CN106682456A - Method for exploring complex disease susceptibility genes based on characteristics of genome epigenetic regulation elements - Google Patents
Method for exploring complex disease susceptibility genes based on characteristics of genome epigenetic regulation elements Download PDFInfo
- Publication number
- CN106682456A CN106682456A CN201611258007.9A CN201611258007A CN106682456A CN 106682456 A CN106682456 A CN 106682456A CN 201611258007 A CN201611258007 A CN 201611258007A CN 106682456 A CN106682456 A CN 106682456A
- Authority
- CN
- China
- Prior art keywords
- gene
- tumor susceptibility
- genome
- disease
- commitment
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B20/00—ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Biotechnology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioethics (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- Epidemiology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Genetics & Genomics (AREA)
- Molecular Biology (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention discloses a method for exploring complex disease susceptibility genes based on characteristics of genome epigenetic regulation elements, wherein known susceptibility genes of a to-be-analyzed disease as well as all the epigenetic regulation element information of the known susceptibility genes are collected; the epigenetic regulation element information is used to annotate all promoter sub-areas of all the known susceptibility genes according to a physical position of the genome, a target set and a reference set are compared through enrichment analysis, the regulation elements with significant enrichment in the known susceptibility genes are found, and the characteristics of the epigenetic regulation elements of the known susceptibility genes are extracted; and reserve prediction is conducted to the extracted characteristics of the epigenetic regulation elements, all the known susceptibility genes are re-graded, and a final judgment results can be obtained. According to the invention, epigenetic science information and genome DNA sequence information are combined organically; through extraction of the characteristics of the epigenetic regulation elements, the disease characteristic susceptibility gens can be predicted as a whole; and new susceptibility genes can be found significantly.
Description
Technical field
The invention belongs to genomic data digging technology field, it is related to a kind of based on genome commitment element characteristics
The method for digging of complex disease tumor susceptibility gene.
Background technology
At present, developing rapidly with high-throughput techniques, biomedical sector have accumulated the human genome data of magnanimity.
Using these data, it has now been found that numerous disease tumor susceptibility gene.However, for specific complex disease, the disease for being found
Tumor susceptibility gene is accumulated the disease genetic of explanation and is made a variation less than 15%, and this is encountered in all complex disease genetics research
One total phenomenon, i.e. " heritability of loss ", this reflects the utilization to existing mass data resource and excavates far from
Foot.In the face of these data, how to find complex disease " heritability of loss " is a current difficult problem urgently to be resolved hurrily, and needing to adopt has
Efficacious prescriptions method finds a large amount of valuable hereditary information hidden in data, predictive disease tumor susceptibility gene, so as to be used for examining for disease
Disconnected treatment.The significant challenge that complex disease tumor susceptibility gene becomes in disease research is deeply excavated, its result is for announcement disease
The clinical early screening and individuation preventing and treating of sick pathogeny and Basic of Biology, design medicine target spot and disease, all will produce
The highly important theoretical and realistic meaning of life.
The method of existing complex disease tumor susceptibility gene prediction is varied, is mostly based on the prediction of gene itself.Root
According to the information of DNA sequence, the information such as combined function, place path, biomolecule network is predicted.However, complex disease is
Occurred what is developed by multiple inherited genetic factorss and the common reciprocal action of environmental factorss, only consider DNA sequence information, it is difficult to be true anti-
The state of complex disease is mirrored, epigenetics effect can not be ignored.
Genome includes two class hereditary informations:That is DNA sequence hereditary information and epigenetics information.Epigenetic-effect
The maintenance for being independent of the change of gene order, human body and cell function is the result that both information interacted, kept balance.
At present, the achievement in research of epigenetics has been applied in the research of some diseases and treatment.Therefore, disease-susceptible humans are being carried out
During predictive genes, it is highly desirable to include the information of epigenetics, it will bring new opportunity for disease research.
The content of the invention
Present invention solves the problem in that it is susceptible to provide a kind of complex disease based on genome commitment element characteristics
The method for digging of gene, epigenetics information and genomic dna sequence information are organically combined, by extracting commitment unit
Part feature, the predictive disease characteristic tumor susceptibility gene from the overall situation.
