){kind=logo}
){kind=logo}
- Discovery Biology
- Main Stage (Afternoon Sessions)
- Main Stage
- Innovation Incubator
- Immuno-oncology
- Discovery Chemistry
- Genomics & Neurology
- Data
- HPC & AI infrastructure
- AI Platforms
- Clinical Trials
- TechOps
- AI Platforms Morning Workshops
- Genomics & Neurology Morning Workshops
- Immuno-oncology Morning Workshops
- Quantum Advances Morning Workshops
Premium Pass
-
-
Analyze how structural AI is advancing understanding of protein interactions, conformational states and functional modulation. Consider how structure-informed modeling is refining druggability assessm …
-
-
-
• Define what AI-enabled biologics design means in practice at Takeda.• Explore structure-informed and structure-free approaches to biologics design.• Assess how AI can compress design-make-test cycle …
-
Examine how leading organizations are shifting to AI-first target identification and embedding multimodal models into core discovery workflows. Assess how causal systems biology and integrated data pl …Speakers
-
Investigate how AI integrates genomic, proteomic and clinical signals to uncover target-linked biomarkers. Assess how multimodal analytics are supporting earlier and more precise stratification hypoth …
-
-
-
Assess how AI can integrate multi-modal data to reveal actionable insights across heterogeneous patient populations. Understand how factors such as disease subtypes and treatment-response variability …
-
Examine how autonomous AI systems are proposing and refining experimental hypotheses in real time. Understand how closed-loop experimentation integrates computational prediction with iterative biologi …
-
Evaluate where AI has improved target identification and validation by strengthening clinically relevant hypotheses, and where it has failed to translate into better discovery decisions. Identify the …
-
-
-
-
AI now designs antibodies, antigens and membrane proteins faster than the wet lab can validate them. This panel asks whether cell-free protein synthesis is the layer that closes that gap — turning dig …
-
-
-
-
• How large-scale functional and omics datasets, interrogated through systematic unbiased approaches, can reveal high-confidence oncology targets • Real-world examples of targets identified through th …
-
-
-
-
-
-
-
-
Examine how generative AI systems are proposing mechanistic target hypotheses grounded in multimodal data. Explore how hypothesis-generation models complement human expertise in identifying novel biol …Speakers
-
Assess how high-content imaging and multi-omic integration are uncovering functional insights beyond single-gene analyses. Explore how AI-driven phenotypic profiling is clarifying mechanism of action …
-
Examine how AI integrates single-cell and spatial data to map cellular states and tissue architecture in disease. Explore how cellular heterogeneity and microenvironment context influence target local …
-
• Examine how AI analyzes large-scale CRISPR and Perturb-seq screens to distinguish causal drivers from correlative signals. • Using AI-based modeling to infer causal targets and target combinations w …
-
-
• Examine how AI is clarifying mechanism of action by integrating pathway biology, perturbation data and disease context. • Explore how deeper mechanistic insight is shaping target differentiation and …
-
-
-
-
-
Analyze how AI maps high-dimensional SAR to guide molecular refinement. Investigate strategies for balancing potency, selectivity and developability simultaneously. Evaluate how predictive prioritizat …
-
-
• Examine how AI models support the design of bifunctional molecules for targeted protein degradation.• Explore strategies for predicting ternary complex formation, linker optimization and degrader se …
-
-
Understand how predictive and generative models are enabling antibody, peptide and protein sequence design and optimization. Analyze how structure-aware AI is improving affinity, stability, specificit …
-
Examine how foundation models learn chemical and reaction language at scale. Explore how LLMs enable de novo design, retrosynthesis and reaction prediction. Assess how these systems are improving desi …
-
- Discuss how AI is reshaping the overall paradigm of molecular design and optimization in modern drug discovery.- Explore the challenges of scaling AI from promising tools to fully integrated discove …
-
-
-
-
• Assess how multimodal data integration reveals novel disease–target–compound relationships.• Explore network-based and foundation model approaches for identifying new therapeutic indications.• Evalu …
-
• Understand how advanced ML models deliver increasingly reliable ADME, PK and developability predictions.• Examine multi-parameter optimization frameworks that integrate permeability, stability, solu …
-
