Molcure provides an AI-driven antibody discovery platform that generates de novo VHH antibody sequences using a proprietary large language model trained on over 1 billion antibody and peptide datapoints. The end‑to‑end workflow combines AI design, high‑throughput screening, next‑generation sequencing, and directed evolution to rapidly prioritize high‑affinity leads and optimize candidates for biopharma and research partners.
Funding
$7.3M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Discovering high-affinity therapeutic antibodies traditionally relies on large library screens and extensive wet‑lab experimentation, which are time‑consuming, costly, and limited by existing sequence diversity. This slows the development of novel biologics, especially when rapid response to emerging targets such as viral variants is required.
Solution
MOLCURE offers an AI-driven antibody discovery platform that generates de novo VHH antibody sequences without prior knowledge of the target. Their proprietary large language model, trained on over 1 billion antibody and peptide datapoints, predicts binding affinities and epitope coverage, enabling rapid prioritization of candidates. The platform integrates high‑throughput screening, next‑generation sequencing, and directed evolution experiments to validate and refine designs. By delivering diverse, high‑affinity leads—demonstrated by an 83 % sub‑micromolar hit rate against SARS‑CoV‑2 RBD—the system accelerates therapeutic candidate identification while reducing experimental workload.
Target Audience
Primary customers are biopharmaceutical companies and research organizations seeking rapid antibody lead generation and optimization for therapeutic programs, as well as partners requiring AI‑augmented molecular design services.
Features
- Proprietary Antibody Large Language Model built from scratch for sequence generation and affinity prediction
- Database of >1 billion antibody/peptide datapoints enabling robust training on biological data
- End‑to‑end workflow combining AI design, high‑throughput screening, NGS, and directed evolution validation
- Accurate KD prediction with strong correlation to experimental measurements, supporting efficient candidate ranking
- Ability to design antibodies targeting diverse epitopes, confirmed by independent epitope mapping
- De novo generation of novel VHH antibodies with picomolar to nanomolar affinities, expanding beyond traditional library limits