Side-chain Packing Using SE(3)-Transformer

Akhil Jindal; Sergei Kotelnikov; Dzmitry Padhorny; Dima Kozakov; Yimin Zhu; Rezaul Chowdhury; Sandor Vajda

doi:10.1142/9789811250477_0005

Side-chain Packing Using SE(3)-Transformer

Akhil Jindal
, Sergei Kotelnikov
, Dzmitry Padhorny
, Dima Kozakov
, Yimin Zhu
, Rezaul Chowdhury
, Sandor Vajda

Stony Brook University
Boston University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

Predicting protein side-chains is important for both protein structure prediction and protein design. Modeling approaches to predict side-chains such as SCWRL4 have become one of the most widely used tools of its type due to fast and highly accurate predictions. Motivated by the recent success of AlphaFold2 in CASP14, our group adapted a 3D equivariant neural network architecture to predict protein side-chain conformations, specifically within a protein-protein interface, a problem that has not been fully addressed by AlphaFold2.

Original language	English
Title of host publication	Pacific Symposium on Biocomputing 2022, PSB 2022
Editors	Russ B. Altman, A. Keith Dunker, Lawrence Hunter, Marylyn D. Ritchie, Teri E. Klein
Publisher	World Scientific
Pages	46-55
Number of pages	10
ISBN (Electronic)	9789811250460
DOIs	https://doi.org/10.1142/9789811250477_0005
State	Published - 2022
Event	27th Pacific Symposium on Biocomputing, PSB 2022 - Kohala Coast, United States Duration: Jan 3 2022 → Jan 7 2022

Conference

Conference	27th Pacific Symposium on Biocomputing, PSB 2022
Country/Territory	United States
City	Kohala Coast
Period	01/3/22 → 01/7/22

Keywords

Deep Learning
Protein Structure Prediction
Sidechain Packing
Transformers

Access to Document

10.1142/9789811250477_0005

Cite this

@inproceedings{888fab278f3145b5aa61db41aad3db49,

title = "Side-chain Packing Using SE(3)-Transformer",

abstract = "Predicting protein side-chains is important for both protein structure prediction and protein design. Modeling approaches to predict side-chains such as SCWRL4 have become one of the most widely used tools of its type due to fast and highly accurate predictions. Motivated by the recent success of AlphaFold2 in CASP14, our group adapted a 3D equivariant neural network architecture to predict protein side-chain conformations, specifically within a protein-protein interface, a problem that has not been fully addressed by AlphaFold2.",

keywords = "Deep Learning, Protein Structure Prediction, Sidechain Packing, Transformers",

author = "Akhil Jindal and Sergei Kotelnikov and Dzmitry Padhorny and Dima Kozakov and Yimin Zhu and Rezaul Chowdhury and Sandor Vajda",

note = "Publisher Copyright: {\textcopyright} 2021 The Authors.; 27th Pacific Symposium on Biocomputing, PSB 2022 ; Conference date: 03-01-2022 Through 07-01-2022",

year = "2022",

doi = "10.1142/9789811250477\_0005",

language = "English",

pages = "46--55",

editor = "Altman, \{Russ B.\} and Dunker, \{A. Keith\} and Lawrence Hunter and Ritchie, \{Marylyn D.\} and Klein, \{Teri E.\}",

booktitle = "Pacific Symposium on Biocomputing 2022, PSB 2022",

publisher = "World Scientific",

}

Jindal, A, Kotelnikov, S, Padhorny, D, Kozakov, D, Zhu, Y, Chowdhury, R & Vajda, S 2022, Side-chain Packing Using SE(3)-Transformer. in RB Altman, AK Dunker, L Hunter, MD Ritchie & TE Klein (eds), Pacific Symposium on Biocomputing 2022, PSB 2022. World Scientific, pp. 46-55, 27th Pacific Symposium on Biocomputing, PSB 2022, Kohala Coast, United States, 01/3/22. https://doi.org/10.1142/9789811250477_0005

Side-chain Packing Using SE(3)-Transformer. / Jindal, Akhil; Kotelnikov, Sergei; Padhorny, Dzmitry et al.
Pacific Symposium on Biocomputing 2022, PSB 2022. ed. / Russ B. Altman; A. Keith Dunker; Lawrence Hunter; Marylyn D. Ritchie; Teri E. Klein. World Scientific, 2022. p. 46-55.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Side-chain Packing Using SE(3)-Transformer

AU - Jindal, Akhil

AU - Kotelnikov, Sergei

AU - Padhorny, Dzmitry

AU - Kozakov, Dima

AU - Zhu, Yimin

AU - Chowdhury, Rezaul

AU - Vajda, Sandor

PY - 2022

Y1 - 2022

N2 - Predicting protein side-chains is important for both protein structure prediction and protein design. Modeling approaches to predict side-chains such as SCWRL4 have become one of the most widely used tools of its type due to fast and highly accurate predictions. Motivated by the recent success of AlphaFold2 in CASP14, our group adapted a 3D equivariant neural network architecture to predict protein side-chain conformations, specifically within a protein-protein interface, a problem that has not been fully addressed by AlphaFold2.

AB - Predicting protein side-chains is important for both protein structure prediction and protein design. Modeling approaches to predict side-chains such as SCWRL4 have become one of the most widely used tools of its type due to fast and highly accurate predictions. Motivated by the recent success of AlphaFold2 in CASP14, our group adapted a 3D equivariant neural network architecture to predict protein side-chain conformations, specifically within a protein-protein interface, a problem that has not been fully addressed by AlphaFold2.

KW - Deep Learning

KW - Protein Structure Prediction

KW - Sidechain Packing

KW - Transformers

UR - https://www.scopus.com/pages/publications/85122526755

U2 - 10.1142/9789811250477_0005

DO - 10.1142/9789811250477_0005

M3 - Conference contribution

C2 - 34890135

AN - SCOPUS:85122526755

SP - 46

EP - 55

BT - Pacific Symposium on Biocomputing 2022, PSB 2022

A2 - Altman, Russ B.

A2 - Dunker, A. Keith

A2 - Hunter, Lawrence

A2 - Ritchie, Marylyn D.

A2 - Klein, Teri E.

PB - World Scientific

T2 - 27th Pacific Symposium on Biocomputing, PSB 2022

Y2 - 3 January 2022 through 7 January 2022

ER -

Side-chain Packing Using SE(3)-Transformer

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this