Improved contact prediction in proteins: using pseudolikelihoods to infer Potts models.

By Magnus Ekeberg, Cecilia Lövkvist, Yueheng Lan, Martin Weigt, Erik Aurell. 2012

642 citations recorded by the source corpus.

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/.

Subfields: Atomic and Molecular Physics, and Optics, Molecular Biology, Probabilistic & Bayesian Methods, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Molecular Biology

In Probabilistic & Bayesian Methods

In Computational Biology & Bioinformatics

Citations in the corpus

MSA Transformer (2021, neutral): “…have been proposed to efﬁciently ﬁt the MRF, including mean-ﬁeld inference (Morcos et al., 2011), sparse-inverse covariance estimation (Jones et al., 2012), and the current state-of-the-art, pseudolikelihood maximization (Balakrishnan et al., 2011; Ekeberg et al., 2013; Seemayer et al., 2014).”
CopulaNet: Learning residue co-evolution directly from multiple sequence alignment for protein structure prediction (2020, methodology): “To extract the direct correlations, a variety of direct coupling analysis (DCA) methods have been proposed using precision matrix (the inverse of covariance matrix) or Potts model [11–15].”
Evolutionary context-integrated deep sequence modeling for protein engineering (2020, methodology): “We refer the interested [38,58,59] for the details of the optimization.”
Coevolutionary Landscape Inference and the Context-Dependence of Mutations in Beta-Lactamase TEM-1 (2015, background): “Estimating parameters from aligned sequences is a computationally hard task, but over the last years a number of accurate and computationally efficient approximate algorithms have been developed [38, 39, 52, 53].”
Robust and accurate prediction of residue–residue interactions across protein interfaces using evolutionary information (2014, methodology): “…et al., 2011 ; Morcos et al., 2011 ; Jones et al., 2012 ), more recent studies have shown that a pseudo-likelihood-based approach ( Balakrishnan et al., 2011 ) results in more accurate predictions ( Ekeberg et al., 2013 ; Kamisetty et al., 2013 ) for a range of alignment sizes and protein lengths.”
Enhancing Evolutionary Couplings with Deep Convolutional Neural Networks (2017, methodology): “Notably, evolutionary coupling analysis methods, such as direct-coupling analysis, GREMLIN, (meta-) PSICOV, and EVFold, take an MSA as input and predict residue-residue contacts by learning an inherent graphical model structure that incorporates pairwise terms to capture evolutionary constraints amo”
Sequence co-evolution gives 3D contacts and structures of protein complexes (2014, methodology): “Computation of evolutionary couplings Inter- and intra-ECs were calculated on the alignment of concatenated sequences using a global probability model of sequence co-evolution, adapted from the method for single proteins29,30,34 using a pseudo-likelihood maximization (PLM)36 rather than mean field a”
Large-scale determination of previously unsolved protein structures using evolutionary information (2015, positive): “…by inverting a covariance matrix ( Marks et al., 2011 ; Morcos et al., 2011 ; Jones et al., 2012 ), subsequent studies have shown that a pseudo-likelihood (PLM)-based approach ( Balakrishnan et al., 2011 ) results in more accurate predictions ( Ekeberg et al., 2013 ; Kamisetty et al., 2013 ).”
Improved Contact Predictions Using the Recognition of Protein Like Contact Patterns (2014, methodology): “PconsC2 uses the same combination of predictions from PSICOV [32] and plmDCA [33], as PconsC.”
Fast and Accurate Multivariate Gaussian Modeling of Protein Families: Predicting Residue Contacts and Protein-Interaction Partners (2014, positive): “carrying biologically relevant information) could further enhance the prediction power of the method, although it is not obvious how to set a prior directly on the predicted interaction strengths, whereas with other methods – notably plmDCA [15] and PSICOV [12] – this should be straightforward.”
Protein contact prediction by integrating joint evolutionary coupling analysis and supervised learning (2013, background): “Our joint multifamily EC analysis predicts contacts of a target family not only using its own residue co-evolution information, but also those in its related families, which may share similar contact maps.”
Transformer protein language models are unsupervised structure learners (2020, methodology): “We compare ESM-1b (Rives et al., 2020), a large-scale (650M parameters) Transformer model trained on UniRef50 (Suzek et al., 2007) to the Gremlin (Kamisetty et al., 2013) pipeline which implements a log linear model trained with pseudolikelihood (Balakr-ishnan et al., 2011; Ekeberg et al., 2013).”