CN110335639A - A kind of Transcription Factor Binding Sites Prediction Algorithm and device across transcription factor - Google Patents
A kind of Transcription Factor Binding Sites Prediction Algorithm and device across transcription factor Download PDFInfo
- Publication number
- CN110335639A CN110335639A CN201910511069.3A CN201910511069A CN110335639A CN 110335639 A CN110335639 A CN 110335639A CN 201910511069 A CN201910511069 A CN 201910511069A CN 110335639 A CN110335639 A CN 110335639A
- Authority
- CN
- China
- Prior art keywords
- transcription factor
- dna
- binding site
- dna fragmentation
- target
- 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
- G16B20/30—Detection of binding sites or motifs
Landscapes
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Genetics & Genomics (AREA)
- Biotechnology (AREA)
- Biophysics (AREA)
- Chemical & Material Sciences (AREA)
- Molecular Biology (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Bioinformatics & Computational Biology (AREA)
- Analytical Chemistry (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Theoretical Computer Science (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The present invention provides a kind of Transcription Factor Binding Sites Prediction Algorithm and device across transcription factor, described method includes following steps: step 1: predicting can be with the amino acid in conjunction with DNA in all transcription factors, referred to as DNA binding site, the DNA binding site of prediction are mainly used for measuring contribution of the labeled data of different transcription factors during target transcription factor model training；Step 2: learning the expression vector of transcription factor from the sequence being made of the DNA binding site predicted；Step 3: learning the high-order dependence of DNA fragmentation from the histone modification feature of DNA fragmentation；Step 4: learning the low order dependence of DNA fragmentation from the sequence signature of DNA fragmentation；Step 5: the transcription factor vector of study is indicated, the high-order dependence of DNA fragmentation and low order dependence are spliced into feature vector and input in multilayer perceptron and classify to target DNA fragments, determine its whether be target transcription factor binding site.
Description
Technical field
The present invention relates to bioinformatics technique fields, and in particular to a kind of Binding site for transcription factor across transcription factor
Prediction algorithm and device.
Background technique
Binding site for transcription factor is the base pair fragment that factor combination can be transcribed in DNA.Because transcription factor with
Interaction between DNA plays an important role in gene expression regulation, so Transcription Factor Binding Sites Prediction is to gene
Regulated and control network and the elementary cell mistake including cell function of growth control, cell cycle progression and development and differentiation etc.
The understanding of journey has very important effect.
Method in the prior art mostly identifies Binding site for transcription factor using PWM, but the basic assumption of PWM
It is base-pair in binding site at all positions is all the phase interaction independently participated between the binding site and corresponding transcription factor
With.In order to by correlation is melted into prediction between base-pair at different location in binding site, a kind of new representation method DWM
It is proposed for indicating binding site.In addition to DWM, Mathelier and Wasserman propose a kind of prediction based on HMM
Method TFFM, this method can model the phase interaction in binding site between the base-pair of adjacent position by the transition probability of HMM model
With.
For binding site of the prediction target transcription factor in a particular cell types, there is currently prediction techniques to be both needed to
Want a large amount of target transcription factor labeled data in particular cell types.Mark of the target transcription factor in particular cell types
Note data need to obtain by BIOLOGICAL TEST METHODSs such as ChIP-seq or ChIP-chip.Due to ChIP-seq or ChIP-
The time cost and economic cost that the BIOLOGICAL TEST METHODSs such as chip execute are very high, so for the mankind and other life entities
For a large amount of transcription factors, only fraction transcription factor has labeled data in the cell type of minority further investigation, and
Labeled data is all not present in most transcription factor in any cell type.Therefore, for transcription factor in cell type
In there is no the case where labeled data, current prediction technique is not used to combination of the prediction transcription factor in its target cell class
Site.
Although most of transcription factor all has different amino acid sequence and biological function, the different transcription in part
The factor still has similar amino acid sequence and biological function.Since amino acid sequence similar between different transcription factors can be
The binding site of similarity is generated in DNA sequence, and similar biological function is also given the credit to a certain extent between different transcription factors
In binding site similar in DNA sequence, thus the different transcription factor in part can exist in target cell type it is similar
Binding site.
