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
1885 - Factors associated with disease progression in patients treated with trametinib in combination with dabrafenib for unresectable advanced BRAFV600-mutant melanoma: an open label, non randomized study
Presenter: Philippe Saiag
Session: Poster Display session 3
Resources:
Abstract
5259 - Integrative RNAseq and Target panel sequencing reveals common and distinct innate and adaptive resistance mechanisms to BRAF inhibitors
Presenter: Phil Cheng
Session: Poster Display session 3
Resources:
Abstract
5619 - Effective treatment with T-VEC monotherapy in Stage IIIB/C-IVM1a Melanoma of the Head & Neck Region
Presenter: Viola Franke
Session: Poster Display session 3
Resources:
Abstract
5666 - Re-introduction of T-VEC Monotherapy in Recurrent Stage IIIB/C-IVM1a melanoma is effective
Presenter: Viola Franke
Session: Poster Display session 3
Resources:
Abstract
4117 - Efficacy of talimogene laherparepvec (T-VEC) in melanoma patients (pts) with locoregional (LR) recurrence, including in-transit metastases (ITM): subgroup analysis of the phase 3 OPTiM study
Presenter: Mark Middleton
Session: Poster Display session 3
Resources:
Abstract
5303 - Real Life Use of Talimogene Laherparepvec in Melanoma in Centers in Austria and Switzeland
Presenter: Christoph Hoeller
Session: Poster Display session 3
Resources:
Abstract
4130 - Outcomes of advanced melanoma patients who discontinued pembrolizumab (pembro) after complete response (CR) in the French early access program (EAP)
Presenter: Philippe Saiag
Session: Poster Display session 3
Resources:
Abstract
2050 - Outcome of patients with elevated LDH treated with first-line targeted therapy (TT) or PD-1 based immune checkpoint inhibitors (ICI)
Presenter: Sarah Knispel
Session: Poster Display session 3
Resources:
Abstract
1618 - Comparative-Effectiveness of Pembrolizumab vs. Nivolumab for Patients with Metastatic Melanoma
Presenter: Justin Moser
Session: Poster Display session 3
Resources:
Abstract
3556 - Long-term efficacy of combination nivolumab and ipilimumab for first-line treatment of advanced melanoma: a network meta-analysis
Presenter: Peter Mohr
Session: Poster Display session 3
Resources:
Abstract