig. 9 is the bad osteosarcoma of the therapeutic effect according to shown in the application exemplary embodiment
The gene mutation thermal map of patient.
It in the present embodiment, can be from the target lesion of Patients with Osteosarcoma (93 Patients with Osteosarcoma samples as shown in Figure 7)
In (osteosarcoma diseased region) extract corresponding tissue, cell, and therefrom determine the gene mutation information of Patients with Osteosarcoma.Specifically
, the gene mutation letter of Patients with Osteosarcoma can be determined by the process step of determining tumor patient gene mutation information above-mentioned
Breath.
In the present embodiment, predominantly detected sample 315 genes (according in existing document report to cancer have compared with
The gene significantly affected) catastrophe (e.g., gene mutation abundance).In some alternate embodiments, gene detected
Quantity can be increased or decreased optionally.As Fig. 7-9 lists the good patient of all Patients with Osteosarcoma, outcome and pre- respectively
Afterwards before the mutation ratio in the patient of effect difference 29 gene mutation thermal map, wherein the left ordinate of Fig. 7-9 represent some mutation base
Because of the ratio shared by mutating in 93 samples, right ordinate represents mutated gene, abscissa representative sample.Specifically,
In the present embodiment, the higher mutated gene information of ratio shared by gene mutation (fractional mutations base as Figure 7-9 in sample
Because of information) include: Lysine N-methyltransferase 2C (KMT2C), SRY-box 9 (SOX9), LDL
receptor related protein 1B(LRP1B)、Neurofibromatosis type I(NF-1)、protein
kinase(PRKDC)、FAT atypical cadherin 1(FAT1)、slit guidance ligand 2(SLIT2)、
Notch1、EPH receptor A7(EPHA7)、ATRX、Lysine demethylase 6A(KDM6A)、APC、RAN
binding protein 2(RANBP2)、ROS proto-oncogene 1(ROS1)、EMSY(C11orf30)、AT-rich
interactive domain-containing protein 2(ARID2)、RARA antisense RNA 1
(RARA.AS1)、TATA-box binding protein associated factor 1(TAF1)、mutS homolog 2
(MSH2)、mutS homolog 6(MSH6)、Tumor protein p53(TP53)、dicer 1(DICER1)、lysine
demethylase 5A(KDM5A)、Janus kinase 2(JAK2)、ALK receptor tyrosine kinase(ALK)、
RB transcriptional corepressor 1(RB1)、NOTCH2、RPTOR independent companion of
MTOR complex 2(RICTOR)、stromal antigen 2(STAG2)、polybromo 1(PBRM1)、
melanogenesis associated transcription factor(MITF)、cytochrome P450family
2subfamily C member 8(CYP2C8)、phosphatidylinositol-4,5-bisphosphate 3-kinase
catalytic subunit alpha(PIK3CA)、phosphatidylinositol-4,5-bisphosphate 3-
kinase catalytic subunit beta(PIK3CB)、B-Raf proto-oncogene(BRAF)、MET proto-
oncogene,receptor tyrosine kinase(MET)、heat shock protein 90alpha family
class A member 1(HSP90AA1)、membrane associated guanylate kinase,WW and PDZ
domain containing 2(MAGI2)、mitogen-activated protein kinase kinase kinase 1
(MAP3K1)、hepatocyte growth factor(HGF)、E1A binding protein p300(EP300)、AKT
serine/threonine kinase 3(AKT3)、ASXL transcriptional regulator 1(ASXL1)、ATM
serine/threonine kinase(ATM)、AXIN1、AXL receptor tyrosine kinase(AXL)、BLM RecQ
like helicase(BLM)、BRCA2DNA repair associated(BRCA2)、cell division cycle 73
(CDC73)、cyclin dependent kinase 12(CDK12)、CREB binding protein(CREBBP)、
catenin alpha 1(CTNNA1)、CYLD lysine 63deubiquitinase(CYLD)、EPH receptor A3
(EPHA3)、EPH receptor B1(EPHB1)、erb-b2receptor tyrosine kinase 3(ERBB3)、erb-
b2receptor tyrosine kinase 4(ERBB4)、ERBB receptor feedback inhibitor 1
(ERRFI1)、FA complementation group A(FANCA)、FA complementation group D2
(FANCD2)、FAT atypical cadherin 1(FAT1)、far upstream element binding protein 1
(FUBP1)、GATA binding protein 1(GATA1)、GATA binding protein 2(GATA2)、
interleukin 7receptor(IL7R)、Janus kinase 1(JAK1)、lysine acetyltransferase 6A
(KAT6A)、LOC101929829、LOC115110、leucine zipper like transcription regulator 1
(LZTR1)、mitogen-activated protein kinase kinase 2(MAP2K2)、MDM4、mediator
complex subunit 12(MED12)、mutL homolog 1(MLH1)、MYC proto-oncogene(MYC)、MYCN
proto-oncogene(MYCN)、NFKB inhibitor alpha(NFKBIA)、PARK2、phosphatidylinositol-
4,5-bisphosphate 3-kinase catalytic subunit gamma(PIK3CG)、phosphoinositide-3-
kinase regulatory subunit 2(PIK3R2)、protein kinase C iota(PRKCI)、patched 1
(PTCH1)、ret proto-oncogene(RET)、SET domain containing 2(SETD2)、SMAD family
member 4(SMAD4)、SMARCA4、spen family transcriptional repressor(SPEN)、spectrin
alpha,erythrocytic 1(SPTA1)、signal transducer and activator of transcription
3(STAT3)、transforming growth factor beta receptor 2(TGFBR2)、TSC complex
The genes such as subunit 1 (TSC1).
In addition, after 315 genes of each patient are sequenced, it has also been found that the different mutation bases in clinical samples
The mutation abundance of cause is different, as shown in table 1.