• Understand how integrated Design–Make–Test–Analyze platforms enable rapid, iterative molecular optimization.• Analyze the role of robotics, real-time analytics and active learning in autonomous expe …
-
• Discuss how organizations are evaluating the real-world impact of AI on drug discovery productivity and success rates.• Examine which metrics matter most when assessing AI performance across hit dis …
-
• Explore how AI models help identify potential safety risks earlier in the drug discovery process.• Examine advances in predictive modeling for assessing compound liabilities alongside potency and de …
-
Examine how ML-augmented docking and foundation models are improving hit identification accuracy. Explore strategies for screening billion- to trillion-scale virtual libraries efficiently. Assess how …
-
-
• Investigate advances in reaction prediction, condition optimization and yield estimation using data-driven approaches• AI Agents and humans working hand in hand on reaction data• Future of synthesis …
-
Examine how generative models enable direct in silico molecular design across modalities. Explore how agentic systems and lab-in-the-loop learning create closed-loop chemistry platforms. Assess how en …
-
-
-
-
-
-
Examine how AI refines binding poses and predicts protein–ligand interactions beyond classical docking. Explore fragment growing, scaffold hopping and structure-guided hit expansion strategies. Assess …
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Data
-
-
-
-
-
DataExplore how robust biological data management, governance and integration strategies can enable AI-driven target identification across discovery workflows. Model how structured genomic, functional and …
-
-
-
-
-
-
Ligand-directed degraders (LDDs) represent a rapidly expanding therapeutic modality with increasingly complex and diverse datasets. We describe an AI-powered scientific platform that enables scalable …
-
-
Discuss how pharma organizations are broadening compute strategy from research into development, technical operations and enterprise deployment. Compare where infrastructure priorities stay the same a …Speakers
-
Infrastructure Operating Models for AI-Enabled R&D: Who Owns the Platform, the Compute and the Risk?Examine how compute-intensive modelling, simulation and AI are being applied in process development and manufacturing environments. Review where infrastructure is needed to support scale-up, process u …
-
-
Track how modern HPC environments are supporting molecular dynamics, free-energy methods and structure-based workflows at greater scale. Demonstrate how physics-based simulation is being combined with …
-
Explore how multimodal workloads are changing infrastructure needs across development as well as discovery. Discuss the compute, storage and orchestration challenges involved in supporting imaging-hea …
-
Analyze how error propagation, tool misuse and cascading failures emerge in multi-agentic AI systems. Explore the guardrails needed to support reliable deployment, including orchestration controls, hu …
-
Analyze what it takes to deploy AI in environments where validation, traceability, access control and oversight matter more. Consider how regulated use cases change expectations around infrastructure …
-
-
-
-
Examine how data engineering challenges are changing as AI, simulation and multimodal workflows place greater demands on scientific infrastructure. Explore how organizations are managing storage tiers …
-
Discuss how biopharma organizations are moving beyond fragmented AI pilots to build shared, enterprise-grade compute environments for discovery and development. Compare the strategic choices between c …
-
-
Discuss how lab infrastructure is evolving to support real-time data capture, model-driven experimentation and faster decision-making. Explore how instrument connectivity, workflow orchestration and l …
-
Consider how organizations are segmenting workloads across on-prem HPC, elastic cloud and specialized GPU environments. Review which drug discovery and development workloads benefit most from hybrid d …
-
-
Analyze how leading organizations are redesigning scientific computing platforms around the needs of researchers rather than infrastructure teams. Consider how self-service workflows, preconfigured en …
-
-
-
Analyze how growing demand for model training, inference and simulation is reshaping GPU infrastructure strategies across pharma R&D. Explore what it takes to scale GPU environments effectively, inclu …
-
-
Analyze how biopharma leaders are deciding when to own infrastructure, rely on hyperscalers or work with specialist compute partners. Weigh the trade-offs across talent, speed, capital efficiency, res …
-
-
Clinical trials are technical and expensive endeavours and therefore require extensive planning. AI agents are beginning to need to self evolve to catch up, but what does this look like Attendees can …
-
