PozeSCAF Inc. (also trading as PozeSCAF Discovery Solutions) was founded in 2020 and operates as a preclinical drug discovery CRO based in India, with incorporated presence in the United States. The company recently rebranded to PozeSCAF — a name derived from two central concepts in small molecule drug discovery: molecular pose (the three-dimensional binding orientation of a ligand within a target binding site) and scaffold (the core chemical framework around which medicinal chemistry exploration is conducted). The company is led by its founding team, which includes Ravi Kumar Muttineni, Founder and Chief R&D Officer as a primary scientific contributor.

PozeSCAF’s model integrates computational drug discovery — encompassing generative AI, machine learning, molecular dynamics simulations, free energy perturbation (FEP) studies, and quantum mechanics-based docking — with in-house medicinal chemistry and synthetic chemistry capabilities, enabling it to take a programme from target validation through to the delivery of lead candidates with accompanying SAR data and synthesised material. This integrated in silico–to–synthesis workflow differentiates PozeSCAF from purely computational CROs that do not provide physical compounds, and from pure synthesis houses that lack AI-driven design capabilities.

The company’s client base includes academic medical institutions and biotechnology organisations, with named clients including Penn State College of Medicine, TGen (Translational Genomics Research Institute), Tuskegee University, Stingray Therapeutics, and the Schepens Eye Research Institute (Harvard Medical School). The company’s scientific team has a published track record in peer-reviewed chemistry journals, including work on total synthesis, structure-based virtual screening, and in silico target identification.

Key Products and Services

AxDrug™ Platform

• Proprietary AI and computational chemistry platform integrating generative AI, machine learning, deep learning, and physics-based computational methods for small molecule drug design
• Chemical space coverage spanning a database of 20 billion drug-like small molecules generated through generative AI and commercial library fusion, used as the foundational screening resource
• Graph-based transformer generative models operating within a Reinforcement Learning framework for de novo generation of potent, selective, and drug-like compounds
• Continually evolving ML/DL models for candidate prioritisation from large chemical spaces

Small Molecule Drug Discovery Services

• Target Validation — AI-enhanced protein structure prediction for disordered and complex targets, druggable site identification, and computational target tractability assessment
• Hit Identification — virtual screening of extensive compound databases using consensus docking models, active learning docking with soft potentials, and quantum mechanics-based scoring; delivered as in silico hit lists with optional synthesis and in vitro confirmation
• Hit-to-Lead Generation — scaffold hopping, compound enumeration, and binding affinity prediction using quantum mechanics; generative AI-driven exploration of chemical space around validated hits to identify structurally distinct lead series
• Lead Optimisation — multi-parameter optimisation combining generative AI with molecular dynamics simulations and FEP studies; ADME and toxicity prediction models for drug-likeness and safety-related property profiling; off-target prediction and polypharmacology assessment
• Discovery Synthesis — medicinal chemistry and synthetic chemistry delivery of small molecules, peptides, PROTACs, macromolecules, and carbohydrate-based compounds from milligram to kilogram scale; custom peptide synthesis services available

Specialist Modality Design

• PROTACs Design — computational design and synthesis of Proteolysis Targeting Chimeras (PROTACs) for targeted protein degradation programmes
• Molecular Glues — design and optimisation of molecular glue degraders
• Biologics Design — AI-enabled biologics design services, including antibody and peptide engineering applications

In Silico Toxicology

• Mutagenicity and toxicity prediction using in silico models to flag safety liabilities early in the discovery process, prior to synthesis and in vitro profiling

Integrated Drug Discovery

• End-to-end integrated programme delivery from target validation through to IND-stage candidate identification, combining all computational, chemistry, and biology capabilities under a single project management framework

Industry Positioning

PozeSCAF occupies a focused niche at the computational and early synthetic end of the drug discovery CRO landscape, targeting clients who require AI-driven small molecule design capability combined with the ability to rapidly synthesise and deliver physical compounds — an integration that compresses the design-make-test cycle relative to programmes relying on separate computational and chemistry vendors. Its AxDrug™ platform, built around generative AI and physics-based computational methods, positions it within a growing category of AI-native drug discovery CROs that have emerged in response to the pharmaceutical industry’s increasing investment in computational approaches. The company’s India base provides a cost structure that makes its integrated offering accessible to academic and early-stage biotech clients who would face prohibitive costs at equivalent Western CROs. Published peer-reviewed output and named client relationships with US academic medical institutions lend credibility to the team’s scientific capabilities.