scholarly journals Text mining for modeling of protein complexes enhanced by machine learning

2020 ◽  
Author(s):  
Varsha D Badal ◽  
Petras J Kundrotas ◽  
Ilya A Vakser
Keyword(s):  
Machine Learning ◽  
Text Mining ◽  
Protein Interactions ◽  
Full Text ◽  
Protein Complexes ◽  
Protein Docking ◽  
Supplementary Information ◽  
Support Vector ◽  
Learning Approaches ◽  
Protein Protein Interactions

Abstract Motivation Procedures for structural modeling of protein-protein complexes (protein docking) produce a number of models which need to be further analyzed and scored. Scoring can be based on independently determined constraints on the structure of the complex, such as knowledge of amino acids essential for the protein interaction. Previously, we showed that text mining of residues in freely available PubMed abstracts of papers on studies of protein-protein interactions may generate such constraints. However, absence of post-processing of the spotted residues reduced usability of the constraints, as a significant number of the residues were not relevant for the binding of the specific proteins. Results We explored filtering of the irrelevant residues by two machine learning approaches, Deep Recursive Neural Network (DRNN) and Support Vector Machine (SVM) models with different training/testing schemes. The results showed that the DRNN model is superior to the SVM model when training is performed on the PMC-OA full-text articles and applied to classification (interface or non-interface) of the residues spotted in the PubMed abstracts. When both training and testing is performed on full-text articles or on abstracts, the performance of these models is similar. Thus, in such cases, there is no need to utilize computationally demanding DRNN approach, which is computationally expensive especially at the training stage. The reason is that SVM success is often determined by the similarity in data/text patterns in the training and the testing sets, whereas the sentence structures in the abstracts are, in general, different from those in the full text articles. Availability The code and the datasets generated in this study are available at https://gitlab.ku.edu/vakser-lab-public/text-mining/-/tree/2020-09-04. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals InterPep2: global peptide–protein docking using interaction surface templates

2020 ◽  
Vol 36 (8) ◽  
pp. 2458-2465 ◽  
Author(s):  
Isak Johansson-Åkhe ◽  
Claudio Mirabello ◽  
Björn Wallner
Keyword(s):  
Protein Interactions ◽  
Protein Complexes ◽  
Structural Features ◽  
Protein Docking ◽  
Supplementary Information ◽  
Peptide Ligand ◽  
Protein Protein Interactions ◽  
Intrinsically Disordered ◽  
Intrinsically Disordered Regions ◽  
Improved Performance

Abstract Motivation Interactions between proteins and peptides or peptide-like intrinsically disordered regions are involved in many important biological processes, such as gene expression and cell life-cycle regulation. Experimentally determining the structure of such interactions is time-consuming and difficult because of the inherent flexibility of the peptide ligand. Although several prediction-methods exist, most are limited in performance or availability. Results InterPep2 is a freely available method for predicting the structure of peptide–protein interactions. Improved performance is obtained by using templates from both peptide–protein and regular protein–protein interactions, and by a random forest trained to predict the DockQ-score for a given template using sequence and structural features. When tested on 252 bound peptide–protein complexes from structures deposited after the complexes used in the construction of the training and templates sets of InterPep2, InterPep2-Refined correctly positioned 67 peptides within 4.0 Å LRMSD among top10, similar to another state-of-the-art template-based method which positioned 54 peptides correctly. However, InterPep2 displays a superior ability to evaluate the quality of its own predictions. On a previously established set of 27 non-redundant unbound-to-bound peptide–protein complexes, InterPep2 performs on-par with leading methods. The extended InterPep2-Refined protocol managed to correctly model 15 of these complexes within 4.0 Å LRMSD among top10, without using templates from homologs. In addition, combining the template-based predictions from InterPep2 with ab initio predictions from PIPER-FlexPepDock resulted in 22% more near-native predictions compared to the best single method (22 versus 18). Availability and implementation The program is available from: http://wallnerlab.org/InterPep2. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Mass spectrometry-based cross-linking study shows that the Psb28 protein binds to cytochrome b559 in Photosystem II

