It is demonstrated that empirical lab data is more valuable than existing computational proxies, showing how iterative experimental feedback enables AI agents to diagnose assay artifacts and refine molecular designs across rounds.
Abstract
Despite breakthroughs in AI-driven molecular generation, existing discovery pipelines operate largely in silico, with wet-lab feedback reserved for validation rather than iterative improvement. Whether large language model (LLM)-based reasoning agents can accelerate de novo discovery by iterating with lab data remains unproven. Here we use protein-binding aptamer design as a sandbox (1-2 week cycles, \$1-\$3 per candidate) to demonstrate a wet lab in a closed loop with AI systems. We tasked agentic pipelines with developing aptamer binders against $\alpha$-thrombin and myoglobin across three design-test-improve cycles ($\sim$1,000 candidates per round; $\sim$4,400 constructs). Statistically significant, bead-corrected on-target hit rates among new candidates rose across rounds from 0.0% in Round 1 to 26.0% in Round 2 and 42.1% in Round 3 on $\alpha$-thrombin (37.1% excluding literature motif descendants), and from 10.2% in Round 1 to 3.7% in Round 2 and 33.5% in Round 3 on myoglobin. Single-clone bead-binding titrations of eight full-length $\alpha$-thrombin candidates confirmed concordance with pooled sequencing enrichment (Pearson $r = 0.90$). In these assays, literature-derived motifs engineered by the agents to reduce off-target reactivity in the pooled screen reached apparent affinities of $K_D = 24.6$--$133$ nM, whereas de novo scaffolds showed low-micromolar binding ($K_D>1\ \mu$M). We also report how our pipelines used myoglobin binding data to exploit the G-quadruplex binder space, diagnose cross-reactivity as on-target specificity dropped from 75.0% to 19.1%, and recover by developing strategies that restored specificity to 72.4%. We demonstrate that empirical lab data is more valuable than existing computational proxies, showing how iterative experimental feedback enables AI agents to diagnose assay artifacts and refine molecular designs across rounds.
Conventional aptamer discovery by systematic evolution of ligands by exponential enrichment (SELEX) is often constrained by limited library capacity, PCR bias, and multi-round screening. The recent convergence of artificial intelligence with aptamer development is driving a paradigm shift from empirical screening towar...
Bo-Ming Cui, X. Lian, Wei-Wei Song et al.· Biotechnology Advances· 0 citations
By converting single-prediction design into a cross-validated, dynamics-tested workflow, UnibindMD provides a rapid, scalable, and generalizable path from any protein target to validated peptide-binder candidates.
Xuan Wu, A. Huang, Cong-Mei Fu et al.· bioRxiv· 0 citations
Together, these capabilities establish AnewDDE as an integrated engine for addressing challenging therapeutic targets and translating molecular insights into experimentally validated candidates at scale.
Accelerating the identification of viable drug candidates across therapeutic areas demands autonomous systems for molecular generation that enforce chemical correctness by structural invariants rather than model capability. We present MolecureAI, an autonomous AI agent architecture for closed-loop drug discovery with c...
M. Chadi, Asmaa Amzil, Hajar Ezzahoud et al.· Frontiers in Pharmacology· 0 citations
Bridging AI and self-driving laboratories, we report an integrated, closed-loop molecular discovery workflow with automation spanning all four stages of the Design-Make-Test-Analyse (DMTA) cycle, exemplified by the identification of novel JAK inhibitors (JAK1, JAK2, JAK3, and TYK2). We combined AI-driven molecular desi...
Jannis Born, Carlo Baldassari, Doriela Grabocka et al.· Digital Discovery· 0 citations
Molecular discovery requires navigating vast combinatorial search spaces while balancing competing biological objectives. AI agents can automate expert-defined molecular design protocols, but automation alone does not address how to optimize workflows for new tasks or improve their development through experience. Here...
Yi-Kun Zhang, Xi-Wei Cheng, Ming-Ze Yuan et al.· 1 citation