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
2036 - Salivary metabolomics for colorectal cancer detection
Presenter: Hiroshi Kuwabara
Session: Poster Display session 3
Resources:
Abstract
1868 - Evaluation and diagnostic potential of plasma biomarkers in bladder cancer
Presenter: Veronika Voronova
Session: Poster Display session 3
Resources:
Abstract
3655 - Liquid biopsy assays using combined circulating tumor cells and circulating tumor DNA in the same patients for the diagnosis of primary lung cancer
Presenter: Yongjoon Suh
Session: Poster Display session 3
Resources:
Abstract
3685 - Peripheral Cytotoxic T Cell Correlates with Tumor Mutational Burden and is Predictive for Progression Free Survival in Advanced Breast Cancer
Presenter: Xiao-ran Liu
Session: Poster Display session 3
Resources:
Abstract
1050 - Splenic Metabolic Activity as Biomarker in Cervical Cancer
Presenter: Emiel De Jaeghere
Session: Poster Display session 3
Resources:
Abstract
1413 - Identification of distinct subtypes revealing prognostic and therapeutic relevance in diffuse type gastric cancer
Presenter: Seon-Kyu Kim
Session: Poster Display session 3
Resources:
Abstract
2140 - Recurrence risk evaluation in stage IB/IIA gastric cancer with TP53 codon 72 polymorphisms
Presenter: Satoshi Nishizuka
Session: Poster Display session 3
Resources:
Abstract
1573 - Identification and validation of a prognostic 4 genes signature for hepatocellular carcinoma: integrated ceRNA network analysis
Presenter: Yongcong Yan
Session: Poster Display session 3
Resources:
Abstract
1196 - Plasma KIM-1 is associated with clinical outcomes after resection for localized renal cell carcinoma: A trial of the ECOG-ACRIN Research Group (E2805)
Presenter: Wenxin Xu
Session: Poster Display session 3
Resources:
Abstract
2657 - Prognostic immunoprofiling of muscle invasive bladder cancer (MIBC) patients in a multicentre setting
Presenter: Katharina Nekolla
Session: Poster Display session 3
Resources:
Abstract