Regulatory agencies are rapidly advancing their thinking on AI in clinical trials, but expectations are still evolving across regions and use cases. That uncertainty is showing up in differing validat …
-
-
-
AI is being embedded into GxP workflows, but organizations still face challenges around validation, lifecycle management, and cross-functional governance. DiMe will lead the discussion covering: What …
-
-
-
AI is moving rapidly from pilot use cases into core clinical trial decision-making, but most organizations are still not structured to capture consistent, scalable value. That gap is showing up in fra …Speakers
-
AI ambitions are often limited by fragmented, study-level data that isn’t designed for reuse or scale. Siloed systems, inconsistent metadata, and limited ability to generate cross-study insights are a …
-
AI deployment in early stage clinical trials and impact on commercial
-
Learning Outcomes: How near real-time data infrastructure can transform clinical trial execution and decision-making Key challenges in integrating data across sponsors, CROs, and vendors—and strategie …
-
Designing successful clinical trials requires balancing a complex set of tradeoffs, including statistical power, sample size, recruitment timelines, operational feasibility, study cost, site selection …
-
-
AI adoption is accelerating and organizations are facing increasingly complex build vs. buy decisions, with no one-size-fits-all approach even possible. This is causing a friction that is showing up i …
-
Deploying AI in clinical setting is just the first hurdle; maintaining performance, compliance and trust over time has to be successful. This complexity is showing up in model drift, unclear re-valida …
-
-
As AI becomes embedded in high-stakes drug development processes, trust and reliability are becoming essential for adoption. This is especially true in clinical and regulatory workflows, where AI mode …
-
-
-
-
R&D teams often work in silos prototyping AI capabilities for narrow use cases Prototypes and pilots are very fit for purpose and often do not share architectures even for similar use cases In this ta …
-
The most under-served user in healthcare AI is the patient. Most of the field’s energy has gone into clinician copilots, back-office automation, and pipeline acceleration. Meanwhile, the patient gets …
-
This session explores how regulators are shaping the use of artificial intelligence in drug development. It covers FDA's framework for assessing AI credibility, what FDA and EMA expect organizations t …
-
-
-
-
-
-
-
TechOps
-
Speakers
-
-
-
Speakers
-
-
-
-
TechOps
-
-
TechOps
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Premium Pass
-
-
Analyze how structural AI is advancing understanding of protein interactions, conformational states and functional modulation. Consider how structure-informed modeling is refining druggability assessm …
-
-
-
• Define what AI-enabled biologics design means in practice at Takeda.• Explore structure-informed and structure-free approaches to biologics design.• Assess how AI can compress design-make-test cycle …
-
Examine how leading organizations are shifting to AI-first target identification and embedding multimodal models into core discovery workflows. Assess how causal systems biology and integrated data pl …Speakers
-
Investigate how AI integrates genomic, proteomic and clinical signals to uncover target-linked biomarkers. Assess how multimodal analytics are supporting earlier and more precise stratification hypoth …
-
-
-
Assess how AI can integrate multi-modal data to reveal actionable insights across heterogeneous patient populations. Understand how factors such as disease subtypes and treatment-response variability …
-
Examine how autonomous AI systems are proposing and refining experimental hypotheses in real time. Understand how closed-loop experimentation integrates computational prediction with iterative biologi …
-
Evaluate where AI has improved target identification and validation by strengthening clinically relevant hypotheses, and where it has failed to translate into better discovery decisions. Identify the …
-
-
-
-
AI now designs antibodies, antigens and membrane proteins faster than the wet lab can validate them. This panel asks whether cell-free protein synthesis is the layer that closes that gap — turning dig …
-
-
-
-
• How large-scale functional and omics datasets, interrogated through systematic unbiased approaches, can reveal high-confidence oncology targets • Real-world examples of targets identified through th …
-
-
-
-
-
-
-
-
Examine how generative AI systems are proposing mechanistic target hypotheses grounded in multimodal data. Explore how hypothesis-generation models complement human expertise in identifying novel biol …Speakers
-
Assess how high-content imaging and multi-omic integration are uncovering functional insights beyond single-gene analyses. Explore how AI-driven phenotypic profiling is clarifying mechanism of action …
