Back

COT: an efficient Python tool for detecting marker genes among many subtypes

Lu, Y.; Wu, C.-T.; Parker, S. J.; Chen, L.; Saylor, G.; Van Eyk, J. E.; Herrington, D. M.; Wang, Y.

2021-01-11 bioinformatics
10.1101/2021.01.10.426146 bioRxiv
Show abstract

We develop an accurate and efficient method to detect marker genes among many subtypes using subtype-enriched expression profiles. We implement a Cosine based One-sample Test (COT) Python software that is easy to use and applicable to multi-omics data. We demonstrate the performance and utility of COT on gene expression and proteomics data acquired from tissue or cell subtypes. Formulated as a one-sample test with Cosine similarity test statistic in scatter space, the detected de novo marker genes will allow biologists to perform a more comprehensive and unbiased molecular characterization, deconvolution and classification of complex tissue or cell subtypes.

Matching journals

The top 1 journal accounts 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.