Search for: All records

Abstract MotivationThousands of genomes are publicly available, however, most genes in those genomes have poorly defined functions. This is partly due to a gap between previously published, experimentally characterized protein activities and activities deposited in databases. This activity deposition is bottlenecked by the time-consuming biocuration process. The emergence of large language models presents an opportunity to speed up the text-mining of protein activities for biocuration. ResultsWe developed FuncFetch—a workflow that integrates NCBI E-Utilities, OpenAI’s GPT-4, and Zotero—to screen thousands of manuscripts and extract enzyme activities. Extensive validation revealed high precision and recall of GPT-4 in determining whether the abstract of a given paper indicates the presence of a characterized enzyme activity in that paper. Provided the manuscript, FuncFetch extracted data such as species information, enzyme names, sequence identifiers, substrates, and products, which were subjected to extensive quality analyses. Comparison of this workflow against a manually curated dataset of BAHD acyltransferase activities demonstrated a precision/recall of 0.86/0.64 in extracting substrates. We further deployed FuncFetch on nine large plant enzyme families. Screening 26 543 papers, FuncFetch retrieved 32 605 entries from 5459 selected papers. We also identified multiple extraction errors including incorrect associations, nontarget enzymes, and hallucinations, which highlight the need for further manual curation. The BAHD activities were verified, resulting in a comprehensive functional fingerprint of this family and revealing that ∼70% of the experimentally characterized enzymes are uncurated in the public domain. FuncFetch represents an advance in biocuration and lays the groundwork for predicting the functions of uncharacterized enzymes. Availability and implementationCode and minimally curated activities are available at: https://github.com/moghelab/funcfetch and https://tools.moghelab.org/funczymedb. 

Abstract MotivationGene set enrichment (GSE) analysis allows for an interpretation of gene expression through pre-defined gene set databases and is a critical step in understanding different phenotypes. With the rapid development of single-cell RNA sequencing (scRNA-seq) technology, GSE analysis can be performed on fine-grained gene expression data to gain a nuanced understanding of phenotypes of interest. However, with the cellular heterogeneity in single-cell gene profiles, current statistical GSE analysis methods sometimes fail to identify enriched gene sets. Meanwhile, deep learning has gained traction in applications like clustering and trajectory inference in single-cell studies due to its prowess in capturing complex data patterns. However, its use in GSE analysis remains limited, due to interpretability challenges. ResultsIn this paper, we present DeepGSEA, an explainable deep gene set enrichment analysis approach which leverages the expressiveness of interpretable, prototype-based neural networks to provide an in-depth analysis of GSE. DeepGSEA learns the ability to capture GSE information through our designed classification tasks, and significance tests can be performed on each gene set, enabling the identification of enriched sets. The underlying distribution of a gene set learned by DeepGSEA can be explicitly visualized using the encoded cell and cellular prototype embeddings. We demonstrate the performance of DeepGSEA over commonly used GSE analysis methods by examining their sensitivity and specificity with four simulation studies. In addition, we test our model on three real scRNA-seq datasets and illustrate the interpretability of DeepGSEA by showing how its results can be explained. Availability and implementationhttps://github.com/Teddy-XiongGZ/DeepGSEA 

Abstract MotivationTimetrees depict evolutionary relationships between species and the geological times of their divergence. Hundreds of research articles containing timetrees are published in scientific journals every year. The TimeTree (TT) project has been manually locating, curating and synthesizing timetrees from these articles for almost two decades into a TimeTree of Life, delivered through a unique, user-friendly web interface (timetree.org). The manual process of finding articles containing timetrees is becoming increasingly expensive and time-consuming. So, we have explored the effectiveness of text-mining approaches and developed optimizations to find research articles containing timetrees automatically. ResultsWe have developed an optimized machine learning system to determine if a research article contains an evolutionary timetree appropriate for inclusion in the TT resource. We found that BERT classification fine-tuned on whole-text articles achieved an F1 score of 0.67, which we increased to 0.88 by text-mining article excerpts surrounding the mentioning of figures. The new method is implemented in the TimeTreeFinder (TTF) tool, which automatically processes millions of articles to discover timetree-containing articles. We estimate that the TTF tool would produce twice as many timetree-containing articles as those discovered manually, whose inclusion in the TT database would potentially double the knowledge accessible to a wider community. Manual inspection showed that the precision on out-of-distribution recently published articles is 87%. This automation will speed up the collection and curation of timetrees with much lower human and time costs. Availability and implementationhttps://github.com/marija-stanojevic/time-tree-classification. Supplementary informationSupplementary data are available at Bioinformatics online. 

