Biology subjects

Webb, G. I.

Publications and source records attributed to Webb, G. I..

8 recordsLinked to original sources

bioRxiv2026

Decoding Cell-type Specific Gene Regulation with CellReg3D by Integrating DNA Large Language Models and 3D Genome Structure

Gene regulation is a core biological mechanism crucial for organismal growth and development. Recent advances in deep learning, coupled with increasing computational resources, have enabled large-scale modelling of gene regulatory processes. While numerous models have been proposed, effectively capturing long-range genomic interactions remains a central challenge. Here, we introduce CellReg3D, a multiscale and multi-modal deep learning framework designed to model cell-type-specific gene regulation by integrating local sequence patterns with long-range genomic interactions. Existing approaches often overlook the contribution of 3D genome architecture and face limitations in combining sequence-based features with chromatin interaction data. Specifically, CellReg3D overcomes these gaps by leveraging a DNA language model to encode sequence-level information and incorporating Hi-C-derived 3D chromatin interactions to capture chromatin spatial organization. We demonstrate that CellReg3D effectively learns epigenetic patterns and chromatin activity states, achieving state-of-the-art performance in predicting epigenetic marks and gene expression profiles across multiple cell types. Using interpretable methods, we illustrate how the model identifies cell-type-specific regulatory mechanisms and prioritizes functional non-coding variants. Furthermore, we apply CellReg3D to enhance the interpretation of expression quantitative trait loci (eQTLs) and uncover novel potential gene regulatory interactions. Overall, CellReg3D offers a integrative framework for decoding regulatory genomics, unifying sequence and 3D genome structure data to advance variant prioritization, disease mechanism discovery, and personalized functional genomics.

bioinformatics↗

bioRxiv2026

Bioactivity foundation model for hit identification and hit-to-lead optimization from sequence data

Learning from large-scale bioactivity archives is complicated by heterogeneous assay readouts and differences in data reliability. Here we show that a model that predicts probability distributions over binding affinities from sequence data opens model training to vast and diverse troves of heterogeneous bioactivity data. We develop PSICHIC+, a bioactivity foundation model trained on approximately 82 million protein-ligand records using a distributional objective that preserves quantitative resolution while incorporating variation in data reliability. Given a protein sequence and ligand SMILES, PSICHIC+ predicts binding affinity in milliseconds. In zero-shot virtual-screening benchmarks without target-specific training data, it improves enrichment over regression- and classification-based approaches and performs competitively with leading structure-based methods. In lab-in-the-loop campaigns, distribution-guided acquisition improves recovery of high-activity compounds under fixed screening budgets. Combining PSICHIC+ with Boltz-2 improves hit-to-lead affinity prediction over Boltz-2 alone, with mean correlation approaching that of FEP+ on the evaluated benchmarks, without requiring high-resolution protein structures. These results support distributional learning as a scalable approach to using heterogeneous bioactivity data for hit identification and hit-to-lead optimization.

bioinformatics↗

bioRxiv2025

KcatNet: advancing genome-wide enzyme turnover number prediction through structural enzymatic characterization

Enzyme turnover numbers (Kcat) are fundamental kinetic constants that quantify enzymatic efficiency. Systematic studies of Kcat are essential for characterizing the mechanisms underlying proteomic composition and cellular metabolism. However, experimental measurements of Kcat remain limited and prone to noise. To address this, we present KcatNet, a geometric deep learning model designed for high-throughput prediction of Kcat in metabolic enzymes across all organisms, leveraging paired enzyme sequence and substrate representations. KcatNet consistently outperforms existing predictors, particularly for enzymes with high catalytic efficiency, and demonstrates strong generalization to enzymes that are dissimilar to those in the training set. Furthermore, KcatNet uncovers structural mechanisms and interaction patterns within enzyme-substrate complexes, providing insights into architectural principles that are inaccessible with existing methods by harnessing the representational power of large-scale protein language models. We applied KcatNet to genome-scale Kcat prediction across diverse yeast species, improving proteome allocation predictions by integrating its outputs into metabolic models. Experimental validation further confirmed the models ability to identify enzyme mutants with enhanced activity. By bridging the gap between sequence, structure, and function, KcatNet establishes a robust foundation for advancing understanding of molecular-level mechanisms and accelerating enzyme engineering efforts.

bioinformatics↗

bioRxiv2024

SCREEN: a graph-based contrastive learning tool to infer catalytic residues and assess mutation tolerance in enzymes

The accurate identification of catalytic residues contributes to our understanding of enzyme functions in biological processes and pathways. The increasing number of protein sequences necessitates computational tools for the automated prediction of catalytic residues in enzymes. Here, we introduce SCREEN, a graph neural network for the high-throughput prediction of catalytic residues via the integration of enzyme functional and structural information. SCREEN constructs residue representations based on spatial arrangements and incorporates enzyme function priors into such representations through contrastive learning. We demonstrate that SCREEN (i) consistently outperforms currently-available predictors; (ii) provides accurate results when applied to inferred enzyme structures; and (iii) generalizes well to enzymes dissimilar from those in the training set. We also show that the putative catalytic residues predicted by SCREEN mimic key structural and biophysical characteristics of native catalytic residues. Moreover, using experimental data sets, we show that SCREENs predictions can be used to distinguish residues with a high mutation tolerance from those likely to cause functional loss when mutated, indicating that this tool might be used to infer disease-associated mutations.

bioinformatics↗

bioRxiv2024

A deep learning-based model integrating base-pairing patterns improves microRNA target site prediction

