Structured Q-learning For Antibody Design
- URL: http://arxiv.org/abs/2209.04698v2
- Date: Tue, 13 Sep 2022 20:43:47 GMT
- Title: Structured Q-learning For Antibody Design
- Authors: Alexander I. Cowen-Rivers, Philip John Gorinski, Aivar Sootla, Asif
Khan, Liu Furui, Jun Wang, Jan Peters, Haitham Bou Ammar
- Abstract summary: One of the crucial steps involved in antibody design is to find an arrangement of amino acids in a protein sequence that improves its binding with a pathogen.
Combinatorial optimization of antibodies is difficult due to extremely large search spaces and non-linear objectives.
Applying traditional Reinforcement Learning to antibody design optimization results in poor performance.
We propose Q-learning, an extension of Q-learning that incorporates structural priors for optimization.
- Score: 82.78798397798533
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Optimizing combinatorial structures is core to many real-world problems, such
as those encountered in life sciences. For example, one of the crucial steps
involved in antibody design is to find an arrangement of amino acids in a
protein sequence that improves its binding with a pathogen. Combinatorial
optimization of antibodies is difficult due to extremely large search spaces
and non-linear objectives. Even for modest antibody design problems, where
proteins have a sequence length of eleven, we are faced with searching over
2.05 x 10^14 structures. Applying traditional Reinforcement Learning algorithms
such as Q-learning to combinatorial optimization results in poor performance.
We propose Structured Q-learning (SQL), an extension of Q-learning that
incorporates structural priors for combinatorial optimization. Using a
molecular docking simulator, we demonstrate that SQL finds high binding energy
sequences and performs favourably against baselines on eight challenging
antibody design tasks, including designing antibodies for SARS-COV.
Related papers
- SGNet: Folding Symmetrical Protein Complex with Deep Learning [4.064036667570452]
We propose a protein folding framework called SGNet to model protein-protein interactions in symmetrical assemblies.
Thanks to the elaborate design of modeling symmetry consistently, we can model all global symmetry types in quaternary protein structure prediction.
arXiv Detail & Related papers (2024-03-07T10:39:48Z) - Inverse folding for antibody sequence design using deep learning [2.8998926117101367]
We propose a fine-tuned folding inverse model that is specifically optimised for antibody structures.
We study the canonical conformations of complementarity-determining regions and find improved encoding of these loops into known clusters.
arXiv Detail & Related papers (2023-10-30T13:12:41Z) - A Hierarchical Training Paradigm for Antibody Structure-sequence
Co-design [54.30457372514873]
We propose a hierarchical training paradigm (HTP) for the antibody sequence-structure co-design.
HTP consists of four levels of training stages, each corresponding to a specific protein modality.
Empirical experiments show that HTP sets the new state-of-the-art performance in the co-design problem.
arXiv Detail & Related papers (2023-10-30T02:39:15Z) - Cross-Gate MLP with Protein Complex Invariant Embedding is A One-Shot
Antibody Designer [58.97153056120193]
The specificity of an antibody is determined by its complementarity-determining regions (CDRs)
Previous studies have utilized complex techniques to generate CDRs, but they suffer from inadequate geometric modeling.
We propose a textitsimple yet effective model that can co-design 1D sequences and 3D structures of CDRs in a one-shot manner.
arXiv Detail & Related papers (2023-04-21T13:24:26Z) - A Pareto-optimal compositional energy-based model for sampling and
optimization of protein sequences [55.25331349436895]
Deep generative models have emerged as a popular machine learning-based approach for inverse problems in the life sciences.
These problems often require sampling new designs that satisfy multiple properties of interest in addition to learning the data distribution.
arXiv Detail & Related papers (2022-10-19T19:04:45Z) - Mind Your Solver! On Adversarial Attack and Defense for Combinatorial
Optimization [111.78035414744045]
We take an initiative on developing the mechanisms for adversarial attack and defense towards optimization solvers.
We present a simple yet effective defense strategy to modify the graph structure to increase the robustness of solvers.
arXiv Detail & Related papers (2021-12-28T15:10:15Z) - EBM-Fold: Fully-Differentiable Protein Folding Powered by Energy-based
Models [53.17320541056843]
We propose a fully-differentiable approach for protein structure optimization, guided by a data-driven generative network.
Our EBM-Fold approach can efficiently produce high-quality decoys, compared against traditional Rosetta-based structure optimization routines.
arXiv Detail & Related papers (2021-05-11T03:40:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.