Machine Learning

The Machine Learning Group at UofT

Nov 9th, 17

New Faculty Members

Sep 1st, 16

We welcome three new faculty members to the ML group: David Duvenaud, Sanja Fidler, and Roger Grosse.

U of T ML spinout Deep Genomics graduates first summer interns

Congratulations to Michael Wainberg, Victoria Dean and Omar Wagih on their summer projects, which used machine learning to understand the genetics of disease (3rd, 4th and 5th from left).

U of T Machine Learning group spins out company Deep Genomics

Aug 5th, 15

Checkout for more details.

Reconstructing the evolutionary history of tumors

Feb 19th, 15

Phylo* is a family of statistical methods that use nonparametric Bayesian tree priors to infer clonal evolution of tumors from whole genome sequencing data.


Amit G. Deshwar, Shankar Vembu, Christina K. Yung, Gun Ho Jang, Lincoln Stein, Quaid Morris. PhyloWGS: Reconstructing subclonal composition and evolution from whole genome sequencing of tumors. Genome Biology 16:35, 2015.


Amit G. Deshwar, Shankar Vembu, Quaid Morris. Comparing Nonparametric Bayesian Tree priors for clonal reconstruction of tumors. InProceedings of the Pacific Symposium on Biocomputing, 2015.


Wei Jiao, Shankar Vembu, Amit G. Deshwar, Lincoln Stein, Quaid Morris. Inferring clonal Evolution of tumors from single nucleotide Somatic Mutations. BMC Bioinformatics 15:35, 2014.

Deep Learning Discovers Genetic Causes of Diseases

Jan 6th, 15

Wired Magazine describes how Toronto researchers used deep learning to make new discoveries about the genetics of disease.

Also check out the Science article describing this work.

Image by Olena Shmahalo/Quanta Magazine.

Toronto Deep Learning Projects

Aug 13th, 14

Check out the exciting deep learning research in our group and the new website for deep learning projects!

pqR – a pretty quick version of R

May 8th, 14

My new, faster, version of R, called pqR.

pqR is a new version of the R interpreter. It is based on R-2.15.0, distributed by the R Core Team, but improves on it in many ways, mostly ways that speed it up, but also by implementing some new features and fixing some bugs.

– Radford Neal




Feb 8th, 14

Together with Stephen Rumble (with contributions from Adrian Dalca, Marc Fiume, Vlad Yanovsky, and in a collaboration with Arend Sidow and his group) we developed SHRiMP — the SHort Read Mapping Program. SHRiMP can align short reads to a reference genome quickly and accurately, while allowing for insertions/deletions. It also comes with special color-space options to handle reads made by the AB SOLiD technology. More recently Matei David, Misko Dzamba, and others have worked on the second version of SHRiMP (SHRiMP2), which significantly speeds up mapping without sacrificing sensitivity.