Deep Apple Therapeutics uses a deep learning‑driven platform that combines cryo‑EM structural data, AI‑based pocket extraction, molecular dynamics, and ultra‑high‑throughput virtual screening of massive internal libraries to identify novel small‑molecule candidates. By modeling protein flexibility and rapidly evaluating billions of virtual compounds, the engine accelerates discovery and optimization of therapeutics for inflammatory, immune, metabolic, and endocrine targets, offering pharma and biotech partners a faster path to potent drug candidates.
Funding
$52M 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
Identifying potent small‑molecule candidates for specific disease targets traditionally requires extensive experimental screening and iterative chemistry, which is time‑consuming, costly, and limited by the size of physical compound libraries.
Solution
Deep Apple Therapeutics employs a deep learning‑driven drug discovery engine that integrates cryo‑EM structural data, AI‑based pocket extraction, molecular dynamics simulations, and ultra‑high‑throughput virtual screening of internally generated virtual libraries. By modeling protein conformational flexibility and rapidly evaluating billions of virtual compounds, the platform can pinpoint novel small‑molecule candidates for well‑validated biological targets across inflammatory, immune, metabolic, and endocrine disease areas. The approach accelerates candidate identification and optimization, enabling the company to advance multiple therapeutic programs in a fraction of the time required by conventional methods.
Target Audience
Primary customers are pharmaceutical and biotech companies seeking accelerated discovery of small‑molecule therapeutics for validated targets in inflammatory, immune, metabolic, and endocrine indications.
Features
- Cryo‑EM enabled structural biology to generate high‑resolution protein models for accurate target definition
- AI‑powered pocket detection and protein movement modeling to capture dynamic binding sites
- Molecular dynamics simulations that assess ligand‑protein interactions over realistic conformational landscapes
- Ultra‑high‑volume virtual screening of massive, internally curated virtual chemical libraries
- Deep learning models that prioritize compounds based on predicted potency, selectivity, and drug‑like properties
- Integrated workflow that combines computational predictions with expert medicinal chemistry insight for rapid candidate advancement