Robert Marino
CEO
Qubit Pharmaceuticals
Qubit Pharmaceuticals offers a quantum‑AI platform that combines first‑principles synthetic data with a quantum‑enabled foundation model to deliver atomistic simulations of molecular behavior at near‑experimental accuracy. By unifying advanced quantum chemistry methods (DFT, QMC, sCI, FCI) with deep learning, the system predicts structures, reactivity, and binding affinities across the chemical space, dramatically reducing experimental testing and accelerating drug‑discovery pipelines for pharma and biotech R&D.
- Artificial Intelligence
- Biotechnology
- Quantum Computing
Updated 5 months ago
Funding
Raised to date
$16.9MRaised 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
Drug discovery often stalls because existing computational chemistry methods lack the accuracy to reliably predict molecular behavior, especially for complex targets such as RNA, covalent binding sites, and solvent effects. This forces extensive experimental testing, prolonging timelines and inflating costs.
Solution
Qubit Pharmaceuticals addresses this bottleneck with a quantum‑AI platform that combines first‑principles synthetic data, quantum‑enabled foundation models, and advanced AI techniques to deliver atomistic simulations at near‑experimental accuracy. Their ATLAS platform generates proprietary high‑precision molecular data using transfer learning across DFT, QMC, sCI and FCI methods, then trains the FeNNix‑Bio1 foundation model to predict structures, reactivity, and binding affinities across the entire chemical space. By unifying physics‑based quantum calculations with deep learning, the system can model ground‑state energies, solvent configurations, and dynamic protein‑RNA interactions with orders‑of‑magnitude fewer quantum operations, making it practical on noisy intermediate‑scale quantum hardware. The resulting predictions reduce the need for laboratory synthesis by at least tenfold and cut candidate selection time in half, accelerating the path from concept to clinical candidate.
Target Audience
Primary customers are pharmaceutical R&D teams, biotech companies, and contract research organizations that need high‑accuracy computational tools for small‑molecule and RNA‑target drug discovery.
Features
- Proprietary first‑principles synthetic database created via transfer learning across multiple quantum chemistry methods (DFT, QMC, sCI, FCI) for fast, cost‑effective data generation
- World‑leading quantum‑enabled foundation model (FeNNix‑Bio1) that delivers quantum‑level accuracy while remaining scalable for large‑scale drug‑discovery pipelines
- Greedy Gradient‑Free Adaptive VQE algorithm that efficiently finds molecular ground states on noisy quantum hardware with minimal measurements
- Analog quantum computing workflow (neutral‑atom qubits) for accurate solvent‑configuration prediction in protein binding sites
- Integrated polarizable force field (AMOEBA) and Lambda‑ABF free‑energy method for high‑precision RNA‑small‑molecule binding affinity calculations
- End‑to‑end pipeline that automates molecule generation, reactivity prediction, and binding‑site modeling, reducing experimental validation by ≥10×