The present invention is to be achieved through the following technical solutions:
A kind of method for digging of the complex disease tumor susceptibility gene based on genome commitment element characteristics, including following behaviour
Make:
S1:Collect the known tumor susceptibility gene of disease to be analyzed, and all commitment elements letter of known tumor susceptibility gene
Breath;Using commitment component information, the promoter region of all known tumor susceptibility genes is entered according to the physical location of genome
Row annotation, if promoter region be equipped with the physical bit that certain controlling element is recognized it is Chong Die, then it is assumed that the promoter region is noted
Release;
S2:Using known tumor susceptibility gene promoter collection of comments as goal set, with all gene promoters of full-length genome
Collection of comments compares goal set and reference set as reference set using the method for enrichment analysis, finds out known easily sensillary base
The controlling element of significant enrichment, carries out the feature extraction of known tumor susceptibility gene commitment element because in;
S3:Commitment element characteristics according to extracting carry out backward prediction, and all known tumor susceptibility genes are entered again
Row marking, obtains final court verdict, screens known tumor susceptibility gene in the top as the potential easy sensillary base for giving priority to
Cause.
Step S1 specifically includes following operation:
S11:Collect susceptible known to a certain disease using public database GWAS catalog and PubMed pertinent literature
Gene;
S12:The all commitment component informations of genome are obtained from UCSC data bases, including Binding site for transcription factor,
Histone modification site and chromatin cutting state;Every kind of controlling element is stored as a text;
S13:It is easy to all known diseases according to the physical location of genome using the commitment component information for obtaining
Sensillary base because promoter region annotated, promoter region as and the physical bit of certain controlling element be equipped with overlap, then it is assumed that
It is annotated into.
Step S2 specifically includes following operation:
S21:For the result after S1 annotations, using the method for enrichment analysis, goal set and reference set are compared, found out
The controlling element of significant enrichment, extracts its feature;
After the completion of annotation, compare with the annotation situation of disease related gene, using Fisher exact tests, really
Determine the significant enrichment of controlling element;
For certain element, under the annotation data distribution of n sampling:
Then P values are calculated:
S22:The P values of acquisition are carried out into decimal logarithm conversion.
To reflect the annotation distribution situation of full-length genome, n times sampling is also carried out, and calculate adding and average for all sampling
To represent the annotation situation of the promoter of full-length genome.
For ratio significantly elevated controlling element in disease gene set, P values are after conversion:Transformed P=-
log10(P);
The significantly reduced controlling element of ratio in disease gene set, P values are after conversion:Transformed P=log10
(P)。
The step S3 concrete operations include:
S31:Analyze P values after the conversion of all genes;
S32:Backward prediction scoring is carried out to all genes:Assume that enrichment analysis has obtained the Functional Unit of n significant enrichment
Part, P values are designated as tPi after the conversion of i-th element, and the number of times of certain gene annotation to these elements is Si, then the gene is anti-
It is to analysis scoring:
S33:All genes are ranked up according to backward prediction scoring, numerical value S is bigger, are sorted higher, it is used as disease
The probability of tumor susceptibility gene is higher, and the forward gene that will sort is used as the potential tumor susceptibility gene of this disease.
Compared with prior art, the present invention has following beneficial technique effect:
It is an object of the invention to provide a kind of complex disease tumor susceptibility gene based on genome commitment element characteristics
Method for digging, epigenetics information and genomic dna sequence information are organically combined, it is special by extracting commitment element
Levy, the predictive disease characteristic tumor susceptibility gene from the overall situation can significantly provide the effect for finding new tumor susceptibility gene, be that follow-up being directed to is closed
Key controlling element design medicine target spot has established important foundation.
A kind of excavation side of complex disease tumor susceptibility gene based on genome commitment element characteristics proposed by the present invention
Method, in combination with DNA sequence information and epigenetics information, by the commitment element rule for finding diseases predisposing gene
Rule carries out the prediction of new tumor susceptibility gene, is remarkably improved the statistical power for finding new tumor susceptibility gene.By carrying out to latent gene
It is integrated ordered, global optimum's result of decision is obtained, the screening for diseases predisposing gene provides optimum.The heredity mark for predicting
Note is rich in biological function, is that important foundation has been established in further biological function evaluation and drug targeting exploitation.
