Back

DeepSomatic: Accurate somatic small variant discovery for multiple sequencing technologies

Park, J.; Cook, D. E.; Chang, P.-C.; Kolesnikov, A.; Brambrink, L.; Mier, J. C.; Gardner, J.; McNulty, B.; Sacco, S.; Keskus, A.; Bryant, A.; Ahmad, T.; Shetty, J.; Zhao, Y.; Tran, B.; Narzisi, G.; Helland, A.; Yoo, B.; Pushel, I.; Lansdon, L. A.; Bi, C.; Walter, A.; Gibson, M.; Pastinen, T.; Farooqi, M. S.; Robine, N.; Miga, K. H.; Carroll, A.; Kolmogorov, M.; Paten, B.; Shafin, K.

2024-08-19 bioinformatics
10.1101/2024.08.16.608331 bioRxiv
Show abstract

Somatic variant detection is an integral part of cancer genomics analysis. While most methods have focused on short-read sequencing, long-read technologies now offer potential advantages in terms of repeat mapping and variant phasing. We present DeepSomatic, a deep learning method for detecting somatic SNVs and insertions and deletions (indels) from both short-read and long-read data, with modes for whole-genome and exome sequencing, and able to run on tumor-normal, tumor-only, and with FFPE-prepared samples. To help address the dearth of publicly available training and benchmarking data for somatic variant detection, we generated and make openly available a dataset of five matched tumor-normal cell line pairs sequenced with Illumina, PacBio HiFi, and Oxford Nanopore Technologies, along with benchmark variant sets. Across samples and technologies (short-read and long-read), DeepSomatic consistently outperforms existing callers, particularly for indels.

Published in Nature Biotechnology (predicted rank #6) · training set

Matching journals

The top 5 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.