The corresponding high abundance mutated gene information list of each patient of table 1 (only show the good patient of 10 outcomes and
The patient of 10 outcome differences is as example).
It should be noted that the above-mentioned description in relation to determining the process of tumor patient gene mutation information is used for the purpose of showing
Example and explanation, the scope of application without limiting the application.It to those skilled in the art, can be under the guidance of the application
Reach the technical purpose of patient's prognosis prediction using any tumor patient gene mutation information obtained by other technologies means.
Fig. 6 is the exemplary flow that training obtains tumor prognosis prediction model according to shown in the application some embodiments
Figure.Specifically, (such as step 610, step 620) can be executed process shown in Fig. 6 by training module 330.As shown in fig. 6, instruction
Practice obtain tumor prognosis prediction model exemplary flow may include:
Step 610, the characteristic information and its prognosis information of several tumor patients are obtained.
In some embodiments, the characteristic information of several tumor patients may include: tumor patient gene mutation information,
One or more any combination such as the basic information of tumor patient.Specifically, the gene mutation information of several tumor patients can
With include every tumor patient DNA on the gene that mutates and its mutation abundance.In certain embodiments, this is several
The gene mutation information of tumor patient can be gene mutation information of the tumor patient in tumor locus (such as target lesion).About true
The specific method of the gene mutation information of the fixed several tumor patients may refer to determination tumor patient gene described in Fig. 5
The process of abrupt information.The basic information of tumor patient can reflect relevant to tumor patient other than gene mutation information
Other information.For example, the basic information of tumor patient may include the age of tumor patient, gender, smoking history, receive an education year
Limit, length of service, therapeutic scheme, Sample preservation time, types of medicines etc., or any combination thereof.
In some embodiments, the prognosis information of several tumor patients can be divided into progression of disease according to the variation of target lesion
(PR, partial are alleviated in (PD, progressive disease), stable disease (SD, stable disease), part
) and complete incidence graph (CR, complete response) four classes response.In another example prognosis situation may include: treatment effect
Fruit is good and bad two class of therapeutic effect.In some embodiments, prognosis situation can also be the numerical value of certain specific index.For example,
Prognosis situation can include but is not limited to remission rate, recurrence rate, disease recurred in several years, disease survival rate, life
Deposit time, Near-term mortality rate, case fatality rate at a specified future date, hospital mortality, case fatality rate, operative mortality rate etc. outside institute.In some embodiments
In, prognosis situation described herein can be corresponding with prognosis prediction result identified in step 420.
Step 620, using the characteristic information and its prognosis information of several tumor patients, it is pre- that training initial model obtains tumour
Prediction model afterwards.In some embodiments, tumor prognosis prediction model can be supervised learning model.Specifically, supervised learning
Model may include: one of supporting vector machine model, decision-tree model, neural network model, nearest neighbor classifier etc. or
Several combinations.It will illustrate the training process of tumor prognosis prediction model by taking supporting vector machine model as an example in the present embodiment.
In some embodiments, can set original model parameter (e.g., parameter c (cost), parameter g (gamma) etc.) with
Establish initial supporting vector machine model.And grid dividing method can be used, characteristic information based on several tumor patients and its pre-
Information afterwards is searched for optimal model parameters (e.g., parameter c (cost), parameter g (gamma) etc.), with update, Optimized model.Some
In embodiment, kernel function (such as linear kernel function, Polynomial kernel function, Gauss (RBF) core of supporting vector machine model can be selected
Function, sigmoid kernel function), and the characteristic information based on several tumor patients and its prognosis information training obtain the support to
Amount machine model.In some embodiments, it can be combined with grid dividing method and find optimal model parameters in conjunction with verification method.Example
Such as, model parameter (e.g., parameter c (cost), parameter g (gamma) etc.) is adjusted by grid dividing method, to adjusting parameter
Model afterwards is verified, and is determined according to verification result and is selected optimal model parameter.
It in yet other embodiments, can be using particle swarm optimization algorithm to the parameter optimization of supporting vector machine model.Tool
Body, the parameter of particle swarm optimization algorithm can be initialized first, then found more using the particle swarm optimization algorithm
The optimal parameter (e.g., pairs of parameter c, g etc.) of new model, and using the optimal parameter as the model parameter after optimization.Wherein,
Particle swarm optimization algorithm can include but is not limited to basic particle swarm optimization algorithm, TSP question particle swarm optimization algorithm
Deng.The parameter of particle swarm optimization algorithm may include local search ability parameter, ability of searching optimum parameter, speed update bullet
The change of property coefficient, maximum evolution quantity, population maximum quantity, the folding times of cross validation, the variation range of parameter C, parameter g
Change range etc., or any combination thereof.In some embodiments, can the artificial or unartificial parameter to particle swarm optimization algorithm into
Row Initialize installation.
In other embodiments, can also combine using grid search and particle swarm optimization algorithm to supporting vector machine model
Parameter optimize.For example, can first optimize using parameter of the grid search to supporting vector machine model, then use grain
Subgroup optimization algorithm is to its suboptimization again.
In order to improve model accuracy or improve training effectiveness, can also characteristic information to several tumor patients it is further
Screening carries out model training using the characteristic information after screening.
In some embodiments, the mutation small Mr. Yu of abundance in the gene mutation information of the several tumor patients can be removed
The mutated gene information of given threshold.Gene mutation abundance can be the mutation abundance in multiple and different mutational sites in the gene
It is cumulative and, can be manually set mutational site gene mutation abundance threshold value (such as 0.05%, 0.1%, 0.2%, 1%, 2%,
3% etc.) mutated gene information of the abundance less than the given threshold, will be mutated to be removed.For example, small for some mutation abundance
It can be not counted in its gene mutation abundance in the mutational site of certain value (such as 0.05%, 0.1%, 0.2%).