Description of the drawings
Fig. 1 is method of the present invention schematic flow sheet.
Specific embodiment
With reference to specific embodiment, the present invention is described in further detail, it is described be explanation of the invention and
It is not to limit.
Referring to Fig. 1, a kind of method for digging of the complex disease tumor susceptibility gene based on genome commitment element characteristics, bag
Include following steps:
S1:Collect the known tumor susceptibility gene of disease to be analyzed, and all commitment elements letter of known tumor susceptibility gene
Breath;Using commitment component information, the promoter region of all known tumor susceptibility genes is entered according to the physical location of genome
Row annotation, if promoter region be equipped with the physical bit that certain controlling element is recognized it is Chong Die, then it is assumed that the promoter region is noted
Release;
S2:Using known tumor susceptibility gene promoter collection of comments as goal set, with all gene promoters of full-length genome
Collection of comments compares goal set and reference set as reference set using the method for enrichment analysis, finds out known easily sensillary base
The controlling element of significant enrichment, carries out the feature extraction of known tumor susceptibility gene commitment element because in;
S3:Commitment element characteristics according to extracting carry out backward prediction, and all known tumor susceptibility genes are entered again
Row marking, obtains final court verdict, screens known tumor susceptibility gene in the top as the potential easy sensillary base for giving priority to
Cause.
Step S1 is specifically included:
S11:Collect susceptible known to a certain disease using public database GWAS catalog and PubMed pertinent literature
Gene;
S12:The all commitment component informations of genome are obtained from UCSC data bases, including Binding site for transcription factor,
Histone modification site and chromatin cutting state;Every kind of controlling element is stored as a text;
S13:It is easy to all known diseases according to the physical location of genome using the commitment component information for obtaining
Sensillary base because promoter region annotated.The principle of correspondence is how promoter region is equipped with the physical bit of certain controlling element
Overlap, then it is assumed that be annotated into.
Step S2 is specifically included:
S21:For the result after above-mentioned annotation, using the method for enrichment analysis, studied goal set is compared (known
Tumor susceptibility gene promoter collection of comments) and reference set (all gene promoter collection of comments of full-length genome), find out notable richness
The controlling element of collection, extracts its feature.In order to preferably reflect the distribution situation of full-length genome, 1000 sampling are carried out,
And calculate this 1000 times sampling plus and average representing the annotation situation of the promoter of full-length genome.After the completion of annotation, with
The annotation situation of disease related gene is compared, and using Fisher exact tests, determines the significant enrichment of controlling element.Pin
To some element, data distribution is as shown in table 1:
The enrichment analysis of table 1 data distribution situation used
P value computing formula:
S22:For the ease of visualizing and comparing, the P values of acquisition are carried out into decimal logarithm conversion.For disease gene collection
Ratio significantly elevated controlling element in conjunction, P values (Transformed P) are after conversion:Transformed P=-log10
(P);
The significantly reduced controlling element of ratio, P values are after conversion:Transformed P=log10(P)。
Step S3 is specifically included:
S31:Analyze P values after the conversion of all genes;
S32:Backward prediction scoring is carried out to all genes:Assume that enrichment analysis has obtained the Functional Unit of n significant enrichment
Part, P values are designated as tPi after the conversion of i-th element, and the number of times of certain gene annotation to these elements is Si, then the gene is anti-
It is to analysis scoring:
S33:All genes are ranked up according to backward prediction scoring, numerical value S is bigger, are sorted higher, it is used as disease
The probability of tumor susceptibility gene is higher, using the gene of sequence top ten as the potential tumor susceptibility gene of this disease.
The method for predicting complex disease tumor susceptibility gene based on commitment element characteristics of the present invention, it is adaptable to Ren Heyi
Plant complex disease, such as various cancers, endocrinopathy, cardiovascular disease, immune class disease etc..
