Sign up to save your podcasts
Or
Share #32 Deep tensor factorization and a pitfall for machine learning methods with Jacob Schreiber
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
#32 Deep tensor factorization and a pitfall for machine learning methods with Jacob Schreiber
In this episode, we hear from Jacob Schreiber about his algorithm,
Avocado.
Avocado uses deep tensor factorization to break a three-dimensional tensor of
epigenomic data into three orthogonal dimensions corresponding to cell types,
assay types, and genomic loci. Avocado can extract a low-dimensional,
information-rich latent representation from the wealth of experimental data
from projects like the Roadmap Epigenomics Consortium and ENCODE. This
representation allows you to impute genome-wide epigenomics experiments that
have not yet been performed.
Jacob also talks about a pitfall he discovered when trying to predict gene
expression from a mix of genomic and epigenomic data. As you increase the
complexity of a machine learning model, its performance may be increasing for
the wrong reason: instead of learning something biologically interesting, your
model may simply be memorizing the average gene expression for that gene
across your training cell types using the nucleotide sequence.
Links:
If you enjoyed this episode, please consider supporting the podcast on Patreon.
View all episodes
By Roman Cheplyaka
4.7
3535 ratings
In this episode, we hear from Jacob Schreiber about his algorithm,
Avocado.
Avocado uses deep tensor factorization to break a three-dimensional tensor of
epigenomic data into three orthogonal dimensions corresponding to cell types,
assay types, and genomic loci. Avocado can extract a low-dimensional,
information-rich latent representation from the wealth of experimental data
from projects like the Roadmap Epigenomics Consortium and ENCODE. This
representation allows you to impute genome-wide epigenomics experiments that
have not yet been performed.
Jacob also talks about a pitfall he discovered when trying to predict gene
expression from a mix of genomic and epigenomic data. As you increase the
complexity of a machine learning model, its performance may be increasing for
the wrong reason: instead of learning something biologically interesting, your
model may simply be memorizing the average gene expression for that gene
across your training cell types using the nucleotide sequence.
Links:
If you enjoyed this episode, please consider supporting the podcast on Patreon.