In some embodiments, the redundancy gene mutation in the gene mutation information of the several tumor patients can be removed
Information.Specifically, in gene mutation information, it is understood that there may be two or more genes, mutual correlation ratio
It is higher.In some embodiments, when the catastrophe of two genes is same or similar or the table of the mutation abundance of two genes
Up to it is close when, it is believed that the two gene associations are higher.For the gene of such high correlation, it is believed that one of them is more
A is redundancy gene.It, can by removing redundancy gene mutation information (for example, only retaining a gene in high correlation gene)
Gene dimension to be effectively reduced under the premise of not influencing model training effect.
In some embodiments, can in the characteristic information according to several tumor patients each gene mutation information to support to
The contribution margin of amount machine model determines that at least partly gene is that tumor prognosis predicts related gene.
It in some embodiments, can further each gene mutation information carries out in the characteristic information to several tumor patients
Screening.Specifically, recursive feature removing method can be used to each gene mutation information in the characteristic information of several tumor patients
It is screened.Using the predictablity rate of model as evaluation criterion, to each gene mutation in the characteristic information of several tumor patients
Information carries out selecting the multiple training sets of elimination acquisition respectively, is respectively trained to obtain a model on each training set, based on pre-
The gene mutation information eliminated when surveying accuracy rate to each model training carries out contribution margin sequence, it can be understood as, prediction is accurate
The gene mutation information of the corresponding elimination of the lower model of rate is greater than the gene of the corresponding elimination of the higher model of predictablity rate
Abrupt information.Each gene mutation information can finally be screened according to contribution margin size, it is swollen for obtaining at least partly gene
Tumor prognosis prediction related gene.In some embodiments, random forests algorithm can also be selected to the feature of several tumor patients
Each gene mutation information is screened in information.Specifically, (1) constructs decision tree first: can define in forest has P tree
(such as 20,40)；Can use the bootstrap method of sampling extracted from 93 parts of samples multiple sample sets as every certainly
The training sample set of plan tree repeats the training sample set that P wheel samples available every decision tree, and every wheel sampling can be from 93 parts
It is sampled in a manner of sampling with replacement in sample 93 times and obtains the training set of a decision tree；At each node of decision tree,
Assuming that sharing 315 characteristic variables, m characteristic variable is therefrom randomly selected, a feature is selected in m characteristic variable and is carried out
Dendritic growth calculates its optimal divisional mode during the growth process without cut operator；(2) by trained P decision
Tree combination obtains random forest.Each several tumor patients can be predicted according to P decision tree, by weighting or voting
Method, final prediction result is the output of random forest.During each decision tree of training, it can calculate each
Feature reduces the impurity level how much set.For a decision tree forest, each feature can be calculated averagely reduce and is more
Few impurity level, and it is averaged reduced impurity level as contribution margin how many evaluation criterion.For example, impurity level can will be reduced most
More gene mutation information as the maximum feature of contribution margin, and so on, determine different mutated genes to the contribution margin of model
(as shown in table 2), to filter out at least partly gene as tumor prognosis prediction related gene.For example, can occur to tumour
With selection in the mutated gene significantly affected maximum to the contribution margin of the tumor prognosis prediction model n (such as 20,29
A, 40,100 etc.) mutated gene as tumor prognosis predicts related gene.
Contribution value list of the different mutated genes of table 2 to model
In some embodiments, the tumor prognosis prediction model that can be obtained to training is verified.For example, for supporting
Vector machine model can verify modelling effect using cross-validation method.Specifically, cross validation method may include: to reserve method
(Hold-Out Method), K roll over cross-validation method (K-fold Cross Validation, K-CV) He Liuyi cross-validation method
(Leave-One-Out Cross Validation, LOO-CV).By taking LOO-CV as an example, it is total training sample can be divided into sample
Several parts (for example, 93 parts), wherein 1 part of conduct verifying sample, remaining 92 parts conduct training samples it will input initial support vector machines
Model is trained, and repeated overlapping verification process 93 times, obtains 93 verification results, is combined 93 verification results and is determined instruction
Practice the final verification result of the tumor prognosis prediction model obtained.Further, it is possible to draw out subject's work according to verification result
Make indicatrix (ROC curve) visual representation (as shown in Figure 10).As shown in Figure 10, the point on the ROC curve is represented not
The sensibility and specificity of osteosarcoma prognostic predictive model under same truncation condition (such as outcome classification standard).The ROC curve
The most upper left corner point close to the upper left corner, it is accurate to can reflect out the prognosis in osteosarcoma prediction model prediction obtained in the present embodiment
Property is higher；Area AUC below the ROC curve is 0.988, very close 1, can reflect out the bone and flesh obtained in the present embodiment
Tumor prognostic predictive model classifying quality is preferable；In addition, the prognosis in osteosarcoma prediction model of the application is under different truncation conditions
Sensibility mean value (0.95) and specific mean value (0.97) are higher.
In the present embodiment, additionally have chosen 6 Patients with Osteosarcoma (it is known wherein 4 outcome it is poor, in addition 2
Outcome it is good).The gene mutation information of its osteosarcoma diseased region is obtained, the information is based on, is instructed according in the present embodiment
Practicing the prognosis in osteosarcoma prediction model obtained determines the prognosis prediction result of 6 Patients with Osteosarcoma (as shown in table 3, wherein in advance
The threshold value of measured value is set as 0.5, is good prognosis less than 0.5, and being greater than 0.5 is poor prognosis), gained prediction result and known outcome
It is completely the same.
