DLPacker: Deep learning for prediction of amino acid side chain conformations in proteins

Simple item page
dc.citation.firstpage1278en_US
dc.citation.issueNumber6en_US
dc.citation.journalTitlePROTEINS : Structure, Function, and Bioinformaticsen_US
dc.citation.lastpage1290en_US
dc.citation.volumeNumber90en_US
dc.contributor.authorMisiura, Mikitaen_US
dc.contributor.authorShroff, Raghaven_US
dc.contributor.authorThyer, Rossen_US
dc.contributor.authorKolomeisky, Anatoly B.en_US
dc.contributor.orgCenter for Theoretical Biological Physicsen_US
dc.date.accessioned2022-05-02T15:17:00Zen_US
dc.date.available2022-05-02T15:17:00Zen_US
dc.date.issued2022en_US
dc.description.abstractPrediction of side chain conformations of amino acids in proteins (also termed “packing”) is an important and challenging part of protein structure prediction with many interesting applications in protein design. A variety of methods for packing have been developed but more accurate ones are still needed. Machine learning (ML) methods have recently become a powerful tool for solving various problems in diverse areas of science, including structural biology. In this study, we evaluate the potential of deep neural networks (DNNs) for prediction of amino acid side chain conformations. We formulate the problem as image-to-image transformation and train a U-net style DNN to solve the problem. We show that our method outperforms other physics-based methods by a significant margin: reconstruction RMSDs for most amino acids are about 20% smaller compared to SCWRL4 and Rosetta Packer with RMSDs for bulky hydrophobic amino acids Phe, Tyr, and Trp being up to 50% smaller.en_US
dc.identifier.citationMisiura, Mikita, Shroff, Raghav, Thyer, Ross, et al.. "DLPacker: Deep learning for prediction of amino acid side chain conformations in proteins." <i>PROTEINS : Structure, Function, and Bioinformatics,</i> 90, no. 6 (2022) Wiley: 1278-1290. https://doi.org/10.1002/prot.26311.en_US
dc.identifier.doihttps://doi.org/10.1002/prot.26311en_US
dc.identifier.urihttps://hdl.handle.net/1911/112201en_US
dc.language.isoengen_US
dc.publisherWileyen_US
dc.rightsThis is an author's pre-print. The published article is copyrighted by Wiley.en_US
dc.titleDLPacker: Deep learning for prediction of amino acid side chain conformations in proteinsen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpre-printen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
3DCNN_Paper.pdf
Size:
730.44 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Faculty Publications
Chemical and Biomolecular Engineering Publications
Chemistry Publications
Physics and Astronomy Publications