Back

Real-time molecular classification of leukemias

Sagniez, M.; Simpson, S. M.; Caron, M.; Rozendaal, M.; Pare, B.; Sontag, T.; Langlois, S.; Rouette, A.; Lavalee, V.-P.; Cellot, S.; Sinnett, D.; Tran, T.-H.; Smith, M. A.

2022-06-27 genetic and genomic medicine
10.1101/2022.06.22.22276550 medRxiv
Show abstract

Gene expression profiling provides a detailed molecular snapshot of cellular phenotypes that can be used to compare different biological conditions. Nanopore sequencing technology can generate high-resolution transcriptomic data in real-time and at low cost, which heralds new opportunities for molecular medicine. In this study, we demonstrate the clinical utility of real-time transcriptomic profiling by processing RNA sequencing data from childhood acute lymphoblastic leukemia (ALL) patients on-the-fly with a trained neural network classifier. This strategy successfully distinguished 11/12 representative ALL molecular subtypes and one non-leukemia control in as little as 5 minutes of sequencing on a MinION sequencer or in less than 1 hour on disposable, low cost Flongle flow cells. Our findings suggest that real-time transcriptomics constitutes a drastically efficient solution for the molecular diagnosis of ALL and other diseases, where conventional clinical workflows require days if not weeks to achieve similar results.

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.