-
Examine how AI integrates single-cell and spatial data to map cellular states and tissue architecture in disease. Explore how cellular heterogeneity and microenvironment context influence target local …
-
• Examine how AI analyzes large-scale CRISPR and Perturb-seq screens to distinguish causal drivers from correlative signals. • Using AI-based modeling to infer causal targets and target combinations w …
-
-
• Examine how AI is clarifying mechanism of action by integrating pathway biology, perturbation data and disease context. • Explore how deeper mechanistic insight is shaping target differentiation and …
-
-
-
-
-
Analyze how AI maps high-dimensional SAR to guide molecular refinement. Investigate strategies for balancing potency, selectivity and developability simultaneously. Evaluate how predictive prioritizat …
-
-
• Examine how AI models support the design of bifunctional molecules for targeted protein degradation.• Explore strategies for predicting ternary complex formation, linker optimization and degrader se …
-
-
Understand how predictive and generative models are enabling antibody, peptide and protein sequence design and optimization. Analyze how structure-aware AI is improving affinity, stability, specificit …
-
Examine how foundation models learn chemical and reaction language at scale. Explore how LLMs enable de novo design, retrosynthesis and reaction prediction. Assess how these systems are improving desi …
-
- Discuss how AI is reshaping the overall paradigm of molecular design and optimization in modern drug discovery.- Explore the challenges of scaling AI from promising tools to fully integrated discove …
-
-
-
-
• Assess how multimodal data integration reveals novel disease–target–compound relationships.• Explore network-based and foundation model approaches for identifying new therapeutic indications.• Evalu …
-
• Understand how advanced ML models deliver increasingly reliable ADME, PK and developability predictions.• Examine multi-parameter optimization frameworks that integrate permeability, stability, solu …
-
• Understand how integrated Design–Make–Test–Analyze platforms enable rapid, iterative molecular optimization.• Analyze the role of robotics, real-time analytics and active learning in autonomous expe …
-
• Discuss how organizations are evaluating the real-world impact of AI on drug discovery productivity and success rates.• Examine which metrics matter most when assessing AI performance across hit dis …
-
• Explore how AI models help identify potential safety risks earlier in the drug discovery process.• Examine advances in predictive modeling for assessing compound liabilities alongside potency and de …
-
Examine how ML-augmented docking and foundation models are improving hit identification accuracy. Explore strategies for screening billion- to trillion-scale virtual libraries efficiently. Assess how …
-
-
• Investigate advances in reaction prediction, condition optimization and yield estimation using data-driven approaches• AI Agents and humans working hand in hand on reaction data• Future of synthesis …
-
Examine how generative models enable direct in silico molecular design across modalities. Explore how agentic systems and lab-in-the-loop learning create closed-loop chemistry platforms. Assess how en …
-
-
-
-
-
-
Examine how AI refines binding poses and predicts protein–ligand interactions beyond classical docking. Explore fragment growing, scaffold hopping and structure-guided hit expansion strategies. Assess …
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Data
-
-
-
-
-
DataExplore how robust biological data management, governance and integration strategies can enable AI-driven target identification across discovery workflows. Model how structured genomic, functional and …
-
-
-
-
-
-
Ligand-directed degraders (LDDs) represent a rapidly expanding therapeutic modality with increasingly complex and diverse datasets. We describe an AI-powered scientific platform that enables scalable …
-
-
Discuss how pharma organizations are broadening compute strategy from research into development, technical operations and enterprise deployment. Compare where infrastructure priorities stay the same a …Speakers
-
Infrastructure Operating Models for AI-Enabled R&D: Who Owns the Platform, the Compute and the Risk?Examine how compute-intensive modelling, simulation and AI are being applied in process development and manufacturing environments. Review where infrastructure is needed to support scale-up, process u …
-
-
Track how modern HPC environments are supporting molecular dynamics, free-energy methods and structure-based workflows at greater scale. Demonstrate how physics-based simulation is being combined with …
-
