Kieran Campbell Lab Toronto

Current projects

Astir - Automated cell identity from single-cell multiplexed imaging and proteomics

Astir is a modelling framework for the assignment of cell type across a range of single-cell highly mutliplexed imaging technologies such as Imaging Mass Cytometry (IMC). Astir is built using Pytorch and uses recognition networks for fast minibatch stochastic variational inference.

Other software

Nature Methods 2019

Automated, probabilistic assignment of cells to known cell types in single-cell RNA-seq data accounting for patient and batch specific effects.

Genome Biology 2019

A probabilistic model to assign gene expression states to cancer clones by integrating scRNA-seq and scDNA-seq data, implemented in Tensorflow.

Wellcome Open Research 2017

MFA models genomic bifurcations using a Bayesian hierarchical mixture of factor analysers.

Bioinformatics 2018

Ouija is a probabilistic pseudotime framework that infers pseudotimes from a small number of marker genes providing parameter estimates (with uncertainty) for interpretable gene regulation behaviour.

Nature Communications 2018

Genomic trajectories (pseudotimes) in the presence of heterogenous environmental and genetic backgrounds

Bioinformatics 2016

Inference and detection of switch-like differential expression across single-cell RNA-seq trajectories.