The prediction result and actual prognosis Contrast on effect of 3 prognosis in osteosarcoma prediction model of table
| Sample name | Predicted value | Prediction effect | Actual prognosis effect |
| Patient 1 | 0.335717 | Good prognosis | Good prognosis |
| Patient 2 | 0.44896 | Good prognosis | Good prognosis |
| Patient 3 | 0.67417 | Poor prognosis | Poor prognosis |
| Patient 4 | 0.735268 | Poor prognosis | Poor prognosis |
| Patient 5 | 0.756405 | Poor prognosis | Poor prognosis |
| Patient 6 | 0.930926 | Poor prognosis | Poor prognosis |
It should be noted that the above-mentioned description in relation to process 600 is used for the purpose of example and explanation, without limiting the application
The scope of application.To those skilled in the art, process 600 can be carried out under the guidance of the application it is various amendment and
Change.However, these modifications and variations are still within the scope of the present application.
The possible beneficial effect of the embodiment of the present application includes but is not limited to: (1) may be implemented based on tumor patient
Its outcome of gene mutation information prediction；(2) tumor prognosis predictablity rate is improved；(3) tumor prognosis predicts implementation Process
It is convenient；It (4) is the formulation of therapeutic scheme, selection provides reference.It should be noted that different embodiments are issuable beneficial to effect
Fruit is different, in different embodiments, it is possible to create beneficial effect can be the combinations of any of the above one or more, can also
Be other it is any can obtainable beneficial effect.
Basic conception is described above, it is clear that those skilled in the art, above-mentioned detailed disclosure is only
As an example, and not constituting the restriction to the application.Although do not clearly state herein, those skilled in the art may
The application is carry out various modifications, improve and is corrected.Such modification, improvement and amendment are proposed in this application, so such
Modification improves, corrects the spirit and scope for still falling within the application example embodiment.
Meanwhile the application has used particular words to describe embodiments herein.Such as " one embodiment ", " one implements
Example ", and/or " some embodiments " mean a certain feature relevant at least one embodiment of the application, structure or feature.Cause
This, it should be highlighted that and it is noted that " embodiment " or " an implementation referred to twice or repeatedly in this specification in different location
Example " or " alternate embodiment " are not necessarily meant to refer to the same embodiment.In addition, in one or more embodiments of the application
Certain features, structure or feature can carry out combination appropriate.
In addition, it will be understood by those skilled in the art that the various aspects of the application can be by several with patentability
Type or situation are illustrated and described, the combination or right including any new and useful process, machine, product or substance
Their any new and useful improvement.Correspondingly, the various aspects of the application can completely by hardware execute, can be complete
It is executed, can also be executed by combination of hardware by software (including firmware, resident software, microcode etc.).Hardware above is soft
Part is referred to alternatively as " data block ", " module ", " engine ", " unit ", " component " or " system ".In addition, the various aspects of the application
The computer product being located in one or more computer-readable mediums may be shown as, which includes computer-readable program
Coding.
Computer storage medium may include the propagation data signal containing computer program code in one, such as in base
Take or as carrier wave a part.The transmitting signal may there are many forms of expression, including electromagnetic form, light form etc., or
Suitable combining form.Computer storage medium can be any computer-readable Jie in addition to computer readable storage medium
Matter, the medium can realize communication, propagation or transmission for using by being connected to an instruction execution system, device or equipment
Program.Program coding in computer storage medium can be propagated by any suitable medium, including wireless
The combination of electricity, cable, fiber optic cables, RF or similar mediums or any of above medium.
Computer program code needed for the operation of the application each section can use any one or more programming language,
Including Object-Oriented Programming Language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET,
Python etc., conventional procedural programming language for example C language, Visual Basic, 2003 Fortran, Perl, COBOL 2002,
PHP, ABAP, dynamic programming language such as Python, Ruby and Groovy or other programming languages etc..The program coding can be complete
Entirely on the user computer run run on the user computer as independent software package or partially in subscriber computer
Upper operation part runs in remote computer or runs on a remote computer or server completely.In the latter cases, remotely
Computer can be connect by any latticed form with subscriber computer, such as local area network (LAN) or wide area network (WAN), or even
It is connected to outer computer (such as passing through internet), or in cloud computing environment, or is serviced as service using such as software
(SaaS)。
In addition, except clearly stating in non-claimed, the sequence of herein described processing element and sequence, digital alphabet
Using or other titles use, be not intended to limit the sequence of the application process and method.Although by each in above-mentioned disclosure
Kind of example discuss it is some it is now recognized that useful inventive embodiments, but it is to be understood that, such details only plays explanation
Purpose, appended claims are not limited in the embodiment disclosed, on the contrary, claim is intended to cover and all meets the application
The amendment and equivalent combinations of embodiment spirit and scope.For example, although system component described above can be set by hardware
It is standby to realize, but can also be only achieved by the solution of software, such as pacify on existing server or mobile device
Fill described system.
Similarly, it is noted that in order to simplify herein disclosed statement, to help real to one or more invention
Apply the understanding of example, above in the description of the embodiment of the present application, sometimes by various features merger to one embodiment, attached drawing or
In descriptions thereof.But this disclosure method is not meant to mention in aspect ratio claim required for the application object
And feature it is more.In fact, the feature of embodiment will be less than whole features of the single embodiment of above-mentioned disclosure.
The number of description ingredient, number of attributes is used in some embodiments, it should be appreciated that such to be used for embodiment
The number of description has used qualifier " about ", " approximation " or " generally " to modify in some instances.Unless in addition saying
It is bright, " about ", " approximation " or " generally " show the variation that the number allows to have ± 20%.Correspondingly, in some embodiments
In, numerical parameter used in description and claims is approximation, approximation feature according to needed for separate embodiment
It can change.In some embodiments, numerical parameter is considered as defined significant digit and using the reservation of general digit
Method.Although the Numerical Range and parameter in some embodiments of the application for confirming its range range are approximation, specific real
It applies in example, being set in for such numerical value is reported as precisely as possible in feasible region.
