Reduce Protein Structure Bottlenecks in AI-Driven Drug Discovery
About this webinar
Large-scale protein prediction often stalls when teams rely on local compute, fragmented setup steps and inconsistent execution environments. This webinar explores how scalable AI-driven workflows for protein structure prediction and visualization can support faster, more reproducible research.
The featured speakers will demonstrate how researchers can move beyond local compute limitations to achieve streamlined data setup, high-performance GPU execution and reproducible results in a collaborative cloud environment.
Attendees will receive a comprehensive walkthrough of the end-to-end workflow, from preparing input sequences and accessing preloaded databases to launching pipelines via both the user interface and command line interface. The session also covers the interpretation of key outputs and highlights how these scalable AI-based folding workloads can be directly applied to downstream drug discovery and biological research.
Register for this webinar to learn how protein structure workflows can improve scalability, reproducibility and downstream analysis.
Who should attend
- Director / Senior Director, Computational Sciences
- Director / Senior Director, Structural Biology
- Director / Senior Director, Structure-Based Drug Design
- Head of Computational Chemistry
- VP, Discovery Research (at smaller biotechs)
- Research Computing Director / Head of Scientific Computing
- IT Director, Research Infrastructure (at larger pharmas)
What you will learn
- Protein structure prediction fundamentals
- How to prepare inputs and run a scalable protein folding workflow
- Best practices for using cloud infrastructure to support reproducible, collaborative analysis
- How to interpret workflow outputs for visualization and downstream research use
- Where protein structure workflows can support drug discovery and biological research
Featured Speakers
Eric Talevich, PhD
Eric leads the design and delivery of validated bioinformatics pipelines and multi-omic data products for pharma and clinical genomics customers. He has built and led bioinformatics teams at Caris Life Sciences, Karius and DNAnexus, and developed the UCSF500 clinical cancer genome pipeline at UCSF Medical Center. He created CNVkit, a widely used open-source tool for copy number detection from sequencing data.
Darren Ames
Darren Ames is Head of Solutions Science at DNAnexus, where he works with researchers and organizations tackling complex genomics and biomedical data challenges. His team bridges the gap between powerful cloud technology and the scientists who rely on it, helping turn ambitious ideas into solutions that work in practice. Darren enjoys the messy middle of hard problems, where curiosity, clear thinking and good collaboration matter as much as the tools themselves. As a leader, he focuses on building thoughtful teams, staying close to the real problems scientists face, and creating the kind of trust and clarity that lets people do their best work.
Partner for this event
DNAnexus
DNAnexus® has built the world’s most secure cloud platform and global network for scientific collaboration and accelerated discovery. We embrace challenges and partnership to tackle the world’s most exciting opportunities in human health.
Related webinars
More from DNAnexus.
How to Build a Measurable Evidence Engine for Cell, Gene and RNA Therapies
Cleaning Up Clinical Data: A Step-by-Step Approach to Remediation That Actually Works
Transforming Medical Imaging with AI: Open Tools, Faster Insights
Optimizing GWAS Results Using an Interactive Machine Learning Approach