Anthony Gitter

icon indicating a website link https://www.biostat.wisc.edu/~gitter/

icon location Associate professor in Biostatistics and Medical Informatics at the University of Wisconsin-Madison; Investigator at the Morgridge Institute for Research

Results 237 comments of Anthony Gitter

Reviewer suggestions

A few more suggestions. I haven't cross-referenced potential conflicts: - James Zou https://scholar.google.com/citations?user=23ZXZvEAAAAJ&hl=en&oi=ao - Anna Goldenberg https://scholar.google.com/citations?user=cEepZOEAAAAJ&hl=en&oi=ao - Smita Krishnaswamy https://scholar.google.com/citations?user=l2Pr9m8AAAAJ&hl=en&oi=ao

Outstanding issues not specific to any tips

I'm copying my comment from https://github.com/Benjamin-Lee/deep-rules/pull/313#issuecomment-760316895 here so we don't lose track of it. - There is a lot of existing guidance about best practices for machine learning and deep...

Add requested merge style to `CONTRIBUTING.md`

@Benjamin-Lee you've been using merge commits in this repository, right? Regardless of what we specify as the preferred merged style for general updates, we need to specify that rootstock updates...

Dealing with class imbalance in Deep Learning

I agree that class imbalance is a common issue in biology. How much of the discussion would be specific to deep learning as opposed to general ML? If the solutions...

Deep learning in bioinformatics: introduction, application, and perspective in big data era

Welcome @lykaust15. The GitHub issues track TODO items and other ideas for updating the manuscript. Issue https://github.com/Benjamin-Lee/deep-rules/issues/116 has some discussion of the intended timeline. There are also open pull requests....

For full reproducibility, always report all details of your analyses, including sharing of data, methods, and models

Reporting these details is critical, and recording them in that way that enables them to be run and built upon (e.g. containers, executable notebooks, [kipoi models](http://kipoi.org)) is even better.

Close issues that have been addressed

I looked at updates in the wrong order, so my comments in #130 would be better discussed here. I agree with your ordered steps to finish this. I also suggest...

Don't forget your ML fundamentals/Rules that apply to ML also apply to DL

[Machine learning applications in genetics and genomics](http://doi.org/10.1038/nrg3920) is a good reference for ML basics in biology, in addition to the manuscript in #1.

Perform sanity checks and follow good coding practices

I also recommend [*Top considerations for creating bioinformatics software documentation*](https://doi.org/10.1093/bib/bbw134) for software documentation

Future-proof: Plan how you will support and share your model

> Will they provide the model, weights, and a code example of how to use it for inference (least convenient)? [Kipoi](http://kipoi.org/) is intended to address this subset of your questions....