Back

Development of a CMS Classifier for Clinical CRC Samples

Torang, A.; van de Weerd, S.; van Lammers, V.; van Hooff, S.; Koster, J.; Medema, J. P.

2023-06-29 bioinformatics
10.1101/2023.06.28.546869 bioRxiv
Show abstract

Colorectal cancer (CRC) is a leading cause of cancer-related deaths worldwide, emphasizing the need for improved predictive biomarkers to guide treatment decisions. A classification system based on gene expression profiles, known as CMS, has shown promise in stratifying CRC into distinct subtypes with varying clinical outcomes. However, the lack of a reliable assay to classify formalin-fixed paraffin-embedded (FFPE) samples poses a challenge for translating this system into routine clinical practice. In this paper, we introduce the NanoClassifier, an NanoString-based CMS classifier to classify both FFPE and Fresh frozen (FF) tumors. We demonstrate the strong accuracy of the NanoClassifier in predicting CMS for CRC samples. By validating its performance on FF and FFPE samples, we highlight the prognostic significance of CMS in CRC.

Matching journals

The top 13 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.