Insilico Medicine's PandaOmics Enables AI-Driven Indication Expansion Strategy for THPharm's Phase 3 Metabolic Disease Program

THPharm, a company specializing in the development of metabolic disease drugs, announced that it is actively advancing a bio-AI-based 'reverse engineering' drug development strategy in partnership with Insilico Medicine, a leading global AI drug discovery company. This joint research is an indication expansion strategy that uses confirmed pharmacological effects from the non-clinical stage as a starting point, leveraging bio-AI technology to reverse-engineer optimal diseases, mechanisms of action, and biomarkers.

While conventional drug development typically follows a forward approach—selecting a specific disease first and then screening for suitable candidates—THPharm’s reverse engineering strategy approaches from the opposite direction. Based on multiple pharmacological effects and phenotypes already proven in non-clinical trials, bio-AI analyzes gene expression, pathways of action, diseases, and biomarkers to select indications with high development value. This approach lowers the initial risks associated with discovering new substances and allows resources to be concentrated on programs with a high probability of success by utilizing existing data.

The two companies have built a robust analysis infrastructure by introducing Insilico Medicine’s core bio-AI platform, 'PandaOmics'. They are currently conducting integrated analysis of THP-001's drug targets, literature-based knowledge graphs, public omics data, and post-treatment gene expression data. The system derives new indication and biomarker candidates by comprehensively analyzing downstream signals of drug targets and related gene networks.

Currently, in the primary data integration stage, a total of 16 public datasets and 269 samples have been secured to establish a foundation for gene expression and meta-analysis. Initial analysis connecting the observed non-clinical effects with disease-specific molecular mechanisms and biomarker candidates is underway. After establishing this analysis system for THP-001, a core asset currently in multinational Phase 3 clinical trials, THPharm plans to gradually expand its application to its drug delivery system (DDS)-based metabolic disease follow-up candidates, which have already secured non-clinical efficacy and safety/toxicity profiles.

Major metabolic disease areas such as heart failure, fatty liver disease, and obesity are primarily being considered for indications. Rather than developing multiple diseases simultaneously, THPharm plans to prioritize targets based on a comprehensive evaluation of AI analysis results, biomarker reproducibility, non-clinical validation feasibility, and marketability. The derived indications and biomarker candidates will undergo further validation in disease-specific cell and animal models, and only elite candidates demonstrating reproducible efficacy and mechanisms will enter early-stage clinical trials.

"Artificial intelligence enables us to extract far more value from existing biological data than was previously possible," said Alex Zhavoronkov, PhD, Founder and CEO of Insilico Medicine. "We're excited to support THPharm's reverse engineering strategy with PandaOmics, helping connect pharmacological effects to disease biology and identify promising new therapeutic opportunities."

"We will build a capital-efficient drug development model that selects clinically valuable pathways by linking confirmed pharmacological effects with disease mechanisms, ultimately creating multiple pipelines from a single asset," said Tae Hee “Theo” Han, CEO, THPharm Corp.