Summary of the invention
Based on different transcription factors, there are common characteristics between target cell type binding site, and the purpose of the present invention is mention
A kind of Transcription Factor Binding Sites Prediction Algorithm and device across transcription factor is gone out.Turn for not having the target of labeled data
The factor is recorded, which can predict it in target cell type by the labeled data of other transcription factors in target cell type
In binding site.
In order to achieve the above object, the present invention provides a kind of Transcription Factor Binding Sites Prediction sides across transcription factor
Method, described method includes following steps:
Step 1: predicting to tie with the amino acid in conjunction with DNA, referred to as DNA binding site, the DNA of prediction in all transcription factors
Coincidence point is mainly used for measuring contribution of the labeled data of different transcription factors during target transcription factor model training；
Step 2: learning the expression vector of transcription factor from the sequence being made of the DNA binding site predicted；
Step 3: learning the high-order dependence of DNA fragmentation from the histone modification feature of DNA fragmentation；
Step 4: learning the low order dependence of DNA fragmentation from the sequence signature of DNA fragmentation；
Step 5: the transcription factor vector of study being indicated, the high-order dependence of DNA fragmentation and low order dependence are spliced into
Feature vector and input in multilayer perceptron to target DNA fragments classify, determine its whether be target transcription factor bound site
Point.
Further, in the step 1, predict that DNA binding site specifically includes in transcription factor:
Step 101: the location specific scoring matrix of target transcription factor amino acid sequence, position are calculated using PSI-BLAST
Specific scoring matrix is the Evolution of target transcription factor；
Step 102: target transcription factor is spliced by the one-hot vector of its all amino acid to be indicated, convolutional Neural net is utilized
Network is from wherein mode of learning feature；
Step 103: by the pattern feature of the target transcription factor of study and its sequence signature and Evolution be spliced into feature to
Whether predicted amino acid is DNA binding site in amount input multilayer perceptron.
Further, the multilayer perceptron is made of full articulamentum and softmax classifier.
Further, in the step 2 using length memory network model from the sequence being made of the DNA binding site predicted
Learn the expression vector of transcription factor in column.
Further, histone modification feature middle school of the convolutional neural networks model from DNA fragmentation is used in the step 3
Practise the high-order dependence of DNA fragmentation.
Further, learn DNA from the sequence signature of DNA fragmentation using convolutional neural networks model in the step 4
The low order dependence of segment.
A kind of binding site prediction meanss across transcription factor, described device includes following module:
The module of DNA binding site prediction, for predict can be with the amino acid in conjunction with DNA, referred to as DNA in all transcription factors
Binding site, the DNA binding site of prediction are mainly used for measuring the labeled data of different transcription factors in target transcription factor mould
Contribution in type training process；
The expression vector field homoemorphism block for learning transcription factor, for the study turn from the sequence being made of the DNA binding site predicted
Record the expression vector of the factor；
The module for learning the high-order dependence of DNA fragmentation, for learning DNA piece from the histone modification feature of DNA fragmentation
The high-order dependence of section；
The module for learning the low order dependence of DNA fragmentation, for learning the low of DNA fragmentation from the sequence signature of DNA fragmentation
Rank dependence；
Binding site judgment module, the high-order dependence and low order of the expression of transcription factor vector, DNA fragmentation for that will learn
Dependence, which is spliced into feature vector and inputs in multilayer perceptron, classifies to target DNA fragments, determines whether it is that target turns
Record the binding site of the factor.
The beneficial effects of the present invention are: for be not present labeled data target transcription factor, it is proposed by the invention across
The binding site prediction meanss of transcription factor can predict it by the labeled data of other transcription factors in target cell type
Binding site in target cell type.The binding site of a variety of transcription factors based on device prediction, the present invention can be with
For for only there are the cell type predicted gene expressions of known binding site for a small amount of transcription factor.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is flow chart of the method for the present invention.
Fig. 2 is that the heterogeneous network of the invention based between subjects constructs schematic diagram.
