ZetaDial introduces a post‑sampling, per‑protein secant controller that adjusts the net charge of protein binders generated by fixed‑backbone ProteinMPNN, enabling inference‑time tuning of developability‑relevant charge. On benchmark datasets, the secant loop reduced mean absolute charge error compared to fixed‑slope and global‑bias approaches, achieving significant improvements on RCSB complexes and comparable performance on Cas13 monomers. The method also highlights trade‑offs between charge calibration and foldability, with exploratory tests on PD‑L1, IL‑7R‑alpha, and RBD designs illustrating its impact on design success rates and interface properties.
arXiv:2606. 00555v1 Announce Type: new Abstract: Structure-based drug design increasingly employs LLM agents to iteratively refine ligands against a target pocket, yet a viable ligand must satisfy two often-conflicting objectives -- binding affinity and druggability -- which single optimization steps rarely improve together.
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.
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.
PMO-Dock introduces a standardized benchmark for docking‑based molecular optimization, comprising 25 tasks that span hit generation, lead optimization, and a specificity task that rewards strong on‑target binding while penalizing off‑target interactions. The protocol separates model development from final evaluation, using validation tasks for hyperparameter tuning and held‑out test tasks evaluated under a strict oracle budget to mimic realistic drug‑discovery constraints. Four diverse methods—Saturn, GenMol, Genetic‑guided GFlowNet, and ChemLlama—were benchmarked, revealing no single method dominates across all tasks and highlighting limited hyperparameter transferability, which underscores the need for method‑dependent selection strategies.
arXiv:2512. 02328v2 Announce Type: replace-cross Abstract: Selecting an effective docking algorithm is highly context-dependent, and no single method performs reliably across structural, chemical, and protocol regimes.
Budgeted Quotient-Residual Guidance (QRG) is an inference-time correction that enables quotient-based lead‑optimization objectives—such as distances, contacts, and anchored substructures—to be actively used with frozen pocket‑conditioned molecular diffusion models without retraining. QRG lifts quotient covectors to metric‑horizontal ambient directions and delivers them through a trust budget set by the sampler’s step norm, providing a closed‑form sampler‑budget update and a product‑budget split for section and residual controls. Experiments on frozen TargetDiff backbones show that QRG improves ligand‑generation quality on fragment growing, scaffold hopping, and linker design while preserving novelty and diversity.
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.
SurfSpec is a new framework for lead optimization that improves drug specificity without needing off‑target structures. It works by measuring and reducing the geometric mismatch between a ligand and its target pocket, using the triangle inequality to infer a lower bound on mismatch to off‑target pockets. In tests on the CrossDocked2020 dataset, SurfSpec lowers geometric mismatch and achieves higher empirical specificity while still improving target affinity.
The study reports the first computational design of de novo miniprotein binders that target the IL‑23 cytokine subunit p19, specifically the IL‑23R‑binding face. Using a length‑robust interface metric (ipSAE) derived from AlphaFold‑predicted aligned error, the authors identified 42 of 50 designs with high interface quality, and five all‑alpha‑helical leads that engage all six targeted hotspots without affecting the p40 subunit. These candidates are proposed as potential neutralizers of IL‑23 activity, offering a smaller, potentially cheaper alternative to existing anti‑p19 antibodies. whyItMatters":"The work introduces a novel computational approach to generate miniprotein candidates that could inhibit IL‑23‑mediated inflammation, addressing a therapeutic need unmet by current large antibody treatments."
Mirror-Score is a calibrated, inference‑only scoring framework that evaluates heterochiral D‑peptide/L‑protein complexes, addressing the inadequacies of raw ProteinMPNN negative log‑likelihood (NLL) ranking. The authors benchmarked 31 crystal complexes across four target families, showing that NLL has poor affinity correlation (Spearman 0.19) while Boltz‑2 mirror‑space co‑folding confidence and pLDDT metrics can correctly rank peptides within a viral‑entry family. The study also proposes a prospective design protocol for antimicrobial‑resistance targets and releases all code, data, and structures publicly.
MLIPDiff is an inference‑time guidance technique that enhances pretrained denoising diffusion models for ligand generation by incorporating physics‑informed guidance from a machine‑learned interatomic potential (UMA). It combines four weighted energy terms—protein‑ligand interaction, ligand strain, steric clash, and pocket anchoring—to eliminate protein‑ligand collisions while preserving local geometry, without requiring model retraining. On the CrossDocked2020 benchmark, MLIPDiff produces clash‑free, physically plausible ligand poses and achieves superior binding‑affinity metrics compared to both the base diffusion model and NucleusDiff.
arXiv:2610.24806v1 Announce Type: cross Abstract: Despite breakthroughs in AI-driven molecular generation, existing discovery pipelines operate largely in silico, with wet-lab feedback reserved for v...