Structure-templated predictions of novel protein interactions from sequence information.
Ontology highlight
ABSTRACT:
SUBMITTER: Betel D
PROVIDER: S-EPMC1988853 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:We combine advances in neural language modeling and structurally motivated design to develop D-SCRIPT, an interpretable and generalizable deep-learning model, which predicts interaction between two proteins using only their sequence and maintains high accuracy with limited training data and across species. We show that a D-SCRIPT model trained on 38,345 human PPIs enables significantly improved functional characterization of fly proteins compared with the state-of-the-art approach. Evaluating the same D-SCRIPT model on protein complexes with known 3D structure, we find that the inter-protein contact map output by D-SCRIPT has significant overlap with the ground truth. We apply D-SCRIPT to screen for PPIs in cow (Bos taurus) at a genome-wide scale and focusing on rumen physiology, identify functional gene modules related to metabolism and immune response. The predicted interactions can then be leveraged for function prediction at scale, addressing the genome-to-phenome challenge, especially in species where little data are available.
| S-EPMC8586911 | biostudies-literature
Project description:BackgroundRNA-protein interactions (RPIs) play important roles in a wide variety of cellular processes, ranging from transcriptional and post-transcriptional regulation of gene expression to host defense against pathogens. High throughput experiments to identify RNA-protein interactions are beginning to provide valuable information about the complexity of RNA-protein interaction networks, but are expensive and time consuming. Hence, there is a need for reliable computational methods for predicting RNA-protein interactions.ResultsWe propose RPISeq, a family of classifiers for predicting RNA-protein interactions using only sequence information. Given the sequences of an RNA and a protein as input, RPIseq predicts whether or not the RNA-protein pair interact. The RNA sequence is encoded as a normalized vector of its ribonucleotide 4-mer composition, and the protein sequence is encoded as a normalized vector of its 3-mer composition, based on a 7-letter reduced alphabet representation. Two variants of RPISeq are presented: RPISeq-SVM, which uses a Support Vector Machine (SVM) classifier and RPISeq-RF, which uses a Random Forest classifier. On two non-redundant benchmark datasets extracted from the Protein-RNA Interface Database (PRIDB), RPISeq achieved an AUC (Area Under the Receiver Operating Characteristic (ROC) curve) of 0.96 and 0.92. On a third dataset containing only mRNA-protein interactions, the performance of RPISeq was competitive with that of a published method that requires information regarding many different features (e.g., mRNA half-life, GO annotations) of the putative RNA and protein partners. In addition, RPISeq classifiers trained using the PRIDB data correctly predicted the majority (57-99%) of non-coding RNA-protein interactions in NPInter-derived networks from E. coli, S. cerevisiae, D. melanogaster, M. musculus, and H. sapiens.ConclusionsOur experiments with RPISeq demonstrate that RNA-protein interactions can be reliably predicted using only sequence-derived information. RPISeq offers an inexpensive method for computational construction of RNA-protein interaction networks, and should provide useful insights into the function of non-coding RNAs. RPISeq is freely available as a web-based server at http://pridb.gdcb.iastate.edu/RPISeq/.
| S-EPMC3322362 | biostudies-literature
Project description:Although residue-residue contact maps dictate the topology of proteins, sequence-based ab initio contact predictions have been found little use in actual structure prediction due to the low accuracy. We developed a composite set of nine SVM-based contact predictors that are used in I-TASSER simulation in combination with sparse template contact restraints. When testing the strategy on 273 nonhomologous targets, remarkable improvements of I-TASSER models were observed for both easy and hard targets, with p value by Student's t test<0.00001 and 0.001, respectively. In several cases, template modeling score increases by >30%, which essentially converts "nonfoldable" targets into "foldable" ones. In CASP9, I-TASSER employed ab initio contact predictions, and generated models for 26 FM targets with a GDT-score 16% and 44% higher than the second and third best servers from other groups, respectively. These findings demonstrate a new avenue to improve the accuracy of protein structure prediction especially for free-modeling targets.
