New AI/ML AWG Member (Elizabeth Senin)

AWG Discussions AI/ML AWG Topics
1

Good morning everybody, I would also like to introduce myself!

My biggest strength is sorting/analyzing data. I have some (but very little) experience with Python. I have no background or experience in either AI, ML, or biology. I am just a very curious person, and would love to be a helping hand where I can.

I am an intern at NASA AFRC’s financial office. This coming year I will be pursuing an undergraduate degree in Policy Studies with a minor in AI policy at Syracuse University. I currently have community college credits towards a Business Administration degree.

I am looking forward to working with you guys! Thank you for having me!

Elizabeth

2 Likes
2

Data cleaning/engineering is a CRUCIAL skill! I’d say between data and metadata, a huge amount of the dry lab aspects of life/biomedical sciences today, is still stuck on that step :slight_smile: OSDR/GeneLab has done all it can to make the data as organized, findable, interoperable, accessible, and resuable as possible

Have you checked out any of the OSDR datasets yet?

The dashboard ‘at-a-glance’ is here: NASA OSDR Biological Data and Visualization Portal

And the traditional search portal is here: NASA OSDR: Open Science for Life in Space

I’d suggest checking out several datasets to see how they are organized, such as this array:
-https://osdr.nasa.gov/bio/repo/data/studies/OSD-557
-https://osdr.nasa.gov/bio/repo/data/studies/OSD-964
-https://osdr.nasa.gov/bio/repo/data/studies/OSD-48
-https://osdr.nasa.gov/bio/repo/data/studies/OSD-120
-https://osdr.nasa.gov/bio/repo/data/studies/OSD-952

All ~1000 datasets are organized in the same manner, with invetigation metadata, subject metadata, and assay metadata maximally curated (with long-hand protocols), followed by any publications connected to the dataset, followed by the actual downloadable/accessible data. These are great accessible too by the BioDATAapi: https://visualization.osdr.nasa.gov/biodata/api/

There’s actually a whole publication on the topic of the data, its quality, and the associated tools and community (this AWG :slight_smile:): Samrawit G Gebre, Ryan T Scott, Amanda M Saravia-Butler, Danielle K Lopez, Lauren M Sanders, Sylvain V Costes, NASA open science data repository: open science for life in space, Nucleic Acids Research, Volume 53, Issue D1, 6 January 2025, Pages D1697–D1710, https://doi.org/10.1093/nar/gkae1116

1 Like