Coarse composition suffices: tabular in-context learning for multi-activity antimicrobial peptide profiling
2026-08-31 • Machine Learning
Machine Learning
AI summaryⓘ
The authors studied how to predict if antimicrobial peptides (AMPs) can fight multiple types of pathogens at once, a more realistic challenge than simple yes/no answers. They showed that using just the amino acid sequences with 330 easy-to-understand features, combined with a special tabular model called TabPFN, performs better than complex models relying on protein structure. Their method improved prediction accuracy on a large benchmark dataset and worked especially well on distant peptide relatives. They also found that including relationships between different antimicrobial activities helps prioritize which activities to test next, and that predicted 3D structures are not necessary for good performance.
Antimicrobial peptidesMulti-label classificationSequence descriptorsTabPFNBenchmark datasetProtein sequenceLabel-powersetProbabilistic classifier chainRemote homologuesPhysicochemical properties
Authors
Raunak Kumar, Anuj Pal, Dhruvi Solanki, Parikshit Pareek, Juhi Singh, Jitin Singla
Abstract
Antimicrobial peptides (AMPs) often act against multiple pathogen classes, making multi-label activity prediction a more realistic screening target than binary antimicrobial classification. The ESCAPE benchmark formalizes this setting, but leading approaches typically rely on multimodal, structure-conditioned deep models that are costly to train and tune. We show that a simple, sequence-only pipeline can match and surpass these methods by combining 330 interpretable sequence descriptors with TabPFN, a tabular foundation model that performs in-context prediction in a single forward pass without gradient-based training or hyperparameter search. On ESCAPE (82,359 peptides; five labels), a label-powerset TabPFN model achieves mAP-5 = 77.8%, improving on the previously best reported 72.1%. A probabilistic classifier chain is the first method to match or exceed the best published average precision on each of the five labels simultaneously. The gains persist under the prior state-of-the-art single-fold training protocol, indicating they are not a training-set-size artefact, and are largest for remote homologues (+11.2 points below 30% sequence identity). Ablations further show that predicted structure is unnecessary at inference and that performance is not driven by any single descriptor family: ten global physicochemical scalars recover 91% of full-feature performance. Finally, explicitly modelling label dependence yields targeted benefits for scarce activities and supports ranking which activity to assay next from partial positive evidence.