2017 ◽  
Vol 114 (9) ◽  
pp. 2224-2229 ◽  
Author(s):  
Daniel A. Weisz ◽  
Haijun Liu ◽  
Hao Zhang ◽  
Sundarapandian Thangapandian ◽  
Emad Tajkhorshid ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Photosystem Ii ◽  
Protein Interactions ◽  
Protein Complexes ◽  
Protein Docking ◽  
Cross Linking ◽  
Protein Protein Interactions ◽  
Cytochrome B559 ◽  
Reaction Center Complex ◽  
Assembly Intermediate

Photosystem II (PSII), a large pigment protein complex, undergoes rapid turnover under natural conditions. During assembly of PSII, oxidative damage to vulnerable assembly intermediate complexes must be prevented. Psb28, the only cytoplasmic extrinsic protein in PSII, protects the RC47 assembly intermediate of PSII and assists its efficient conversion into functional PSII. Its role is particularly important under stress conditions when PSII damage occurs frequently. Psb28 is not found, however, in any PSII crystal structure, and its structural location has remained unknown. In this study, we used chemical cross-linking combined with mass spectrometry to capture the transient interaction of Psb28 with PSII. We detected three cross-links between Psb28 and the α- and β-subunits of cytochrome b559, an essential component of the PSII reaction-center complex. These distance restraints enable us to position Psb28 on the cytosolic surface of PSII directly above cytochrome b559, in close proximity to the QB site. Protein–protein docking results also support Psb28 binding in this region. Determination of the Psb28 binding site and other biochemical evidence allow us to propose a mechanism by which Psb28 exerts its protective effect on the RC47 intermediate. This study also shows that isotope-encoded cross-linking with the “mass tags” selection criteria allows confident identification of more cross-linked peptides in PSII than has been previously reported. This approach thus holds promise to identify other transient protein–protein interactions in membrane protein complexes.

scholarly journals Protein-protein docking using learned three-dimensional representations

2019 ◽  
Author(s):  
Georgy Derevyanko ◽  
Guillaume Lamoureux
Keyword(s):  
Protein Interactions ◽  
Network Architecture ◽  
Protein Complexes ◽  
Three Dimensional ◽  
Spatial Arrangement ◽  
Protein Docking ◽  
Protein Protein Interactions ◽  
Translational Invariance ◽  
Shape Complementarity ◽  
Spatial Features

AbstractProtein-protein interactions are determined by a number of hard-to-capture features related to shape complementarity, electrostatics, and hydrophobicity. These features may be intrinsic to the protein or induced by the presence of a partner. A conventional approach to protein-protein docking consists in engineering a small number of spatial features for each protein, and in minimizing the sum of their correlations with respect to the spatial arrangement of the two proteins. To generalize this approach, we introduce a deep neural network architecture that transforms the raw atomic densities of each protein into complex three-dimensional representations. Each point in the volume containing the protein is described by 48 learned features, which are correlated and combined with the features of a second protein to produce a score dependent on the relative position and orientation of the two proteins. The architecture is based on multiple layers of SE(3)-equivariant convolutional neural networks, which provide built-in rotational and translational invariance of the score with respect to the structure of the complex. The model is trained end-to-end on a set of decoy conformations generated from 851 nonredundant protein-protein complexes and is tested on data from the Protein-Protein Docking Benchmark Version 4.0.

scholarly journals Aligning text mining and machine learning algorithms with best practices for study selection in systematic literature reviews

2020 ◽  
Vol 9 (1) ◽  
Author(s):  
E. Popoff ◽  
M. Besada ◽  
J. P. Jansen ◽  
S. Cope ◽  
S. Kanters
Keyword(s):  
Machine Learning ◽  
Text Mining ◽  
Sensitivity And Specificity ◽  
Full Text ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Support Vector ◽  
Study Selection ◽  
Literature Reviews

