Ainnocence reports 91.4% success rate across 58 antibody campaigns

Ainnocence said its SentinusAI platform delivered positive results in 53 of 58 antibody affinity maturation campaigns and opened 28 programs for licensing or partnering. The company says the sequence-first system can narrow wet-lab testing to 20-50 designs per round while producing picomolar leads across oncology, immunology and metabolic programs.

Why it matters: - Ainnocence is pitching a faster antibody discovery model that cuts the number of molecules sent to the lab and can still produce high-affinity leads. - The company is also trying to turn that performance into deals, with 28 programs now available for licensing or partnering. - The pipeline spans oncology, immunology and metabolic indications, which broadens the commercial reach.

What happened: - Ainnocence said it completed 75 protein design programs and is seeking licensing and partnering agreements for 28 antibody, bispecific and ADC programs. - The company said those 28 programs have generated positive preclinical data. - The announcement covers work across oncology, immunology and metabolic indications. - Across 58 affinity maturation campaigns, SentinusAI succeeded in 53, for a 91.4% program success rate. - Five campaigns did not produce an improved binder. - On novel targets with no structural information and no prior binder, 9 of 17 de novo campaigns yielded validated hits.

The details: - SentinusAI predicts binding directly from sequence and does not require a resolved co-crystal or predicted complex. - Ainnocence said that approach delivers about a 10,000-fold reduction in computational cost versus conventional 3D modeling workflows. - The company said each compute cycle takes one to two weeks per round. - Ainnocence said it can run more than 100 programs at once. - Wet-lab rounds are narrowed to 20-50 designs before synthesis. - De novo design produced a 7.5% positive rate on round-1 zero-shot prediction, rising to 30% on round 2 with reinforcement-learning iteration. - Affinity maturation produced a 21.5% positive rate on round-1 zero-shot prediction, rising to 43.8% on round 2. - Ainnocence said leads have shown affinity gains ranging from tens-fold to thousands-fold over the parent molecule. - Quantified results include 28 campaigns reaching sub-nanomolar affinity and seven reaching 100 pM or better. - Reported leads include an IL-15×IL-21 bispecific at about 0.09 pM on the IL-21 arm, a TNFα-OX40L bispecific at 8.6 pM, an anti-C1q program at 1-20 pM and a TL1A×p40 bispecific at 23 pM. - An anti-VEGF scFv-IgG measured 27.8-34.6 pM by SPR and outperformed the bevacizumab reference run in the same experiment. - The internal pipeline includes 37 programs, with 28 showing positive data and available for licensing or partnering individually or as a portfolio. - Pipeline highlights include a TL1A×p40 bispecific at KD 0.16 nM, with duvakitug listed as the benchmark. - An anti-IL-36R Fab had 13 of 21 matured variants binding below the 1 pM detection limit, with spesolimab-class HB-0034 listed as the benchmark. - An anti-TROP2 ADC lead measured 0.37-0.43 nM with confirmed internalization, with Trodelvy listed as the benchmark. - An anti-B7-H3 program measured about 0.56 nM, with ifinatamab deruxtecan listed as the benchmark. - Seven ADC-ready internalizing oncology targets were validated by FACS and internalization assay. - Leads expressed at titers up to about 440 mg/L and achieved greater than 99% SEC purity.

Between the lines: - The pitch centers on reducing discovery cost and lab burden, not just improving model scores. - The sequence-first approach is positioned as an alternative for targets that structure-dependent platforms may not pursue. - The use of benchmark drugs suggests Ainnocence is trying to frame the programs as commercially relevant rather than purely experimental.

What's next: - Ainnocence is looking for partners to advance programs through affinity finalization, ADC conjugation, in vivo efficacy and clinical development. - The company said additional non-confidential and confidential materials are available on request. - Dr. Lurong Pan said Ainnocence is focused on targets other platforms set aside because the system does not depend on a resolved structure. - Ainnocence said it was founded in 2021 and is headquartered in California. - The company said its platform can evaluate up to 10 billion molecules across proteins, antibodies, small molecules, nucleic acids and chemical formulations within hours to weeks. - The company provided social media links: LinkedIn, YouTube and X.