John Lafin
@johnlafin.bsky.social
Computational Biologist in Strand Lab @ UTSW in Dallas, TX. Building better bladder... (b)atlases
Great explainer! Unrelated: anyone have an extra fire extinguisher? Asking for a friend.
We need to have a conversation about random seeds. Don't use 42.
blog.genesmindsmachines.com/p/if-your-ra...
blog.genesmindsmachines.com/p/if-your-ra...
If your random seed is 42 I will come to your office and set your computer on fire🔥
Figuratively. More likely you'll get a stern talking to.
blog.genesmindsmachines.com
October 22, 2025 at 3:08 PM
Great explainer! Unrelated: anyone have an extra fire extinguisher? Asking for a friend.
A thoughtful take on improving the conduct of science. We can't reasonably agree on how to improve things until there is agreement on what specifically needs improvement!
How can we reform science? I have some ideas. But I am not sure you’ll like them, because they don’t promise much. elevanth.org/blog/2025/07...
Which Kind of Science Reform
What hope is there for science reform, if we can't agree on what to reform? Right now, principles are more important than practices.
elevanth.org
July 22, 2025 at 2:37 PM
A thoughtful take on improving the conduct of science. We can't reasonably agree on how to improve things until there is agreement on what specifically needs improvement!
What a great resource for public benchmarking of single cell methods. Also a nice reminder that complex models aren't always the best performing ones: logistic regression and ComBat are among top performers in label transfer and batch correction respectively! www.nature.com/articles/s41...
Defining and benchmarking open problems in single-cell analysis - Nature Biotechnology
Nature Biotechnology - Defining and benchmarking open problems in single-cell analysis
www.nature.com
July 2, 2025 at 1:45 PM
What a great resource for public benchmarking of single cell methods. Also a nice reminder that complex models aren't always the best performing ones: logistic regression and ComBat are among top performers in label transfer and batch correction respectively! www.nature.com/articles/s41...