As one of embodiment of the present invention, the judgement of the diseases predisposing gene in the rapid S33 of the method for the invention, including
But it is not limited to the top ten gene for sorting.Those skilled in the art can also be according to the experimental conditions voluntarily forward base of selected and sorted
Because as tumor susceptibility gene.
Below by taking complex disease osteoporosis as an example, using the method for the present invention, osteoporosis susceptible gene is carried out
Prediction, be below described in detail.
As shown in figure 1, the present invention provides a kind of side that complex disease tumor susceptibility gene is predicted based on commitment element characteristics
Method, comprises the following steps S1-S3.
S1:Known osteoporosis susceptible gene is collected, and carries out the annotation of commitment element.
Specifically include:Tumor susceptibility gene known to osteoporosis is collected from public database GWAS catalog, totally 259
It is individual, as gene set.The all commitment component informations of genome, including 161 kinds of transcription factor knots are obtained from UCSC data bases
Close site, 273 kinds of histone modification sites and 135 kinds of chromatin cutting states.Using these commitment component informations to institute
The promoter region for having gene is annotated.
S2:Carry out the feature extraction of osteoporosis susceptible gene commitment element.
Specifically include:Using enrichment analysis, annotation and the full-length genome institute of known osteoporosises tumor susceptibility gene set are compared
There is the annotation of gene promoter, it is found that one has 52 kinds of commitment element significant enrichments in known osteoporosises tumor susceptibility gene
In set.The gene sets that contrast is randomly selected, with significantly regulation and control feature.
S3:Gene backward prediction is carried out according to commitment element characteristics.
Specifically include:According to the result of enrichment analysis, comprehensive grading is carried out to all genes.According to score value size to all
Gene carries out sequence from high to low.
Experimental result:The score value of gene score is higher, it is believed that it is bigger as the probability of osteoporosises tumor susceptibility gene.With
Gene score carries out path analysis for weight, finds gene significant enrichment in Wnt signaling, calcium signaling,
In Hedgehog signaling, MAPK signaling, and the path such as TGF-β signaling, these paths are all generally acknowledged
Osteoporosis related pathways, this explanation predicts that the method for osteoporosises tumor susceptibility gene is feasible based on commitment element characteristics
's.
It is as follows according to 20 most forward genes of marking ranking:
Example given above is to realize the present invention preferably example, the invention is not restricted to above-described embodiment.This area
Technical staff any nonessential addition, the replacement made according to the technical characteristic of technical solution of the present invention, belong to this
The protection domain of invention.
Claims (6)
1. a kind of method for digging of the complex disease tumor susceptibility gene based on genome commitment element characteristics, it is characterised in that
Including following operation:
S1:Collect the known tumor susceptibility gene of disease to be analyzed, and all commitment component informations of known tumor susceptibility gene;Profit
Commitment component information is used, the promoter region of all known tumor susceptibility genes is noted according to the physical location of genome
Release, if promoter region be equipped with the physical bit of certain controlling element identification it is Chong Die, then it is assumed that the promoter region is annotated into;
S2:Using known tumor susceptibility gene promoter collection of comments as goal set, with all gene promoter annotations of full-length genome
Set compares goal set and reference set, in finding out known tumor susceptibility gene as reference set using the method for enrichment analysis
The controlling element of significant enrichment, carries out the feature extraction of known tumor susceptibility gene commitment element;
S3:Commitment element characteristics according to extracting carry out backward prediction, all known tumor susceptibility genes are re-started and is beaten
Point, final court verdict is obtained, known tumor susceptibility gene in the top is screened as the potential tumor susceptibility gene for giving priority to.
2. the excavation side of the complex disease tumor susceptibility gene of genome commitment element characteristics is based on as claimed in claim 1
Method, it is characterised in that step S1 specifically includes following operation:
S11:The known tumor susceptibility gene of a certain disease is collected using public database GWAS catalog and PubMed pertinent literature;
S12:The all commitment component informations of genome, including Binding site for transcription factor, group egg are obtained from UCSC data bases
White decorating site and chromatin cutting state;Every kind of controlling element is stored as a text;
S13:Using the commitment component information for obtaining, according to the physical location of genome to all known disease-susceptible humans bases
The promoter region of cause is annotated, promoter region as and the physical bit of certain controlling element be equipped with overlap, then it is assumed that noted
Release.
