Back

Manual curation of TCGA treatment data and identification of potential markers of therapy response.

Moiso, E.

2021-05-05 oncology
10.1101/2021.04.30.21251941 medRxiv
Show abstract

The Cancer Genome Atlas (TCGA) represents a valuable source of genomic and clinical data across different tumor types. In this work, TCGA treatment response information have been manually curated in order to be computationally exploited. Drug names were manually corrected to remove typos and to unify commercial and molecule names. Moreover the drug therapy related information has been reorganized in a table to facilitate readability and analysis. The data were benchmarked with uni and multivariable statistical analyses to identify putative markers of response.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.