Improved contact prediction in proteins: Using pseudolikelihoods to infer Potts models

Abstract

Spatially proximate amino acids in a protein tend to coevolve. A protein's three-dimensional (3D) structure hence leaves an echo of correlations in the evolutionary record. Reverse engineering 3D structures from such correlations is an open problem in structural biology, pursued with increasing vigor as more and more protein sequences continue to fill the data banks. Within this task lies a statistical inference problem, rooted in the following: correlation between two sites in a protein sequence can arise from firsthand interaction but can also be network-propagated via intermediate sites; observed correlation is not enough to guarantee proximity. To separate direct from indirect interactions is an instance of the general problem of inverse statistical mechanics, where the task is to learn model parameters (fields, couplings) from observables (magnetizations, correlations, samples) in large systems. In the context of protein sequences, the approach has been referred to as direct-coupling analysis. Here we show that the pseudolikelihood method, applied to 21-state Potts models describing the statistical properties of families of evolutionarily related proteins, significantly outperforms existing approaches to the direct-coupling analysis, the latter being based on standard mean-field techniques. This improved performance also relies on a modified score for the coupling strength. The results are verified using known crystal structures of specific sequence instances of various protein families. Code implementing the new method can be found at http://plmdca.csc.kth.se/.

19 pages, 16 figures, published version

References in corpus (14)

• Weak pairwise correlations imply strongly correlated network states in a neural population
• Direct-coupling analysis of residue co-evolution captures native contacts across many protein families
• Identification of direct residue contacts in protein-protein interaction by message passing
• High-dimensional Ising model selection using ${\ell }_1$-regularized logistic regression
• Inverse Ising inference using all the data
• Adaptive Cluster Expansion for Inferring Boltzmann Machines with Noisy Data
• Learning by message-passing in networks of discrete synapses
• Statistical physics of pairwise probability models
• Small-correlation expansions for the inverse Ising problem
• The Bethe approximation for solving the inverse Ising problem: a comparison with other inference methods
• Mean-field theory for the inverse Ising problem at low temperatures
• Bethe-Peierls approximation and the inverse Ising model
• Inference algorithms for gene networks: a statistical mechanics analysis
• Intrinsic limitations of inverse inference in the pairwise Ising spin glass

Cited by in corpus (107)

• Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
• Quantification of the effect of mutations using a global probability model of natural sequence variation
• Sequence co-evolution gives 3D contacts and structures of protein complexes
• Coevolutionary landscape inference and the context-dependence of mutations in beta-lactamase TEM-1
• Inverse statistical problems: from the inverse Ising problem to data science
• Inverse Statistical Physics of Protein Sequences: A Key Issues Review
• Fast pseudolikelihood maximization for direct-coupling analysis of protein structure from many homologous amino-acid sequences
• What is a meaningful representation of protein sequences?
• Inferring interaction partners from protein sequences
• How pairwise coevolutionary models capture the collective residue variability in proteins
• Fast and accurate multivariate Gaussian modeling of protein families: Predicting residue contacts and protein-interaction partners
• Simultaneous identification of specifically interacting paralogs and inter-protein contacts by Direct-Coupling Analysis
• From principal component to direct coupling analysis of coevolution in proteins: Low-eigenvalue modes are needed for structure prediction
• DeepBach: a Steerable Model for Bach Chorales Generation
• Large-scale identification of coevolution signals across homo-oligomeric protein interfaces by Direct Coupling Analysis
• Efficient generative modeling of protein sequences using simple autoregressive models
• 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
• Pseudolikelihood Decimation Algorithm Improving the Inference of the Interaction Network in a General Class of Ising Models
• Inter-protein sequence co-evolution predicts known physical interactions in bacterial ribosomes and the trp operon
• Inferring interaction partners from protein sequences using mutual information
• Influence of Multiple Sequence Alignment Depth on Potts Statistical Models of Protein Covariation
• Metropolized Knockoff Sampling
• Benchmarking inverse statistical approaches for protein structure and design with exactly solvable models
• Generative power of a protein language model trained on multiple sequence alignments
• Variational auto-encoding of protein sequences
• On perturbed proximal gradient algorithms
• Selection of sequence motifs and generative Hopfield-Potts models for protein familiesilies
• Phylogenetic correlations can suffice to infer protein partners from sequences
• SESNet: sequence-structure feature-integrated deep learning method for data-efficient protein engineering
• Revealing evolutionary constraints on proteins through sequence analysis
• Mapping of attention mechanisms to a generalized Potts model
• Parsimonious evolutionary scenario for the origin of allostery and coevolution patterns in proteins
• Modeling sequence-space exploration and emergence of epistatic signals in protein evolution
• Sparse generative modeling via parameter-reduction of Boltzmann machines: application to protein-sequence families
• Assessing the accuracy of direct-coupling analysis for RNA contact prediction
• On the entropy of protein families
• Inference of compressed Potts graphical models
• Consistent inference of a general model using the pseudo-likelihood method
• Marginal Pseudo-Likelihood Learning of Markov Network structures
• Size and structure of the sequence space of repeat proteins
• Direct Coupling Analysis of Epistasis in Allosteric Materials
• Quantifying Relevance in Learning and Inference
• Population-specific design of de-immunized protein biotherapeutics
• Identifying relevant positions in proteins by Critical Variable Selection
• A generative model for protein contact networks
• A Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines
• Correlations from structure and phylogeny combine constructively in the inference of protein partners from sequences
• Aligning biological sequences by exploiting residue conservation and coevolution
• Solving the inverse Ising problem by mean-field methods in a clustered phase space with many states
• Correlation-Compressed Direct Coupling Analysis
• Selection originating from protein stability/foldability: Relationships between protein folding free energy, sequence ensemble, and fitness
• A primer on model-guided exploration of fitness landscapes for biological sequence design
• Detection of cheating by decimation algorithm
• Inference of the sparse kinetic Ising model using the decimation method
• Style Imitation and Chord Invention in Polyphonic Music with Exponential Families
• Statistical physics of interacting proteins: impact of dataset size and quality assessed in synthetic sequences
• Inferring genetic fitness from genomic data
• Optimal regularizations for data generation with probabilistic graphical models
• Estimating probabilistic context-free grammars for proteins using contact map constraints
• Predicting B Cell Receptor Substitution Profiles Using Public Repertoire Data
• Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model
• Statistical mechanics of the inverse Ising problem and the optimal objective function
• Regularization and decimation pseudolikelihood approaches to statistical inference in $XY$-spin models
• Sparse model selection in the highly under-sampled regime
• High-dimensional structure learning of binary pairwise Markov networks: A comparative numerical study
• A unified statistical model of protein multiple sequence alignment integrating direct coupling and insertions
• Resummed mean-field inference for strongly coupled data
• Impact of phylogeny on structural contact inference from protein sequence data
• An exact study of phase transitions in mean field Potts models
• Structure Learning of Contextual Markov Networks using Marginal Pseudo-likelihood
• Unified framework for modeling multivariate distributions in biological sequences
• Prediction of residue-residue contacts from protein families using similarity kernels and least squares regularization
• L_1-regularized Boltzmann machine learning using majorizer minimization
• Statistical Genetics in and out of Quasi-Linkage Equilibrium (Extended)
• Maximum Entropy Approach for the Prediction of Urban Mobility Patterns
• On a Multilocus Wright-Fisher Model with Mutation and a Svirezhev-Shahshahani Gradient-like Selection Dynamics
• Maximum entropy models for generation of expressive music
• Interpretable Neural Networks based classifiers for categorical inputs
• Covariate-Assisted Bayesian Graph Learning for Heterogeneous Data
• Inferring Higher-Order Couplings with Neural Networks
• Reconstruction of Pairwise Interactions using Energy-Based Models
• The grammar of the Ising model: A new complexity hierarchy
• Prediction of Structures and Interactions from Genome Information
• Protein Structure Prediction by Protein Alignments
• adabmDCA 2.0 -- a flexible but easy-to-use package for Direct Coupling Analysis
• Protein Contact Prediction by Integrating Joint Evolutionary Coupling Analysis and Supervised Learning
• Cooperative "folding transition" in the sequence space facilitates function-driven evolution of protein families
• Impact of phylogeny on the inference of functional sectors from protein sequence data
• Data-driven Discovery of Biophysical T Cell Receptor Co-specificity Rules
• Bayesian Analysis of High-dimensional Discrete Graphical Models
• Boltzmann machine learning and regularization methods for inferring evolutionary fields and couplings from a multiple sequence alignment
• Correlated evolution: models and methods
• Half-ice, half-fire-driven ultranarrow phase crossover in one-dimensional decorated $q$-state Potts ferrimagnets: An AI-co-led exploration
• AmoebaContact and GDFold: a new pipeline for rapid prediction of protein structures
• 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
• Inferring repeat protein energetics from evolutionary information
• DCAlign v1.0: Aligning biological sequences using co-evolution models and informed priors
• Predicting diverse M-best protein contact maps
• Data quality for the inverse Ising problem
• adabmDCA: Adaptive Boltzmann machine learning for biological sequences
• Unsupervised and Supervised Structure Learning for Protein Contact Prediction
• Computational Pipeline to probe NaV1.7 gain-of-functions variants in neuropathic painful syndromes
• Prediction of native contacts in proteins from an out--of--equilibrium coevolutionary process
• Molecular recognition between cadherins studied by a coarse-grained model interacting with a coevolutionary potential