For each patent, patent application, patent application publication object and the other materials of the application reference, such as article, book
Entire contents, are incorporated herein as reference by nationality, specification, publication, document etc. hereby.It is inconsistent with teachings herein
Or except generating the application history file of conflict, (currently or later to the conditional file of the claim of this application widest scope
Be additional in the application) also except.It should be noted that if description, definition, and/or art in the application attaching material
The use of language with it is herein described it is interior have place that is inconsistent or conflicting, with making for the description of the present application, definition and/or term
Subject to.
Finally, it will be understood that embodiment described herein is only to illustrate the principle of the embodiment of the present application.Other
Deformation may also belong to scope of the present application.Therefore, as an example, not a limit, the alternative configuration of the embodiment of the present application is visual
It is consistent with teachings of the present application.Correspondingly, embodiments herein is not limited only to the implementation that the application is clearly introduced and described
Example.
Claims (30)
1. a kind of tumor prognosis prediction technique characterized by comprising
The characteristic information of tumor patient is obtained, the characteristic information at least reflects the gene mutation information of the tumor patient；
Based on the characteristic information of the tumor patient, according to tumor prognosis prediction model, determine that the prognosis of the tumor patient is pre-
Survey result.
2. tumor prognosis prediction technique as described in claim 1, which is characterized in that the gene mutation information includes on DNA
The gene of mutation and its tumor prognosis prediction related gene on mutation abundance and/or DNA and its mutation abundance.
3. tumor prognosis prediction technique as described in claim 1, which is characterized in that the characteristic information for obtaining tumor patient
Further comprise:
Obtain the tissue samples of the tumor patient；
Extract the DNA of the tissue samples；
Prepare the library of the DNA；
Gene sequencing is carried out according to the library, obtains sequencing result；
The sequencing result is analyzed, determines the gene mutation information of the tumor patient.
4. tumor prognosis prediction technique as described in claim 1, which is characterized in that the characteristic information further includes the tumour
At least one in the following information of patient: age, gender, smoking history, the length of education enjoyed, length of service, therapeutic scheme and sample
This holding time.
5. tumor prognosis prediction technique as described in claim 1, which is characterized in that the tumor prognosis prediction model is to support
Vector machine model or neural network model.
6. tumor prognosis prediction technique as described in claim 1, which is characterized in that further include:
The tumor prognosis, which is obtained, using characteristic information and its prognosis information the training initial model of several tumor patients predicts mould
Type.
7. tumor prognosis prediction technique as claimed in claim 6, which is characterized in that the feature using several tumor patients
Information and its prognosis information training initial model obtain the tumor prognosis prediction model and include:
Remove the mutated gene information that the small Mr. Yu's given threshold of abundance is mutated in the gene mutation information of the several tumor patients.
8. tumor prognosis prediction technique as claimed in claim 6, which is characterized in that the feature using several tumor patients
Information and its prognosis information training initial model obtain the tumor prognosis prediction model and include:
Remove the redundancy gene mutation information in the gene mutation information of the several tumor patients.
9. tumor prognosis prediction technique as claimed in claim 6, which is characterized in that
The tumor prognosis prediction model is supporting vector machine model；
It is pre- that characteristic information and its prognosis information the training initial model using several tumor patients obtains the tumor prognosis
Surveying model includes:
According to gene mutation information each in the characteristic information of several tumor patients to the contribution margin of supporting vector machine model, determine extremely
Small part gene is that tumor prognosis predicts related gene；
Utilize the gene mutation information and its prognosis information training of the tumor prognosis prediction related gene of several tumor patients
The initial model obtains the tumor prognosis prediction model.
10. tumor prognosis prediction technique as claimed in claim 6, which is characterized in that
The tumor prognosis prediction model is supporting vector machine model；
The trained initial model obtains the tumor prognosis prediction model further include: utilizes particle swarm algorithm or grid dividing method
Optimize the parameter of the supporting vector machine model.
11. tumor prognosis prediction technique as described in claim 1, which is characterized in that
The prognosis prediction result includes: progression of disease, stable disease, part alleviates and complete incidence graph；Alternatively,
The prognosis prediction result includes: that therapeutic effect is good and therapeutic effect is bad.
12. the tumor prognosis prediction technique as described in claim 1-11, which is characterized in that the tumour is osteosarcoma.
13. tumor prognosis prediction technique as claimed in claim 12, which is characterized in that the characteristic information at least reflects bone and flesh
The abrupt information of at least one following gene of tumor patient: KMT2C, SOX9, LRP1B, NF-1, PRKDC, FAT1, STAG2,
SLIT2、NOTCH1、EPHA7、ATRX、KDM6A、APC、RANBP2、RARA.AS1、C11orf30、ROS1、ARID2、TAF1、
DICER1, MSH2, MSH6, TP53, KDM5A, JAK2, ALK, RB1, NOTCH2 and RICTOR.
14. tumor prognosis prediction technique as claimed in claim 12, which is characterized in that the tumor patient gene mutation information
For the gene mutation information of osteosarcoma diseased region.
15. a kind of tumor prognosis forecasting system, which is characterized in that including obtaining module and prediction module, wherein
The characteristic information for obtaining module and being used to obtain tumor patient, the characteristic information at least reflect the tumor patient
Gene mutation information；
The prediction module is used for the characteristic information based on the tumor patient, according to tumor prognosis prediction model, determine described in
The prognosis prediction result of tumor patient.
16. tumor prognosis forecasting system as claimed in claim 15, which is characterized in that the gene mutation information includes DNA
The gene of upper mutation and its tumor prognosis prediction related gene on mutation abundance and/or DNA and its mutation abundance.