Fig. 3 is DNA binding site schematic diagram in prediction transcription factor of the invention.
Specific embodiment
Understand for the ease of those of ordinary skill in the art and implement the present invention, with reference to the accompanying drawing to technology of the invention
Scheme is clearly and completely described, it is clear that described embodiments are only a part of the embodiments of the present invention, rather than complete
The embodiment in portion.Based on the embodiments of the present invention, those of ordinary skill in the art are without creative efforts
Every other embodiment obtained, shall fall within the protection scope of the present invention.
Predict do not have turning for labeled data wherein by the labeled data of other transcription factors in target cell type
The binding site for recording the factor is key point of the invention.The present invention uses prediction in across Transcription Factor Binding Sites Prediction method
DNA binding site measures the contribution of the labeled data of different transcription factors in the training process.
Embodiment one
Refering to fig. 1, Fig. 2, the embodiment of the present invention one provide a kind of binding site prediction technique across transcription factor, key step
Have:
One, it can be tied with the amino acid in conjunction with DNA, referred to as DNA using in all transcription factors of convolutional neural networks model prediction
Coincidence point, the DNA binding site of prediction are mainly used for measuring the labeled data of different transcription factors in target transcription factor model
Contribution in training process.
Two, learn to turn from the sequence being made of the DNA binding site predicted using length memory network model (LSTM)
Record the expression vector of the factor.
Three, learn the high-order of DNA fragmentation from the histone modification feature of DNA fragmentation using convolutional neural networks model
Dependence.
Four, learn the interdependent pass of low order of DNA fragmentation from the sequence signature of DNA fragmentation using convolutional neural networks model
System.
Five, the transcription factor vector of study is indicated, the high-order dependence of DNA fragmentation and low order dependence are spliced
Classify in the multilayer perceptron being made of at feature vector and input full articulamentum and softmax classifier to target DNA fragments,
Determine its whether be target transcription factor binding site.
Refering to attached drawing 3, in above method step 1, the step of DNA binding site, is as follows in prediction transcription factor:
1. calculating the location specific scoring matrix of target transcription factor amino acid sequence, location specific using PSI-BLAST
Scoring matrix is the Evolution of target transcription factor；
2. by target transcription factor by its all amino acid one-hot vector splice indicate, using convolutional neural networks from its
Middle study pattern feature；
3. the pattern feature of the target transcription factor of study and its sequence signature and Evolution are spliced into feature vector input
In multilayer perceptron predicted amino acid whether be DNA target transcription factor binding site.
Embodiment two
The binding site prediction meanss across transcription factor that second embodiment of the present invention provides a kind of mainly include following module:
The module of DNA binding site prediction, can be with DNA in all transcription factors of convolutional neural networks model prediction for utilizing
In conjunction with amino acid, referred to as DNA binding site, the DNA binding site of prediction be mainly used for measuring the mark of different transcription factors
Contribution of data during target transcription factor model training.
The expression vector field homoemorphism block for learning transcription factor, for using length memory network model (LSTM) from by predicting
Learn the expression vector of transcription factor in the sequence of DNA binding site composition.
The module for learning the high-order dependence of DNA fragmentation, for using group of the convolutional neural networks model from DNA fragmentation
Learn the high-order dependence of DNA fragmentation in protein modified feature.
The module for learning the low order dependence of DNA fragmentation, for using sequence of the convolutional neural networks model from DNA fragmentation
Learn the low order dependence of DNA fragmentation in column feature.
Binding site judgment module, transcription factor vector for that will learn indicates, the high-order dependence of DNA fragmentation and
Low order dependence be spliced into feature vector and input it is right in the multilayer perceptron being made of full articulamentum and softmax classifier
Target DNA fragments classification, determine its whether be target transcription factor binding site.
Those skilled in the art can be clearly understood that, for convenience of description and succinctly, the dress of foregoing description
It sets, the specific work process of module and unit, the corresponding process of preceding method embodiment can be referred to, details are not described herein.
