Join Synlico during SF Tech Week for a scientific discussion exploring two connected areas at the intersection of AI and biomedical research:

Causal AI for Drug Discovery: Learning from Patient Data

– Learning causal structure across environments and task-aware data enhancement.

Registration Page: https://partiful.com/e/gh9DqJ2U5W9uTkivd92w 

Much of the patient-derived biological data available for drug discovery is observational, capturing biology across individuals, disease states, tissues, and cellular contexts. These observations offer opportunities to learn more about causal relationships, while noise and sparsity create challenges for extracting reliable information.

What more can observational patient data reveal about causal relationships in biology? What theoretical foundations enable us to learn from differences across biological environments? How can task-aware data enhancement and synthetic data generation help us learn from noisy, sparse biological measurements?

Moderator:

Dr. Jingwei Lu, Founder & CEO at Synlico

Speakers:

Dr. Yingzhen Yang, Assistant Professor in the School of Computing and Augmented Intelligence at Arizona State University

Topic: Task-aware data enhancement

Dr. Amin Jaber, Machine Learning Scientist at Synlico

Topic: Learning causal structure across environments from observational data

Synlico is developing SynCausal™, a patient-native causal AI platform, which represents biology through causal graphs that link upstream genes and pathways to downstream cell states and phenotypes, enabling intervention effects to be simulated, traced, and compared. It operates one level upstream of medicinal chemistry and modality engineering: determining which biological intervention is worth pursuing, why it may work, and in which patient contexts the hypothesis is most credible. Learn more at www.synlico.com.