Abstract Background Despite existing research on text mining and machine learning for title and abstract screening, the role of machine learning within systematic literature reviews (SLRs) for health technology assessment (HTA) remains unclear given lack of extensive testing and of guidance from HTA agencies. We sought to address two knowledge gaps: to extend ML algorithms to provide a reason for exclusion—to align with current practices—and to determine optimal parameter settings for feature-set generation and ML algorithms. Methods We used abstract and full-text selection data from five large SLRs (n = 3089 to 12,769 abstracts) across a variety of disease areas. Each SLR was split into training and test sets. We developed a multi-step algorithm to categorize each citation into the following categories: included; excluded for each PICOS criterion; or unclassified. We used a bag-of-words approach for feature-set generation and compared machine learning algorithms using support vector machines (SVMs), naïve Bayes (NB), and bagged classification and regression trees (CART) for classification. We also compared alternative training set strategies: using full data versus downsampling (i.e., reducing excludes to balance includes/excludes because machine learning algorithms perform better with balanced data), and using inclusion/exclusion decisions from abstract versus full-text screening. Performance comparisons were in terms of specificity, sensitivity, accuracy, and matching the reason for exclusion. Results The best-fitting model (optimized sensitivity and specificity) was based on the SVM algorithm using training data based on full-text decisions, downsampling, and excluding words occurring fewer than five times. The sensitivity and specificity of this model ranged from 94 to 100%, and 54 to 89%, respectively, across the five SLRs. On average, 75% of excluded citations were excluded with a reason and 83% of these citations matched the reviewers’ original reason for exclusion. Sensitivity significantly improved when both downsampling and abstract decisions were used. Conclusions ML algorithms can improve the efficiency of the SLR process and the proposed algorithms could reduce the workload of a second reviewer by identifying exclusions with a relevant PICOS reason, thus aligning with HTA guidance. Downsampling can be used to improve study selection, and improvements using full-text exclusions have implications for a learn-as-you-go approach.

scholarly journals PPI_SVM: Prediction of protein-protein interactions using machine learning, domain-domain affinities and frequency tables

2011 ◽  
Vol 16 (2) ◽  
Author(s):  
Piyali Chatterjee ◽  
Subhadip Basu ◽  
Mahantapas Kundu ◽  
Mita Nasipuri ◽  
Dariusz Plewczynski
Keyword(s):  
Machine Learning ◽  
Protein Interactions ◽  
Three Dimensional ◽  
Prediction Method ◽  
Protein Sequences ◽  
Dimensional Structure ◽  
Support Vector ◽  
Interacting Proteins ◽  
Protein Protein Interactions ◽  
Protein Functions

AbstractProtein-protein interactions (PPI) control most of the biological processes in a living cell. In order to fully understand protein functions, a knowledge of protein-protein interactions is necessary. Prediction of PPI is challenging, especially when the three-dimensional structure of interacting partners is not known. Recently, a novel prediction method was proposed by exploiting physical interactions of constituent domains. We propose here a novel knowledge-based prediction method, namely PPI_SVM, which predicts interactions between two protein sequences by exploiting their domain information. We trained a two-class support vector machine on the benchmarking set of pairs of interacting proteins extracted from the Database of Interacting Proteins (DIP). The method considers all possible combinations of constituent domains between two protein sequences, unlike most of the existing approaches. Moreover, it deals with both single-domain proteins and multi domain proteins; therefore it can be applied to the whole proteome in high-throughput studies. Our machine learning classifier, following a brainstorming approach, achieves accuracy of 86%, with specificity of 95%, and sensitivity of 75%, which are better results than most previous methods that sacrifice recall values in order to boost the overall precision. Our method has on average better sensitivity combined with good selectivity on the benchmarking dataset. The PPI_SVM source code, train/test datasets and supplementary files are available freely in the public domain at: http://code.google.com/p/cmater-bioinfo/.

scholarly journals New machine learning and physics-based scoring functions for drug discovery

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Isabella A. Guedes ◽  
André M. S. Barreto ◽  
Diogo Marinho ◽  
Eduardo Krempser ◽  
Mélaine A. Kuenemann ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Protein Interactions ◽  
In Silico ◽  
Drug Targets ◽  
Support Vector ◽  
Scoring Functions ◽  
Protein Protein Interactions ◽  
Energy Prediction ◽  
Original Class

AbstractScoring functions are essential for modern in silico drug discovery. However, the accurate prediction of binding affinity by scoring functions remains a challenging task. The performance of scoring functions is very heterogeneous across different target classes. Scoring functions based on precise physics-based descriptors better representing protein–ligand recognition process are strongly needed. We developed a set of new empirical scoring functions, named DockTScore, by explicitly accounting for physics-based terms combined with machine learning. Target-specific scoring functions were developed for two important drug targets, proteases and protein–protein interactions, representing an original class of molecules for drug discovery. Multiple linear regression (MLR), support vector machine and random forest algorithms were employed to derive general and target-specific scoring functions involving optimized MMFF94S force-field terms, solvation and lipophilic interactions terms, and an improved term accounting for ligand torsional entropy contribution to ligand binding. DockTScore scoring functions demonstrated to be competitive with the current best-evaluated scoring functions in terms of binding energy prediction and ranking on four DUD-E datasets and will be useful for in silico drug design for diverse proteins as well as for specific targets such as proteases and protein–protein interactions. Currently, the MLR DockTScore is available at www.dockthor.lncc.br.