3. the excavation side of the complex disease tumor susceptibility gene of genome commitment element characteristics is based on as claimed in claim 1
Method, it is characterised in that step S2 specifically includes following operation:
S21:For the result after S1 annotations, using the method for enrichment analysis, goal set and reference set are compared, found out significantly
The controlling element of enrichment, extracts its feature;
After the completion of annotation, compare with the annotation situation of disease related gene, using Fisher exact tests, it is determined that adjusting
The significant enrichment of control element;
For certain element, under the annotation data distribution of n sampling:
Then P values are calculated:
S22:The P values of acquisition are carried out into decimal logarithm conversion.
4. the excavation of the complex disease tumor susceptibility gene based on genome commitment element characteristics as described in claim 1 or 3
Method, it is characterised in that to reflect the annotation distribution situation of full-length genome, also carries out n times sampling, and calculates all sampling
Plus with average representing the annotation situation of the promoter of full-length genome.
5. the excavation side of the complex disease tumor susceptibility gene of genome commitment element characteristics is based on as claimed in claim 3
Method, it is characterised in that for ratio significantly elevated controlling element in disease gene set, P values are after conversion:
Transformed P=-log10(P);
The significantly reduced controlling element of ratio in disease gene set, P values are after conversion:Transformed P=log10(P)。
6. the excavation side of the complex disease tumor susceptibility gene of genome commitment element characteristics is based on as claimed in claim 3
Method, it is characterised in that the step S3 concrete operations include:
S31:Analyze P values after the conversion of all genes;
S32:Backward prediction scoring is carried out to all genes:Assume that enrichment analysis has obtained the function element of n significant enrichment, the
P values are designated as tPi after the conversion of i element, and the number of times of certain gene annotation to these elements is Si, then the reverse analysis of the gene
Score and be:
S33:All genes are ranked up according to backward prediction scoring, numerical value S is bigger, are sorted higher, it is used as disease-susceptible humans
The probability of gene is higher, and the forward gene that will sort is used as the potential tumor susceptibility gene of this disease.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611258007.9A CN106682456B (en) | 2016-12-30 | 2016-12-30 | A kind of method for digging of the complex disease tumor susceptibility gene based on genome commitment element characteristics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611258007.9A CN106682456B (en) | 2016-12-30 | 2016-12-30 | A kind of method for digging of the complex disease tumor susceptibility gene based on genome commitment element characteristics |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106682456A true CN106682456A (en) | 2017-05-17 |
CN106682456B CN106682456B (en) | 2019-01-29 |
Family
ID=58872370
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611258007.9A Active CN106682456B (en) | 2016-12-30 | 2016-12-30 | A kind of method for digging of the complex disease tumor susceptibility gene based on genome commitment element characteristics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106682456B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN115083517A (en) * | 2022-07-07 | 2022-09-20 | 南华大学附属第一医院 | Data processing method and system for identifying enhancer and super enhancer |
CN117457068A (en) * | 2023-06-30 | 2024-01-26 | 上海睿璟生物科技有限公司 | Multi-genetics-based functional biomarker screening method, system, terminal and medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101712997A (en) * | 2009-12-29 | 2010-05-26 | 西安交通大学 | Three novel human dystrophin gene STR loci and typing method thereof |
CN102586420A (en) * | 2011-12-27 | 2012-07-18 | 盛司潼 | Method and kit for assaying breast cancer susceptibility genes |
CN102808030A (en) * | 2012-08-21 | 2012-12-05 | 首都医科大学附属北京儿童医院 | Application of single nucleotide polymorphism rs3888188 to detection of tuberculosis susceptibility |
CN103667326A (en) * | 2008-02-21 | 2014-03-26 | 国立大学法人爱媛大学 | Identification of group of hypertension-susceptibility genes |
-
2016
