ProteinGLUE: A multi-task benchmark suite for self-supervised protein modeling.

Self-supervised language modeling is a rapidly developing approach for the analysis of protein sequence data. However, work in this area is heterogeneous and diverse, making comparison of models and methods difficult. Moreover, models are often evaluated only on one or two downstream tasks, making it unclear whether the models capture generally useful properties. We introduce the ProteinGLUE benchmark for the evaluation of protein representations: a set of seven tasks for evaluating learned protein representations. We also offer reference code, and we provide two baseline models with hyperparameters specifically trained for these benchmarks. Pre-training was done on two tasks, masked symbol prediction and next sentence prediction. We show that pre-training yields higher performance on a variety of downstream tasks such as secondary structure and protein interaction interface prediction, compared to no pre-training. However, the larger base model does not outperform the smaller medium. We expect the ProteinGLUE benchmark dataset introduced here, together with the two baseline pre-trained models and their performance evaluations, to be of great value to the field of protein sequence-based property prediction. Availability: code and datasets from https://github.com/ibivu/protein-glue

Improved protein docking by predicted interface residues.

Scoring docking solutions is a difficult task, and many methods have been developed for this purpose. In docking, only a handful of the hundreds of thousands of models generated by docking algorithms are acceptable, causing difficulties when developing scoring functions. Today’s best scoring functions can significantly increase the number of top-ranked models but still fails for most targets. Here, we examine the possibility of utilising predicted residues on a protein-protein interface to score docking models generated during the scan stage of a docking algorithm. Many methods have been developed to infer the portions of a protein surface that interact with another protein, but most have not been benchmarked using docking algorithms. Different interface prediction methods are systematically tested for scoring >300.000 low-resolution rigid-body template free docking decoys. Overall we find that BIPSPI is the best method to identify interface amino acids and score docking solutions. Further, using BIPSPI provides better docking results than state of the art scoring functions, with >12% of first ranked docking models being acceptable. Additional experiments indicated precision as a high-importance metric when estimating interface prediction quality, focusing on docking constraints production. We also discussed several limitations for the adoption of interface predictions as constraints in a docking protocol.

Improved protein docking by predicted interface residues

ABSTRACTScoring docking solutions is a difficult task, and many methods have been developed for this purpose. In docking, only a handful of the hundreds of thousands of models generated by docking algorithms are acceptable, causing difficulties when developing scoring functions. Today’s best scoring functions can significantly increase the number of top-ranked models but still fails for most targets. Here, we examine the possibility of utilising predicted residues on a protein-protein interface to score docking models generated during the scan stage of a docking algorithm. Many methods have been developed to infer the portions of a protein surface that interact with another protein, but most have not been benchmarked using docking algorithms. Different interface prediction methods are systematically tested for scoring >300.000 low-resolution rigid-body template free docking decoys. Overall we find that BIPSPI is the best method to identify interface amino acids and score docking solutions. Further, using BIPSPI provides better docking results than state of the art scoring functions, with >12% of first ranked docking models being acceptable. Additional experiments indicated precision as a high-importance metric when estimating interface prediction quality, focusing on docking constraints production. We also discussed several limitations for the adoption of interface predictions as constraints in a docking protocol.

Modeling of protein complexes in CASP14 with emphasis on the interaction interface prediction

The goal of CASP experiments is to monitor the progress in the protein structure prediction field. During the 14th CASP edition we aimed to test our capabilities of predicting structures of protein complexes. Our protocol for modeling protein assemblies included both template-based modeling and free docking. Structural templates were identified using sensitive sequence-based searches. If sequence-based searches failed, we performed structure-based template searches using selected CASP server models. In the absence of reliable templates we applied free docking starting from monomers generated by CASP servers. We evaluated and ranked models of protein complexes using an improved version of protein structure quality assessment method, VoroMQA, taking into account both interaction interface and global structure scores. If reliable templates could be identified, generally accurate models of protein assemblies were generated with the exception of an antibody-antigen interaction. The success of free docking mainly depended on the accuracy of initial subunit models and on the scoring of docking solutions. To put our overall results in perspective, we analyzed our performance in the context of other CASP groups. Although the subunits in our assembly models often were not of the top quality, these models had, overall, the best predicted interfaces according to several protein-protein interface accuracy measures. Since we did not use co-evolution-based prediction of inter-chain contacts, we attribute our relative success in predicting interfaces primarily to the emphasis on the interaction interface when modeling and scoring.

Study on the Interface Constitutive Relation between Carbon Fiber Fabric and Steel

Peeling failure at the interface is one of the main failure modes for CFRP (Carbon Fiber-Reinforced Polymer)-reinforced steel structures. However, there are very few reported studies on the bond-slip relationship at the CFRP-steel interface. A series of simple shear tests were carried out in the present paper. The influence of the fiber fabric’s width and thickness, the surface roughness of the steel sheet, and the thickness of the adhesive layer on the bonding performance of the CFRP fabric to steel interface was considered. The interface constitutive model and bonding strength model were further established under multiple factors. The results show that with the decrease of the surface roughness, the interface’ ultimate peeling load increases gradually, and the failure has a tendency to develop from a glue-steel interface to a glue-CFRP interface. The test pieces that were subjected to sand blasting obtained the peak value of the ultimate peeling load. This indicates that sand blasting can effectively enhance the interface bonding strength. The theoretical values obtained via the interface prediction model are consistent with the experimental values. This proves that the newly developed interface prediction model can effectively predict the local bonding slip and bonding strength of the interface.

Patch-DCA: improved protein interface prediction by utilizing structural information and clustering DCA scores

Motivation Over the past decade, there have been impressive advances in determining the 3D structures of protein complexes. However, there are still many complexes with unknown structures, even when the structures of the individual proteins are known. The advent of protein sequence information provides an opportunity to leverage evolutionary information to enhance the accuracy of protein–protein interface prediction. To this end, several statistical and machine learning methods have been proposed. In particular, direct coupling analysis has recently emerged as a promising approach for identification of protein contact maps from sequential information. However, the ability of these methods to detect protein–protein inter-residue contacts remains relatively limited. Results In this work, we propose a method to integrate sequential and co-evolution information with structural and functional information to increase the performance of protein–protein interface prediction. Further, we present a post-processing clustering method that improves the average relative F1 score by 70% and 24% and the average relative precision by 80% and 36% in comparison with two state-of-the-art methods, PSICOV and GREMLIN. Availability and implementation https://github.com/BioMLBoston/PatchDCA Supplementary information Supplementary data are available at Bioinformatics online.