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
5056 - Phase 2 study of 2 dosing regimens of cemiplimab, a human monoclonal anti–PD-1, in metastatic cutaneous squamous cell carcinoma (mCSCC)
Presenter: Danny Rischin
Session: Poster Display session 3
Resources:
Abstract
5710 - Avelumab for advanced Merkel cell carcinoma in the Netherlands; a nationwide survey
Presenter: Sonja Levy
Session: Poster Display session 3
Resources:
Abstract
3152 - Health-related quality of life in patients with metastatic Merkel cell carcinoma receiving second-line or later avelumab treatment: 36-month follow-up data
Presenter: Sandra D'Angelo
Session: Poster Display session 3
Resources:
Abstract
5715 - A Phase 2, Randomized Study of Nivolumab (NIVO) and Ipilimumab (IPI) versus NIVO, IPI and Stereotactic Body Radiation Therapy (SBRT) for Metastatic Merkel Cell Carcinoma (MCC, NCT03071406) – a preliminary report.
Presenter: Sungjune Kim
Session: Poster Display session 3
Resources:
Abstract
2854 - Real-world impact of immune checkpoint inhibitors in metastatic uveal melanoma
Presenter: Kalijn Bol
Session: Poster Display session 3
Resources:
Abstract
2928 - Immune checkpoint inhibitors in a cohort of 206 metastatic uveal melanomas patients
Presenter: Mathilde Saint-Ghislain
Session: Poster Display session 3
Resources:
Abstract
1235 - Incidence and survival of Uveal Melanoma occurring as single cancer versus its occurrence as a first or second primary neoplasm
Presenter: Ahmad Alfaar
Session: Poster Display session 3
Resources:
Abstract
3615 - Validation of a Clinicopathological and Gene Expression Profile (CP-GEP) Model for Sentinel Lymph Node Metastasis in Primary Cutaneous Melanoma
Presenter: Evalyn Mulder
Session: Poster Display session 3
Resources:
Abstract
1793 - External validation of the 8th Edition Melanoma Staging System of the American Joint Committee on Cancer (AJCC) using the Surveillance, Epidemiology and End Results (SEER) Program
Presenter: Angelina Tjokrowidjaja
Session: Poster Display session 3
Resources:
Abstract
4278 - Clinical factors and overall survival (OS) associated with patterns of metastases (mets) in melanoma patients (pts).
Presenter: Ines Pires da Silva
Session: Poster Display session 3
Resources:
Abstract