In today’s market, every company wants to apply ML to their R&D pipeline. To do this effectively requires a data platform that is dramatically different than was common in the recent past. To empower ML innovation, companies require a ‘lab in the loop’, where data and insights can flow freely across team and departmental boundaries. This talk will equip engineering leaders to understand strategic trade offs as well as practical on-the-ground tactical decisions based on hard-learned lessons from getting a startup off the ground to establishing it as a leader in ML-guided design.

This talk will provide practical, real-world advice based on Dwan's quarter century of experience designing and implementing high-performance computing and large-scale data systems for health care and the life sciences. Topics will include network architectures, cloud vs. "terrestrial" infrastructure, practical data strategies, information security, quality and compliance from R&D to the clinic, differentiated computing platforms, human and organizational factors, and of course AI.

This session provides key lessons from our journey implementing a data mesh strategy to make FAIR data available for enterprise use, moving from a centralized monolithic platform to a cloud-based self-service system with federated governance. We'll discuss successes, challenges, and failures encountered, offering insights on the technology, process, and people aspects of this transformation. Our goal is to humbly help others avoid the pitfalls we experienced modernizing our data platform.

NCI's Cancer Research Data Commons is a data ecosystem built to administer and manage the data generated by the various NCI funded programs for FAIR data sharing across the research community. NCI has been a pioneer in establishing a democratized ecosystem co-locating data and compute, building secure and scalable data commons and cloud analytical platforms for the diverse users from cancer community.

Discover how Metaphore leverages molecular mimicry alongside cutting-edge AI and ML algorithms to optimize molecular functions for drug development. This presentation will explore our function-first approach, integrating high-throughput experimental data with scalable data platforms and storage infrastructure. We will discuss how unifying data management and employing advanced analytics enable us to map, mimic, and optimize millions of molecules efficiently. Learn how our innovative integration of AI/ML with robust data solutions accelerates the discovery of next-generation therapeutics, transforming the landscape of drug development.

Come explore the best practices that have driven the success of Generate’s Next-Gen Data Lake. Learn how we leveraged a central repository of entities and vocabularies and reimagined lab processes to capture experimental context, and enhanced our computational infrastructure to be implicitly traceable. By building a unified data exchange we empower scientists to confidently access and interpret data across the platform.

Integrating various tools, workflows, and data products into a connected suite helps scientists make faster and better decisions. Intuence Discovery (ID), which supports early drug discovery, focusing on lead optimization and technologies like protein degraders and cyclic peptides. ID helps with data annotation, gathering, analysis, and decision-making, covering the DMTA cycle from data querying to compound selection and analysis. ID is a fast, single webpage that enhances data-driven discussion.

As the world's largest publicly available repository of raw sequence data, the Sequence Read Archive (SRA) plays a pivotal role in advancing public health and life sciences research. This presentation highlights state-of-the-art tools and strategies for managing and analyzing the SRA’s massive datasets, showcasing its impact on infectious disease surveillance, genomic epidemiology, and precision medicine. Discover how innovative informatics solutions are transforming raw data into actionable insights for global health challenges.

With AI taking center stage in coding, research teams are leveraging AI-enabled IDEs to refactor legacy systems into modern, efficient languages. This talk presents a balanced view of generative AI-supported coding, cutting through the hype to focus on real-world applications. Discover practical strategies and examples of how AI is transforming outdated research systems into scalable, maintainable, and future-ready platforms for life sciences.

Since 2010, “Trends from the Trenches” has been a cornerstone of the Bio-IT program, delivering candid and occasionally blunt assessments of the most impactful and overhyped IT technologies in life sciences. This talk will provide a deep dive into computing, storage, cloud, data science, machine learning, and more, with a focus on supporting data-intensive science. Looking ahead, this talk will share forward-thinking predictions about emerging technologies and trends poised to shape the future of life sciences innovation, offering actionable insights for navigating the next wave of IT evolution.