@maxhaeu.bsky.social
Reposted
A huge shoutout to all the dedicated grants management specialists at the NIH who are working around the clock to push grants out before the Sep 30 deadline. And also to the POs responding to frantic emails.
Not an easy job under the best of circumstances and right now it's the pits.
Thank you!
Not an easy job under the best of circumstances and right now it's the pits.
Thank you!
September 15, 2025 at 8:17 PM
A huge shoutout to all the dedicated grants management specialists at the NIH who are working around the clock to push grants out before the Sep 30 deadline. And also to the POs responding to frantic emails.
Not an easy job under the best of circumstances and right now it's the pits.
Thank you!
Not an easy job under the best of circumstances and right now it's the pits.
Thank you!
Reposted
10/ Bonus reading:
Why do tree-based models still outperform deep learning on tabular data?
arxiv.org/abs/2207.08815
Why do tree-based models still outperform deep learning on tabular data?
arxiv.org/abs/2207.08815
Why do tree-based models still outperform deep learning on tabular data?
While deep learning has enabled tremendous progress on text and image datasets, its superiority on tabular data is not clear. We contribute extensive benchmarks of standard and novel deep learning...
arxiv.org
August 17, 2025 at 1:15 PM
10/ Bonus reading:
Why do tree-based models still outperform deep learning on tabular data?
arxiv.org/abs/2207.08815
Why do tree-based models still outperform deep learning on tabular data?
arxiv.org/abs/2207.08815
Reposted
Think you need deep learning for every bioinformatics problem? Think again. Most of the time, simpler models win. 🧵
August 17, 2025 at 1:15 PM
Think you need deep learning for every bioinformatics problem? Think again. Most of the time, simpler models win. 🧵
Reposted
methylGrapher: genome-graph-based processing of DNA methylation data from whole genome bisulfite sequencing
academic.oup.com/nar/article/...
academic.oup.com/nar/article/...
methylGrapher: genome-graph-based processing of DNA methylation data from whole genome bisulfite sequencing
Abstract. Genome graphs, including the recently released draft human pangenome graph, can represent the breadth of genetic diversity and thus transcend the
academic.oup.com
January 30, 2025 at 8:00 PM
methylGrapher: genome-graph-based processing of DNA methylation data from whole genome bisulfite sequencing
academic.oup.com/nar/article/...
academic.oup.com/nar/article/...
Reposted
Transposon invasion of primate genomes shaped human inflammatory enhancers and susceptibility to inflammatory diseases https://www.biorxiv.org/content/10.1101/2025.01.21.632732v1
January 23, 2025 at 8:35 AM
Transposon invasion of primate genomes shaped human inflammatory enhancers and susceptibility to inflammatory diseases https://www.biorxiv.org/content/10.1101/2025.01.21.632732v1
Reposted
And now for something (not so) straightforward: Enhancers and Promoters 🧬🧪
If you thought enhancers and promoters were easy, think again!
And now for something (not so) straightforward: Enhancers and Promoters
buff.ly
January 23, 2025 at 4:00 PM
And now for something (not so) straightforward: Enhancers and Promoters 🧬🧪
Reposted
Another Emma Farley paper on how binding site *syntax* can compensate for low *affinity*. Essentially, a whole plane where affinity * syntax = same activity.
Syntax compensates for poor binding sites to encode tissue specificity of developmental enhancers
pubmed.ncbi.nlm.nih.gov/27155014/
Syntax compensates for poor binding sites to encode tissue specificity of developmental enhancers
pubmed.ncbi.nlm.nih.gov/27155014/
Syntax compensates for poor binding sites to encode tissue specificity of developmental enhancers - PubMed
Transcriptional enhancers are short segments of DNA that switch genes on and off in response to a variety of intrinsic and extrinsic signals. Despite the discovery of the first enhancer more than 30 y...
pubmed.ncbi.nlm.nih.gov
January 21, 2025 at 12:06 PM
Another Emma Farley paper on how binding site *syntax* can compensate for low *affinity*. Essentially, a whole plane where affinity * syntax = same activity.
Syntax compensates for poor binding sites to encode tissue specificity of developmental enhancers
pubmed.ncbi.nlm.nih.gov/27155014/
Syntax compensates for poor binding sites to encode tissue specificity of developmental enhancers
pubmed.ncbi.nlm.nih.gov/27155014/