Fast, accurate antibody structure prediction from deep learning on massive set of natural antibodies

Ruffolo, Jeffrey A.; Gray, Jeffrey J.

doi:10.1016/j.bpj.2021.11.1942

Cited by 51 publications

(84 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, we study protein structure as learned by language models trained purely on protein sequence data with a simple language modeling objective (15)(16)(17)(18)(19)(20)(21)(22). Previous work has shown that protein language models can capture some functional (23) and structural properties of proteins, including secondary structure, tertiary contacts, backbone structure, and antibody structure (15,19,24,25).…”

Section: Introductionmentioning

confidence: 99%

Evolutionary-scale prediction of atomic level protein structure with a language model

Lin¹,

Akin²,

Rao³

et al. 2022

Preprint

664

989

View full text Add to dashboard Cite

Large language models have recently been shown to develop emergent capabilities with scale, going beyond simple pattern matching to perform higher level reasoning and generate lifelike images and text. While language models trained on protein sequences have been studied at a smaller scale, little is known about what they learn about biology as they are scaled up. In this work we train models up to 15 billion parameters, the largest language models of proteins to be evaluated to date. We find that as models are scaled they learn information enabling the prediction of the three-dimensional structure of a protein at the resolution of individual atoms. We present ESMFold for high accuracy end-to-end atomic level structure prediction directly from the individual sequence of a protein. ESMFold has similar accuracy to AlphaFold2 and RoseTTAFold for sequences with low perplexity that are well understood by the language model. ESMFold inference is an order of magnitude faster than AlphaFold2, enabling exploration of the structural space of metagenomic proteins in practical timescales.

show abstract

Section: Introductionmentioning

confidence: 99%

Evolutionary-scale prediction of atomic level protein structure with a language model

Lin¹,

Akin²,

Rao³

et al. 2022

Preprint

664

989

View full text Add to dashboard Cite

show abstract

“…Other structure prediction methods, such as OmegaFold (Wu et al, 2022), Helixfold-single (Fang et al, 2022), ESM-Fold (Lin et al, 2022), employ large-scale protein language models to replace computationally extensive MSA searching and achieve comparable performance with AlphaFold2. Models designed specifically for antibody structure prediction, such as DeepAb (Ruffolo et al, 2022), ABlooper (Abanades et al, 2022a), IgFold (Ruffolo and Gray, 2022), xTrimoABFold (Wang et al, 2022), ImmuneBuilder (Abanades et al, 2022b) have recently been developed. In particular, xTrimoABFold uses a pretrained antibody language model and crossmodal template searching algorithm to obtain the most accurate heavy or light chain structure of an antibody.…”

Section: Backgrounds and Related Workmentioning

confidence: 99%

xTrimoDock: Rigid Protein Docking via Cross-Modal Representation Learning and Spectral Algorithm

Luo¹,

Li²,

Sun³

et al. 2023

Preprint

View full text Add to dashboard Cite

Protein-protein interactions are the basis for the formation of protein complexes which are essential for almost all cellular processes. Knowledge of the structures of protein complexes is of major importance for understanding the biological function of these protein-protein interactions and designing protein drugs. Here we address the problem of rigid protein docking which assumes no deformation of the involved proteins during interactions. We develop a method called, xTrimoDock, which leverages a cross-modal representation learning to predict the protein distance map, and then uses a spectral initialization and gradient descent to obtain the roto-translation transformation for docking. We show that, on antibody heavy-chain and light-chain docking, and antibody-antigen docking, xTrimoDock consistently outperforms the state-of-the-art such as AlphaFold-Multimer and HDock, and can lead to as much as a 10% improvement in DockQ metric. xTrimoDock has been applied as a useful tool in protein drug design at BioMap.

show abstract

“…Training an accurate model for antibody structure prediction is challenging due to the limited number of experimentally tested antibodies, which stands at only a few thousand according to SabDab [18]. Methods have been proposed in prior works to deal with this data limitation problem, for example, in IgFold [14], a pre-trained language model extracts patterns from millions of natural antibody sequences to get the evolutionary embeddings; and in DeepAb [16], a recurrent neural network (RNN) encoder-decoder model obtains evolutionary and structural representations of antibody sequences. We diverge from existing methods since the representations they provided do not have enough information for determined CDR H3 prediction.…”

Section: Self-supervised Learning For Dataset Augmentationmentioning

confidence: 99%

“…Furthermore, AlphaFold-Multimer [13] continues pushing the prediction accuracy of protein complexes. In the area of antibody protein structure prediction, a few deep-learning models have been proposed, and the state-of-the-art method IgFold has achieved an RMSD of about 3 Å for the H3 loop [14]. The neural network architecture of IgFold is a fast end-to-end deep learning model utilizing a pretrained BERT language model [15], a simplified AlphaFold-like transformer, and an invariant point attention structure.…”

Section: Introductionmentioning

confidence: 99%

AbFold -- an AlphaFold Based Transfer Learning Model for Accurate Antibody Structure Prediction

Peng

Wang

Zhao³

et al. 2023

Preprint

View full text Add to dashboard Cite

MotivationAntibodies are a group of proteins generated by B cells, which are crucial for the immune system. The importance of antibodies is ever-growing in pharmaceutics and biotherapeutics. Despite recent advancements pioneered by AlphaFold in general protein 3D structure prediction, accurate structure prediction of antibodies still lags behind, primarily due to the difficulty in modeling the Complementarity-determining regions (CDRs), especially the most variable CDR-H3 loop.ResultsThis paper presents AbFold, a transfer learning antibody structure prediction model with 3D point cloud refinement and unsupervised learning techniques. AbFold consistently produces state-of-the-art results on the prediction accuracy of the six CDR loops. The predictions of AbFold achieve an average RMSD of 1.51 Å for both heavy and light chains and an average RMSD of 3.04 Å for CDR-H3, bettering current models AlphaFold and IgFold. AbFold will contribute to antibody structure prediction and design processes.

show abstract

Fast, accurate antibody structure prediction from deep learning on massive set of natural antibodies

Cited by 51 publications

References 0 publications

Evolutionary-scale prediction of atomic level protein structure with a language model

Evolutionary-scale prediction of atomic level protein structure with a language model

xTrimoDock: Rigid Protein Docking via Cross-Modal Representation Learning and Spectral Algorithm

AbFold -- an AlphaFold Based Transfer Learning Model for Accurate Antibody Structure Prediction

Contact Info

Product

Resources

About