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
3630 - Results of phase 1 clinical trial of high doses of Seleno-L-methionine (SLM) in sequential combination with Axitinib in previously treated and relapsed clear cell renal carcinoma (ccRCC) patients
Presenter: Yousef Zakharia
Session: Poster Display session 3
Resources:
Abstract
2356 - Safety and Efficacy of CDX-014 , an Antibody-Drug Conjugate against T Cell immunoglobulin mucin-1 (TIM-1), in advanced Renal Cell Carcinoma
Presenter: Bradley McGregor
Session: Poster Display session 3
Resources:
Abstract
1028 - SPAZO2 (SOGUG): Outcomes and prognostic significance of IMDC intermediate prognosis subclassification in metastatic renal cell carcinoma (mRCC) in patients treated with 1st-line pazopanib (1stPz).
Presenter: Begona P. Valderrama
Session: Poster Display session 3
Resources:
Abstract
2293 - Effect of Antacid Intake on the Therapeutic Efficacy of Sunitinib (SUN) in Metastatic Renal Cell Carcinoma (mRCC) Patients (pts): a Sub-Analysis of the STAR-TOR Registry
Presenter: Katrin Schlack
Session: Poster Display session 3
Resources:
Abstract
1451 - Randomized phase 3 trial of avelumab + axitinib vs sunitinib as first-line treatment for advanced renal cell carcinoma: JAVELIN Renal 101 Japanese subgroup analysis
Presenter: Motohide Uemura
Session: Poster Display session 3
Resources:
Abstract
4399 - Overall and progression-free survival according to MSKCC scores in 1st line sunitinib treatment of metastatic renal cell carcinoma (mRCC)
Presenter: Jindrich Finek
Session: Poster Display session 3
Resources:
Abstract
1344 - Combination therapy with checkpoint inhibitors for first-line treatment of advanced renal cell carcinoma: A systematic review and meta-analysis of randomized controlled trials
Presenter: Kyaw Thein
Session: Poster Display session 3
Resources:
Abstract
3462 - A phase II trial of TKI induction followed by a randomized comparison between nivolumab or TKI continuation in renal cell carcinoma (NIVOSWITCH)
Presenter: Viktor Grünwald
Session: Poster Display session 3
Resources:
Abstract
5268 - Nivolumab (N) treatment beyond progression in a real-world cohort of patients (pts) with metastatic renal cell carcinoma (mRCC)
Presenter: Sophie Hans
Session: Poster Display session 3
Resources:
Abstract
4235 - First results of safety profile of nivolumab (NIVO) in combination with stereotactic body radiotherapy (SBRT) in II and III line of patients (pts) with metastatic renal cell carcinoma (mRCC) in NIVES Study
Presenter: Cristina Masini
Session: Poster Display session 3
Resources:
Abstract