The study evaluates whether a portfolio of compact, semantically named descriptor blocks can match the performance of a 2048‑dimensional CheMeleon embedding in low‑data molecular assays. Using a fixed 11‑dimensional physicochemical base and greedily adding provenance‑screened blocks, the portfolio achieves a mean test AUC of 0.762 across nine ADME/Tox assays, comparable to CheMeleon’s 0.764 and better than Mordred’s 0.756. The results meet a predeclared pooled parity threshold but not all per‑assay thresholds, and further analysis confirms the competitiveness of the auditable representation while highlighting unresolved assay‑level differences.
By Yiqi Yao, Miquel Duran-Frigola
Monroe is a new molecular foundation model that improves upon existing models by pre‑training on over 81 million molecules from the PM6 quantum chemistry dataset, enhancing stereochemistry representation, and introducing novel training losses such as conformer denoising and embedding decorrelation. It also incorporates a prior‑data‑fitted model (TabPFN) for downstream in‑context prediction and demonstrates superior performance on Polaris benchmarks and activity cliff tests. Ablation studies show that the PFN‑based downstream approach can upgrade other models, producing state‑of‑the‑art variants MiniMol_PFN and CheMeleon_PFN.
By Blazej Banaszewski, Andrew W. Fitzgibbon
arXiv:2608. 19906v1 Announce Type: new Abstract: Accurately ranking active ligands for a target protein pocket from massive chemical libraries remains a central challenge in virtual screening.
By Jia-Qi Lin, Yinghua Yao, Chang-Dong Wang, Yew-Soon Ong, Yuangang Pan
TopU-LBVS is a new multi‑target benchmark for ligand‑based virtual screening that addresses shortcomings of existing datasets by using hard‑negative decoys and a fixed 1:40 active‑to‑decoy ratio. It covers 93 protein targets across seven classes, provides three evaluation protocols (full, low‑data, and mini), and includes curated ChEMBL‑35 bioactivity data with property‑matched, structurally similar decoys. The benchmark demonstrates that performance drops sharply when moving from random‑decoy to hard‑negative evaluation, and it releases data, splits, code, and baseline implementations for reproducible comparison.
By Surbhi Kumar, Yuhe Zhou, Varun Shiralkar, Niu Huang, Baris Coskunuzer
arXiv:2608. 01734v1 Announce Type: new Abstract: Predicting transcriptomic responses to small-molecule perturbations across cell lines is central to drug discovery, but exhaustive profiling of drug-cell combinations is infeasible.
By Betty Xiong, Jan-Christian Huetter, Gabriele Scalia, Tommaso Biancalani, Sepideh Maleki
arXiv:2607. 06605v1 Announce Type: new Abstract: Conformal prediction is being adopted in drug discovery to put an honest number on model reliability: pick an error rate alpha, and the method returns prediction sets containing the true label with probability at least 1 - alpha.
By Muhammadjon Tursunbadalov (School of Science and Technology, Champions College Prep, United States), Mustafojon Tursunbadalov (School of Science and Technology, Champions College Prep, United States)
arXiv:2603.03517v2 Announce Type: replace-cross
Abstract: General-purpose large language models (LLMs) that rely on in-context learning do not reliably deliver the scientific understanding and perfor...
By Maksim Kuznetsov, Zulfat Miftahutdinov, Rim Shayakhmetov, Mikolaj Mizera, Roman Schutski, Bogdan Zagribelnyy, Ivan Ilin, Nikita Bondarev, Thomas MacDougall, Mathieu Reymond, Mihir Bafna, Kaeli Kaymak-Loveless, Eugene Babin, Maxim Malkov, Mathias Lechner, Ramin Hasani, Alexander Amini, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov
TopU-LBVS is a new multi‑target benchmark for ligand‑based virtual screening that addresses shortcomings of previous datasets by using hard‑negative decoys and a fixed 1:40 active‑to‑decoy ratio. It covers 93 protein targets across seven classes, provides three evaluation protocols (full, low‑data, and mini), and includes curated ChEMBL‑35 bioactivity data with property‑matched, structurally similar decoys to reduce shortcut learning. The benchmark comes with released data, fixed splits, evaluation code, and baseline implementations for reproducible comparison of LBVS and molecular representation methods.
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...
The study demonstrates that a simple, sequence-only approach using 330 interpretable descriptors and the TabPFN tabular foundation model can outperform complex multimodal deep learning methods for multi-label antimicrobial peptide activity prediction. On the ESCAPE benchmark (82,359 peptides, five labels), a label‑powerset TabPFN model achieved a mean average precision of 77.8%, surpassing the previous best of 72.1%. The approach also shows that predicted structure is unnecessary, that a small set of global physicochemical scalars can recover most performance, and that modeling label dependence benefits rare activities and informs assay prioritization.
By Raunak Kumar, Anuj Pal, Dhruvi Solanki, Parikshit Pareek, Juhi Singh, Jitin Singla
ProbeMatchDTI introduces a probe-driven framework for drug‑target interaction prediction that preserves weak biochemical signals by using IterProbe to retain contextual states and BindingProbe to model cross‑entity complementarity at multiple scales. The method improves AUC‑ROC by 2.0% on BindingDB and 0.5% on DrugBank compared to prior biochemical representation learning approaches. Feature‑level analyses confirm the effectiveness of the probe-driven pattern matching, and the predictions are linked to an evidence‑guided downstream drug‑discovery workflow for candidate refinement and validation planning.
CaliPPer is a post‑hoc framework that calibrates and predicts the performance of binding‑prediction models by combining a multi‑chain Sample‑to‑Domain Distance (S2DD) metric with distance‑aware Bayesian recalibration. It operates at three resolutions—generalisability score, aggregate performance prediction, and per‑sample confidence—achieving strong distance‑performance correlations (|r| = 0.80–0.92) and low prediction errors for AUROC, AP, and F1. In retrospective analyses of five published studies, CaliPPer increased true discovery rates, improving AUROC by up to +0.20 on unseen epitopes and variants and raising confirmed neoantigen findings from 0/5 to 3/5.
By Jian-Qing Zheng, Hantao Lou, Zinan Yin, Sam Farrar, Yuze Zhou, Elie Antoun, Xiangxi Wang, Xuetao Cao, Tao Dong