Abstract 5820
Background
DNA sequencing to identify variants is becoming increasingly valuable in clinical settings; including matching patients to approved targeted therapies, immunotherapies, and/or clinical trials. However, accurate calling of genetic variants from sequencing still remains challenging. With little corroboration between the different tools available, patients are at risk of being treated with therapies that are unsuitable for their cancer.
Methods
Here we present a novel machine learning based method for the accurate identification of somatic variants in cancer patient tumour samples, with a neural network architecture from encoded raw sequencing read information of tumour/normal sample pairings into an image, enabling it to classify whether a variant is germline, somatic, or sequencing error. The model was trained and tested on in-silico spike-in data using bam-surgeon, and then validated on a multi-cancer and multi-center dataset and benchmarked against industry standard variant callers.
Results
The approach, called somaticNET, outperforms existing industry standard tools in sensitivity and specificity, achieving an AUROC of ∼1.00 on the bam-surgeon dataset and an AUROC of ∼0.99 on the multi-cancer multicenter dataset. The model also works faster than other variant callers, in minutes compared to hours.
Conclusions
Using the power of machine learning for accurate somatic variant calling can improve patient matching to approved therapies and clinical trials, thus ensuring patients are given the right therapy at the right time to treat their cancer.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Cambridge Cancer Genomics.
Disclosure
G. Dubourg-Felonneau: Shareholder / Stockholder / Stock options, Full / Part-time employment: Cambridge Cancer Genomics. D. Rebergen: Shareholder / Stockholder / Stock options, Full / Part-time employment: Cambridge Cancer Genomics. C. Parsons: Shareholder / Stockholder / Stock options, Full / Part-time employment: Cambridge Cancer Genomics. H. Thompson: Shareholder / Stockholder / Stock options, Full / Part-time employment: Cambridge Cancer Genomics. J.W. Cassidy: Leadership role, Shareholder / Stockholder / Stock options, Full / Part-time employment, Officer / Board of Directors: Cambridge Cancer Genomics. N. Patel: Leadership role, Shareholder / Stockholder / Stock options, Full / Part-time employment: Cambridge Cancer Genomics. H.W. Clifford: Leadership role, Shareholder / Stockholder / Stock options, Full / Part-time employment: Cambridge Cancer Genomics.
Resources from the same session
1707 - Clinical utility of precision immunoprofiling and monitoring of the tumor microenvironment using flow cytometry and CyTOF in patients with advanced NSCLC treated with atezolizumab: results from a phase II study for biomarker analysis (EPOC1702)
Presenter: Keisuke Kirita
Session: Poster Display session 3
Resources:
Abstract
3594 - Tumor mutation burden (TMB), PD-L1, IFN-γ signaling identify subgroups of patients (pts) who benefit from durvalumab (D, anti-PDL1) or D and tremelimumab (T, anti-CTLA4) treatment in urothelial bladder cancer (UC)
Presenter: Christophe Massard
Session: Poster Display session 3
Resources:
Abstract
744 - The decrease of TMB, TNB and HLA expression are the Mechanism of Drug Resistance of NSCLC to immunosuppressive PD-1/PD-l1.
Presenter: Sheng Yu
Session: Poster Display session 3
Resources:
Abstract
2350 - Eosinophilia during treatment of immune checkpoint inhibitors (ICIs) predicts succeeding onset of immune-related adverse events (irAEs)
Presenter: Rika Kizawa
Session: Poster Display session 3
Resources:
Abstract
5930 - A transcriptomic immunologic signature predicts favorable outcome in neoadjuvant chemotherapy treated triple negative breast tumors.
Presenter: Javier Pérez-peña
Session: Poster Display session 3
Resources:
Abstract
6127 - Alterations of TMB and TCR repertoires during Chemotherapy in East Asian lung cancer patients without TKI-related driver gene mutations
Presenter: Lele Song
Session: Poster Display session 3
Resources:
Abstract
1310 - Association of SCFA in gut microbiome and clinical response in solid cancer patients treated with andi-PD-1 antibody.
Presenter: Motoo Nomura
Session: Poster Display session 3
Resources:
Abstract
2286 - Extracellular matrix and tissue derived metabolites in a liquid biopsy identifies endotypes of metastatic melanoma patients with differential response to immune checkpoint inhibitor treatment
Presenter: Nicholas Willumsen
Session: Poster Display session 3
Resources:
Abstract
4107 - Pathologic scoring of pre-treatment H&E biopsies predicts overall survival in patients with metastatic clear cell renal cell carcinoma receiving nivolumab monotherapy
Presenter: Julie Stein
Session: Poster Display session 3
Resources:
Abstract
1291 - PD-L1 expression in uncommon EGFR-mutant non-small cell lung cancer and its response to immunotherapy
Presenter: Yun Fan
Session: Poster Display session 3
Resources:
Abstract