As autonomous AI agents evolve from conversational assistants into true scientific collaborators, the pharmaceutical industry is entering the next chapter of its AI transformation, one in which discovery workflows are not merely assisted by AI, but orchestrated by it. To help accelerate the advent of Pharmaceutical Superintelligence, Insilico Medicine (03696.HK), a clinical-stage generative AI-driven drug discovery company, today announced that the Pharma.AI Webinar 2026 Q3 Fall Updates will take place on September 30, from 10 EST. Registration and event details are available at: https://insilico.zoom.us/webinar/register/2417878444165/WN_gLMYTGF2RYW3EoupiucfTA#/registration
The Pharma.AI 2026 Q3 Fall Update will spotlight the rise of the agentic layer across the life sciences. With Model Context Protocol (MCP) servers now available across the Pharma.AI stack, autonomous AI agents can connect directly to Insilico's biology, chemistry, and biologics engines — automating multi-step discovery workflows from within the AI environments researchers already use. The event will also introduce new scientific skills for the PandaOmics Agent, showcase two new open-access resources for rigorous AI evaluation — including the O3DC Consortium and DDD Benchmarks — and preview the multi-agent Virtual Aging Cell platform alongside the latest specialist models to emerge from the MMAI Gym, underscoring why domain-specific foundation models remain essential to biological, chemical, and translational research.
"The next leap in pharmaceutical AI is not one bigger model ,it is an ecosystem of specialized engines, scientific agents, and rigorous benchmarks working as one," says Alex Aliper, PhD, President of Insilico Medicine. "With Pharma.AI now speaking MCP, researchers can plug our platforms directly into their own AI environments and let autonomous agents run real discovery workflows — from target evaluation to antibody design. That is how we move beyond AI-powered tools to true pharmaceutical superintelligence."
Generative Biologics accelerates early-stage drug discovery by generating novel, high-affinity biologics against challenging targets in under 72 hours. Powered by more than 10 generative AI models combined with physics-based simulation algorithms, the updated suite introduces powerful agentic capabilities to large-molecule design. Key updates include a dedicated Epitope Prediction Workflow equipped with custom scoring functions to deliver high-precision binding affinity predictions and structural interface optimization for complex antibody-antigen targets. Additionally, the new Generative Biologics MCP integration enables autonomous AI agents to connect directly into Insilico's biomolecule stack, driving fully automated, end-to-end antibody design and screening workflows.
PandaOmics is Insilico Medicine's AI-driven platform for biological target discovery and drug program evaluation. The latest platform update introduces expanded agentic capabilities, seamless Model Context Protocol (MCP) deployment, and refined target prioritization algorithms. Through Next-Gen PandaOmics Agent Skills, researchers can now unlock specialized scientific workflows including Single-Cell Signature analysis for granular biological insight, CADD Structural Review for target druggability assessment, and automated Indication Prioritization to accelerate clinical translation. Furthermore, integrating the PandaOmics Agent via MCP connects the engine directly to proprietary AI infrastructures, enabling autonomous agents to execute end-to-end target discovery and validation workflows. Core algorithmic capabilities also receive a major upgrade in PandaOmics Classics with updated Score Weights in TargetID, delivering higher-precision target identification and hypothesis generation.
Chemistry42 is Insilico Medicine's AI-driven platform for the design and discovery of novel small molecules. By combining generative model ensembles with advanced physics-based methods, it helps researchers create and optimize compounds across hit identification, hit-to-lead, and lead optimization programs.
Key updates include a major upgrade to the pharmacophore reward module, adding excluded volumes and more flexible pharmacophore hypothesis generation to enable tailored, specific 3D constraints for molecular generation. We will also announce the integration of ChemCensor into Retrosynthesis to improve the quality of retrosynthesis predictions. Additionally, Pharma.ai MCP connectors bring expanded chemistry capabilities to MCP-enabled apps, enabling complex pipelines that combine molecular generation, property profiling, retrosynthesis, MDFlow, and Alchemistry within connected AI workflows.
Specialist models trained through MMAI Gym, with each specialist addressing multiple related tasks within its domain. The latest release includes models for ADMET prediction, GPCR and kinase potency prediction, and single-step retrosynthesis, alongside specialists for longevity applications. Across chemistry and biology, our evaluations demonstrate state-of-the-art performance on more than 70 benchmark tasks, with models matching or outperforming established computational methods and larger general-purpose LLMs on selected tasks.
A training and benchmarking environment that adapts foundation models into scientific specialists for drug discovery and longevity research. It combines curated scientific datasets, supervised fine-tuning, and reinforcement learning with evaluation on public and proprietary benchmarks to develop models capable of solving multiple related tasks within a domain. Our latest paper with Liquid AI, accepted to the EMNLP 2026 Industry Track, demonstrates this approach with 2.6B-MMAI and 24B-A2B-MMAI, multitask chemistry models.
Beyond the core platforms, the Fall Update highlights a new generation of open-access research infrastructure designed to accelerate community-wide innovation in AI-driven drug discovery.
Join Insilico Medicine for our exclusive Pharma.AI Fall Event, where we move beyond generic AI hype to demonstrate real-world, industrial-strength execution in drug discovery. This virtual event brings together pharmaceutical executives, computational biologists, and medicinal chemists to explore the frontier of Pharmaceutical Superintelligence (PSI) and the practical deployment of agentic workflows.
Secure your spot by registering at https://insilico.zoom.us/webinar/register/2417878444165/WN_gLMYTGF2RYW3EoupiucfTA#/registration