Interactive Breakout Discussions

Engage in in-depth discussions with industry experts and your peers about the progress, trends, and challenges you face in implementing ML/AI in your work! Interactive discussion groups play an integral role in networking with potential collaborators, provide an opportunity to share examples from your work, and allow you to be part of a group problem-solving endeavor.

These will take place IN-PERSON ONLY.

WEDNESDAY, JANUARY 21 | 7:30-8:15 AM

TABLE: Bridging the Gap between AI-Driven Biologics Design to Novel Molecules Entering Clinical Trials

Moderator: Joost Schymkowitz, PhD, Professor & Group Leader, Switch Lab, Catholic University Leuven

Strategies for aligning computational model predictions with pre-clinical experiments
Approaches for AI designs in sparse/fragmented data regimes
Incorporating physics-based constraints or mechanistic priors into AI models

TABLE: Comparing and Contrasting Machine Learning-Based Design of Antibody and Non-Antibody Biologics

Moderator: Jung-Eun (June) Shin, PhD, Senior Machine Learning Scientist, Seismic Therapeutic

Public data availability and ease of screening designs and generating experimental data
Deimmunization and humanization methods for antibodies vs. non-antibody biologics
Computational and deep learning methods for functional engineering and de novo design
Methods for developability predictions and multi-objective optimization

TABLE: Overcoming the Data Bottleneck in AI-Driven Antibody Engineering

Moderator: Roberto Spreafico, PhD, Vice President, Head, Discovery Data Science, Genmab

Data scarcity as the key constraint to progress in antibody model development
High-throughput assays: Current limitations and future potential
Cross-disciplinary insights from medicinal chemistry and related domains

WEDNESDAY, JANUARY 21 | 4:50-5:40 PM

TABLE: Accelerating Antibody Engineering with AI-Driven Active Learning: Optimizing DMTA Cycles

Moderator: Jiangyan Feng, PhD, Senior Advisor, Biotechnology Discovery Research, Eli Lilly and Company

Active learning strategies for antibody optimization
Closing the loop: Integrating experimental feedback into ML models
Multi-objective optimization in antibody DMTA
Speed vs. thoroughness: Designing efficient DMTA cycles

TABLE: Best Practices for Using Agentic and Multi-Agent Systems in R&D

Moderator: Elahe Vedadi, PhD, Research Scientist, Google/DeepMind

Strengths and limitations of the current systems
Practical techniques to evaluate these systems
Best practices for enabling agents to effectively utilize external tools and APIs
Planning for complex problem decomposition and effective action sequencing

WEDNESDAY, JANUARY 21 | 7:30-8:15 AM

TABLE: Language Models to Generate 3D Structures

Moderator: Possu Huang, PhD, Assistant Professor, Bioengineering, Stanford University

TABLE: Leveraging Large Language Models, Deep Learning, and Graph-Based Architectures to Accelerate Biological Design

Co-Moderators: Omar Abudayyeh, PhD, McGovern Fellow/Principal Investigator, Massachusetts Institute of Technology

Jonathan S. Gootenberg, PhD, McGovern Fellow/Principal Investigator, McGovern Institute, Massachusetts Institute of Technology

WEDNESDAY, JANUARY 21 | 4:50-5:40 PM

TABLE: Large-Scale Antibody Discovery Benchmarking Challenge #2

Co-Moderators: Andrew R.M. Bradbury, MD, PhD, CSO, Specifica, an IQVIA business

M. Frank Erasmus, PhD, Head, Bioinformatics, Specifica, an IQVIA business

Review launch of the next phase of the AIntibody Competition Series, during which participants will have four months, using any method (in vivo immunization, in vitro techniques, or ML/AI) to generate human antibodies against targets to be revealed at the challenge's start
Evaluate target affinity, developability (minimum score), and submission time
Goals of the challenge include fostering innovation, expediting therapeutic antibody development, benchmarking capabilities, and providing insights into technology cost–benefit profiles transparently

TABLE: Structure-Guided Antibody and Immunogen Design

Moderator: Monica L. Fernandez-Quintero, PhD, Staff Scientist, Integrative Structural and Computational Biology Department, Scripps Research Institute

Structural biology to map epitope footprints—how important is it still to define epitopes/paratopes experimentally for precise targeting—is AI already there?
Structure prediction and computational design—machine learning or physics-based?
Antibody challenges—structure prediction, dynamics, design, diversity, glycan shields, breadth
When will we have an AI designed therapeutic/vaccine?

Event-At-a-Glance