The flow chart and block diagram in the drawings show the method, apparatus of multiple embodiments according to the present invention and computer journeys
The architecture, function and operation in the cards of sequence product.In this regard, each box in flow chart and block diagram can generation
A part of one module, section or code of table, it is executable for realizing the computer of logic function comprising one or more
Instruction.It should also be noted that in some implementations as replacements, function marked in the box can also be to be different from attached drawing
The sequence marked occurs.It is also noted that the combination of each box or box in block diagram and flow chart, can use execution
Defined function or the dedicated hardware based system of movement realize, or can use specialized hardware and computer instruction
Combination is to realize.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation perhaps operate with another entity and distinguish without necessarily requiring or implying these entities or operate it
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant are intended to
Cover non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or setting
Standby intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in the process, method, article or apparatus that includes the element.
The foregoing description of the disclosed embodiments makes those skilled in the art can be realized or use the present invention, above-mentioned
Embodiment and is not limited the embodiments to illustrate example.To those skilled in the art, upper
State it is bright on the basis of, can also make other variations or changes in different ways, and these variation or change will be aobvious and easy
See, among protection scope of the present invention.
Claims (10)
1. a kind of Transcription Factor Binding Sites Prediction method across transcription factor, which is characterized in that the method includes walking as follows
It is rapid:
Step 1: predicting to tie with the amino acid in conjunction with DNA, referred to as DNA binding site, the DNA of prediction in all transcription factors
Coincidence point is mainly used for measuring contribution of the labeled data of different transcription factors during target transcription factor model training；
Step 2: learning the expression vector of transcription factor from the sequence being made of the DNA binding site predicted；
Step 3: learning the high-order dependence of DNA fragmentation from the histone modification feature of DNA fragmentation；
Step 4: learning the low order dependence of DNA fragmentation from the sequence signature of DNA fragmentation；
Step 5: the transcription factor vector of study being indicated, the high-order dependence of DNA fragmentation and low order dependence are spliced into
Feature vector and input in multilayer perceptron to target DNA fragments classify, determine its whether be target transcription factor bound site
Point.
2. the method as described in claim 1, which is characterized in that in the step 1, predict DNA binding site in transcription factor
It specifically includes:
Step 101: the location specific scoring matrix of target transcription factor amino acid sequence, position are calculated using PSI-BLAST
Specific scoring matrix is the Evolution of target transcription factor；
Step 102: target transcription factor is spliced by the one-hot vector of its all amino acid to be indicated, convolutional Neural net is utilized
Network is from wherein mode of learning feature；
Step 103: by the pattern feature of the target transcription factor of study and its sequence signature and Evolution be spliced into feature to
Whether predicted amino acid is DNA binding site in amount input multilayer perceptron.
3. method according to claim 1 or 2, which is characterized in that the multilayer perceptron is by full articulamentum and softmax points
Class device composition.
4. the method as described in claim 1, which is characterized in that using length memory network model from by pre- in the step 2
Learn the expression vector of transcription factor in the sequence of the DNA binding site composition of survey.
5. the method as described in claim 1, which is characterized in that use convolutional neural networks model from DNA piece in the step 3
Learn the high-order dependence of DNA fragmentation in the histone modification feature of section.
6. the method as described in claim 1, which is characterized in that use convolutional neural networks model from DNA piece in the step 4
Learn the low order dependence of DNA fragmentation in the sequence signature of section.
7. a kind of binding site prediction meanss across transcription factor, which is characterized in that described device includes following module:
The module of DNA binding site prediction, for predict can be with the amino acid in conjunction with DNA, referred to as DNA in all transcription factors
Binding site, the DNA binding site of prediction are mainly used for measuring the labeled data of different transcription factors in target transcription factor mould
Contribution in type training process；
The expression vector field homoemorphism block for learning transcription factor, for the study turn from the sequence being made of the DNA binding site predicted
Record the expression vector of the factor；
The module for learning the high-order dependence of DNA fragmentation, for learning DNA piece from the histone modification feature of DNA fragmentation
The high-order dependence of section；
The module for learning the low order dependence of DNA fragmentation, for learning the low of DNA fragmentation from the sequence signature of DNA fragmentation
Rank dependence；
Binding site judgment module, the high-order dependence and low order of the expression of transcription factor vector, DNA fragmentation for that will learn
Dependence, which is spliced into feature vector and inputs in multilayer perceptron, classifies to target DNA fragments, determines whether it is that target turns
Record the binding site of the factor.
