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
3489 - Overall Survival (OS) and Metastasis-Free Survival (MFS) in men with Biochemically Relapsed (BCR) Prostate Cancer after radical prostatectomy (RP) managed with deferred Androgen Deprivation Treatment (ADT): A combined Johns Hopkins and CPDR study
Presenter: Catherine Marshall
Session: Poster Display session 3
Resources:
Abstract
4606 - ARCHES – the role of androgen deprivation therapy (ADT) with enzalutamide (ENZA) or placebo (PBO) in metastatic hormone-sensitive prostate cancer (mHSPC): Post hoc analyses of high and low disease volume and risk groups
Presenter: Arnulf Stenzl
Session: Poster Display session 3
Resources:
Abstract
2975 - Updated survival analyses of a multicentric phase II randomized trial of docetaxel (D) plus enzalutamide (E) versus docetaxel (D) as first line chemotherapy for patients (pts) with metastatic castration-resistant prostate cancer (mCRPC) (CHEIRON study).
Presenter: Orazio Caffo
Session: Poster Display session 3
Resources:
Abstract
2708 - Real-world analysis of patients (pts) with metastatic castration-resistant prostate cancer (mCRPC) receiving vs not receiving chemotherapy in the treatment sequence
Presenter: Alicia Morgans
Session: Poster Display session 3
Resources:
Abstract
2134 - Baseline fracture risk in men with prostate cancer starting the STAMPEDE trial
Presenter: Janet Brown
Session: Poster Display session 3
Resources:
Abstract
3504 - Risk of falls and fractures in patients with castration resistant prostate cancer (CRPC) treated with new hormonal agents – a meta-analysis of randomized controlled trials.
Presenter: Rodrigo Coutinho Mariano
Session: Poster Display session 3
Resources:
Abstract
2342 - Pain progression at initiation of chemotherapy in metastatic Castration-Resistant Prostate Cancer (mCRPC) is associated with a poor prognosis: a post-hoc analysis of FIRSTANA
Presenter: Nicolas Delanoy
Session: Poster Display session 3
Resources:
Abstract
5331 - Pain evaluation in patients (pts) with metastatic castration-resistant prostate cancer (mCRPC) treated with radium-223 (Ra-223) in the PARABO observation study
Presenter: Holger Palmedo
Session: Poster Display session 3
Resources:
Abstract
2823 - Time to castration resistant prostate cancer (CRPC) and the risk of developing immune disorders
Presenter: Vincenza Conteduca
Session: Poster Display session 3
Resources:
Abstract
1500 - Retrospective evaluation of neutropenic admission events in metastatic or high-risk hormone-sensitive prostate cancer (HSPC) patients having docetaxel chemotherapy upfront or for castrate-resistant prostate cancer (CRPC) in STAMPEDE
Presenter: Harriet Mintz
Session: Poster Display session 3
Resources:
Abstract