Micro RNAs (miRNAs) are short non-coding RNAs involved in various cellular processes, playing a crucial role in gene regulation. Identifying miRNA targets remains a central challenge and is pivotal for elucidating the complex gene regulatory networks. Traditional computational approaches have predominantly focused on identifying miRNA targets through perfect Watson-Crick base pairings within the seed region, referred to as canonical sites. However, emerging evidence suggests that perfect seed matches are not a prerequisite for miRNA-mediated regulation, underscoring the importance of also recognizing imperfect, or non-canonical, sites. To address this challenge, we propose Mimosa, a new computational approach that employs the Transformer framework to enhance the prediction of miRNA targets. Mimosa distinguishes itself by integrating contextual, positional, and base-pairing information to capture in-depth attributes, thereby improving its predictive capabilities. Its unique ability to identify non-canonical base-pairing patterns makes Mimosa a standout model, reducing the reliance on pre-selecting candidate targets. Mimosa achieves superior performance in gene-level predictions and also shows impressive performance in site-level predictions across various non-human species through extensive benchmarking tests. To facilitate research efforts in miRNA targeting, we have developed an easy-to-use web server for comprehensive end-to-end predictions, which is publicly available at http://monash.bioweb.cloud.edu.au/Mimosa/.

bioinformatics↗

bioRxiv2023

Predicting Pseudomonas aeruginosa drug resistance using artificial intelligence and clinical MALDI-TOF mass spectra

Matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS) is widely used in clinical microbiology laboratories for bacterial identification but its use for prediction of antimicrobial resistance (AMR) remains limited. Here, we used MALDI-TOF MS with artificial intelligence (AI) approaches to successfully predict AMR in Pseudomonas aeruginosa, a priority pathogen with complex AMR mechanisms. The highest performance was achieved for modern {beta}-lactam/{beta}-lactamase inhibitor drugs, namely ceftazidime/avibactam and ceftolozane/tazobactam, with area under the receiver operating characteristic curve (AUROC) of 0.86 and 0.87, respectively. As part of this work, we developed dynamic binning, a feature engineering technique that effectively reduces the high-dimensional feature set and has wide-ranging applicability to MALDI-TOF MS data. Compared to conventional methods, our approach yielded superior performance in 10 of 11 antimicrobials. Moreover, we showcase the efficacy of transfer learning in enhancing the performance for 7 of 11 antimicrobials. By assessing the contribution of features to the models prediction, we identified proteins that may contribute to AMR mechanisms. Our findings demonstrate the potential of combining AI with MALDI-TOF MS as a rapid AMR diagnostic tool for Pseudomonas aeruginosa.

microbiology↗

bioRxiv2023

PSICHIC: physicochemical graph neural network for learning protein-ligand interaction fingerprints from sequence data

In drug discovery, determining the binding affinity and functional effects of small-molecule ligands on proteins is critical. Current computational methods can predict these protein-ligand interaction properties but often lose accuracy without high-resolution protein structures and falter in predicting functional effects. We introduce PSICHIC (PhySIcoCHemICal graph neural network), a framework uniquely incorporating physicochemical constraints to decode interaction fingerprints directly from sequence data alone. This enables PSICHIC to attain first-of-its-kind emergent capabilities in deciphering mechanisms underlying protein-ligand interactions, achieving state-of-the-art accuracy and interpretability. Trained on identical protein-ligand pairs without structural data, PSICHIC matched and even surpassed leading structure-based methods in binding affinity prediction. In a library screening for adenosine A1 receptor agonists, PSICHIC discerned functional effects effectively, ranking the sole novel agonist within the top three. PSICHICs interpretable fingerprints identified protein residues and ligand atoms involved in interactions. We foresee PSICHIC reshaping virtual screening and deepening our understanding of protein-ligand interactions.

bioinformatics↗

bioRxiv2019

PRISM: a comprehensive 3D structure database for post-translational modifications and mutations with functional impact

Post-translational modifications (PTMs) play very important roles in various cell signalling pathways and biological process. Due to PTMs extremely important roles, many major PTMs have been thoroughly studied, while the functional and mechanical characterization of major PTMs is well-documented in several databases. However, most currently available databases mainly focus on protein sequences, while the real 3D structures of PTMs have been largely ignored. Therefore, studies of PTMs 3D structural signatures have been severely limited by the deficiency of the data. Here, we develop PRISMOID, a novel publicly available and free 3D structure database for a wide range of PTMs. PRISMOID represents an up-to-date and interactive online knowledge base with specific focus on 3D structural contexts of PTMs sites and mutations that occur on PTMs and in the close proximity of PTM sites with functional impact. The first version of PRISMOID encompasses 17,145 non-redundant modification sites on 3,919 related protein 3D structure entries pertaining to 37 different types of PTMs. Our entry web page is organized in a comprehensive manner, including detailed PTM annotation on the 3D structure and biological information in terms of mutations affecting PTMs, secondary structure features and per-residue solvent accessibility features of PTM sites, domain context, predicted natively disordered regions and sequence alignments. In addition, high-definition JavaScript packages are employed to enhance information visualization in PRISMOID. PRISMOID equips a variety of interactive and customizable search options and data browsing functions; these capabilities allow users to access data via keyword, ID, and advanced options combination search in an efficient and user-friendly way. A download page is also provided to enable users to download the SQL file, computational structural features, and PTM sites data. We anticipate PRISMOID will swiftly become an invaluable online resource, assisting both biologists and bioinformaticians to conduct experiments and develop applications supporting discovery efforts in the sequence-structural-functional relationship of PTMs and providing important insight into mutations and PTM sites interaction mechanisms. The PRISMOID database is freely accessible at http://prismoid.erc.monash.edu/. The database and web interface are implemented in MySQL, JSP, JavaScript, and HTML with all major browsers supported.

bioinformatics↗