Biology subjects

Gambin, A.

Publications and source records attributed to Gambin, A..

3 recordsLinked to original sources

bioRxiv2026

BATTLE-AMP: Benchmarking Antimicrobial Peptide Predictors

As antimicrobial resistance outpaces antibiotic development, antimicrobial peptides (AMPs) have emerged as a promising class of alternative antibacterials, and computational predictors are increasingly used to prioritize AMP candidates. Such predictors are typically evaluated on binary AMP/non-AMP classification, which does not test whether they can identify peptides with clinically relevant potency against specific pathogens. We present BATTLE-AMP, a benchmarking framework that evaluates AMP predictors against experimentally measured minimum inhibitory concentrations (MICs) across clinically relevant bacterial species and strains. We surveyed 48 published methods, finding fewer than 25% reproducible, and benchmarked 10 model families (21 variants) using experimental MIC data, synthetic sequence perturbations, activity cliff analyses, and all-atom molecular dynamics (MD) simulations. Four findings emerge: (i) models trained on MIC data outperform binary classifiers regardless of architecture; (ii) the best model depends on the target pathogen, so model selection must be guided by the biological question; (iii) most models cannot distinguish active peptides from inactive sequences with identical amino acid composition; and (iv) activity cliffs remain unresolved by both machine learning and MD, marking a limit of current computational methods. BATTLE-AMP is released as an open Snakemake framework at https://github.com/szczurek-lab/battleamp-snakemake for benchmarking new models and scoring novel candidate libraries.

bioinformatics↗

bioRxiv2026

Resolution of recursive data corruption to transform T-cell epitope discovery

Accurate prediction of MHC class I-presented peptides is essential for any vaccine or T-cell therapy design, yet reported gains on in silico benchmarks have not translated into clinical successes. Here we show that this discrepancy may come from a common methodological error: immunopeptidomics datasets are fundamentally contaminated by existing prediction models through prediction-based deconvolution and filtering, resulting in an iterative confirmation bias. An audit of the IEDB, the biggest database in the field, reveals that as of January 2025, 55.8% of assessable data are labeled by computational models rather than verified experimentally. This inflates in silico benchmarks while degrading real-world applicability on new data, effectively making it impossible to objectively test model performance, which can lead to choosing suboptimal solutions and decreasing the chance of any therapys clinical success. In silico simulation shows that iterative data corruption maintains high AUROC while top-of-list retrieval collapses. We reframe epitope discovery as a protein-centric learning-to-rank task and introduce deepMHCflare, a model evaluated exclusively on clean data. deepMHCflare achieves 0.80 Precision@4 on mono-allelic benchmarks versus 0.55-0.65 for gold-standard prediction models. A preclinical cancer vaccine study validated that 2 of the 4 deepMHCflare-nominated peptides were immunogenic, with a third independently confirmed in the literature.

bioinformatics↗

bioRxiv2020

Masserstein: robust linear deconvolution by optimal transport

A common theme in many applications of computational mass spectrometry is fitting a linear combination of reference spectra to an experimental one in order to estimate the quantities of different ions, potentially with overlapping isotopic envelopes. In this work, we study this procedure in an abstract setting, in order to develop new approaches applicable to a diverse range of experiments. We introduce an application of a new spectral dissimilarity measure, known in other fields as the Wasserstein or the Earth Movers distance, in order to overcome the sensitivity of ordinary linear regression to measurement inaccuracies. Usinga a data set of 200 mass spectra, we demonstrate that our approach is capable of accurate estimation of ion proportions without extensive pre-processing required for state-of-the-art methods. The conclusions are further substantiated using data sets simulated in a way that mimics most of the measurement inaccuracies occurring in real experiments. We have implemented our methods in a Python 3 package, freely available at https://github.com/mciach/masserstein.

bioinformatics↗