AI for Drug Discovery Workshop

AI for Drug Discovery: Development in Pharmaceuticals, Academia, or joint Collaborations

Register

Call for Submissions

Program

Organizing Committee

The "AI for Drug Discovery" workshop is dedicated to improving the understanding and exploring the transformative role of artificial intelligence (AI) in advancing drug discovery and development processes. Focused on leading-edge research and innovation, the workshop will feature research papers and posters that delve into key aspects of AI and machine learning applications within the pharmaceutical domain, in academia, or through joint industry-academia collaboration. The workshop seeks to facilitate in-depth discussions on the integration of AI technologies to enhance efficiency, accuracy, and speed in drug development, fostering collaboration among researchers, industry professionals, and experts in the field. The workshop aims to serve as a platform for researchers, industry professionals, and experts to investigate into the intricacies of these advanced methodologies, fostering dialogue and collaboration. Attendees can anticipate interactive discussions, presentations, and networking opportunities, gaining valuable insights into the forefront of AI-driven strategies shaping the future of drug discovery and development.

Scope

Artificial intelligence, encompassing statistical and computational machine learning, statistical causal inference, neural networks, convolutional neural networks (CNNs), and generative AI (e.g., Large Language Model, Diffusion Models, Late Fusion Models, etc), are all welcomed approaches. We include innovative AI methods as well as application of AI methods to the field of medicinal drug development.

topics

  • AI methods for acceleration of drug discovery
  • Innovative approaches to enhancing patient representation learning through AI-anchored predictions of family relations in electronic health records
  • Mechanism-based identification of biomarkers and intervention targets from multi-omics datasets leveraging AI
  • AI-driven enhanced precision and personalization of drug interactions
  • The pivotal role of explainable Machine Learning for therapeutic indication expansion
  • Renyi Distillation drug target discovery
  • AI optimization of clinical trials
  • Leveraging graph-based approaches to characterize immunogenetic variation and perform genetic association testing
  • Harnessing genome-wide variant effect predication and evolution for identifying causal variants
  • AI enhancing regulatory aspects of drug development (e.g., documentation, testing, Q&A, etc.)
  • Comprehensive Machine Learning prediction of paralog pairs to synthetically boost cancer immunotherapy
  • Understanding disease-associated tissue microenvironments by integrative Machine Learning analysis of spatial transcriptomic data with high-resolution imaging and single-cell RNA-seq data
  • Bayesian thresholded modeling for integrating network predictors
  • Multimodal network-based cancer heterogeneity analysis
  

program format

 

Time (MT)

Topic

Speakers

8:00 - 8:05 (5 minutes)

Welcome address

Katie Zhu, Yale University

8:05 - 8:40 (35 Minutes)

Keynote: AI Opportunities and Challenges in Pharma

James Cai, Boehringer Ingelheim

 

 

 

8:40 - 10:00 (80 min) 

 

8:40 - 9:00

Topology-Driven Negative Sampling Enhances Generalizability in Protein-Protein Interaction Prediction

 

Babak Ravandi, Alexion
9:00 - 9:20

Learnable Geometric Scattering on Biomedical Knowledge Graphs for Indication Expansion

Dhananjay Bhaskar, Yale-BI Fellow

 

9:20 - 9:40

Using predicted family relations for improving patient representation learning from electronic health records

 

Xiayuan Huang, Yale-BI Fellow

 

9:40 - 10:00

In-silico Prediction of Collaborative Paralog Pairs Enhancing Cancer Immunotherapy

Chuanpeng Dong, Yale-BI Fellow

10-10:15 (15 mins) Coffee Break

 

 

 

10:15-11:15 (60 mins)

 

10:15-10:35

Incorporating prior information in gene expression network-based cancer heterogeneity analysis

 

Rong Li, Yale-BI Fellow

 

10:35-10:55

 Unraveling Tissue Microenvironments Using Integrated Spatial Transcriptomics and Multi-Modal Data through Graph Networks

 

Huanhuan Wei, Yale-BI Fellow

 

10:55-11:15

 Integrating Node and Network Imaging Traits to Boost Prediction Accuracy of Cognitive Ability

 

Zhe Sun, Yale-BI Fellow
 

11:15 – 12:00
(45 mins)

Interactive Panel Q&A on AI for drug discovery topics

Panelists: James Cai (BI), Jake Chen (UAB), Sidi Chen (Yale), Yves Lussier (Utah)
Moderator: Katie Zhu (Yale)

12- 12:15
(15 mins)

Closing Remarks

Jake Chen, The University of Alabama at Birmingham

12:15-1:45

Lunch Break

Scientific Paper Program Committee

Hongyu Zhao, PhD
Ira V. Hiscock Professor of Biostatistics, of Genetics, and of Statistics and Data Science Yale University
Mark Gerstein, PhD
Albert L Williams Professor of Biomedical Informatics and Professor of Molecular Biophysics & Biochemistry, of Computer Science, and of Statistics & Data Science Yale University
Zhongming Zhao, PhD
Chair Professor for Precision Health; Director, Center for Precision Health University of Texas in Houston
Jake Chen, PhD
Chief Bioinformatics Officer Informatics Institute and Professor of Genetics, Computer Science, and Biomedical Engineering University of Alabama
Nima Pouladi, MD, PhD
Research Associate, Department of Biomedical Informatics The University of Utah