Closed jaclyn-taroni closed 3 years ago
AppVeyor build 1.0.215 for commit 4abb24ea8a43199c664aa1938ceb829a4aa51e89 is now complete. Found 1 potential spelling error(s). Preview:
content/05.prior-knowledge.md:34:transcriptome...
AppVeyor build 1.0.216 for commit dd9d84d44ebfeb6401fc273252f29fe850964fb7 is now complete. Found 0 potential spelling error(s). Preview:
...
AppVeyor build 1.0.217 for commit 75260d2c8c595125a85fec7a1c994bb64c032531 is now complete. Found 1 potential spelling error(s). Preview:
content/05.prior-knowledge.md:50:underperform...
AppVeyor build 1.0.218 for commit 304fc0e91acc4fef29ad38d8158b70a6c1e93326 is now complete. Found 1 potential spelling error(s). Preview:
content/05.prior-knowledge.md:50:underperform...
is this PR ready to be merged @jaclyn-taroni ?
Just bumping this up again - once we've merged this and #118, I'll take another stab at my issues and the rest of the doc.
@allaway I don't think I addressed all your comments, so if you are happy with where this is at currently please feel free to merge!
Purpose
Addresses #110. In #109, it was suggested that any in-depth discussion of MultiPLIER and DeepProfile should be moved to a section that is intended to demonstrate that multiple concepts described throughout the paper can and should be used together to study rare diseases (e.g., regularization AND prior knowledge/data).
Moving the discussion of MultiPLIER and DeepProfile out of the prior data/knowledge section required a rewrite of the transfer and multi-task learning section to "briefly" explain these approaches and set up the section about putting it all together.
This pull request is that rewrite! 🚀 Although, I'm not sure I've hit the mark with respect to brevity. I have removed and shortened some references/description of studies from the multi-task and few-shot learning paragraphs. But in the interest of improving the flow of this section of the manuscript, I've also added some text.
Directions for reviewers
Is there anything that you want to discuss further?
What else can I cut? ✂️
Is the pull request ready for review?
Yes
Manuscript checklist
Unless otherwise noted above, this PR will be considered ready for review when all four items have been checked.