The mission of our lab is to provide machine learning tools that extract meaningful insight from high-throughput, high-dimensional biomedical data. We work with data such as: Single-Cell RNA sequencing, Gut microbiome sequencing, Biomedical imaging, and Electronic Health Records.
David van Dijk, et al. "Recovering Gene Interactions from Single-Cell Data Using Data Diffusion." Cell (2018), https://doi.org/10.1016/j.cell.2018.05.061
Kevin R. Moon*, David van Dijk*, et al. “Visualizing Structure and Transitions for Biological Data Exploration.“ Nature Biotech (2019) [in press], bioRxiv 120378; doi: https://doi.org/10.1101/120378
Matthew Amodio*, David van Dijk*, et al. “Exploring Single-Cell Data with Deep Multitasking Neural Networks.“ Nature Methods (2019) [in press], bioRxiv 237065; doi: https://doi.org/10.1101/237065
(Markov Affinity-based Graph Imputation of Cells)
Imputation and denoising of single-cell RNA-seq data using manifold learning. van Dijk, et al. Cell, 2018
(Potential of Heat-diffusion for Affinity-based Transition Embedding)
Embedding high-dimensional data into low dimensions for visualization. link (in press at Nature. Biotech)
(Manifold Enhancement of Latent Dimensions)
Graph signal processing tool to analyze multiple scRNA-seq samples from two or more conditions. link (bioRxiv)
We’re developing tools to visualize, extract features, and predict clinical phenotypes in PET, SPECT, CT, ultrasound, and various other medical imaging data for large patient cohorts.
We use machine learning to accelerate biomedical discovery
We are recruiting at all levels
Are you excited about machine learning and do you want to make an impact in biology and medicine? The van Dijk Lab is recruiting interns, students, postdocs, programmers, and staff researchers. Background in CS, Math, or Engineering is preferred, no background in biology is required. You should be interested in working with real world data and interested in either developing new algorithms or applying existing ones to data, or both!
We are located at the Yale Medical School and have close ties to Yale Computer Science and Applied Math. Our location allows us to work closely with clinicians and have access to the most exciting datasets. Our goal is to impact both biomedicine (e.g. publish in biological and medical journals) and computer science (e.g. publish at CS and Math conferences).
For more information, send an email to: david.vandijk (at) yale.edu