| S-EPMC3154634 | biostudies-literature
Project description:BackgroundDevelopment of new methods for analysis of protein-protein interactions (PPIs) at molecular and nanometer scales gives insights into intracellular signaling pathways and will improve understanding of protein functions, as well as other nanoscale structures of biological and abiological origins. Recent advances in computational tools, particularly the ones involving modern deep learning algorithms, have been shown to complement experimental approaches for describing and rationalizing PPIs. However, most of the existing works on PPI predictions use protein-sequence information, and thus have difficulties in accounting for the three-dimensional organization of the protein chains.ResultsIn this study, we address this problem and describe a PPI analysis based on a graph attention network, named Struct2Graph, for identifying PPIs directly from the structural data of folded protein globules. Our method is capable of predicting the PPI with an accuracy of 98.89% on the balanced set consisting of an equal number of positive and negative pairs. On the unbalanced set with the ratio of 1:10 between positive and negative pairs, Struct2Graph achieves a fivefold cross validation average accuracy of 99.42%. Moreover, Struct2Graph can potentially identify residues that likely contribute to the formation of the protein-protein complex. The identification of important residues is tested for two different interaction types: (a) Proteins with multiple ligands competing for the same binding area, (b) Dynamic protein-protein adhesion interaction. Struct2Graph identifies interacting residues with 30% sensitivity, 89% specificity, and 87% accuracy.ConclusionsIn this manuscript, we address the problem of prediction of PPIs using a first of its kind, 3D-structure-based graph attention network (code available at https://github.com/baranwa2/Struct2Graph ). Furthermore, the novel mutual attention mechanism provides insights into likely interaction sites through its unsupervised knowledge selection process. This study demonstrates that a relatively low-dimensional feature embedding learned from graph structures of individual proteins outperforms other modern machine learning classifiers based on global protein features. In addition, through the analysis of single amino acid variations, the attention mechanism shows preference for disease-causing residue variations over benign polymorphisms, demonstrating that it is not limited to interface residues.
| S-EPMC9464414 | biostudies-literature
Project description:Protein structure prediction has a number of important ad hoc similarity measures for evaluating predictions, but would benefit from a measure that is able to provide a common framework for a broad range of comparisons. Here we show that a mutual information-like measure can provide a comprehensive framework for evaluating protein structure prediction of all types. We discuss the concept of information, its application to secondary structure, and the obstacle to applying it to 3D structure. On the basis of the insights from the secondary structure case, we present an approach to work around the 3D difficulties, and develop a method to measure the mutual information provided by a 3D structure prediction. We integrate the evaluation of all types of protein structure prediction into a single framework, and compare the amount of information provided by various prediction methods, including secondary structure prediction. Within this broadened framework, the idea that structure is better preserved than sequence during evolution is evaluated quantitatively for the globin family. A nearly perfect sequence match in the globin family corresponds to about 300 bits of information, whereas a nearly perfect structural match for the same two proteins corresponds to about 2500 bits of information, where bits of information describes the probability of obtaining a match of similar closeness by chance. Mutual information provides both a theoretical basis for evaluating structure similarity and an explanatory surround for existing similarity measures.
| S-EPMC2629808 | biostudies-literature
Project description:Distant homologies between proteins are often discovered only after three-dimensional structures of both proteins are solved. The sequence divergence for such proteins can be so large that simple comparison of their sequences fails to identify any similarity. New generation of sensitive alignment tools use averaged sequences of entire homologous families (profiles) to detect such homologies. Several algorithms, including the newest generation of BLAST algorithms and BASIC, an algorithm used in our group to assign fold predictions for proteins from several genomes, are compared to each other on the large set of structurally similar proteins with little sequence similarity. Proteins in the benchmark are classified according to the level of their similarity, which allows us to demonstrate that most of the improvement of the new algorithms is achieved for proteins with strong functional similarities, with almost no progress in recognizing distant fold similarities. It is also shown that details of profile calculation strongly influence its sensitivity in recognizing distant homologies. The most important choice is how to include information from diverging members of the family, avoiding generating false predictions, while accounting for entire sequence divergence within a family. PSI-BLAST takes a conservative approach, deriving a profile from core members of the family, providing a solid improvement without almost any false predictions. BASIC strives for better sensitivity by increasing the weight of divergent family members and paying the price in lower reliability. A new FFAS algorithm introduced here uses a new procedure for profile generation that takes into account all the relations within the family and matches BASIC sensitivity with PSI-BLAST like reliability.
| S-EPMC2144550 | biostudies-other
Project description:Infection by the human blood fluke, Schistosoma mansoni involves a variety of cross-species protein- protein interactions. The pathogen expresses a diverse arsenal of proteins that facilitate the breach of physical and biochemical barriers present in skin evasion of the immune system, and digestion of human plasma proteins including albumin and hemoglobin, allowing schistosomes to reside in the host for years. However, only a small number of specific interactions between S. mansoni and human proteins have been identified. We present and apply a protocol that generates testable predictions of S. mansoni-human protein interactions. In this study, we have preliminary predictions of novel interactions between schistosome and human proteins relevant to infection and the ability of the parasite to evade the immune system. We applied a computational whole-genome comparative approach to predict potential S. mansoni-human protein interactions based on similarity to known protein complexes. We first predict S. mansoni -human protein interactions based on similarity to known protein complexes. Putative interactions were then scored and assessed using several contextual filters, including the use of annotation automatically derived from literature using a simple natural language processing methodology. Next, in vitro experiments were carried out between schistosome and host proteins to validate several prospective predictions. Our method predicted 7 out of the 10 previously known cross-species interactions involved in pathogenesis between S. mansoni and its human host. Interestingly, two novel putative interactions involving Schistosoma proteins, the cercarial elastase SmCE, and the adult tegument surface protein Sm29, were also predicted and experimentally characterized. Preliminary data suggest that elafin, a host endogenous serine protease inhibitor, may be a novel substrate for SmCE. Additionally, CD59, an inhibitor of the membrane attack complex, could interact with Sm29. Furthermore, the application framework provides an integrated methodology for investigation of host-pathogen interactions and an extensive source of orthogonal data for experimental analysis. We have made the predictions available for community perusal.