17. tumor prognosis forecasting system as claimed in claim 15, which is characterized in that the characteristic information further includes described swollen
At least one in the following information of tumor patient: the age, gender, smoking history, the length of education enjoyed, the length of service, therapeutic scheme and
The Sample preservation time.
18. tumor prognosis forecasting system as claimed in claim 15, which is characterized in that the tumor prognosis prediction model is branch
Hold vector machine model or neural network model.
19. tumor prognosis forecasting system as claimed in claim 15, which is characterized in that it further include training module, the training
Module is used to obtain the tumor prognosis using characteristic information and its prognosis information the training initial model of several tumor patients pre-
Survey model.
20. tumor prognosis forecasting system as claimed in claim 19, which is characterized in that the training module is also used to remove institute
State the mutated gene information that the small Mr. Yu's given threshold of abundance is mutated in the gene mutation information of several tumor patients.
21. tumor prognosis forecasting system as claimed in claim 19, which is characterized in that the training module is also used to remove institute
State the redundancy gene mutation information in the gene mutation information of several tumor patients.
22. tumor prognosis forecasting system as claimed in claim 19, which is characterized in that
The tumor prognosis prediction model is supporting vector machine model；
The training module is also used to:
According to gene mutation information each in the characteristic information of several tumor patients to the contribution margin of supporting vector machine model, determine extremely
Small part gene is that tumor prognosis predicts related gene；
Utilize the gene mutation information and its prognosis information training of the tumor prognosis prediction related gene of several tumor patients
The initial model obtains the tumor prognosis prediction model.
23. tumor prognosis forecasting system as claimed in claim 19, which is characterized in that
The tumor prognosis prediction model is supporting vector machine model；
The training module is also used to optimize using particle swarm algorithm or grid dividing method the parameter of the supporting vector machine model.
24. tumor prognosis forecasting system as claimed in claim 15, which is characterized in that
The prognosis prediction result includes: progression of disease, stable disease, part alleviates and complete incidence graph；Alternatively,
The prognosis prediction result includes: that therapeutic effect is good and therapeutic effect is bad.
25. the tumor prognosis forecasting system as described in claim 15-24, which is characterized in that the tumour is osteosarcoma.
26. tumor prognosis forecasting system as claimed in claim 25, which is characterized in that the characteristic information at least reflects bone and flesh
The abrupt information of at least one following gene of tumor patient: KMT2C, SOX9, LRP1B, NF-1, PRKDC, FAT1, STAG2,
SLIT2、NOTCH1、EPHA7、ATRX、KDM6A、APC、RANBP2、RARA.AS1、C11orf30、ROS1、ARID2、TAF1、
DICER1, MSH2, MSH6, TP53, KDM5A, JAK2, ALK, RB1, NOTCH2 and RICTOR.
27. tumor prognosis forecasting system as claimed in claim 26, which is characterized in that the tumor patient gene mutation information
For the gene mutation information of osteosarcoma diseased region.
28. a kind of tumor prognosis prediction meanss, which is characterized in that described device include at least one processor and at least one
Memory；
At least one processor is for storing computer instruction；
At least one described processor is used to execute at least partly instruction in the computer instruction to realize such as claim 1
~11 described in any item tumor prognosis prediction techniques.
29. a kind of computer readable storage medium, which is characterized in that the storage medium stores computer instruction, when the meter
When the instruction of calculation machine is executed by processor, tumor prognosis prediction technique as claimed in any one of claims 1 to 11 is realized.
30. a kind of tumor prognosis forecasting system, comprising:
At least one computer readable storage medium, including the one group of instruction predicted for tumor prognosis；And
At least one processor communicated at least one described storage medium, when executing one group of instruction, it is described at least
One processor is configured as:
The characteristic information of tumor patient is obtained, the characteristic information at least reflects the gene mutation information of tumor patient；And
Based on the characteristic information of the tumor patient, according to tumor prognosis prediction model, determine that the prognosis of the tumor patient is pre-
Survey result.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2018/110565 WO2020077552A1 (en) | 2018-10-17 | 2018-10-17 | Tumor prognostic prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109642258A true CN109642258A (en) | 2019-04-16 |
| CN109642258B CN109642258B (en) | 2020-06-09 |
Family
ID=66060220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201880002164.4A Active CN109642258B (en) | 2018-10-17 | 2018-10-17 | Method and system for tumor prognosis prediction |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109642258B (en) |
| WO (1) | WO2020077552A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675956A (en) * | 2019-08-26 | 2020-01-10 | 南京医渡云医学技术有限公司 | Method and device for determining facial paralysis treatment scheme, readable medium and electronic equipment |
