ÌìÃÀ´«Ã½

Research Thrusts

AI4BIO will develop multiscale AI modeling frameworks for a cohesive understanding of genomes, cells, and tissues at different scales. This new paradigm is expected to illuminate fundamental aspects of gene regulation, cellular differentiation, tissue development, and disease progression. Model development will be enhanced by iterative AI/ML-guided experimentation, catalyzing unprecedented exploration into biological complexity with more intelligent and efficient experimental designs.

AI4BIO resources will be used to:

• Galvanize ÌìÃÀ´«Ã½ faculty and foster new team-based research to tackle grand challenges. 
• Recruit new talents and cultivate new research directions.
• Leverage our existing strengths, rooted in the Ray and Stephanie Lane Computational Biology Department’s extensive track record of innovation in AI for biomedicine, extending across departmental boundaries to further broaden ÌìÃÀ´«Ã½’s footprint in AI for biomedicine.

Funded Pilot Projects

AI-Driven Automation for Microbial Genotype–Phenotype Discovery

The team will pair predictive modeling with automated, high-throughput experiments to learn how genotype and environment jointly shape time-resolved microbial growth, using active learning to prioritize the most informative measurements.

• Joshua Kangas, Associate Teaching Professor, Ray and Stephanie Lane Computational Biology
• Andrew Bridges, Assistant Professor, Department of Biological Sciences
• Oana Carja, Associate Professor, Ray and Stephanie Lane Computational Biology Department

 

ML-guided engineering of biomolecular condensates in an automated lab

The team will use Bayesian optimization to drive a closed-loop design-build-test cycle for synthetic condensates, iteratively proposing sequences and validating condensate properties in an autonomous lab.

• Jose Lugo-Martinez, Assistant Professor, Ray and Stephanie Lane Computational Biology Department
• Huaiying Zhang, Assistant Professor, Department of Biological Sciences 

 

Integrating AI and Automated Genomics to Accelerate the Development of Gene Therapies

The team will integrate automated cloning and high-throughput evaluation with AI-driven screening to optimize AAV performance and cell-type targeting, using representative cell lines as an initial proof of concept.

• Andreas Pfenning, Associate Professor, Ray and Stephanie Lane Computational Biology Department
• Anne Robinson,Trustee Professor, Biomedical Engineering and Chemical Engineering

“A ‘lab-on-the-loop’ approach for stem cell research” Christian Cuba-Samaniego (Computational Biology), Newell Washburn (Chemistry; Biomedical Engineering). The team will use laboratory automation to build a dataset of reprogramming outcomes across combinatorial media and protocol variations, then learn interpretable models that predict and improve cell-state transitions.

Together, these projects are designed to produce reusable datasets, validated workflows, and early “model plus experiment” prototypes that can seed larger efforts and longer-term collaborations. By bringing together faculty across departments and connecting AI advances to autonomous experimentation, these efforts reflect AI4BIO’s mission to strengthen ÌìÃÀ´«Ã½’s leadership in AI for biomedical research and to move the field toward more scalable, reliable, and collaborative discovery.