Ji-Eun Park
@jieunpark.bsky.social
Research Fellow at DS in DFCI/Harvard
PhD in Bios @ UNC Chapel Hill
Things I love: statistical genetics, cancer genomics🧬, coffee☕️ and all sorts of 🥖🥐
PhD in Bios @ UNC Chapel Hill
Things I love: statistical genetics, cancer genomics🧬, coffee☕️ and all sorts of 🥖🥐
Reposted by Ji-Eun Park
#tidyomics made it to #NatureMethods! "The tidyomics ecosystem: Enhancing omic data analyses", 👏🏽 Will, Timothy, and Team!
32 researchers | 26 institutes | 10 countries | 4 continents
A #crowd/#community-research success
nature.com/articles/s41...
#CZI, Thanks @mikelove.bsky.social !
32 researchers | 26 institutes | 10 countries | 4 continents
A #crowd/#community-research success
nature.com/articles/s41...
#CZI, Thanks @mikelove.bsky.social !
The tidyomics ecosystem: enhancing omic data analyses - Nature Methods
tidyomics offers a software ecosystem for omic data manipulation and analysis that bridges Bioconductor with the tidyverse framework.
https://nature.com/articles/s41592-024-02299-2?utm_source=twitter&utm_medium=social&utm_campaign=nmeth…
June 17, 2024 at 1:20 AM
#tidyomics made it to #NatureMethods! "The tidyomics ecosystem: Enhancing omic data analyses", 👏🏽 Will, Timothy, and Team!
32 researchers | 26 institutes | 10 countries | 4 continents
A #crowd/#community-research success
nature.com/articles/s41...
#CZI, Thanks @mikelove.bsky.social !
32 researchers | 26 institutes | 10 countries | 4 continents
A #crowd/#community-research success
nature.com/articles/s41...
#CZI, Thanks @mikelove.bsky.social !
Reposted by Ji-Eun Park
Tidyomics, a collection of R packages that enable tidyverse-style syntax on biological datasets, is now published:
rdcu.be/dKNM6
Thanks to the hard work of the authors especially @stemang.bsky.social!
rdcu.be/dKNM6
Thanks to the hard work of the authors especially @stemang.bsky.social!
The tidyomics ecosystem: enhancing omic data analyses
Nature Methods - tidyomics offers a software ecosystem for omic data manipulation and analysis that bridges Bioconductor with the tidyverse framework.
rdcu.be
June 14, 2024 at 12:08 PM
Tidyomics, a collection of R packages that enable tidyverse-style syntax on biological datasets, is now published:
rdcu.be/dKNM6
Thanks to the hard work of the authors especially @stemang.bsky.social!
rdcu.be/dKNM6
Thanks to the hard work of the authors especially @stemang.bsky.social!
Reposted by Ji-Eun Park
The core idea of randomforest is that you use bootstrap and mtry to create fairly uncorrelated trees, then average over them.
I had a rough go at adding a bunch of extra randomness. Different hyperparameters, different sample sizes, oversampling.
Was surprised that just nothing helped at all.
I had a rough go at adding a bunch of extra randomness. Different hyperparameters, different sample sizes, oversampling.
Was surprised that just nothing helped at all.
September 21, 2023 at 10:01 AM
The core idea of randomforest is that you use bootstrap and mtry to create fairly uncorrelated trees, then average over them.
I had a rough go at adding a bunch of extra randomness. Different hyperparameters, different sample sizes, oversampling.
Was surprised that just nothing helped at all.
I had a rough go at adding a bunch of extra randomness. Different hyperparameters, different sample sizes, oversampling.
Was surprised that just nothing helped at all.