Substantial improvement is possible by increasing the accuracy of contact prediction methods as evidenced by the correct contact results.

2 pg. The evolutionary methods for contact prediction, which use rapidly growing pool of protein sequence information can be expected to render more proteins (including MPs) amenable to analysis and hence improve our understanding of MP structure. Search ADS. Possible additional information that may improve DeepGOPlus in the future is information about protein structure, in particular as structure prediction methods are improving significantly (Wang et al., 2017).

Department of Electrical Engineering; Research output: Contribution to journal › Article. Crossref. Article Google Scholar Chi Yuan Yu, Lih Ching Chou, Darby T. Chang. Senior, A. W. et al.

31 (pg. 3789-3791) Google Scholar. Search ADS. We have already experimented with several types of neural networks such as recurrent neural networks, long-short term memory networks and autoencoders to learn seqeunce features. Read the paper: Improved protein structure prediction using potentials from deep learning. 57 Citations (Scopus) Overview; Fingerprint; Abstract . Improved method for predicting linear B-cell epitopes, Immunome Res, 2006, vol.

refineD: improved protein structure refinement using machine learning based restrained relaxation Debswapna Bhattacharya ... Computational protein structure prediction is an integral part of structural bioinformatics (Cavasotto and Phatak, 2009). B. UniqueProt: creating representative protein-sequence sets, Nucleic Acids Res, 2003, vol. Predicting protein-protein interactions in unbalanced data using the primary structure of proteins.

S, Rost. Improved protein structure prediction using potentials from deep learning.

2 Google Scholar. Nature 577 , 706–710 (2020).

PubMed Mika. The prediction of inter-residue contacts and distances from co-evolutionary data using deep learning has considerably advanced protein structure prediction.

In recent years, protein residue–residue contacts have been identified as a key feature for accurate de novo protein structure prediction (Jones, 2001; Mabrouk et al., 2016; Marks et al., 2012; Michel et al., 2014, 2017a).

Crossref. PredictProtein integrates feature prediction for secondary structure, solvent accessibility, transmembrane helices, globular regions, coiled-coil regions, structural switch regions, B-values, disorder regions, intra-residue contacts, protein-protein and protein-DNA binding sites, sub-cellular localization, domain boundaries, beta-barrels, cysteine bonds, metal binding sites and disulphide bridges.