drug discovery teams

Abstract: Large language models (LLMs) can generate biomedical hypotheses, but it remains unclear whether they truly reason from scientific evidence or simply produce convincing-sounding ideas. To study this, we combine three major biological databases: the Kyoto Encyclopedia of Genes and Genomes (KEGG), Rhea, and UniProt, into a unified biochemical knowledge graph and construct a benchmark of 550 paths connecting enzyme sources to rare disease endpoints, yielding 13,200 hypotheses from six LLMs under four conditions varying the biological information each model receives: source enzyme only, full biological path, or source and disease endpoint only. Hypotheses are scored using an expert-derived five-criterion rubric on a 1-5 scale per criterion. We find that models given both the source and disease endpoint often produce the highest-scoring hypotheses, showing that LLMs can generate compelling ideas from minimal information. However, these hypotheses are less grounded in the evidence. In contrast, models given the full biological path generate hypotheses more consistent with known mechanistic relationships. We call this evidence-disciplined reasoning. To confirm this effect, we shuffled intermediate path steps while keeping endpoints fixed. Evidence grounding dropped significantly (delta = -0.793, p < 0.001), confirming models genuinely used path structure during reasoning. Our findings show that knowledge graphs support hypothesis generation in two ways: they identify biological endpoint pairs absent from the literature, and their mechanistic paths guide how LLMs reason between them.

Abstract: Many biological discovery problems require experiments to be selected sequentially under constrained budgets. CRISPR screening is a prominent example, as exhaustive perturbation testing is often infeasible and candidate perturbations must instead be prioritized over multiple experimental rounds. Despite the importance of this problem, existing benchmarks for adaptive hit discovery remain limited in scale and diversity. Here, we introduce AssayBench-Loop, a large-scale benchmark for adaptive hit discovery comprising 1,389 CRISPR screens across five phenotype categories. Beyond enabling systematic evaluation, its scale makes it possible to learn acquisition strategies across historical experiments. Building on this resource, we introduce AssayLoop, a sequential experimental design framework combining AssayFormer, a transformer-based amortized acquisition policy trained across historical screens to adapt from experimental feedback, with LLM-derived biological priors through an adaptive handoff. In this view, completed experiments become training data for learning how accumulated evidence should guide what to test next, while LLMs provide prior biological knowledge to seed the search. We further introduce AssayLLM, showing that the same principle can be extended directly to an LLM through task-specific post-training. On temporally held-out screens, AssayLoop achieves a 5.67-fold enrichment over random selection and recovers 27.7% of hits after assaying approximately 5% of the candidate library, outperforming existing adaptive-design methods and standalone LLMs, and AssayFormer alone. Performance improves with increasing historical training data and transfers to phenotype categories excluded from training. These results demonstrate the value of learning acquisition policies across historical experiments and combining them with broad biological priors for efficient adaptive hit discovery.

Abstract: Proteolysis-targeting chimeras (PROTACs) have emerged as a transformative therapeutic strategy that selectively degrades historically ''undruggable'' targets via the ubiquitin-proteasome system. Despite growing efforts to develop computational predictors of PROTAC degradation activity, existing supervised approaches remain severely challenged by data scarcity and imbalance across E3 ligases, limiting their ability to generalize beyond well-studied ligase contexts. In practice, labeled data are heavily concentrated on a few ligases (e.g., CRBN and VHL), while the majority of E3 ligases remain underexplored yet are critical for expanding the design space of targeted degraders. Developing methods that enable robust cross-ligase generalization with minimal labeled data is therefore essential for improving the practical utility of computational PROTAC discovery. We reformulate PROTAC degradation activity prediction across E3 ligases as a few-shot meta-learning problem and present ProMeta, a prototype-based graph neural network trained through episodic meta-learning on source-E3 tasks and evaluated on held-out target-E3 tasks through support-conditioned inference. ProMeta performs inference without updating the encoder by dynamically estimating class prototypes from minimal target-ligase support samples. On the CRBN-to-VHL benchmark, ProMeta achieves AUROC values of 0.796 under K=2, Q=3 and 0.883 under K=2, Q=5, improving by 19.9% and 6.8%, respectively, over the corresponding supervised GNN baseline. Reverse VHL-to-CRBN transfer under the same protocol yielded AUROC values of 0.702 (K=2, Q=3) and 0.821 (K=2, Q=5), confirming bidirectional applicability while revealing direction and data-regime dependence. Together, these results support ProMeta as a practical framework for cross-ligase few-shot prediction under the evaluated support/query protocols.

Abstract: In molecular discovery, molecule size is coupled to composition, structure, and other target properties. Yet most 3D generators require molecule size to be specified before generation. Here, we introduce Equivariant-Free Transformer-Autoencoded Latent Flow Matching, a two-stage generative framework that relies entirely on a single fixed-dimensional molecule-level latent representation to generate variable-size molecules. The second-stage flow matching model samples this latent vector, and an autoregressive Transformer decoder then determines molecule size while generating atom types, coordinates, and chemically informative states. Canonical atom ordering and rigid-pose alignment enable standard Transformers without equivariant layers, while joint decoding of molecular geometry and an enriched chemical state enables reliable, deterministic, chemistry-guided graph recovery without requiring a learned dense pairwise bond decoder. The same fixed-dimensional latent supports unconditional and property-conditioned flow matching, while optional property supervision adds an internal ranking readout, with no separate predictor or reference calculations. On PCQM4Mv2, EF-TALFM achieves the highest fraction of molecules that are unique, training-set novel, pass sanitization and PoseBusters sanity checks, 89.4\%, compared with 75.6\% for UAE-3D and 69.8\% for FlowMol. EF-TALFM also achieves higher measured computational throughput for training and sampling. Across ten target HOMO--LUMO gaps, internal ranking doubles the density functional theory (DFT)-verified hit rate within $0.1\,\mathrm{eV}$, while preserving 97\% novelty among unique verified hits. These results demonstrate that fixed-dimensional molecule-level generation followed by symmetry-resolved autoregressive realization provides a practical architecture for open-ended and property-directed 3D molecular design.

Abstract: Protein-conditioned 3D molecule generation is a central challenge in structure-based drug design, requiring a balance between pocket compatibility, molecular properties, and physical geometry. We propose \textbf{PocketVE}, a protein-pocket-conditioned variance-exploding (VE) diffusion framework that couples stable coordinate denoising with inference-time property guidance. Specifically, PocketVE combines an EDM-style training and sampling setup for 3D denoising, classifier-free guidance for multi-property steering without external property classifiers, and adaptive protein perturbation as a training-time pocket regularizer. Evaluated on CrossDocked2020 under the GenBench3D protocol, PocketVE improves Valid$_{3\text{D}}$ from 58.6 to 80.6 and reduces strain energy from 457.4 to 127.9 relative to its TAGMol architectural baseline, while retaining competitive docking and molecular-property scores under moderate guidance. A guidance-scale study shows that moderate guidance gives a favorable balance between target-related objectives and geometric quality, whereas stronger guidance can degrade geometry and distributional fidelity. Pocket-permutation and PoseCheck diagnostics further support pocket-specific spatial compatibility with reduced steric conflicts. Overall, the results suggest that geometric stability and inference-time property guidance should be considered as coupled design objectives.