MedGraph - RubieTM
AI-automated Platform
for Rapid & Precise Drug Design
Screen a curated library of compounds, including FDA-approved drugs, investigational drugs, and PubChem/ChEMBL compounds, against a target protein of interest to identify potential binders and accelerate drug discovery
Scalable
All our platforms are real-time, scalable products deployable in both cloud and on-premise environments. They feature a highly secure and infrastructure-agnostic architecture.
Agile
Our AI-augmented, data-intensive computing platforms significantly reduce drug discovery time from years to weeks.
MedGraph - Rubie TM
With two different approaches, our data-driven and AI accelerated platform is a one stop solution for drug repurposing
- 1.Knowledge graph
Our knowledge discovery engine consolidates data from diverse sources, extracts valuable insights, and creates a knowledge graph repository. Clients have full access to this repository for identifying drug repositioning opportunities and more.
- 2.Traditional Docking Approach (For input target)
A) LEAD IDENTIFICATION
Our current database of FDA-approved and investigational drugs is docked to the target's active site. Our search engine selects the most potent drugs with promising activity profiles. To enhance accuracy, we employ post-docking filtering using a protein-ligand interaction fingerprint, considering the structure-activity relationship for active identification.
B) LEAD OPTIMIZATION
Molecular dynamics-FEP precisely calculates the binding free energy of protein-ligand complexes, mimicking the biological environment. It also scrutinizes atomic-level conformational stability and changes induced by protein-ligand dynamics.
- 3.Reverse Docking Approach (For input drug)
A) TARGET IDENTIFICATION
We maintain a regularly updated database of structurally prepared targets covering a wide spectrum of therapeutic and specialty areas. Utilizing HPC-parallel computing, we conduct extensive reverse docking to discover new targets for the ligand of interest. This approach is renowned for identifying safe targets and novel drug use cases. To enhance accuracy and reduce false positives and negatives in classical docking programs, we employ a post-docking rescoring function based on protein-ligand interaction fingerprints within our pipeline.
B) TARGET OPTIMIZATION
We employ Free Energy Perturbation Molecular Dynamics (FEP-MD) simulations to accurately estimate the absolute binding free energy of the complex and analyze conformational changes resulting from protein-ligand binding.