8. device as claimed in claim 7, which is characterized in that the module of the DNA binding site prediction specifically includes:
The submodule of the location specific scoring matrix of target transcription factor amino acid sequence is calculated using PSI-BLAST, wherein
Location specific scoring matrix is the Evolution of target transcription factor；
Target transcription factor is spliced by the one-hot vector of its all amino acid to be indicated, using convolutional neural networks from wherein
The submodule of mode of learning feature；
It is more that the pattern feature of the target transcription factor of study and its sequence signature and Evolution are spliced into feature vector input
Layer perceptron in predicted amino acid whether be DNA binding site submodule.
9. device as claimed in claim 7, which is characterized in that combined using length memory network model from the DNA by predicting
Learn the expression vector of transcription factor in the sequence of site composition；Using convolutional neural networks model from the histone of DNA fragmentation
Learn the high-order dependence of DNA fragmentation in decorative features；Using convolutional neural networks model from the sequence signature of DNA fragmentation
Learn the low order dependence of DNA fragmentation.
10. a kind of computer program product, including computer program instructions, when the instructions are executed by a processor, for real
Now such as method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910511069.3A CN110335639B (en) | 2019-06-13 | 2019-06-13 | Transcription factor binding site prediction algorithm and device of trans-transcription factor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910511069.3A CN110335639B (en) | 2019-06-13 | 2019-06-13 | Transcription factor binding site prediction algorithm and device of trans-transcription factor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110335639A true CN110335639A (en) | 2019-10-15 |
| CN110335639B CN110335639B (en) | 2021-10-29 |
Family
ID=68141143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910511069.3A Active CN110335639B (en) | 2019-06-13 | 2019-06-13 | Transcription factor binding site prediction algorithm and device of trans-transcription factor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110335639B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113096732A (en) * | 2021-05-11 | 2021-07-09 | 同济大学 | Die body mining method based on deep embedded convolutional neural network |
| CN113593634A (en) * | 2021-08-06 | 2021-11-02 | 中国海洋大学 | Transcription factor binding site prediction method fusing DNA shape characteristics |
| CN114639441A (en) * | 2022-05-18 | 2022-06-17 | 山东建筑大学 | Transcription factor binding site prediction method based on weighted multi-granularity scanning |
| CN114758721A (en) * | 2022-04-28 | 2022-07-15 | 广西科学院 | Deep learning-based transcription factor binding site positioning method |
| CN116403645A (en) * | 2023-03-03 | 2023-07-07 | 阿里巴巴（中国）有限公司 | Method and device for predicting transcription factor binding site |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390119A (en) * | 2013-07-03 | 2013-11-13 | 哈尔滨工程大学 | Method for recognizing transcription factor binding site |
| CN103425900A (en) * | 2012-05-21 | 2013-12-04 | 上海聚类生物科技有限公司 | Statistical-significance-based system capable of quickly identifying genome transcription factor binding sites |
| CN107151708A (en) * | 2017-07-05 | 2017-09-12 | 昆明医科大学第附属医院 | Multi-functional transcription regulatory factor CTCF DNA binding sites CTCF_13 application |
-
2019
- 2019-06-13 CN CN201910511069.3A patent/CN110335639B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425900A (en) * | 2012-05-21 | 2013-12-04 | 上海聚类生物科技有限公司 | Statistical-significance-based system capable of quickly identifying genome transcription factor binding sites |
| CN103390119A (en) * | 2013-07-03 | 2013-11-13 | 哈尔滨工程大学 | Method for recognizing transcription factor binding site |
| CN107151708A (en) * | 2017-07-05 | 2017-09-12 | 昆明医科大学第附属医院 | Multi-functional transcription regulatory factor CTCF DNA binding sites CTCF_13 application |
Non-Patent Citations (1)
| Title |
|---|
