Arjun Krishnan
@compbiologist.bsky.social
ML/AI methods & tools for using massive public data collections to gain insights into complex disease mechanisms.
Associate Professor & Group leader thekrishnanlab.org at the Dept. of Biomedical Informatics at CU Anschutz.
Associate Professor & Group leader thekrishnanlab.org at the Dept. of Biomedical Informatics at CU Anschutz.
We just use the #papers-articles channel our group’s Slack workspace.
January 3, 2025 at 3:15 AM
We just use the #papers-articles channel our group’s Slack workspace.
I participated in a faculty panel a few weeks ago in which senior (ahem) faculty gave advice on careers in academia by pretending luck had very little to do with our success. One piece of advice riled me up, in which it was argued that a reason for their success was their ability to say no. 1/
December 9, 2024 at 3:28 PM
… And what I hear is that we need smthing to be good for ourselves, our careers, & our personal advancement in order to do smthing that's good for science[/world]. And I just don't believe that's true.”
Love it: what’s the best thing to do, the right thing to do?
podcasts.apple.com/us/podcast/o...
Love it: what’s the best thing to do, the right thing to do?
podcasts.apple.com/us/podcast/o...
86. Prachee Avasthi, CSO at Arcadia Science, on exercising agency and doing science differently
Podcast Episode · Once a Scientist · 07/17/2024 · 1h 8m
podcasts.apple.com
December 9, 2024 at 3:26 PM
… And what I hear is that we need smthing to be good for ourselves, our careers, & our personal advancement in order to do smthing that's good for science[/world]. And I just don't believe that's true.”
Love it: what’s the best thing to do, the right thing to do?
podcasts.apple.com/us/podcast/o...
Love it: what’s the best thing to do, the right thing to do?
podcasts.apple.com/us/podcast/o...
Reposted by Arjun Krishnan
Same reason that nanopore work with direct clinical application gets published in Annals of Obscurities while the tumor poopome and AlphaFold3 (which wasn’t even competitive in CASP16!) get published in Nature over the objections of highly qualified reviewers
December 3, 2024 at 2:42 PM
Same reason that nanopore work with direct clinical application gets published in Annals of Obscurities while the tumor poopome and AlphaFold3 (which wasn’t even competitive in CASP16!) get published in Nature over the objections of highly qualified reviewers
Reposted by Arjun Krishnan
Because it makes for a better $$$ barrier to entry.
Broke: we fit a linear model and predicted results of a CRISPR screen
Woke: we burned down the Amazon to train a 96-head transformer on 500 million cells and did ALMOST AS WELL as the linear model that runs on my phone
Broke: we fit a linear model and predicted results of a CRISPR screen
Woke: we burned down the Amazon to train a 96-head transformer on 500 million cells and did ALMOST AS WELL as the linear model that runs on my phone
December 3, 2024 at 2:40 PM
Because it makes for a better $$$ barrier to entry.
Broke: we fit a linear model and predicted results of a CRISPR screen
Woke: we burned down the Amazon to train a 96-head transformer on 500 million cells and did ALMOST AS WELL as the linear model that runs on my phone
Broke: we fit a linear model and predicted results of a CRISPR screen
Woke: we burned down the Amazon to train a 96-head transformer on 500 million cells and did ALMOST AS WELL as the linear model that runs on my phone