| CN110993106A (en) * | 2019-12-11 | 2020-04-10 | 深圳市华嘉生物智能科技有限公司 | Liver cancer postoperative recurrence risk prediction method combining pathological image and clinical information |
| CN111528918A (en) * | 2020-04-30 | 2020-08-14 | 深圳开立生物医疗科技股份有限公司 | Tumor volume change trend graph generation device after ablation, equipment and storage medium |
| CN111784637A (en) * | 2020-06-04 | 2020-10-16 | 复旦大学附属中山医院 | Prognostic characteristic visualization method, system, equipment and storage medium |
| CN112397172A (en) * | 2020-12-24 | 2021-02-23 | 上海墩庐生物医学科技有限公司 | Intelligent consultant internet application system for breast cancer survival |
| CN113345564A (en) * | 2021-05-31 | 2021-09-03 | 电子科技大学 | Early prediction method and device for patient hospitalization duration based on graph neural network |
| CN114627969A (en) * | 2022-03-23 | 2022-06-14 | 中国医学科学院肿瘤医院 | Application of complement-associated-gene-based prognosis prediction model and kit for sarcoma patient |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764837A (en) * | 2003-03-24 | 2006-04-26 | 魏念之 | Methods for predicting an individual's clinical treatment outcome from sampling a group of patients' biological profiles |
| CN102713606A (en) * | 2009-11-13 | 2012-10-03 | 无限制药股份有限公司 | Compositions, kits, and methods for identification, assessment, prevention, and therapy of cancer |
| WO2012166700A2 (en) * | 2011-05-29 | 2012-12-06 | Lisanti Michael P | Molecular profiling of a lethal tumor microenvironment |
| WO2013134786A2 (en) * | 2012-03-09 | 2013-09-12 | Caris Life Sciences Luxembourg Holdings, S.A.R.L. | Biomarker compositions and methods |
| CN104769131A (en) * | 2012-09-21 | 2015-07-08 | 英特盖根公司 | A method for prognosis of global survival and survival without relapse in hepatocellular carcinoma |
| WO2016141324A2 (en) * | 2015-03-05 | 2016-09-09 | Trovagene, Inc. | Early assessment of mechanism of action and efficacy of anti-cancer therapies using molecular markers in bodily fluids |
| WO2017062989A1 (en) * | 2015-10-08 | 2017-04-13 | Urology Diagnostics, Inc. | Diagnostic assay for urine monitoring of bladder cancer |
| JP2017216882A (en) * | 2016-06-02 | 2017-12-14 | 国立大学法人金沢大学 | Method of detecting the existence of osteopathy, osteopathy therapeutic agent, and method for screening osteopathy therapeutic agent |
| CN107545144A (en) * | 2017-09-05 | 2018-01-05 | 上海市内分泌代谢病研究所 | pheochromocytoma branch prediction system based on molecular marker |
| CN107750279A (en) * | 2015-03-16 | 2018-03-02 | 个人基因组诊断公司 | Foranalysis of nucleic acids system and method |
| CN108027372A (en) * | 2015-05-27 | 2018-05-11 | 卡纳比克斯制药公司 | System and method for high flux screening cancer cell |
| US20180246104A1 (en) * | 2015-08-18 | 2018-08-30 | Agency For Science, Technology And Research | Method for detecting circulating tumor cells and uses thereof |
| CN108474723A (en) * | 2015-12-02 | 2018-08-31 | 克莱尔莱特诊断有限责任公司 | Prepare and analyze the method that neoplasmic tissue sample is used to detecting and monitoring cancer |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106202969B (en) * | 2016-08-01 | 2018-10-23 | 东北大学 | A kind of tumor cells parting forecasting system |
| CN106960122A (en) * | 2017-03-17 | 2017-07-18 | 晶能生物技术（上海）有限公司 | Genetic disease Forecasting Methodology and device caused by gene mutation |
| CN107169264B (en) * | 2017-04-14 | 2019-12-06 | 广东药科大学 | complex disease diagnosis system |
| CN107341366A (en) * | 2017-07-19 | 2017-11-10 | 西安交通大学 | A kind of method that complex disease susceptibility loci is predicted using machine learning |
| CN107833636A (en) * | 2017-12-04 | 2018-03-23 | 浙江鸿赋堂健康管理有限公司 | A kind of tumour Forecasting Methodology |
| CN108416190A (en) * | 2018-02-11 | 2018-08-17 | 广州市碳码科技有限责任公司 | Tumour methods for screening, device, equipment and medium based on deep learning |
-
2018
- 2018-10-17 CN CN201880002164.4A patent/CN109642258B/en active Active
- 2018-10-17 WO PCT/CN2018/110565 patent/WO2020077552A1/en active Application Filing
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764837A (en) * | 2003-03-24 | 2006-04-26 | 魏念之 | Methods for predicting an individual's clinical treatment outcome from sampling a group of patients' biological profiles |
| CN102713606A (en) * | 2009-11-13 | 2012-10-03 | 无限制药股份有限公司 | Compositions, kits, and methods for identification, assessment, prevention, and therapy of cancer |
| WO2012166700A2 (en) * | 2011-05-29 | 2012-12-06 | Lisanti Michael P | Molecular profiling of a lethal tumor microenvironment |
| WO2013134786A2 (en) * | 2012-03-09 | 2013-09-12 | Caris Life Sciences Luxembourg Holdings, S.A.R.L. | Biomarker compositions and methods |
| CN104769131A (en) * | 2012-09-21 | 2015-07-08 | 英特盖根公司 | A method for prognosis of global survival and survival without relapse in hepatocellular carcinoma |
| WO2016141324A2 (en) * | 2015-03-05 | 2016-09-09 | Trovagene, Inc. | Early assessment of mechanism of action and efficacy of anti-cancer therapies using molecular markers in bodily fluids |
| CN107750279A (en) * | 2015-03-16 | 2018-03-02 | 个人基因组诊断公司 | Foranalysis of nucleic acids system and method |
| CN108027372A (en) * | 2015-05-27 | 2018-05-11 | 卡纳比克斯制药公司 | System and method for high flux screening cancer cell |
| US20180246104A1 (en) * | 2015-08-18 | 2018-08-30 | Agency For Science, Technology And Research | Method for detecting circulating tumor cells and uses thereof |
| WO2017062989A1 (en) * | 2015-10-08 | 2017-04-13 | Urology Diagnostics, Inc. | Diagnostic assay for urine monitoring of bladder cancer |
| CN108474723A (en) * | 2015-12-02 | 2018-08-31 | 克莱尔莱特诊断有限责任公司 | Prepare and analyze the method that neoplasmic tissue sample is used to detecting and monitoring cancer |