| JUN-TAO GUO: "《Structure-Based Prediction of Transcription Factor Binding Sites》", 《TSINGHUA SCIENCE AND TECHNOLOGY》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113096732A (en) * | 2021-05-11 | 2021-07-09 | 同济大学 | Die body mining method based on deep embedded convolutional neural network |
| CN113593634A (en) * | 2021-08-06 | 2021-11-02 | 中国海洋大学 | Transcription factor binding site prediction method fusing DNA shape characteristics |
| CN113593634B (en) * | 2021-08-06 | 2022-03-11 | 中国海洋大学 | Transcription factor binding site prediction method fusing DNA shape characteristics |
| CN114758721A (en) * | 2022-04-28 | 2022-07-15 | 广西科学院 | Deep learning-based transcription factor binding site positioning method |
| CN114758721B (en) * | 2022-04-28 | 2022-11-18 | 广西科学院 | Deep learning-based transcription factor binding site positioning method |
| CN114639441A (en) * | 2022-05-18 | 2022-06-17 | 山东建筑大学 | Transcription factor binding site prediction method based on weighted multi-granularity scanning |
| CN116403645A (en) * | 2023-03-03 | 2023-07-07 | 阿里巴巴（中国）有限公司 | Method and device for predicting transcription factor binding site |
| CN116403645B (en) * | 2023-03-03 | 2024-01-09 | 阿里巴巴（中国）有限公司 | Method and device for predicting transcription factor binding site |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110335639B (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110335639A (en) | A kind of Transcription Factor Binding Sites Prediction Algorithm and device across transcription factor | |
| Wei et al. | Prediction of human protein subcellular localization using deep learning | |
| Al-Ajlan et al. | CNN-MGP: convolutional neural networks for metagenomics gene prediction | |
| Zhang et al. | Weakly-supervised convolutional neural network architecture for predicting protein-DNA binding | |
| Wang et al. | Fast prediction of protein–protein interaction sites based on extreme learning machines | |
| WO2019041333A1 (en) | Method, apparatus, device and storage medium for predicting protein binding sites | |
| Huang et al. | ProLoc: prediction of protein subnuclear localization using SVM with automatic selection from physicochemical composition features | |
| Kountouris et al. | Predicting β-turns and their types using predicted backbone dihedral angles and secondary structures | |
| He et al. | Large-scale prediction of protein ubiquitination sites using a multimodal deep architecture | |
| Jing et al. | Prediction of enhancer–promoter interactions using the cross-cell type information and domain adversarial neural network | |
| Minhas et al. | Multiple instance learning of Calmodulin binding sites | |
| Liu et al. | Prediction of protein binding sites in protein structures using hidden Markov support vector machine | |
| Padovani de Souza et al. | Machine learning meets genome assembly | |
| Montazer et al. | A new approach in e-learners grouping using hybrid clustering method | |
| Horlacher et al. | A systematic benchmark of machine learning methods for protein–RNA interaction prediction | |
| Lai et al. | LSA-ac4C: a hybrid neural network incorporating double-layer LSTM and self-attention mechanism for the prediction of N4-acetylcytidine sites in human mRNA | |
| Zhou et al. | Prediction of TF-binding site by inclusion of higher order position dependencies | |
| CN108154522A (en) | Target tracking system | |
| Wang et al. | Motif discovery via convolutional networks with K-mer embedding | |
| Sheng et al. | Weakly supervised coarse-to-fine learning for human action segmentation in HCI videos | |
| Kalakoti et al. | Modulation of DNA-protein Interactions by Proximal Genetic Elements as Uncovered by Interpretable Deep Learning | |
| Re | Comparing early and late data fusion methods for gene expression prediction | |
| Zhou et al. | An artificial neural network method for combining gene prediction based on equitable weights | |
| Halder et al. | ccLoopER: Deep Prediction of C TCF and c ohesin Mediated Chromatin loop ing Using DNA Transform er Model | |
| Bao et al. | ILSES: Identification lysine succinylation-sites with ensemble classification |
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 |