Explore how multimodal workloads are changing infrastructure needs across development as well as discovery. Discuss the compute, storage and orchestration challenges involved in supporting imaging-hea …
-
Analyze how error propagation, tool misuse and cascading failures emerge in multi-agentic AI systems. Explore the guardrails needed to support reliable deployment, including orchestration controls, hu …
-
Analyze what it takes to deploy AI in environments where validation, traceability, access control and oversight matter more. Consider how regulated use cases change expectations around infrastructure …
-
-
-
-
Examine how data engineering challenges are changing as AI, simulation and multimodal workflows place greater demands on scientific infrastructure. Explore how organizations are managing storage tiers …
-
Discuss how biopharma organizations are moving beyond fragmented AI pilots to build shared, enterprise-grade compute environments for discovery and development. Compare the strategic choices between c …
-
-
Discuss how lab infrastructure is evolving to support real-time data capture, model-driven experimentation and faster decision-making. Explore how instrument connectivity, workflow orchestration and l …
-
Consider how organizations are segmenting workloads across on-prem HPC, elastic cloud and specialized GPU environments. Review which drug discovery and development workloads benefit most from hybrid d …
-
-
Analyze how leading organizations are redesigning scientific computing platforms around the needs of researchers rather than infrastructure teams. Consider how self-service workflows, preconfigured en …
-
-
-
Analyze how growing demand for model training, inference and simulation is reshaping GPU infrastructure strategies across pharma R&D. Explore what it takes to scale GPU environments effectively, inclu …
-
-
Analyze how biopharma leaders are deciding when to own infrastructure, rely on hyperscalers or work with specialist compute partners. Weigh the trade-offs across talent, speed, capital efficiency, res …
-
-
Clinical trials are technical and expensive endeavours and therefore require extensive planning. AI agents are beginning to need to self evolve to catch up, but what does this look like Attendees can …
-
Regulatory agencies are rapidly advancing their thinking on AI in clinical trials, but expectations are still evolving across regions and use cases. That uncertainty is showing up in differing validat …
-
-
-
AI is being embedded into GxP workflows, but organizations still face challenges around validation, lifecycle management, and cross-functional governance. DiMe will lead the discussion covering: What …
-
-
-
AI is moving rapidly from pilot use cases into core clinical trial decision-making, but most organizations are still not structured to capture consistent, scalable value. That gap is showing up in fra …Speakers
-
AI ambitions are often limited by fragmented, study-level data that isn’t designed for reuse or scale. Siloed systems, inconsistent metadata, and limited ability to generate cross-study insights are a …
-
AI deployment in early stage clinical trials and impact on commercial
-
Learning Outcomes: How near real-time data infrastructure can transform clinical trial execution and decision-making Key challenges in integrating data across sponsors, CROs, and vendors—and strategie …
-
Designing successful clinical trials requires balancing a complex set of tradeoffs, including statistical power, sample size, recruitment timelines, operational feasibility, study cost, site selection …
-
-
AI adoption is accelerating and organizations are facing increasingly complex build vs. buy decisions, with no one-size-fits-all approach even possible. This is causing a friction that is showing up i …
-
Deploying AI in clinical setting is just the first hurdle; maintaining performance, compliance and trust over time has to be successful. This complexity is showing up in model drift, unclear re-valida …
-
-
As AI becomes embedded in high-stakes drug development processes, trust and reliability are becoming essential for adoption. This is especially true in clinical and regulatory workflows, where AI mode …
-
-
-
-
R&D teams often work in silos prototyping AI capabilities for narrow use cases Prototypes and pilots are very fit for purpose and often do not share architectures even for similar use cases In this ta …
-
The most under-served user in healthcare AI is the patient. Most of the field’s energy has gone into clinician copilots, back-office automation, and pipeline acceleration. Meanwhile, the patient gets …
-
This session explores how regulators are shaping the use of artificial intelligence in drug development. It covers FDA's framework for assessing AI credibility, what FDA and EMA expect organizations t …
-
-
-
-
-
-
-
TechOps
-
Speakers
-
-
-
Speakers
-
-
-
-
TechOps
-
-
TechOps
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-