Huafeng Xu
CEO
Atommap
Atommap uses computational modeling to simulate biomolecular motion and identify dynamic protein-protein interfaces. Their generative design platform creates novel molecular glues and degraders by stabilizing these interfaces, accelerating the discovery of targeted therapeutics.
- Artificial Intelligence
- Data & Analytics
- Biotechnology
Updated 6 months ago
Funding
Raised to date
$7.1MRaised 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.
Funding rounds are not available yet.
Founders
Product
Problem
Traditional drug discovery methods often struggle to identify novel therapeutic molecules by solely focusing on static protein structures, limiting the exploration of dynamic protein-protein interactions. This approach can miss opportunities to stabilize or destabilize transient interfaces, which are crucial for modulating cellular function and treating diseases.
Solution
Atommap employs computational modeling to simulate biomolecular motion and uncover novel therapeutic strategies by analyzing dynamic protein-protein interfaces. Their generative design platform creates diverse molecular glues and degraders by stabilizing these interfaces, effectively reprogramming protein function. Predictive computational assays are utilized to accurately evaluate the potency and functional effects of these designed molecules, accelerating the identification of promising drug candidates. This data-driven approach allows for the exploration of previously inaccessible design spaces, leading to the discovery of molecules with enhanced specificity and efficacy.
Target Audience
Atommap's primary customers are pharmaceutical and biotechnology companies engaged in early-stage drug discovery, particularly those focused on developing novel therapeutics for complex diseases through protein-protein interaction modulation.
Features
- Computational modeling of biomolecular motion to identify dynamic protein-protein interfaces.
- Generative design platform for creating molecular glues and degraders by stabilizing protein-protein interactions.
- Predictive computational assays for high-throughput evaluation of molecular potency and functional effects.
- Binding free energy calculations incorporating pocket flexibility for accurate affinity predictions.
- Autonomous generation of pocket-compatible molecular designs.
- Prediction of protein degradation efficacy, including the induction of ubiquitin transfer.
- Development of mutant-selective degraders targeting specific oncogenic proteins.
- Virtual creation of large libraries of PROTACs and molecular glues.
- Identification of novel protein-protein interfaces through target insights.
- Enumeration of synthesizable degrader designs.