| S-EPMC6117258 | biostudies-literature
Project description:Pre-trained deep Transformers have had tremendous success in a wide variety of disciplines. However, in computational biology, essentially all Transformers are built upon the biological sequences, which ignores vital stereochemical information and may result in crucial errors in downstream predictions. On the other hand, three-dimensional (3D) molecular structures are incompatible with the sequential architecture of Transformer and natural language processing (NLP) models in general. This work addresses this foundational challenge by a topological Transformer (TopoFormer). TopoFormer is built by integrating NLP and a multiscale topology techniques, the persistent topological hyperdigraph Laplacian (PTHL), which systematically converts intricate 3D protein-ligand complexes at various spatial scales into a NLP-admissible sequence of topological invariants and homotopic shapes. Element-specific PTHLs are further developed to embed crucial physical, chemical, and biological interactions into topological sequences. TopoFormer surges ahead of conventional algorithms and recent deep learning variants and gives rise to exemplary scoring accuracy and superior performance in ranking, docking, and screening tasks in a number of benchmark datasets. The proposed topological sequences can be extracted from all kinds of structural data in data science to facilitate various NLP models, heralding a new era in AI-driven discovery.
| S-EPMC10889053 | biostudies-literature
Project description:BackgroundAccurate identification of potential interactions between drugs and protein targets is a critical step to accelerate drug discovery. Despite many relative experimental researches have been done in the past decades, detecting drug-target interactions (DTIs) remains to be extremely resource-intensive and time-consuming. Therefore, many computational approaches have been developed for predicting drug-target associations on a large scale.ResultsIn this paper, we proposed an deep learning-based method to predict DTIs only using the information of drug structures and protein sequences. The final results showed that our method can achieve good performance with the accuracies up to 92.0%, 90.0%, 92.0% and 90.7% for the target families of enzymes, ion channels, GPCRs and nuclear receptors of our created dataset, respectively. Another dataset derived from DrugBank was used to further assess the generalization of the model, which yielded an accuracy of 0.9015 and an AUC value of 0.9557.ConclusionIt was elucidated that our model shows improved performance in comparison with other state-of-the-art computational methods on the common benchmark datasets. Experimental results demonstrated that our model successfully extracted more nuanced yet useful features, and therefore can be used as a practical tool to discover new drugs.Availabilityhttp://deeplearner.ahu.edu.cn/web/CnnDTI.htm.
| S-EPMC6929541 | biostudies-literature
Project description:The structures of protein complexes are increasingly predicted via protein-protein docking (PPD) using ambiguous interaction data to help guide the docking. These data often are incomplete and contain errors and therefore could lead to incorrect docking predictions. In this study, we performed a series of PPD simulations to examine the effects of incompletely and incorrectly assigned interface residues on the success rate of PPD predictions. The results for a widely used PPD benchmark dataset obtained using a new interface information-driven PPD (IPPD) method developed in this work showed that the success rate for an acceptable top-ranked model varied, depending on the information content used, from as high as 95% when contact relationships (though not contact distances) were known for all residues to 78% when only the interface/non-interface state of the residues was known. However, the success rates decreased rapidly to ?40% when the interface/non-interface state of 20% of the residues was assigned incorrectly, and to less than 5% for a 40% incorrect assignment. Comparisons with results obtained by re-ranking a global search and with those reported for other data-guided PPD methods showed that, in general, IPPD performed better than re-ranking when the information used was more complete and more accurate, but worse when it was not, and that when using bioinformatics-predicted information on interface residues, IPPD and other data-guided PPD methods performed poorly, at a level similar to simulations with a 40% incorrect assignment. These results provide guidelines for using information about interface residues to improve PPD predictions and reveal a bottleneck for such improvement imposed by the low accuracy of current bioinformatic interface residue predictions.
| S-EPMC3591660 | biostudies-literature