This startup develops optimized AI models specifically for drug discovery, accelerating R&D for pharmaceutical companies. Their system offers features like protein and enzyme design, antibody engineering, and small molecule discovery, streamlining the drug development process.
Funding
Funding not disclosed
Founders
Product
Problem
Traditional protein engineering methods often involve extensive experimentation and fail to fully capture epistatic effects, leading to suboptimal protein variants and prolonged R&D cycles. Optimizing multiple protein properties simultaneously, such as activity, stability, and solubility, presents a significant challenge with conventional techniques.
Solution
BioChest offers an AI-powered platform that accelerates biotech R&D by predicting improved protein variants with fewer experiments. Their machine learning models learn from experimental data to overcome epistasis and optimize multiple properties concurrently. The platform enables scientists to identify high-value mutations, reduce experimental iterations, and achieve project goals faster. BioChest's technology is applicable to enzyme, antibody, and peptide design, allowing for the optimization of properties such as thermostability, activity, solubility, and expression.
Target Audience
BioChest targets scientists and researchers in the biotechnology and pharmaceutical industries who are involved in protein engineering, enzyme design, antibody development, and peptide engineering.
Features
- Experimentally validated machine learning models that overcome epistasis.
- Multi-property optimization, allowing for simultaneous improvement of stability, activity, and other desired characteristics.
- AI-driven prioritization of protein variants to reduce the number of experimental rounds needed.
- Support for enzyme design, including optimization of activity, thermostability, solubility, and solvent stability.
- Capabilities for antibody design, focusing on affinity, thermostability, solubility, solvent stability, and expression.
- Peptide design features, including optimization of affinity, stability, solubility, and cell penetration.