Table 1.

Representative problems and methods addressing them by incorporating machine learning (ML) with bioinformatics tools in four areas.

Bioinformatics Area	Problem Category	Goal	ML Method	Bioinformatic Tools
Molecular evolution	Biological sequence clustering	Protein family prediction	CNN	Clusters of Orthologous Groups (COGs) and G protein-coupled receptor (GPCR) dataset [30]
		Protein function prediction	deep RNN	BLAST and HMMER search [32]
		Anti-CRISPR proteins identification	Random forest	MSA and PSI-BLAST [24]
			EXtreme Gradient Boosting	K-mer based clustering (CD-HIT), BLAST [25]
		Viral pathogenicity feature identification	SVM	MSA, phylogenetic tree construction [20,21]
	Alignment free biological sequence analysis	Identification of viral genomes	RNN	BLAST, Sequence clustering, HHPRED [27]
			CNN	BLAST [28]
protein structure analysis	Post translational modifications	Phosphorylation sites prediction	KNN	Local sequence similarity [53]
			CNN	K-mer based clustering (CD-HIT), BLAST [55]
		Glycosylation sites prediction	ensemble SVM	curated glycosylated protein database (O-GLYCBASE) [54]
	Protein structure prediction	Protein contact prediction	CNN	MSA [72]
		Prediction of distances between pairs of residues	CNN	MSA, HHPRED, PSI-BLAST [77]
systems biology	inference of biological networks	Gene regulatory network prediction	SVM	GeneNetWeaver, RegulonDB [81]
		Protein-protein interaction network prediction	SVM	Domain affinity and frequency tables [90]
			Elastic-net regression	Protein descriptors [91]
	Analysis of biological networks	Drug target prediction	K-means	Network analysis tools [98]
		Drug side effect prediction	SVM	Genome scale metabolic modeling [112]
		Drug Synergism prediction	Random Forest Ensemble	A chemical-genetic interaction matrix [117]
	Multi-omics integration	Cancer subtype prediction	Neighborhood based clustering	Similarity based integration [141]
		Drug response prediction	logistic regression	Cancer hallmarks datasets, pathway data [144]
biomarker analysis for disease research	Disease-associated genes investigation	Pulmonary sarcoidosis genes identification	Hierarchical clustering	Differential expression analysis [150]
		Identification of miRNA-disease association	NMF	Disease semantic information and miRNA functional information [151]
		Disease-phenotype visualization	t-SNE	OMIM database and human disease networks [154]
	Biomarker discovery	Cancer diagnosis	SVM	Reference gene selection [170]
		Biomarker signature identification	SVM	Network-based gene selection [167]
		Cancer outcome prediction	Random forest	Evolutionary conservation estimation [181]