Self-supervised neural language models with attention have recently been applied to biological sequence data, advancing structure, function and mutational effect prediction. Some protein language models, including MSA Transformer and AlphaFold's EvoFormer, take multiple sequence alignments (MSAs) of evolutionarily related proteins as inputs. Simple combinations of MSA Transformer's row attentions have led to state-of-the-art unsupervised structural contact prediction. We demonstrate that similarly simple, and universal, combinations of MSA Transformer's column attentions strongly correlate with Hamming distances between sequences in MSAs. Therefore, MSA-based language models encode detailed phylogenetic relationships. We further show that these models can separate coevolutionary signals encoding functional and structural constraints from phylogenetic correlations reflecting historical contingency. To assess this, we generate synthetic MSAs, either without or with phylogeny, from Potts models trained on natural MSAs. We find that unsupervised contact prediction is substantially more resilient to phylogenetic noise when using MSA Transformer versus inferred Potts models.
Modeling Protein Evolution via Generative Inference From Monte Carlo Chains to Population Genetics
Politecnico di Torino（都灵理工大学）；Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；Laboratory of Computational and Quantitative Biology（计算与定量生物学实验室）；École Normale Supérieure（巴黎高等师范学院）；PSL Université（巴黎文理研究大学）；Université de Paris（巴黎大学）；The James Franck Institute（詹姆斯·弗兰克研究所）；The University of Chicago（芝加哥大学）；Department of Physics, The University of Chicago（芝加哥大学物理系）；INFN, Sezione di Torino（意大利国家核物理研究所都灵分部）；Italian Institute for Genomic Medicine, IRCCS Candiolo（意大利基因组医学研究所坎迪奥洛医院）；Dipartimento di Fisica, Sapienza Università di Roma（罗马大学物理系）
Generative power of a protein language model trained on multiple sequence alignments
École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Institute of Bioengineering（生物工程研究所）；School of Life Sciences（生命科学学院）；SIB Swiss Institute of Bioinformatics（瑞士生物信息学研究所）
Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation
Shanghai AI Laboratory（上海人工智能实验室）；Mila, Université de Montréal（蒙特利尔大学米拉研究所）；Zelixir Biotech（泽列西尔生物科技公司）；Fudan University（复旦大学）；The Chinese University of Hong Kong（香港中文大学）
Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction
Department of Systems Biology, Harvard Medical School（系统生物学系，哈佛医学院）；Department of Computer Science, University of Oxford（计算机科学系，牛津大学）；Department of Computer Science, University of Copenhagen（计算机科学系，哥本哈根大学）；Enzyme research, Novonesis（酶研究，Novonesis）
Deep Recurrent Neural Network for Protein Function Prediction from Sequence
Wyss Institute for Biologically Inspired Engineering（威斯生物启发工程研究所）；School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）；Department of Systems Biology, Harvard Medical School（哈佛医学院系统生物学系）
Aligning Large Language Models and Geometric Deep Models for Protein Representation
Northwestern University（西北大学）；University of Pittsburgh（匹兹堡大学）；Michigan State University（密歇根州立大学）；North Carolina State University（北卡罗来纳州立大学）；New Jersey Institute of Technology（新泽西理工学院）
Towards coevolution-aware ancestral sequence reconstruction
Sorbonne Université（索邦大学）；CNRS, Computational, Quantitative and Synthetic Biology（法国国家科学研究中心，计算、定量与合成生物学）；Dipartimento di Fisica, Sapienza Università di Roma（罗马智慧大学物理系）；DISAT, Politecnico di Torino（都灵理工大学地球与环境科学系）；Institut Universitaire de France (IUF)（法国高等研究院）
Boltzmann Machine Learning with a Parallel, Persistent Markov chain Monte Carlo method for Estimating Evolutionary Fields and Couplings from a Protein Multiple Sequence Alignment
Estimation of Amino Acid Residue Substitution Rates at Local Spatial Regions and Application in Protein Function Inference: A Bayesian Monte Carlo Approach
An Automatable Analytical Algorithm for Structure-Based Protein Functional Annotation via Detection of Specific Ligand 3D Binding Sites: Application to ATP (ser/thr Protein Kinases) and GTP (Small Ras-type G-Proteins) Binding Sites
Statistical mechanical properties of sequence space determine the efficiency of the various algorithms to predict interaction energies and native contacts from protein coevolution
