Biology subjects

Paige, B.

Publications and source records attributed to Paige, B..

5 recordsLinked to original sources

bioRxiv2025

ProFam: Open-Source Protein Family Language Modelling for Fitness Prediction and Design

Protein language models have become essential tools for engineering novel functional proteins. The emerging paradigm of family-based language models makes use of homologous sequences to steer protein design and enhance zero-shot fitness prediction, by imbuing models with an ability to explicitly reason over evolutionary context. To provide an open foundation for this modelling approach, we introduce ProFam-1, a 251M-parameter autoregressive protein family language model (pfLM) trained with next-token prediction on millions of protein families represented as concatenated, unaligned sets of sequences. ProFam-1 is competitive with state-of-the-art models on the ProteinGym zero-shot fitness prediction benchmark, achieving Spearman correlations of 0.47 for substitutions and 0.53 for indels. For homology-guided generation, ProFam-1 generates diverse sequences with predicted structural similarity, while preserving residue conservation and covariance patterns. All of ProFams training and inference pipelines, together with our curated, large-scale training dataset ProFam Atlas, are released fully open source, lowering the barrier to future method development.

bioinformatics↗

bioRxiv2025

Design in Voxel Space Decode in SMILES Space: Plixer Generates Drug-Like Molecules for Protein Pockets

We introduce Plixer, a two-stage generative model for de novo drug design that generates small-molecule ligand binders conditioned on an empty protein pocket. Plixer combines a conditional voxel inpainting network to generate 3D ligand hypotheses with an independently trained voxel-to-SMILES decoder that translates these voxel representations into valid chemical structures. By de-coupling the learning of spatial protein-ligand interactions from the learning of chemical grammar, our approach leverages large libraries of 3D ligand conformers to augment the limited data available for protein-ligand complexes. We show that this approach generates molecules with higher predicted binding affinity than recent methods.

molecular biology↗

bioRxiv2023

Chainsaw: protein domain segmentation with fullyconvolutional neural networks

0.1 MotivationProtein domains are fundamental units of protein structure and play a pivotal role in understanding folding, function, evolution, and design. The advent of accurate structure prediction techniques has resulted in an influx of new structural data, making the partitioning of these structures into domains essential for inferring evolutionary relationships and functional classification. 0.2 ResultsThis manuscript presents Chainsaw, a supervised learning approach to domain parsing that achieves accuracy that surpasses current state-of-the-art methods. Chainsaw uses a fully convolutional neural network which is trained to predict the probability that each pair of residues is in the same domain. Domain predictions are then derived from these pairwise predictions using an algorithm that searches for the most likely assignment of residues to domains given the set of pairwise co-membership probabilities. Chainsaw matches CATH domain annotations in 78% of protein domains versus 72% for the next closest method. When predicting on AlphaFold models expert human evaluators were twice as likely to prefer Chainsaws predictions versus the next best method. 0.3 Availability and ImplementationCode implementation of Chainsaw is available at github.com/JudeWells/chainsaw.

molecular biology↗

bioRxiv2022

Approximated Gene Expression Trajectories (AGETs) for Gene Regulatory Network Inference on Cell Tracks

The study of pattern formation has greatly benefited from our ability to reverse-engineer gene regulatory network (GRN) structure from spatio-temporal quantitative gene expression data. Traditional approaches omit tissue morphogenesis, and focus on systems where the timescales of pattern formation and morphogenesis can be separated. In such systems, pattern forms as an emergent property of the underlying GRN and mechanistic insight can be obtained from the GRNs alone. However, this is not the case in most animal patterning systems, where patterning and morphogenesis are co-occurring and tightly linked. To address the mechanisms driving pattern formation in such systems we need to adapt our GRN inference methodologies to explicitly accommodate cell movements and tissue shape changes. In this work we present a novel framework to reverse-engineer GRNs underlying pattern formation in tissues undergoing morphogenetic changes and cell rearrangements. By integrating quantitative data from live and fixed embryos, we approximate gene expression trajectories (AGETs) in single cells and use a subset to reverse-engineer candidate GRNs using a Markov Chain Monte Carlo approach. GRN fit is assessed by simulating on cell tracks (live-modelling) and comparing the output to quantitative data-sets. This framework generates candidate GRNs that recapitulate pattern formation at the level of the tissue and the single cell. To our knowledge, this inference methodology is the first to integrate cell movements and gene expression data, making it possible to reverse-engineer GRNs patterning tissues undergoing morphogenetic changes.

systems biology↗

bioRxiv2020

Reconstructing Genotypes in Private Genomic Databases from Genetic Risk Scores

Some organisations like 23andMe and the UK Biobank have large genomic databases that they re-use for multiple different genome-wide association studies (GWAS). Even research studies that compile smaller genomic databases often utilise these databases to investigate many related traits. It is common for the study to report a genetic risk score (GRS) model for each trait within the publication. Here we show that under some circumstances, these GRS models can be used to recover the genetic variants of individuals in these genomic databases--a reconstruction attack. In particular, if two GRS models are trained using a largely overlapping set of participants, then it is often possible to determine the genotype for each of the individuals who were used to train one GRS model, but not the other. We demonstrate this theoretically and experimentally by analysing the Cornell Dog Genome database. The accuracy of our reconstruction attack depends on how accurately we can estimate the rate of co-occurrence of pairs of SNPs within the private database, so if this aggregate information is ever released, it would drastically reduce the security of a private genomic database. Caution should be applied when using the same database for multiple analysis, especially when a small number of individuals are included or excluded from one part of the study.

genomics↗