In silico perturbation (ISP) offers a scalable approach to study gene regulation and prioritize therapeutic targets. We present a biologically grounded evaluation of single-cell foundation models using metrics for cell state separation, perturbation fidelity, and recovery of perturbed genes, with functional analyses across gene categories and contexts. Our results reveal model-specific strengths and limitations, guiding selection and optimization and aligning computational predictions with experimental readouts to accelerate decision-making in drug development.

Advanced AI is making it possible to discover new oral therapeutics for chronic disease and address significant unmet patient needs. Montai’s CONECTA platform integrates proprietary bioassay data from a diverse chemical space and multimodal foundation models built on billions of chemical and biological datapoints. This platform enables us to find diverse compounds inspired by nature’s chemical intelligence that can solve previously undruggable targets with the highest probability of becoming successful drugs.

We have built Enchant, a large-scale multimodal transformer for predicting molecular properties spanning the full scope of drug discovery and development. A key part of the success of Enchant in driving real discovery programs is integration with a flexible high-throughput experimental facility for data generation.

Intracellular targets present major challenges for traditional therapeutic modalities. This talk introduces an AI-driven approach for designing peptide-based medicines capable of engaging targets inside the cell. By combining machine learning models, predictive property estimation, and iterative design workflows, the platform accelerates the generation and ranking of peptide candidates with improved likelihood of successful intracellular activity. The talk will highlight how AI can broaden therapeutic possibilities and streamline discovery for previously difficult-to-address targets.

Neurosteroids are a distinct class of endogenous steroids that are synthesized within the central nervous system. They rapidly modulate neuronal excitability by acting on membrane-bound neurotransmitter receptors, such as GABA_A receptors. The clinical relevance of neurosteroids has been highlighted by the recent FDA approval of neurosteroid-based therapeutics for treating postpartum depression. Our research uses AI-enabled discovery platform for medicinal chemistry. We utilize the unique IOCB Steroid Compound Library and integrate chemoinformatics with high-content in vitro bioactivity profiling. This allows us to uncover novel structural motifs and polypharmacological signatures. This strategy helps decipher the complex activities of neuroactive steroids that lack classical hormonal effects and identifies new compounds capable of selective GABAergic modulation. Together, these advances provide proof of concept for targeted small-molecule discovery in CNS pharmacology and translational neuroscience.

This talk discusses how AI-driven analytics optimize compound design, prioritization, and lead progression in medicinal chemistry workflows.

Medicinal chemistry patents represent an underused resource for drug discovery. Between 2000 and 2024, the per-year medicinal chemistry-centric WO filings rose from 2,636 to 9,521 and include bioactivity data for millions of structure–activity relationships (SAR). Established tools such as OPSIN and DECIMER can convert chemical names and images to structures; PubChem now hosts 48 million patent-extracted compounds including 30 million from SureChEMBL and 22 million from PATENTSCOPE that  enable text and chemistry searches. In addition semi-automated SAR curation from by BindingDB (PMID39574417) has submitted over 1,2 million patent-extracted binding measurements to PubChem BioAssay. Recent advances in AI have the potential to extend the transformation of this data into actionable knowledge. Paradoxically, the combination of new and established workflows are making patent data FAIR-er than paywalled literature, unlocking new opportunities to accelerate discovery.

Model Context Protocol (MCP) is a flexible framework that enables AI agents and agentic AI systems to access and interpret distributed data. We will present a practical and scalable approach for constructing and utilizing MCP to traverse public life-sciences repositories via their API endpoints, enabling rapid, context-aware data gathering, assimilation, and interpretation to accelerate research and discovery. The architecture will be reviewed, with examples shown, and lessons learned from building a scalable MCP server and AI applications that leverage it.

In Research, we have achieved notable success in driving GenAI enterprise adoption and digital upskilling efforts. Currently, we have 80% coverage of our scientists, with an average of six training sessions completed per person. Our approach has focused on integrating upskilling directly into workflows, ensuring that training efforts connect to relevant, discipline-specific use cases.

Strategic planning in biopharma faces regulatory complexity and uncertainty, requiring predictive methods. AI transforms program management by enhancing decision-making, operational efficiency, and risk assessment through machine learning, NLP, and advanced analytics. It optimizes clinical trials, predicts enrollment, and improves site selection. AI also supports regulatory strategy by monitoring global policy shifts. Insights from patents and trials guide portfolio choices, enabling rapid adaptation and discovery of new therapeutic opportunities.

Advances in multimodal AI and computational biology now enable rapid discovery of small molecules that repair mitochondria, opening a previously intractable target space for neurodegenerative and aging-related diseases. This talk will share how modern AI tools, target-specific biophysics, and automated chemistry converge to accelerate mitophagy-enhancing therapeutics into the clinic. Real-world case studies from Vincere Bio will illustrate how AI platforms translate into validated assets nearing the clinic, resulting in partnerships with industry leaders and investment-ready programs.

While AI dominates early-stage drug discovery discussions, pharmaceutical organizations struggle to connect these innovations to downstream clinical operations and real-world patient care. This panel tackles three critical gaps in current AI implementation: 1) integrating AI across R&D functions from target identification through clinical development, 2) leveraging digital health platforms and AI as the bridge between research insights and patient outcomes, and 3) enabling cross-team collaboration and external partnerships through shared AI infrastructure. Industry leaders from biopharma, hospitals, and digital health will debate what it really takes to break down silos between discovery, development, clinical, and commercial teams. Through candid discussion of real implementations, panelists will explore how to build communication channels that connect internal teams with external partners (hospitals, payers, and patients), creating an AI ecosystem that delivers measurable impact across the full therapeutic lifecycle.