Conference Day One | Wednesday, October 23, 2024
8:00 am Registration & Networking
8:55 am Chairs Opening Remarks
Computational Approaches for De Novo Biologics Design: Innovations & Applications
9:00 am Harnessing AI for De Novo Antibody Design
Synopsis
- Presenting AI technologies for sequence design and structure generation
- Discussing Gen AI-driven platforms and algorithms used in de novo antibody design, integrating language models and diffusion-based design
- Exploring case studies demonstrating successful de novo-designed antibodies
9:30 am De Novo Design of Full-Length Antibodies to Diverse Targets
Synopsis
- We use a structure-based design approach to generate antibody-antigen complexes with both high-fidelity and diverse poses to parent-binding antibodies
- We inverse-fold these generated complexes to design CDR sequences
- We find binders in non-parent frameworks
10:00 am AI-Driven Design of Novel Mini Proteins & Multispecific Compounds for Oncology
Synopsis
- Highlighting the use of machine learning and AI tools to design novel mini-proteins with potent therapeutic properties, tailored for oncology
- Exploring the rapid engineering and integration of different mini-protein parts to create versatile therapeutic candidates
- Discussing the development of multispecific compounds capable of engaging multiple targets within a single molecule, enhancing therapeutic efficacy and specificity
10:30 am Morning Break & Speed Networking
Synopsis
As the CDD for Biologics community is reunited, this valuable session will ensure you get the chance to reconnect with peers and make brand-new connections too! This structured networking opportunity will pair you with fellow attendees for several 3-minute introductions, ensuring you have the opportunity to meet and network with your academic
and industry colleagues!
Cutting Edge Insights into Antibody Discovery to Unlock Therapeutic Potentials
11:30 am Exploring the Application of Generative AI to Antibody Discovery
Synopsis
- Generative AI holds the promise to revolutionize antibody discovery
- The current state-of-the-art is able to generate binders
- However, significant challenges remain in generating clinical-like assets
12:00 pm Harnessing Advanced Imaging & Organoid Technology in AI-driven Drug Discovery
Synopsis
- Exploring the use of organoid technology to simulate tissue environments and improve the accuracy of drug testing
- Discussing the role of high-content imaging in characterizing drug effects and disease mechanisms
- Emphasizing the importance of proprietary data collection and its integration with AI algorithms to enhance drug discovery outcomes, showcasing the value of having access to tailored datasets for machine learning applications
12:30 pm Lunch Break
1:30 pm Roundtable Discussion: Data Integration & Privacy in AI-driven Drug Discovery
Synopsis
- Focus on the importance of data collection, privacy, and integration in AI-driven drug discovery processes
- Discuss best practices for collecting and managing proprietary data, ensuring compliance with regulations
- Leveraging integrated datasets to drive meaningful insights and innovations in biologic drug development
Machine Learning Approaches for Enhanced Biologic Structure & Stability
2:00 pm Machine Learning Predictions of Biologic Stability in Early-Stage Antibody Discovery
Synopsis
- Discussing predictions for site-specific chemical stability using in silico machine learning methods
- Leveraging the use of deep learning structural models to include antibody structure and conformation information
- Experimental validation of methodology
2:30 pm Afternoon Break & Poster Session
Synopsis
Witness some of the latest and greatest research in the computational space by drug developers, academics, and researchers in this spotlight poster session
3:15 pm Affinity-Aware In Silico Humanization Using a Domain-Specific Deep Learning Affinity Oracle
Synopsis
- Developed and validated an affinity oracle for antibody-antigen binding by integrating context-specific protein-protein interaction (PPI) data with ESM-2 and transfer learning techniques
- Leveraged the affinity oracle to assess mutations that revert antibodies to their germline state for the purpose of humanization
- Conducted experimental validation of model predictions through biophysical characterization