- 2016-12-30 CN CN201611258007.9A patent/CN106682456B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103667326A (en) * | 2008-02-21 | 2014-03-26 | 国立大学法人爱媛大学 | Identification of group of hypertension-susceptibility genes |
CN101712997A (en) * | 2009-12-29 | 2010-05-26 | 西安交通大学 | Three novel human dystrophin gene STR loci and typing method thereof |
CN102586420A (en) * | 2011-12-27 | 2012-07-18 | 盛司潼 | Method and kit for assaying breast cancer susceptibility genes |
CN102808030A (en) * | 2012-08-21 | 2012-12-05 | 首都医科大学附属北京儿童医院 | Application of single nucleotide polymorphism rs3888188 to detection of tuberculosis susceptibility |
Non-Patent Citations (1)
Title |
---|
刘毅,等: "先天性心脏病相关易感基因的预测性研究", 《中国病理生理杂志》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN115083517A (en) * | 2022-07-07 | 2022-09-20 | 南华大学附属第一医院 | Data processing method and system for identifying enhancer and super enhancer |
CN117457068A (en) * | 2023-06-30 | 2024-01-26 | 上海睿璟生物科技有限公司 | Multi-genetics-based functional biomarker screening method, system, terminal and medium |
CN117457068B (en) * | 2023-06-30 | 2024-05-24 | 上海睿璟生物科技有限公司 | Multi-genetics-based functional biomarker screening method, system, terminal and medium |
Also Published As
Publication number | Publication date |
---|---|
CN106682456B (en) | 2019-01-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105653846B (en) | Drug method for relocating based on integrated similarity measurement and random two-way migration | |
CN112048559B (en) | Model construction and clinical application of m 6A-related IncRNA network gastric cancer prognosis | |
CN107480474B (en) | Classifier modeling evaluation method of calibration and system based on intestinal flora abundance | |
Subramanian et al. | Overfitting in prediction models–is it a problem only in high dimensions? | |
Hassan et al. | Evaluation of computational techniques for predicting non-synonymous single nucleotide variants pathogenicity | |
CN107341366A (en) | A kind of method that complex disease susceptibility loci is predicted using machine learning | |
CN108699602A (en) | The method for identifying male's fertilizability state and embryo quality | |
CN108319984B (en) | The construction method and prediction technique of xylophyta leaf morphology feature and photosynthesis characteristics prediction model based on DNA methylation level | |
CN106446597B (en) | Several species feature selecting and the method for identifying unknown gene | |
Bhargava et al. | DNA barcoding in plants: evolution and applications of in silico approaches and resources | |
CN106682456A (en) | Method for exploring complex disease susceptibility genes based on characteristics of genome epigenetic regulation elements | |
KR102382707B1 (en) | disease onset information generating apparatus based on time-dependent correlation using polygenic risk score and method therefor | |
CN105279369A (en) | Next generation sequencing based coronary heart disease genetic risk evaluation method | |
KR20140061223A (en) | System and method for detecting disease markers by reverse classification using allelic depth, signal intensity and quality score of ngs and snpchip | |
CN110305964A (en) | A kind of foundation of patients with prostate cancer prognosis recurrence risk profile mark tool and its risk evaluation model | |
Yang et al. | Applying the Fisher score to identify Alzheimer’s disease-related genes | |
CN103678954B (en) | Method for setting up multi-class specific expression molecule sets and class network through biological chip data, application of method and evaluation method | |
CN107358056A (en) | A kind of method that automatic on-line analyzes genome sequence comprehensively | |
Sun et al. | Molecular subtyping of cancer based on distinguishing co-expression modules and machine learning | |
CN113362895A (en) | Comprehensive analysis method for predicting anti-cancer drug response related gene | |
CN111429970A (en) | Method and system for obtaining multi-gene risk scores by performing feature selection based on extreme gradient lifting method | |
CN109686414A (en) | It is only used for the choosing method of the special DNA methylation assay Sites Combination of Hepatocarcinoma screening | |
CN108376210A (en) | A kind of breeding parent selection method excavated based on the advantageous haplotypes of full-length genome SNP of genomic information auxiliary breeding means II- | |
CN108172296A (en) | A kind of method for building up of database and the Risk Forecast Method of genetic disease | |
KR20160088663A (en) | Apparatus and Method for selection of disease associated gene |
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 |