3 papers
cs.AI2026
MolBioKG: Grounding Out-of-Graph Molecules in Biomedical Knowledge Graphs via Multi-Resolution Structural Anchoring
Yiming Zhang, Hikaru Shindo, Shuan Chen +5
Biomedical knowledge graphs (KGs) accelerate drug discovery, but standard pipelines assume query molecules already exist as graph entities, leaving unregistered molecules disconnec…
cs.LG2026
Pepti-drift: Scalable Safe-Active Peptide Generation Without Inference-Time Guidance
Takashi Fujiwara, Hikaru Shindo, Kaushalya Madhawa +6
Therapeutic peptides are a promising drug modality, but their generation must satisfy multiple therapeutic constraints. We introduce BindSafe-PepBench, a fixed-budget benchmark tha…
cs.AI2025
Democratizing Drug Discovery with an Orchestrated, Knowledge-Driven Multi-Agent Team for User-Guided Therapeutic Design
Takahide Suzuki, Kazuki Nakanishi, Takashi Fujiwara +1
Therapeutic discovery remains a formidable challenge, impeded by the fragmentation of specialized domains and the execution gap between computational design and physiological valid…