Abstract MotivationProperties of molecules are indicative of their functions and thus are useful in many applications. With the advances of deep-learning methods, computational approaches for predicting molecular properties are gaining increasing momentum. However, there lacks customized and advanced methods and comprehensive tools for this task currently. ResultsHere, we develop a suite of comprehensive machine-learning methods and tools spanning different computational models, molecular representations and loss functions for molecular property prediction and drug discovery. Specifically, we represent molecules as both graphs and sequences. Built on these representations, we develop novel deep models for learning from molecular graphs and sequences. In order to learn effectively from highly imbalanced datasets, we develop advanced loss functions that optimize areas under precision–recall curves (PRCs) and receiver operating characteristic (ROC) curves. Altogether, our work not only serves as a comprehensive tool, but also contributes toward developing novel and advanced graph and sequence-learning methodologies. Results on both online and offline antibiotics discovery and molecular property prediction tasks show that our methods achieve consistent improvements over prior methods. In particular, our methods achieve #1 ranking in terms of both ROC-AUC (area under curve) and PRC-AUC on the AI Cures open challenge for drug discovery related to COVID-19. Availability and implementationOur source code is released as part of the MoleculeX library (https://github.com/divelab/MoleculeX) under AdvProp. Supplementary informationSupplementary data are available at Bioinformatics online. 

Abstract MotivationAccurately predicting drug–target interactions (DTIs) in silico can guide the drug discovery process and thus facilitate drug development. Computational approaches for DTI prediction that adopt the systems biology perspective generally exploit the rationale that the properties of drugs and targets can be characterized by their functional roles in biological networks. ResultsInspired by recent advance of information passing and aggregation techniques that generalize the convolution neural networks to mine large-scale graph data and greatly improve the performance of many network-related prediction tasks, we develop a new nonlinear end-to-end learning model, called NeoDTI, that integrates diverse information from heterogeneous network data and automatically learns topology-preserving representations of drugs and targets to facilitate DTI prediction. The substantial prediction performance improvement over other state-of-the-art DTI prediction methods as well as several novel predicted DTIs with evidence supports from previous studies have demonstrated the superior predictive power of NeoDTI. In addition, NeoDTI is robust against a wide range of choices of hyperparameters and is ready to integrate more drug and target related information (e.g. compound–protein binding affinity data). All these results suggest that NeoDTI can offer a powerful and robust tool for drug development and drug repositioning. Availability and implementationThe source code and data used in NeoDTI are available at: https://github.com/FangpingWan/NeoDTI. Supplementary informationSupplementary data are available at Bioinformatics online. 

Abstract MotivationThe development of proteomic methods for the characterization of domain/motif interactions has greatly expanded our understanding of signal transduction. However, proteomics-based binding screens have limitations including that the queried tissue or cell type may not harbor all potential interacting partners or post-translational modifications (PTMs) required for the interaction. Therefore, we sought a generalizable, complementary in silico approach to identify potentially novel motif and PTM-dependent binding partners of high priority. ResultsWe used as an initial example the interaction between the Src homology 2 (SH2) domains of the adaptor proteins CT10 regulator of kinase (CRK) and CRK-like (CRKL) and phosphorylated-YXXP motifs. Employing well-curated, publicly-available resources, we scored and prioritized potential CRK/CRKL–SH2 interactors possessing signature characteristics of known interacting partners. Our approach gave high priority scores to 102 of the >9000 YXXP motif-containing proteins. Within this 102 were 21 of the 25 curated CRK/CRKL–SH2-binding partners showing a more than 80-fold enrichment. Several predicted interactors were validated biochemically. To demonstrate generalized applicability, we used our workflow to predict protein–protein interactions dependent upon motif-specific arginine methylation. Our data demonstrate the applicability of our approach to, conceivably, any modular binding domain that recognizes a specific post-translationally modified motif. Supplementary informationSupplementary data are available at Bioinformatics online. 

Abstract SummarySequencing data resources have increased exponentially in recent years, as has interest in large-scale meta-analyses of integrated next-generation sequencing datasets. However, curation of integrated datasets that match a user’s particular research priorities is currently a time-intensive and imprecise task. MetaSeek is a sequencing data discovery tool that enables users to flexibly search and filter on any metadata field to quickly find the sequencing datasets that meet their needs. MetaSeek automatically scrapes metadata from all publicly available datasets in the Sequence Read Archive, cleans and parses messy, user-provided metadata into a structured, standard-compliant database and predicts missing fields where possible. MetaSeek provides a web-based graphical user interface and interactive visualization dashboard, as well as a programmatic API to rapidly search, filter, visualize, save, share and download matching sequencing metadata. Availability and implementationThe MetaSeek online interface is available at https://www.metaseek.cloud/. The MetaSeek database can also be accessed via API to programmatically search, filter and download all metadata. MetaSeek source code, metadata scrapers and documents are available at https://github.com/MetaSeek-Sequencing-Data-Discovery/metaseek/. 

Abstract SummaryDifferential Expression Gene Explorer (DrEdGE) is a web-based tool that guides genomicists through easily creating interactive online data visualizations, which colleagues can query according to their own conditions to discover genes, samples or patterns of interest. We demonstrate DrEdGE’s features with three example websites generated from publicly available datasets—human neuronal tissue, mouse embryonic tissue and Caenorhabditis elegans whole embryos. DrEdGE increases the utility of large genomics datasets by removing technical obstacles to independent exploration. Availability and implementationFreely available at http://dredge.bio.unc.edu. Supplementary informationSupplementary data are available at Bioinformatics online.