pyDockEneRes: per-residue decomposition of protein–protein docking energy

2019 ◽  
Vol 36 (7) ◽  
pp. 2284-2285 ◽  
Author(s):  
Miguel Romero-Durana ◽  
Brian Jiménez-García ◽  
Juan Fernández-Recio
Keyword(s):  
Binding Affinity ◽  
Protein Interactions ◽  
Structural Model ◽  
Protein Complexes ◽  
Complex Structure ◽  
Protein Docking ◽  
Supplementary Information ◽  
Scoring Functions ◽  
Residue Decomposition ◽  
Docking Energy

Abstract Motivation Protein–protein interactions are key to understand biological processes at the molecular level. As a complement to experimental characterization of protein interactions, computational docking methods have become useful tools for the structural and energetics modeling of protein–protein complexes. A key aspect of such algorithms is the use of scoring functions to evaluate the generated docking poses and try to identify the best models. When the scoring functions are based on energetic considerations, they can help not only to provide a reliable structural model for the complex, but also to describe energetic aspects of the interaction. This is the case of the scoring function used in pyDock, a combination of electrostatics, desolvation and van der Waals energy terms. Its correlation with experimental binding affinity values of protein–protein complexes was explored in the past, but the per-residue decomposition of the docking energy was never systematically analyzed. Results Here, we present pyDockEneRes (pyDock Energy per-Residue), a web server that provides pyDock docking energy partitioned at the residue level, giving a much more detailed description of the docking energy landscape. Additionally, pyDockEneRes computes the contribution to the docking energy of the side-chain atoms. This fast approach can be applied to characterize a complex structure in order to identify energetically relevant residues (hot-spots) and estimate binding affinity changes upon mutation to alanine. Availability and implementation The server does not require registration by the user and is freely accessible for academics at https://life.bsc.es/pid/pydockeneres. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Harnessing protein folding neural networks for peptide–protein docking

2022 ◽  
Vol 13 (1) ◽  
Author(s):  
Tomer Tsaban ◽  
Julia K. Varga ◽  
Orly Avraham ◽  
Ziv Ben-Aharon ◽  
Alisa Khramushin ◽  
...  
Keyword(s):  
Neural Networks ◽  
Conformational Changes ◽  
Protein Interactions ◽  
Protein Complexes ◽  
Protein Docking ◽  
Great Promise ◽  
Learning Approaches ◽  
Multiple Sequence ◽  
Starting Point ◽  
Wide Range

AbstractHighly accurate protein structure predictions by deep neural networks such as AlphaFold2 and RoseTTAFold have tremendous impact on structural biology and beyond. Here, we show that, although these deep learning approaches have originally been developed for the in silico folding of protein monomers, AlphaFold2 also enables quick and accurate modeling of peptide–protein interactions. Our simple implementation of AlphaFold2 generates peptide–protein complex models without requiring multiple sequence alignment information for the peptide partner, and can handle binding-induced conformational changes of the receptor. We explore what AlphaFold2 has memorized and learned, and describe specific examples that highlight differences compared to state-of-the-art peptide docking protocol PIPER-FlexPepDock. These results show that AlphaFold2 holds great promise for providing structural insight into a wide range of peptide–protein complexes, serving as a starting point for the detailed characterization and manipulation of these interactions.

Application of Machine Learning Approaches for Protein-protein Interactions Prediction

2017 ◽  
Vol 13 (6) ◽  
Author(s):  
Mengying Zhang ◽  
Qiang Su ◽  
Yi Lu ◽  
Manman Zhao ◽  
Bing Niu
Keyword(s):  
Machine Learning ◽  
Protein Interactions ◽  
Learning Approaches ◽  
Protein Protein Interactions
Sign in / Sign up

Export Citation Format

Share Document