Daniel Himmelstein

Nice. Let's also include DOI links when available. For Dudoit et al, the link is https://doi.org/10.1198/016214502753479248. DOIs provide persistent identifiers and make metadata lookup much easier.

Just came across [DoCM: a database of curated mutations in cancer](https://doi.org/10.1038/nmeth.4000): > Large-scale cancer genomics discovery projects such as The Cancer Genome Atlas (TCGA) and the International Cancer Genome Consortium...

> it would increase the percentage of true positives but simultaneously increase false negatives What do you mean by true positives and false negatives? From [Chang et al.](https://doi.org/10.1038/nbt.3391): > Here,...

Reproducing [a comment](https://github.com/cognoma/machine-learning/pull/51#discussion_r80557431) by @gwaygenomics here: > I was at talk by Olivier Elemento - he was building models for a different purpose (predict immunotherapy responders) but was adjusting for...

@stephenshank began work at the last meetup on creating a `covariates.tsv` from `samples.tsv`. @stephenshank any updates?

> Are we comfortable with the way categorical NaN's are handled? As per my review comment on #46: yes, although imputation is definitely an option here. > How do we...

@stephenshank, let's keep discussion related to PR #46 on the actual pull request. I didn't see your latest two comments until after my most recent review ): Let's start a...

> I would like to compose the file, as I have given a tour to many new members who are interested in the machine learning work for Cognoma. Fantastic --...

> Sorry if this is slightly off topic, is there any location where all the feature names are listed in something like a data dictionary or something of the like...

Tagging everyone who said they were interested in contributing to the machine learning part of the project in the [introduction thread](https://github.com/cognoma/cognoma/issues/2): @htcai, @loucru1 @bmcgeehan @umeshiso @swbiggs4 @danrieman @rramyr @Inquisitive-Geek @brankaj...