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.

Foundation and multimodal AI models are beginning to shape drug discovery by making predictions that outperform human intuition while resisting human explanation. This creates a familiar but unsettling moment in science: results that work before we fully understand why. When such models influence decision‑making in drug discovery, what standards should govern trust, validation, and use? And what is the role of the computational biologist in guiding biology into the AI era?

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 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.

Pharmaceutical R&D is stalled by silos and manual tasks. Quantori’s Q-Suite eliminates these barriers, unifying wet and dry labs. Q-Scientist ensures data lineage, while Q-Discover’s AI optimizes candidate design. Q-HPC and Q-Image automate infrastructure and analysis, and Q-Portal/Q-Share drive collaboration. This agentic ecosystem compresses the Design-Make-Test-Analyze cycle from weeks to days, turning the "Laboratory of the Future" into reality today.

ExScalate, the Dompé computational drug-discovery engine, integrates generative AI, virtual screening, and ML models to evaluate billions of molecules across thousands of therapeutic targets. In the emerging landscape of agentic AI, where autonomous systems plan, execute, and learn from experimental cycles, ExScalate is evolving from a high-performance prediction platform into an integrative intelligence layer. By connecting in silico design to laboratory verification through closed-loop workflows and feeding experimental outcomes back into its predictive models, ExScalate compresses the path from target identification to candidate nomination, accelerating drug discovery while continuously improving the quality of its predictions.

• How are knowledge graphs supporting reliable scientific intelligence
• Lessons from early deployments
• Remaining challenges and barriers to scale​

• Learn how leading global pharma companies are applying quantum principles to real-world research. 
• Discover the quantum companies transforming traditional processes around drug development and drug discovery.
• Discuss how quantum, along with HPC and AI, is poised to help researchers tackle historically intractable problems and potentially find new treatments for diseases like cancer, Alzheimer’s, and diabetes.​

• Where are we today? Are AI tools truly integrated into workflows, or still operating in silos?
• What changes with agents? How do LLM-based agents shift drug discovery from prediction to decision-making?
• What is blocking autonomy? Data quality, validation, trust, or organizational readiness for AI-driven discovery?​

• Where are the highest-value collaboration opportunities between academia/TTOs and industry (biopharma, startups, AI/data, investors), and what makes them actually work?
• What types of partnerships are most effective in practice (licensing, co-development, startup creation, sponsored research), and how do both sides evaluate quality and fit quickly?
• What specific formats, access points, or structures at the Bio-IT event would actually drive follow-up, partnerships, and deal-making?

• How do CIOs enable rapid AI and data innovation without breaking governance, compliance, or data integrity frameworks?
• What separates pilot-stage innovation from scalable, production-grade systems? Where do most organizations fail?
• How do leaders manage emerging risks (model bias, data provenance, regulatory exposure) while still pushing competitive advantage?
  

• How real-world data is being used alongside clinical and experimental data
• Challenges in standardization, access, and regulatory acceptance
• Opportunities to improve outcomes, access, and long-term patient insights

• Why critical experimental knowledge is lost across ELNs, LIMS, and siloed teams, and the cost of reinventing work 
• How structured experimental memory makes past decisions, failures, and context reusable across teams
• How organizations can make scientific knowledge reusable for both humans and AI

• How to think strategically about IP early in biotech and AI-driven research
• Common pitfalls in patent and trademark applications and how to avoid them
• Navigating ownership, protection, and commercialization of innovations
  

• Why do current workflow systems fail most scientists in practice? 
• Can no-code and AI-driven workflows meet standards for reproducibility, validation, and clinical readiness? 
• What would a “production-ready” workflow ecosystem actually look like across teams and organizations?

• The gap between AI ambition and the reality of data foundations, platforms, and operating models
• What “AI‑ready data” actually means in practice—beyond pilots, dashboards, and proofs of concept 
• Where AI initiatives most often break down: data integration, data quality, metadata, and governance at scale​

AI agents—systems combining large language models with domain-specific tools and self-correction—are emerging to address the growing gap between spatial omics data generation and analysis. This talk surveys recent works organized by agent topology and goal, distinguishing systems that execute predefined analytical workflows from those that autonomously generate and test biological hypotheses. We trace the arc from early single-agent systems to generalist platforms spanning 25+ biomedical subfields, examine the rapidly maturing infrastructure layer, benchmark evidence showing that agents solve fewer than 50% of real-world tasks, and the spatial-to-therapeutic pipeline where agentic systems are beginning to influence target identification and downstream decision-making. We close with open questions around accuracy, reproducibility, regulatory frameworks, and the evolving balance between human and machine creativity in scientific discovery.

We present the end-to-end journey of building and deploying Ada, AstraZeneca's first large-scale Agentic AI assistant for the biopharmaceutical development team. Ada unifies fragmented structured and unstructured knowledge into intelligent multimodal queries via natural language. Leveraging a specialized multi-agent framework with RAG and knowledge graph capabilities, Ada enables 300+ scientists to access validated, cited insights while reducing experimental duplication and breaking down functional silos, accelerating biologics development and streamlining regulatory submissions.

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.