An end-to-end deep learning method for rotamer-free protein side-chain packing

McPartlon, Matt; Xu, Jinbo

doi:10.1101/2022.03.11.483812

Cited by 10 publications

(18 citation statements)

References 30 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The output of this component, along with the input backbone coordinates, are passed to a deep TFN-transformer which produces side chain conformation and sequence identity for each input residue. The details of these architectural component are fully described in (McPartlon and Xu 2022), and a schematic overview is given in Figure 1.…”

Section: Methodsmentioning

confidence: 99%

“…Here, we extend our recent work on side-chain coordinate prediction (McPartlon and Xu 2022) and introduce a deep SE(3)-equivariant graph transformer architecture which simultaneously predicts each residue’s identity and side-chain conformation. We compare to several existing inverse folding methods on CASP13, CASP14, CATH4.2, and TS50 test sets and show that our method achieves significantly higher native sequence recovery (NSR) rates across all datasets.…”

Section: Introductionmentioning

confidence: 95%

“…Notably, we utilize memory efficient variants of triangle multiplication and triangle attention introduced in AlphaFold2 along with a TFN-based SE(3)-equivariant transformer inspired by the SE(3)-Transformer of Fuchs et al (Fuchs et al 2020). Our work on side-chain coordinate prediction (McPartlon and Xu 2022) details these modifications, which were used to construct a deep GNN for protein side-chain packing.…”

Section: Related Workmentioning

confidence: 99%

“…Our input features are embedded following the strategy proposed in (McPartlon and Xu 2022). The primary difference is that we we remove one-hot encodings of angle-based features.…”

Section: Supplementary Informationmentioning

confidence: 99%

“…Masked cross entropy loss is applied to this output based on the corresponding native structure’s residue type. Side chain conformation loss is computed as in (McPartlon and Xu 2022). The pair and side-chain conformation loss are given a weight of 0.15, and the NSR loss is given a weight of 1.…”

Section: Supplementary Informationmentioning

confidence: 99%

See 4 more Smart Citations

A Deep SE(3)-Equivariant Model for Learning Inverse Protein Folding

McPartlon

Lai

2022

Preprint

Self Cite

View full text Add to dashboard Cite

In this work, we establish a framework to tackle the inverse protein design problem; the task of predicting a protein's primary sequence given its backbone conformation. To this end, we develop a generative SE(3)-equivariant model which significantly improves upon existing autoregressive methods. Conditioned on backbone structure, and trained with our novel partial masking scheme and side-chain conformation loss, we achieve state-of-the-art native sequence recovery on structurally independent CASP13, CASP14, CATH4.2, and TS50 test sets. On top of accurately recovering native sequences, we demonstrate that our model captures functional aspects of the underlying protein by accurately predicting the effects of point mutations through testing on Deep Mutational Scanning datasets. We further verify the efficacy of our approach by comparing with recently proposed inverse protein folding methods and by rigorous ablation studies.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 95%

Section: Related Workmentioning

confidence: 99%

“…Our input features are embedded following the strategy proposed in (McPartlon and Xu 2022). The primary difference is that we we remove one-hot encodings of angle-based features.…”

Section: Supplementary Informationmentioning

confidence: 99%

Section: Supplementary Informationmentioning

confidence: 99%

See 3 more Smart Citations

A Deep SE(3)-Equivariant Model for Learning Inverse Protein Folding

McPartlon

Lai

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

GeoPacker: A novel deep learning framework for protein side‐chain modeling

Liu

Lai

2022

Protein Science

View full text Add to dashboard Cite

Atomic interactions play essential roles in protein folding, structure stabilization, and function performance. Recent advances in deep learning-based methods have achieved impressive success not only in protein structure prediction, but also in protein sequence design. However, highly efficient and accurate protein side-chain prediction methods that can give detailed atomic interactions are still lacking. In the present study, we developed a deep learning based method, GeoPacker, that uses geometric deep learning coupled ResNet for protein side-chain modeling. GeoPacker explicitly represents atomic interactions with rotational and translational invariance for information extraction of relative locations. GeoPacker outperformed the state-of-theart energy function-based methods in side-chain structure prediction accuracy and runs about 10 and 700 times faster than the deep learning-based method DLPacker and OPUS-rota4 with comparable prediction accuracy, respectively. The performance of GeoPacker does not depend on the secondary structures that the residues belong to. GeoPacker gives highly accurate predictions for buried residues in the protein core as well as protein-protein interface, making it a useful tool for protein structure modeling, protein, and interaction design.

show abstract

Flexible protein–protein docking with a multitrack iterative transformer

Chu,

Ruffolo,

Harmalkar

et al. 2024

Protein Science

View full text Add to dashboard Cite

Conventional protein‐protein docking algorithms usually rely on heavy candidate sampling and re‐ranking, but these steps are time‐consuming and hinder applications that require high‐throughput complex structure prediction, e.g., structure‐based virtual screening. Existing deep learning methods for protein‐protein docking, despite being much faster, suffer from low docking success rates. In addition, they simplify the problem to assume no conformational changes within any protein upon binding (rigid docking). This assumption precludes applications when binding‐induced conformational changes play a role, such as allosteric inhibition or docking from uncertain unbound model structures. To address these limitations, we present GeoDock, a multi‐track iterative transformer network to predict a docked structure from separate docking partners. Unlike deep learning models for protein structure prediction that input multiple sequence alignments (MSAs), GeoDock inputs just the sequences and structures of the docking partners, which suits the tasks when the individual structures are given. GeoDock is flexible at the protein residue level, allowing the prediction of conformational changes upon binding. On the DIPS test set, GeoDock achieves a 43% top‐1 success rate, outperforming all other tested methods. However, in the standard DIPS train/test splits, we discovered contamination of close homologs in the training set. After decontaminating the training set, the success rate is 31%. On the DB5.5 test set and a benchmark dataset of antibody‐antigen complexes, GeoDock outperforms the deep learning models trained using the same dataset but falls behind most of the conventional methods and AlphaFold‐Multimer. GeoDock attains an average inference speed of under one second on a single GPU, enabling its application in large‐scale structure screening. Although binding‐induced conformational changes are still a challenge owing to limited training and evaluation data, our architecture sets up the foundation to capture this backbone flexibility. Code and a demonstration Jupyter notebook are available at https://github.com/Graylab/GeoDock.This article is protected by copyright. All rights reserved.

show abstract

An end-to-end deep learning method for rotamer-free protein side-chain packing

Cited by 10 publications

References 30 publications

A Deep SE(3)-Equivariant Model for Learning Inverse Protein Folding

A Deep SE(3)-Equivariant Model for Learning Inverse Protein Folding

GeoPacker: A novel deep learning framework for protein side‐chain modeling

Flexible protein–protein docking with a multitrack iterative transformer

Contact Info

Product

Resources

About