A connected lab is only as useful as the data the next person downstream can actually use. At Satomic, we bet that in-house data, generated on our own platform, is the right foundation for predictive chemistry models, so we built our DataGen automation platform around the needs of training those models from day one.This case study covers the bet, the early decision to define how information would flow in and out of the system before any of it was built, and three concrete choices that fell out: running production and discovery chemistry on shared infrastructure, meeting instruments where they are rather than where vendors promise they will be, and using software to optimize plating around the operator. We close with what we have learned about where the real bottlenecks live in a connected lab, and why, when those early decisions are right, scaling becomes a question of equipment and orchestration rather than redesign.

This talk focuses on the real-world implementation of autonomous labs—drawing directly from active projects with OpenAI and Pacific Northwest National Laboratory (PNNL). Ginkgo's collaboration with OpenAI connected GPT-5 to Ginkgo's autonomous lab, improving cell-free protein synthesis reaction costs by 40% over the scientific state of the art. In parallel, the DOE commissioned over 100 integrated laboratory robots to enable national-lab scale automation for R&D as part of the White House's Genesis Mission to bring AI to science.

Robust data standards enable creation of high-quality FAIR datasets that power trusted AI models. As laboratories become increasingly automated and data-rich, standards ensure that data from instruments, robotics, and digital workflows can be integrated and reused. At the same time, AI is rapidly accelerating automated data standardization. This talk explores how the convergence of AI and data standards enables creation of semantic, AI-ready datasets and faster scientific insight in modern automated development environments.

Semantically driven Data & Digital Transformation spearheads adoption of digitized Clinical Data Standards, Domain ontologies and embedded data models. At Takeda, we drove multiple efforts to broadly define and support metadata-driven approaches in Clinical Trial & Data management, NextGen Lab solution implementation and adoption and cohesive Master data and Data platform integration. Driving cross-functional stakeholder alignment via close collaboration with Clinical Sciences, Therapeutic Areas, IT and Business units across Pharma organizations brings cohesion to the Data ecosystem and accelerates user adoption. This presentation will focus on approaches to developing aligned common data models for institutionally shared metadata object definitions supported by scientific and clinical ontologies. With a Linked-data mindset, harmonized metadata and richly uniformly annotated datasets can be more readily incorporated into LLMs, accelerate analysis and innovation, drive insights and deliver AI-ready FAIR data.

As cell therapy manufacturing scales, traditional QC models built on manual workflows and siloed systems are becoming limiting. Today’s bottlenecks stem from a lack of end-to-end integration rather than assay performance. This talk explores how to design a scalable QC infrastructure that unifies automated assays, reagent and sample management, and LIMS/MES data into a coordinated, high-throughput environment. We will highlight strategies to standardize workflows, integrate upstream processes, and embed QC within manufacturing to increase throughput and reduce risk, with a focus on achieving global consistency across automated QC platforms, positioning QC as a critical, scalable infrastructure for commercial production.  

Modern experimental sciences can generate data faster than teams can analyze and interpret it. We present an automated data analysis system designed to accelerate collaboration between data scientists and laboratory scientists. By integrating experiment design, and analysis into a unified workflow, we shorten iteration cycles, improve reproducibility, and enable faster scientific and organizational decision-making. This talk describes some of the techniques needed to build systems like this at any organization.

• 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​

Modular robotic automation is transforming labs from isolated workcells into orchestrated, modality-agnostic platforms spanning discovery and development. This talk details architectures that standardize labware and data, integrate robotics for conveyance and transportation, and unify high-level functions such as solid/liquid dispensing, mixing, incubation, sampling, and pH control. A recently deployed system will be presented as a case study, illustrating how orchestration, scheduling, and structured data pipelines accelerate DMTA (Design-Make-Test-Analyze), increase instrument utilization, enable remote monitoring and unattended operation, and lay the groundwork for AI-ready, closed-loop optimization and autonomous knowledge generation.

Modern lab automation platforms depend on reliable integration across diverse instruments, yet many research environments still operate with fragmented workflows, legacy systems, and manual data movement. This talk examines the “first mile” barriers that limit scalable data orchestration and automation in practice. Christopher Perkins (Broad Institute) presents strategies for integrating heterogeneous instruments into automation-ready environments through metadata standardization, edge-based architectures, automated ingestion pipelines, and cloud-connected workflows that improve interoperability and support scalable, AI-ready research infrastructure.

AI-enabled drug discovery depends on high-throughput experimental data that is contextualized, reproducible, and decision-ready. At Generate:Biomedicines, robotic workflows explore complex protein fitness landscapes, while automated metadata capture links samples, plates, methods, instruments, timing, and conditions into queryable data trails. This talk highlights how augmented modular labs, AI-powered assistants, and integrated infrastructure reduce friction and enable adaptive, AI-ready experimentation across the Design-Make-Test-Analyze cycle, from automated execution to informed decisions at scale.