What can machine learning do in the field of biological information?

Use "Machine learning genomics" to retrieve (limit the Bioinformatics field) in BIORXIV, see the title and summary of the latest article, and see what the actual project can be.

1.machine-learning annotation of human splicing branchpoints (RNA shear postural point prediction)

Using machine learning to annotate the branch point of a human shear body

Need to have RNA splicing knowledge, first need to understand the concept of branchpoint, Lariat formation

2.The value of prior knowledge in machine learning of complex network systems (Bayesian)

The value of prior knowledge in the complex network system of biological information

Predicting the patient's response under a prescribed drug or treatment regimen

3.Systematic assessment of Multi-gene predictors of pan-cancer cell line sensitivity to drugs exploiting gene expression D ATA (Stochastic forest prediction in pharmacology)

Evaluation of drug sensitivity of multi-gene predictor of universal cancer cell line by gene expression Data system

The specified mutation is often used to guide the drug use of tumor patients, and large-scale drug genome data are used to detect these drug-sensitive single-gene markers, and the recent regression of machine learning has been used for prediction based on molecular spectroscopy. Gene expression data is very important for the study of Pan-cancer. But no one has yet studied machine learning's differences in single-gene and multi-gene. This paper uses RF random forest to do the test.

4.CASTOR:A machine learning platform for reproducible viral genome classification (replicable virus genome classification)

Sequencing has produced a large number of viral genomes, genomic variability, classification characteristics and pathogenesis of the study is very important, the input of new strains sequencing results can be attributed to different virus families.

The software applies limited fragment length polymorphism (RFLP),

5.Complete Fold Annotation of the human proteome using a novel structural feature space (protein folding)

Complete the folding annotation of human protein group through new structure characteristic space

6.A Deep boosting Based approach for capturing the Sequence Binding Preferences of rna-binding proteins from HIGH-THROUGHP UT clip-seq Data (RNA binding protein)

It is important to analyze the binding behavior of RNA binding proteins to understand their function in gene expression regulation.

7.netdx:patient classification using integrated Patient similarity networks (Integrated similar patient network)

The classification of patients is very important

8.Combining transcription factor binding affinities with open-chromatin data for accurate gene expression prediction

Transcription factors combined with open chromatin data for accurate gene expression prediction

9.Identification of new bacterial type III secreted effectors with a recursive Hidden Markov Model profile-alignment Strat Egy (HMM)

10.Assessing pathogens for Natural versus Laboratory origins Using genomic Data and machine learning (to assess the origin of the pathogen)

11.gist:an Ensemble approach to the taxonomic classification of metatranscriptomic sequence data. (System category)

12.A machine learning-based Framework to Identify Type 2 diabetes through Electronic health Records

13.Predicting Protein thermostability upon Mutation Using Molecular Dynamics Timeseries Data (protein thermal stability)

14.fiddle:an Integrative Depth Learning framework for functional genomic data inference (functional genomics, deep learning)

15.Monitoring the circadian clock in human blood using personalized machine learning (biological clock in human blood)

16.The DOE Systems Biology Knowledgebase (KBase) (Open biometric Information System)

17.Partitioned learning of deep Boltzmann machines for SNP data (depth learning analytics SNP)

18.Lowest expressing microRNAs capture indispensable information-identifying cancer types (miRNAs SVM)

miRNA mainly maintains intracellular homeostasis, and in cancer tissue, its expression changes significantly,

19.Modelling the transcription factor dna-binding affinity using genome-wide chip-based data (transcription factor DNA binding protein)

20.Connecting Tumor Genomics with therapeutics through multi-dimensional network modules (Multidimensional network module)

What can machine learning do in the field of biological information?