Fast pseudolikelihood maximization for direct-coupling analysis of protein structure from many homologous amino-acid sequences

Abstract

Direct-Coupling Analysis is a group of methods to harvest information about coevolving residues in a protein family by learning a generative model in an exponential family from data. In protein families of realistic size, this learning can only be done approximately, and there is a trade-off between inference precision and computational speed. We here show that an earlier introduced $l_2$-regularized pseudolikelihood maximization method called plmDCA can be modified as to be easily parallelizable, as well as inherently faster on a single processor, at negligible difference in accuracy. We test the new incarnation of the method on 148 protein families from the Protein Families database (PFAM), one of the largest tests of this class of algorithms to date.

33 pages, 4 figures; M. Ekeberg and T. Hartonen are joint first authors; code and supplementary information on http://plmdca.csc.kth.se/

References in corpus (9)

• Identification of direct residue contacts in protein-protein interaction by message passing
• Improved contact prediction in proteins: Using pseudolikelihoods to infer Potts models
• Sequence co-evolution gives 3D contacts and structures of protein complexes
• Fast and accurate multivariate Gaussian modeling of protein families: Predicting residue contacts and protein-interaction partners
• Small-correlation expansions for the inverse Ising problem
• Improving contact prediction along three dimensions
• Inference of Co-Evolving Site Pairs: an Excellent Predictor of Contact Residue Pairs in Protein 3D structures
• Prediction of residue-residue contacts from protein families using similarity kernels and least squares regularization
• Protein Contact Prediction by Integrating Joint Evolutionary Coupling Analysis and Supervised Learning

Cited by in corpus (29)

• Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
• Inferring interaction partners from protein sequences
• Epistatic models predict mutable sites in SARS-CoV-2 proteins and epitopes
• Improving contact prediction along three dimensions
• Global analysis of more than 50,000 SARS-Cov-2 genomes reveals epistasis between 8 viral genes
• Protein language models trained on multiple sequence alignments learn phylogenetic relationships
• Inter-protein sequence co-evolution predicts known physical interactions in bacterial ribosomes and the trp operon
• Revealing evolutionary constraints on proteins through sequence analysis
• Sparse generative modeling via parameter-reduction of Boltzmann machines: application to protein-sequence families
• Inference of compressed Potts graphical models
• Identifying relevant positions in proteins by Critical Variable Selection
• Aligning biological sequences by exploiting residue conservation and coevolution
• Correlations from structure and phylogeny combine constructively in the inference of protein partners from sequences
• Selection originating from protein stability/foldability: Relationships between protein folding free energy, sequence ensemble, and fitness
• Correlation-Compressed Direct Coupling Analysis
• Optimal regularizations for data generation with probabilistic graphical models
• Inferring genetic fitness from genomic data
• Impact of phylogeny on structural contact inference from protein sequence data
• High-dimensional structure learning of binary pairwise Markov networks: A comparative numerical study
• Prediction of residue-residue contacts from protein families using similarity kernels and least squares regularization
• Statistical Genetics in and out of Quasi-Linkage Equilibrium (Extended)
• Two fitness inference schemes compared using allele frequencies from 1,068,391 sequences sampled in the UK during the COVID-19 pandemic
• Prediction of Structures and Interactions from Genome Information
• Inferring Higher-Order Couplings with Neural Networks
• Boltzmann machine learning and regularization methods for inferring evolutionary fields and couplings from a multiple sequence alignment
• Inferring repeat protein energetics from evolutionary information
• Pseudo-likelihood produces associative memories able to generalize, even for asymmetric couplings
• Classification of SARS-CoV-2 Variants through The Epistatical Circos Plots with Convolutional Neural Networks
• Prediction of native contacts in proteins from an out--of--equilibrium coevolutionary process