Our Research
At the Van Dijk Lab, we specialize in the development of machine learning algorithms that revolutionize understanding of biomedical data, with a strong focus on single-cell genomics and spatiotemporal data.
Core Expertise: ML for Single-Cell Genomics
We are leaders in the field of machine learning for single-cell genomics. Our work leverages large language models and foundation models, such as Cell2Sentence, to redefine the analysis and interpretation of single-cell data. Additionally, we employ Graph Neural Networks to address challenges in spatial genomics, using these networks to model the spatial arrangement of cells in tissues and thereby providing valuable insights into disease mechanisms and tissue organization.
spatiotemporal modeling and Physics-Informed Deep Learning
Our lab integrates ideas from Operator Learning, Differential and Integral Equations, Dynamical Systems, and Physics-Informed Deep Learning to model complex spatiotemporal biomedical systems. This interdisciplinary approach has applications in medical imaging, neuroscience, and beyond.
Causal Inference in biology
We are at the forefront of developing computational methods for causal inference, enabling us to distinguish correlation from causation in biomedical datasets, specifically for single-cell data.
Interpretable & Multi-Task Learning
We focus on creating interpretable deep learning models and utilize multi-modal, multi-task approaches for comprehensive biomedical data analysis.
Selected Projects
Cell2sentence
Cell2Sentence, a method for applying large language models to single-cell transcriptomics. bioRxiv 2023
CINEMA-OT
CINEMA-OT, a method for causal inference in single-cell data. Nature Methods 2023 (in press)
MAGIC
Markov Affinity-based Graph Imputation of Cells.
A method for single-cell imputation. Cell 2018
Selected publications
Dong, et al. Causal identification of single-cell experimental perturbation effects with CINEMA-OT. Nature Methods (2023, in press)
Fonseca, et al. Continuous Spatiotemporal Transformers. ICML (2023)
Zappala, et al. Neural Integral Equations. arXiv (2023)
Ravindra, et al. Disease State Prediction From Single-Cell Data Using Graph Attention Networks CHIL (2020).
van Dijk, et al. Recovering Gene Interactions from Single-Cell Data Using Data Diffusion Cell (2018)
Lab GitHub
Discover our latest projects and code at: github.com/vandijklab
Revolutionizing Biomedical Research with Machine Learning
Join Our Team: Shape the Future of Biomedicine with Machine Learning
Who We're Looking For
Are you passionate about leveraging machine learning to drive groundbreaking advancements in biology and medicine? The Van Dijk Lab is actively seeking talented individuals to join our interdisciplinary team. We have openings for interns, students, postdocs, programmers, and staff researchers.
Preferred Qualifications
While a background in Computer Science, Mathematics, or Engineering is preferred, no prior experience in biology is required. What's essential is your enthusiasm for working with real-world data and your interest in either crafting innovative algorithms or applying them to solve complex problems.
Why Join Us?
As part of both Yale Internal Medicine and Computer Science departments, we are uniquely positioned at the intersection of computational and biomedical research. Located at the Yale Medical School, our lab collaborates closely with clinicians, granting us access to some of the most compelling datasets in the field.
Our Impact
Our dual focus allows us to make significant contributions to both biomedicine—publishing in top-tier biological and medical journals—and computer science—presenting our findings at leading CS and ML conferences.
How to Apply
For more information or to express your interest, please reach out to Dr. David van Dijk at david.vandijk (at) yale.edu.