Search for: All records

Abstract MotivationAccurately predicting the likelihood of interaction between two objects (compound–protein sequence, user–item, author–paper, etc.) is a fundamental problem in Computer Science. Current deep-learning models rely on learning accurate representations of the interacting objects. Importantly, relationships between the interacting objects, or features of the interaction, offer an opportunity to partition the data to create multi-views of the interacting objects. The resulting congruent and non-congruent views can then be exploited via contrastive learning techniques to learn enhanced representations of the objects. ResultsWe present a novel method, Contrastive Stratification for Interaction Prediction (CSI), to stratify (partition) a dataset in a manner that can be exploited via Contrastive Multiview Coding to learn embeddings that maximize the mutual information across congruent data views. CSI assigns a key and multiple views to each data point, where data partitions under a particular key form congruent views of the data. We showcase the effectiveness of CSI by applying it to the compound–protein sequence interaction prediction problem, a pressing problem whose solution promises to expedite drug delivery (drug–protein interaction prediction), metabolic engineering, and synthetic biology (compound–enzyme interaction prediction) applications. Comparing CSI with a baseline model that does not utilize data stratification and contrastive learning, and show gains in average precision ranging from 13.7% to 39% using compounds and sequences as keys across multiple drug–target and enzymatic datasets, and gains ranging from 16.9% to 63% using reaction features as keys across enzymatic datasets. Availability and implementationCode and dataset available at https://github.com/HassounLab/CSI. 

Abstract MotivationWhile traditionally utilized for identifying site-specific metabolic activity within a compound to alter its interaction with a metabolizing enzyme, predicting the site-of-metabolism (SOM) is essential in analyzing the promiscuity of enzymes on substrates. The successful prediction of SOMs and the relevant promiscuous products has a wide range of applications that include creating extended metabolic models (EMMs) that account for enzyme promiscuity and the construction of novel heterologous synthesis pathways. There is therefore a need to develop generalized methods that can predict molecular SOMs for a wide range of metabolizing enzymes. ResultsThis article develops a Graph Neural Network (GNN) model for the classification of an atom (or a bond) being an SOM. Our model, GNN-SOM, is trained on enzymatic interactions, available in the KEGG database, that span all enzyme commission numbers. We demonstrate that GNN-SOM consistently outperforms baseline machine learning models, when trained on all enzymes, on Cytochrome P450 (CYP) enzymes, or on non-CYP enzymes. We showcase the utility of GNN-SOM in prioritizing predicted enzymatic products due to enzyme promiscuity for two biological applications: the construction of EMMs and the construction of synthesis pathways. Availability and implementationA python implementation of the trained SOM predictor model can be found at https://github.com/HassounLab/GNN-SOM. Supplementary informationSupplementary data are available at Bioinformatics online. 

Abstract SummaryLow-complexity domains (LCDs) in proteins are regions enriched in a small subset of amino acids. LCDs exist in all domains of life, often have unusual biophysical behavior, and function in both normal and pathological processes. We recently developed an algorithm to identify LCDs based predominantly on amino acid composition thresholds. Here, we have integrated this algorithm with a webserver and augmented it with additional analysis options. Specifically, users can (i) search for LCDs in whole proteomes by setting minimum composition thresholds for individual or grouped amino acids, (ii) submit a known LCD sequence to search for similar LCDs, (iii) search for and plot LCDs within a single protein, (iv) statistically test for enrichment of LCDs within a user-provided protein set and (v) specifically identify proteins with multiple types of LCDs. Availability and implementationThe LCD-Composer server can be accessed at http://lcd-composer.bmb.colostate.edu. The corresponding command-line scripts can be accessed at https://github.com/RossLabCSU/LCD-Composer/tree/master/WebserverScripts. 

Abstract MotivationGenome-wide maps of epigenetic modifications are powerful resources for non-coding genome annotation. Maps of multiple epigenetics marks have been integrated into cell or tissue type-specific chromatin state annotations for many cell or tissue types. With the increasing availability of multiple chromatin state maps for biologically similar samples, there is a need for methods that can effectively summarize the information about chromatin state annotations within groups of samples and identify differences across groups of samples at a high resolution. ResultsWe developed CSREP, which takes as input chromatin state annotations for a group of samples. CSREP then probabilistically estimates the state at each genomic position and derives a representative chromatin state map for the group. CSREP uses an ensemble of multi-class logistic regression classifiers that predict the chromatin state assignment of each sample given the state maps from all other samples. The difference in CSREP’s probability assignments for the two groups can be used to identify genomic locations with differential chromatin state assignments. Using groups of chromatin state maps of a diverse set of cell and tissue types, we demonstrate the advantages of using CSREP to summarize chromatin state maps and identify biologically relevant differences between groups at a high resolution. Availability and implementationThe CSREP source code and generated data are available at http://github.com/ernstlab/csrep. Supplementary informationSupplementary data are available at Bioinformatics online. 

Abstract MotivationMHC Class I protein plays an important role in immunotherapy by presenting immunogenic peptides to anti-tumor immune cells. The repertoires of peptides for various MHC Class I proteins are distinct, which can be reflected by their diverse binding motifs. To characterize binding motifs for MHC Class I proteins, in vitro experiments have been conducted to screen peptides with high binding affinities to hundreds of given MHC Class I proteins. However, considering tens of thousands of known MHC Class I proteins, conducting in vitro experiments for extensive MHC proteins is infeasible, and thus a more efficient and scalable way to characterize binding motifs is needed. ResultsWe presented a de novo generation framework, coined PepPPO, to characterize binding motif for any given MHC Class I proteins via generating repertoires of peptides presented by them. PepPPO leverages a reinforcement learning agent with a mutation policy to mutate random input peptides into positive presented ones. Using PepPPO, we characterized binding motifs for around 10 000 known human MHC Class I proteins with and without experimental data. These computed motifs demonstrated high similarities with those derived from experimental data. In addition, we found that the motifs could be used for the rapid screening of neoantigens at a much lower time cost than previous deep-learning methods. Availability and implementationThe software can be found in https://github.com/minrq/pMHC. Supplementary informationSupplementary data are available at Bioinformatics online. 

Abstract MotivationReconstruction of genome-scale networks from gene expression data is an actively studied problem. A wide range of methods that differ between the types of interactions they uncover with varying trade-offs between sensitivity and specificity have been proposed. To leverage benefits of multiple such methods, ensemble network methods that combine predictions from resulting networks have been developed, promising results better than or as good as the individual networks. Perhaps owing to the difficulty in obtaining accurate training examples, these ensemble methods hitherto are unsupervised. ResultsIn this article, we introduce EnGRaiN, the first supervised ensemble learning method to construct gene networks. The supervision for training is provided by small training datasets of true edge connections (positives) and edges known to be absent (negatives) among gene pairs. We demonstrate the effectiveness of EnGRaiN using simulated datasets as well as a curated collection of Arabidopsis thaliana datasets we created from microarray datasets available from public repositories. EnGRaiN shows better results not only in terms of receiver operating characteristic and PR characteristics for both real and simulated datasets compared with unsupervised methods for ensemble network construction, but also generates networks that can be mined for elucidating complex biological interactions. Availability and implementationEnGRaiN software and the datasets used in the study are publicly available at the github repository: https://github.com/AluruLab/EnGRaiN. Supplementary informationSupplementary data are available at Bioinformatics online.