Shaun M Kandathil | Searcharxiv

arXiv2020

Near-complete protein structural modelling of the minimal genome

Protein tertiary structure prediction has improved dramatically in recent years. A considerable fraction of various proteomes can be modelled in the absence of structural templates. We ask whether our DMPfold method can model all the proteins without templates in the JCVI-syn3.0 minimal genome, which contains 438 proteins. We find that a useful tertiary structure annotation can be provided for all but 10 proteins. The models may help annotate function in cases where it is unknown, and provide coverage for 29 predicted protein-protein interactions which lacked monomer models. We also show that DMPfold performs well on proteins with structures released since initial publication. It is likely that the minimal genome will have complete structural coverage within a few years.

q-bio.BM↗

arXiv2019

Deep learning extends de novo protein modelling coverage of genomes using iteratively predicted structural constraints

The inapplicability of amino acid covariation methods to small protein families has limited their use for structural annotation of whole genomes. Recently, deep learning has shown promise in allowing accurate residue-residue contact prediction even for shallow sequence alignments. Here we introduce DMPfold, which uses deep learning to predict inter-atomic distance bounds, the main chain hydrogen bond network, and torsion angles, which it uses to build models in an iterative fashion. DMPfold produces more accurate models than two popular methods for a test set of CASP12 domains, and works just as well for transmembrane proteins. Applied to all Pfam domains without known structures, confident models for 25% of these so-called dark families were produced in under a week on a small 200 core cluster. DMPfold provides models for 16% of human proteome UniProt entries without structures, generates accurate models with fewer than 100 sequences in some cases, and is freely available.

q-bio.BM↗