AI-Native Drug Discovery

Antibodies at
picomolar precision,
in weeks.

AINN-P1, our protein foundation model, has produced sub-nanomolar leads on 15 of 40 validated targets — 6 at single-digit picomolar — across 2,872 wet-lab tested molecules.

Explore the platform → Partner with us

Antibody structure rendered in translucent cyan

15/40

Validated targets with sub-nM leads

Single-digit picomolar campaigns

2,872

Molecules experimentally tested in wet lab

167M

Parameter protein foundation model (AINN-P1)

Our Mission

We are rebuilding drug discovery from the sequence up — making therapeutic design computational, honest, and partner-ready.

Most AI drug-discovery platforms stop at a demo. We go further: our models are trained on industry-grade proprietary data and validated at every stage by wet-lab experiments, so what we deliver to pharma partners is already de-risked.

The result is a different kind of handoff — not a screening score, but a program: patentable, validated, licensable, and ready for your development pipeline.

Sequence-first design Protein foundation model, no 3D structure required

Wet-lab validated Every lead confirmed experimentally

Patentable IP Clean freedom-to-operate on novel compositions

Licensed to partners Programs ready for pharma development

Platform

SentinusAI® — a protein foundation model that produces binders, not scores.

Built on AINN-P1, SentinusAI combines sequence modeling, affinity prediction, and generative design into a single pipeline. Trained on proprietary assay data and continuously benchmarked against wet-lab outcomes.

01 · Antibody

De novo & affinity maturation

IgG, Fab, scFv, VHH, bispecifics. Picomolar leads on IL-13, IL-25, IL-36R, TSLP.

Sub-nM · 15/40 targets

02 · Small molecule

CarbonAI — generative chemistry

De novo small molecules, PROTAC design, scaffold hopping. CRBN neosubstrate selectivity panels.

10¹⁰ virtual · overnight

03 · Peptide

PeptideAI — cyclic & stapled

GLP-1 analogs, cyclic peptides, stapled therapeutics. 3.2M-peptide screens with 90%+ accuracy.

3.2M screens

04 · Cell therapy

CellulaAI — CAR-T engineering

CAR construct optimization, activation prediction, persistence modeling.

Preclinical validated

The Science

Published, benchmarked, and reproducible.

AINN-P1 outperforms finetuned ESM2 on leave-program-out AUC for VHH binders (0.81 vs 0.68) at a fraction of the parameter count. Our methods are peer-reviewed, our benchmarks are external, our failures are published alongside our successes.

0.81

Leave-program-out AUC

AINN-P1 on VHH affinity maturation, vs 0.68 for finetuned ESM2 — parity-plus at 3.9× fewer parameters.

482

Peer-reviewed citations

Methods, benchmarks, and validation studies published across antibody, protein-language-model, and chemistry venues.

16+

Years of computational heritage

Founders bring sixteen-plus years of structure-free affinity modeling and protein engineering to the company founded in 2021 — not a ChatGPT-era pivot.

Read the AINN-P1 preprint →

Pipeline

Validated programs available for licensing.

A selection of in-house antibody programs with wet-lab-confirmed picomolar binding. Full data room available under CDA.

Target	Modality	Best Kd	Stage
IL-13 — atopic dermatitis, asthma	VHH / scFv	~1 pM	Lead optimization
IL-25 — atopic & T2 inflammation	IgG	~1 pM	Lead optimization
IL-36R — generalized pustular psoriasis	IgG	~1 pM	Lead optimization
TSLP — severe asthma	IgG / Fab	~1 pM	Lead optimization
IL-15 × IL-21 bispecific — oncology	Bispecific IgG	single-digit pM	Affinity maturation
TNF-α × OX40L bispecific — autoimmune	Bispecific IgG	single-digit pM	Affinity maturation
TROP2 — oncology ADC payload target	IgG / Fab	sub-nM	Wet-lab validated
B7-H3 — solid tumors	IgG	sub-nM	Wet-lab validated

All affinities measured by SPR or BLI from AINN-P1-designed campaigns. Figures from Antibody Model Experimental Validation Statistics (Sep 2026) — 40-target dataset, available under CDA.

Team

Scientists, engineers, and chemists who built this before AI was a buzzword.

Our team brings together decades of experience in protein engineering, cheminformatics, machine learning, and pharmaceutical commercialization.

Founder & CEO

"We report what we found, not what we hoped. We publish failures alongside successes, disclose uncertainty honestly, and correct the record when we are wrong. Metrics are earned, not marketed."

Dr. Lurong Pan — PhD, computational chemistry. Sixteen years in structure-free affinity modeling. Author of 40+ peer-reviewed publications. Named inventor on multiple issued patents.