Generative AI & Predictive Modeling Icon

Cambridge Healthtech Institute’s Inaugural

Generative AI & Predictive Modeling

Understanding the Impact of Breakthroughs in Neural Networks & Data Analytics

APRIL 1, 2024 | 1:00-5:00 PM

 

Currently, we are witnessing the rise of different artificial intelligence (AI) and machine learning (ML) techniques for modeling, predictions, and in silico screening. These models and algorithms are proving to be very useful for prioritizing which drug targets to pursue and for optimizing novel lead candidates with desirable drug-like properties. They are helping with prediction of protein structure, folding, and for peptide drug design as well. This inaugural symposium on Generative AI & Predictive Modeling will bring together experts to discuss basic understanding and emerging applications of various AI/ML tools. This symposium will be a good primer for the AI/Machine Learning for Early Drug Discovery conferences that follow.

Monday, April 1

Pre-Conference Symposium Registration12:00 pm

Welcome Remarks1:00 pm

1:10 pm

Chairperson's Remarks

Tudor Oprea, MD, PhD, CEO, Expert Systems, Inc.

1:15 pm

Efficient Optimization over Chemical Space with Generative AI

Jason Rolfe, PhD, Co-Founder & CTO, Variational AI

Chemical space contains 1060 synthesizable, drug-like molecules. This enormous space is too large to search exhaustively with VHTS. Generative AI promises to find optimized molecules with fewer queries and less data. Rather than zig-zagging across the breadth of the landscape to find the peak of a mountain, generative AI can walk directly uphill. However, many popular techniques, such as Bayesian optimization and reinforcement learning, cannot efficiently navigate latent representations of chemical space. We show that gradient-based optimization is significantly more effective. Combining this with a novel, domain-specific architecture and carefully curated datasets, we demonstrate efficient generative AI for drug discovery.

1:45 pm

Generative AI with Synthesizability Guarantees Identifies Potent Antagonists for a G-Protein-Associated Melanocortin Receptor in a Tera-Scale vHTS Screen

Henry van den Bedem, PhD, Senior Vice President, Machine Learning Research & Cheminformatics, Atomwise Inc.

Commercially available virtual, synthesis-on-demand chemical catalogs are expanding rapidly with trillions of compounds and increasingly complex chemistry, providing value throughout all pre-clinical drug development stages. However, their exponential growth poses significant challenges for traditional search-and-score methods to efficiently explore catalogs. Here, we present and experimentally validate a generative AI that efficiently designs catalog compounds with desired properties.

2:15 pm

Has Generative AI Had an Impact on Small Molecule Design?

Daniel Seeliger, PhD, Associate Vice President, Head of Small Molecule Drug Design, Exscientia

We present Exscientia's approach to drug discovery and the important role of generative small molecule design in the process. The discovery of a novel LSD1 inhibitor and a successful proof-of-concept study leading to the discovery of novel, bispecific anti-malaria agents are presented as applications of generative design.

Networking Refreshment Break3:00 pm

3:15 pm

End-to-End Discovery of Antibodies with Dual Epitope and Tissue Specificity

Alexander Taguchi, PhD, Director, Machine Learning, Antibody Discovery, iBio, Inc.

Therapeutic antibody discovery for oncology is challenging due to an inability to control the epitope binding site as well as toxicity resulting from healthy tissue reactivity. These problems are overcome with machine learning design of peptides that match the sequence and structure of the target epitope. Antibody libraries are screened against the engineered peptides, resulting in efficient discovery of on-epitope binders. The antibodies are then masked with these peptides to improve their off-tissue safety profiles in the case of oncology targets.

3:45 pm

Fine-Tuning Molecular Language Models to Learn the Kinase Inhibitor Chemical Space

Rayees Rahman, PhD, Co-Founder & CEO, Harmonic Discovery

Most out-of-the-box generative chemistry models struggle to encode the chemical properties that medicinal chemists favor during drug discovery campaigns. By fine-tuning molecular language models for specific chemical spaces, such as the kinase inhibitor chemical space, we can align generated molecules more closely with chemists' preferences.

4:15 pm

One GPT to Rule Them All: Large Language Model-Based Platform for Target and Ligand Identification

Tudor Oprea, MD, PhD, CEO, Expert Systems, Inc.

Our team is developing a suite of LLM experts, each focused on different tasks and activities related to early drug discovery. These include PharosGPT (targets, diseases, ligands), litGPT (learn from papers), ChEMBLGPT (compounds and bioactivities) and ActivityGPT (predict bioactivity endpoints) provide LLM-based support for our projects. DrugInteLLM is the human-facing orchestra conductor that oversees our GPT-based platform for target and ligand discovery.

Close of Symposium5:00 pm

Dinner Short Course Registration5:30 pm

Dinner Short Course*6:00 pm

SC3: Fundamentals of Generative AI for Drug Discovery

*Premium Pricing or separate registration required. See Short Courses page for details.