PAUSE: principled feature attribution for unsupervised gene expression analysis - Genome Biology

  • 📰 BioMedCentral
  • ⏱ Reading Time:
  • 25 sec. here
  • 2 min. at publisher
  • 📊 Quality Score:
  • News: 13%
  • Publisher: 71%

Loans Loans Headlines News

Loans Loans Latest News,Loans Loans Headlines

An article published in GenomeBiology presents PAUSE: an unsupervised pathway attribution method that identifies major sources of transcriptomic variation when combined with biologically constrained neural network models.

], who filter out genes and cells with low expression, perform library size normalization and log transformation, and filter out low variance genes. After preprocessing, the final dataset we use contains 1288 samples with 2139 genes. This dataset contains 607 control and 681 stimulated cells.], contains the transcriptional response of cells from 24 cancer lines to idasanutlin, a negative regulator of the tumor suppressor p53.

] and involves retaining only the top 2000 most highly variable genes, library size normalization, and log transformation. After preprocessing, the final dataset we use contains 11,895 samples with 2000 genes. This dataset contains 7275 control and 4620 perturbed cells.], contains single cell RNA-seq values of bone marrow mononuclear cells of patients with acute myeloid leukemia , taken before a stem cell transplant. The dataset also contains measurements from healthy control samples.

 

Thank you for your comment. Your comment will be published after being reviewed.
Please try again later.
We have summarized this news so that you can read it quickly. If you are interested in the news, you can read the full text here. Read more:

 /  🏆 22. in LOANS

Loans Loans Latest News, Loans Loans Headlines