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.
Today's Top 5
5. New Prosthetic Leg Combating Phantom Pain
4. Digital Health Flourishing Overseas
3. FDA Approves First Hypoglycemic Rescue Pen
2. Meru Health Offering "The New Standard of Mental Healthcare"
. @MeruHealth introduces 'The New Standard of Mental Healthcare' along with— Daniel Kraft, MD (@daniel_kraft) September 18, 2019
publication of peer-reviewed 1-year treatment In which enrolled patients had clinically significant reductions in symptoms of depression & anxiety https://t.co/7rgOpTg7p9 #digitalhealth #mentalhealth
1. Hydrogel Use in Modeling Cardiac Tissue
Hydrogel Mimics of Heart Tissue to Study Cardiac Reshaping Following Aortic Valve Implantation #Card #fitness #health #training #healthy #healthylifestyle #cardio #healthyliving #healthylife #medicine #healthcare #AI #cardioworkout #cardiologia #card https://t.co/jek10Y0bqm pic.twitter.com/UgLpzF9jV2— HeartIn 🗯️ (@HeartIn_net) September 20, 2019