| JP2017216882A (en) * | 2016-06-02 | 2017-12-14 | 国立大学法人金沢大学 | Method of detecting the existence of osteopathy, osteopathy therapeutic agent, and method for screening osteopathy therapeutic agent |
| CN107545144A (en) * | 2017-09-05 | 2018-01-05 | 上海市内分泌代谢病研究所 | pheochromocytoma branch prediction system based on molecular marker |
Non-Patent Citations (5)
| Title |
|---|
| CATERINA CHIAPPETTA等: "Whole-exome analysis in osteosarcoma to identify a personalized therapy", 《ONCOTARGET》 * |
| MATLAB中文论坛: "《MATLAB神经网络30个案例分析》", 30 April 2010 * |
| 周敏: "《制造业信息化工程学》", 31 January 2017, 冶金工业出版社 * |
| 肖鑫等: "基于高通量测序技术的骨肉瘤基因研究与个体化治疗", 《中华骨科杂志》 * |
| 陈敏: "《认知计算导论》", 31 May 2017 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675956A (en) * | 2019-08-26 | 2020-01-10 | 南京医渡云医学技术有限公司 | Method and device for determining facial paralysis treatment scheme, readable medium and electronic equipment |
| CN110993106A (en) * | 2019-12-11 | 2020-04-10 | 深圳市华嘉生物智能科技有限公司 | Liver cancer postoperative recurrence risk prediction method combining pathological image and clinical information |
| CN111528918A (en) * | 2020-04-30 | 2020-08-14 | 深圳开立生物医疗科技股份有限公司 | Tumor volume change trend graph generation device after ablation, equipment and storage medium |
| CN111528918B (en) * | 2020-04-30 | 2023-02-21 | 深圳开立生物医疗科技股份有限公司 | Tumor volume change trend graph generation device after ablation, equipment and storage medium |
| CN111784637A (en) * | 2020-06-04 | 2020-10-16 | 复旦大学附属中山医院 | Prognostic characteristic visualization method, system, equipment and storage medium |
| CN112397172A (en) * | 2020-12-24 | 2021-02-23 | 上海墩庐生物医学科技有限公司 | Intelligent consultant internet application system for breast cancer survival |
| CN113345564A (en) * | 2021-05-31 | 2021-09-03 | 电子科技大学 | Early prediction method and device for patient hospitalization duration based on graph neural network |
| CN113345564B (en) * | 2021-05-31 | 2022-08-05 | 电子科技大学 | Early prediction method and device for patient hospitalization duration based on graph neural network |
| CN114627969A (en) * | 2022-03-23 | 2022-06-14 | 中国医学科学院肿瘤医院 | Application of complement-associated-gene-based prognosis prediction model and kit for sarcoma patient |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109642258B (en) | 2020-06-09 |
| WO2020077552A1 (en) | 2020-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109642258A (en) | A kind of method and system of tumor prognosis prediction | |
| US11282610B2 (en) | Cancer evolution detection and diagnostic | |
| CN109689891A (en) | The method of segment group spectrum analysis for cell-free nucleic acid | |
| Nicolò et al. | Machine learning and mechanistic modeling for prediction of metastatic relapse in early-stage breast cancer | |
| Shariat et al. | Comparison of nomograms with other methods for predicting outcomes in prostate cancer: a critical analysis of the literature | |
| Kasius et al. | Risk stratification of endometrial cancer patients: FIGO stage, biomarkers and molecular classification | |
| CN108474040A (en) | Recommended using the treatment based on group of Cell-free DNA | |
| CN108292299A (en) | It is born from genomic variants predictive disease | |
| Tewarie et al. | Survival prediction of glioblastoma patients—are we there yet? A systematic review of prognostic modeling for glioblastoma and its clinical potential | |
| CN112951327B (en) | Drug sensitivity prediction method, electronic device, and computer-readable storage medium | |
| Panagopoulou et al. | Circulating cell-free DNA in breast cancer: Searching for hidden information towards precision medicine | |
| Yuan et al. | Prediction of tumor metastasis from sequencing data in the era of genome sequencing | |
| Zhao et al. | Object-oriented regression for building predictive models with high dimensional omics data from translational studies | |
| Li et al. | Machine learning predicts the prognosis of breast cancer patients with initial bone metastases | |
| Chen et al. | Targeted gene expression profiling predicts meningioma outcomes and radiotherapy responses | |
| Ranasinghe et al. | Relationship between serum markers and volume of liver metastases in castration-resistant prostate cancer | |
| Mbogning et al. | Bagging survival tree procedure for variable selection and prediction in the presence of nonsusceptible patients | |
| TWI671653B (en) | Subtyping of tnbc and methods | |
| Martins-Filho et al. | EGFR-mutated lung adenocarcinomas from patients who progressed on EGFR-inhibitors show high engraftment rates in xenograft models | |
| Chen et al. | Cox regression analysis on the survival rate of breast cancer patients | |
| Cianci et al. | AIC | |
| KR102138517B1 (en) | Extracting method for biomarker for diagnosis of pancreatic cancer, computing device therefor, biomarker, and pancreatic cancer diagnosis device comprising same | |
| Anandaram | A review on application of biomarkers in the field of bioinformatics & nanotechnology for individualized cancer treatment | |
| Coleman et al. | Basic Concepts in Molecular Pathology—Introduction to Molecular Testing in Human Disease | |
| Storey et al. | Spatial measures of genetic heterogeneity during carcinogenesis |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 314001 building 5-1, 3556 linggongtang Road, Daqiao Town, Nanhu District, Jiaxing City, Zhejiang Province Patentee after: Zhejiang Yunying Medical Technology Co.,Ltd. Address before: Room 201, building 18, Caohejing emerging technology development zone, No. 518, Xinzhuan Road, Songjiang District, Shanghai 201600 Patentee before: SHANGHAI YUNYING MEDICAL TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address |