Distance-based protein folding powered by deep learning

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Direct coupling analysis (DCA) for protein folding has made very good progress, but it is not effective for proteins that lack many sequence homologs, even coupled with time-consuming conformation sampling with fragments. We show that we can accurately predict interresidue distance distribution of a protein by deep learning, even for proteins with ∼60 sequence homologs. Using only the geometric constraints given by the resulting distance matrix we may construct 3D models without involving extensive conformation sampling. Our method successfully folded 21 of the 37 CASP12 hard targets with a median family size of 58 effective sequence homologs within 4 h on a Linux computer of 20 central processing units. In contrast, DCA-predicted contacts cannot be used to fold any of these hard targets in the absence of extensive conformation sampling, and the best CASP12 group folded only 11 of them by integrating DCA-predicted contacts into fragment-based conformation sampling. Rigorous experimental validation in CASP13 shows that our distance-based folding server successfully folded 17 of 32 hard targets (with a median family size of 36 sequence homologs) and obtained 70% precision on the top L/5 long-range predicted contacts. The latest experimental validation in CAMEO shows that our server predicted correct folds for 2 membrane proteins while all of the other servers failed. These results demonstrate that it is now feasible to predict correct fold for many more proteins lack of similar structures in the Protein Data Bank even on a personal computer.

Related collections

Most cited references 38

Record: found
Abstract: found
Article: found

Is Open Access

Protein 3D Structure Computed from Evolutionary Sequence Variation

Debora S. Marks, Lucy Colwell, Robert Sheridan … (2011)

The evolutionary trajectory of a protein through sequence space is constrained by its function. Collections of sequence homologs record the outcomes of millions of evolutionary experiments in which the protein evolves according to these constraints. Deciphering the evolutionary record held in these sequences and exploiting it for predictive and engineering purposes presents a formidable challenge. The potential benefit of solving this challenge is amplified by the advent of inexpensive high-throughput genomic sequencing. In this paper we ask whether we can infer evolutionary constraints from a set of sequence homologs of a protein. The challenge is to distinguish true co-evolution couplings from the noisy set of observed correlations. We address this challenge using a maximum entropy model of the protein sequence, constrained by the statistics of the multiple sequence alignment, to infer residue pair couplings. Surprisingly, we find that the strength of these inferred couplings is an excellent predictor of residue-residue proximity in folded structures. Indeed, the top-scoring residue couplings are sufficiently accurate and well-distributed to define the 3D protein fold with remarkable accuracy. We quantify this observation by computing, from sequence alone, all-atom 3D structures of fifteen test proteins from different fold classes, ranging in size from 50 to 260 residues., including a G-protein coupled receptor. These blinded inferences are de novo, i.e., they do not use homology modeling or sequence-similar fragments from known structures. The co-evolution signals provide sufficient information to determine accurate 3D protein structure to 2.7–4.8 Å Cα-RMSD error relative to the observed structure, over at least two-thirds of the protein (method called EVfold, details at http://EVfold.org). This discovery provides insight into essential interactions constraining protein evolution and will facilitate a comprehensive survey of the universe of protein structures, new strategies in protein and drug design, and the identification of functional genetic variants in normal and disease genomes.

0 comments Cited 443 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Version 1.2 of the Crystallography and NMR system.

Axel T. Brunger (2007)

Version 1.2 of the software system, termed Crystallography and NMR system (CNS), for crystallographic and NMR structure determination has been released. Since its first release, the goals of CNS have been (i) to create a flexible computational framework for exploration of new approaches to structure determination, (ii) to provide tools for structure solution of difficult or large structures, (iii) to develop models for analyzing structural and dynamical properties of macromolecules and (iv) to integrate all sources of information into all stages of the structure determination process. Version 1.2 includes an improved model for the treatment of disordered solvent for crystallographic refinement that employs a combined grid search and least-squares optimization of the bulk solvent model parameters. The method is more robust than previous implementations, especially at lower resolution, generally resulting in lower R values. Other advances include the ability to apply thermal factor sharpening to electron density maps. Consistent with the modular design of CNS, these additions and changes were implemented in the high-level computing language of CNS.

0 comments Cited 414 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Direct-coupling analysis of residue coevolution captures native contacts across many protein families.

Faruck Morcos, Andrea Pagnani, Bryan Lunt … (2011)

The similarity in the three-dimensional structures of homologous proteins imposes strong constraints on their sequence variability. It has long been suggested that the resulting correlations among amino acid compositions at different sequence positions can be exploited to infer spatial contacts within the tertiary protein structure. Crucial to this inference is the ability to disentangle direct and indirect correlations, as accomplished by the recently introduced direct-coupling analysis (DCA). Here we develop a computationally efficient implementation of DCA, which allows us to evaluate the accuracy of contact prediction by DCA for a large number of protein domains, based purely on sequence information. DCA is shown to yield a large number of correctly predicted contacts, recapitulating the global structure of the contact map for the majority of the protein domains examined. Furthermore, our analysis captures clear signals beyond intradomain residue contacts, arising, e.g., from alternative protein conformations, ligand-mediated residue couplings, and interdomain interactions in protein oligomers. Our findings suggest that contacts predicted by DCA can be used as a reliable guide to facilitate computational predictions of alternative protein conformations, protein complex formation, and even the de novo prediction of protein domain structures, contingent on the existence of a large number of homologous sequences which are being rapidly made available due to advances in genome sequencing.