Biology subjects

Ille, A. M.

Publications and source records attributed to Ille, A. M..

3 recordsLinked to original sources

bioRxiv2025

Human protein interactome structure prediction at scale with Boltz-2

In humans, protein-protein interactions mediate numerous biological processes and are central to both normal physiology and disease. While extensive research efforts have aimed to characterize the human protein interactome, atom-scale structural coverage is limited and remains challenging to resolve through experimental methodology alone. Boltz-2, a recent artificial intelligence/machine learning (AI/ML)-based model capable of interaction structure prediction, may serve this experimentally constrained objective. Here, we present de novo computed models of binary human protein interaction structures predicted using Boltz-2 based on biochemically determined interaction data sourced from the IntAct database. We assessed the predicted interaction structures through different confidence metrics, examined annotated protein domains with putative interaction involvement, and uncovered interaction networks within the context of biological processes and cancer, highlighting extensive interaction involvement of E3 ubiquitin-protein ligase Mdm2 and p53, among other proteins. This work demonstrates the utility of Boltz-2 for structural modeling of the human protein interactome while also providing novel functional and disease contextualization, holding broad significance for biomedical research at large. GRAPHICAL ABSTRACT O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=200 SRC="FIGDIR/small/663068v3_ufig1.gif" ALT="Figure 1"> View larger version (72K): org.highwire.dtl.DTLVardef@5666d8org.highwire.dtl.DTLVardef@7a1d3dorg.highwire.dtl.DTLVardef@115c040org.highwire.dtl.DTLVardef@100bbbe_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2024

Prediction of peptide structural conformations with AlphaFold2

Protein structure prediction via artificial intelligence/machine learning (AI/ML) approaches has sparked substantial research interest in structural biology and adjacent disciplines. More recently, AlphaFold2 (AF2) has been adapted for the prediction of multiple structural conformations--beyond the original scope of predicting single-state structures. This is accomplished by using multiple random seeds and subsampling the multiple sequence alignment (MSA). Research using this novel approach has focused on proteins (typically 50 residues in length or greater), while multi-conformation prediction of shorter peptides has not yet been explored in this context. Here, we report AF2-based structural conformation prediction of a total of 557 peptides (ranging in length from 10 to 40 residues) for a benchmark dataset with corresponding nuclear magnetic resonance (NMR)-determined conformational ensembles. De novo structure predictions were accompanied by structural comparison analyses to assess prediction accuracy. We found that the prediction of conformational ensembles of peptides with AF2 varied in accuracy versus NMR data, with average root-mean-square deviation (RMSD) among structured regions under 2.5 [A] and average root-mean-square fluctuation (RMSF) differences under 1.5 [A] for the entire set of 557 peptides. Our results reveal notable capabilities of AF2-based structural conformation prediction for peptides but also highlight considerable limitations, underscoring the necessity for interpretation discretion and the need for improved conformational ensemble prediction approaches.

bioinformatics↗

bioRxiv2024

Generative artificial intelligence performs rudimentary structural biology modelling

Natural language-based generative artificial intelligence (AI) has become increasingly prevalent in scientific research. Intriguingly, capabilities of generative pre-trained transformer (GPT) language models beyond the scope of natural language tasks have recently been identified. Here we explored how GPT-4 might be able to perform rudimentary structural biology modeling. We prompted GPT-4 to model 3D structures for the 20 standard amino acids and an -helical polypeptide chain, with the latter incorporating Wolfram mathematical computation. We also used GPT-4 to perform structural interaction analysis between nirmatrelvir and its target, the SARS-CoV-2 main protease. Geometric parameters of the generated structures typically approximated close to experimental references. However, modeling was sporadically error-prone and molecular complexity was not well tolerated. Interaction analysis further revealed the ability of GPT-4 to identify specific amino acid residues involved in ligand binding along with corresponding bond distances. Despite current limitations, we show the capacity of natural language generative AI to perform basic structural biology modeling and interaction analysis with atomic-scale accuracy.

bioinformatics↗