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
3611 - Phase II trial of SM 88 in Non-Metastatic Biochemical Recurrent Prostate Cancer.
Presenter: Benjamin Gartrell
Session: Poster Display session 3
Resources:
Abstract
2492 - A phase 1 study of Ad5 PSA/MUC-1/Brachyury Vaccine in Patients with Metastatic Castration Resistant Prostate Cancer (mCRPC)
Presenter: Marijo Bilusic
Session: Poster Display session 3
Resources:
Abstract
3142 - Multicenter Phase I Trial of a DNA Vaccine Encoding the Androgen Receptor Ligand Binding Domain (pTVG-AR, MVI-118) in Patients with Metastatic Prostate Cancer
Presenter: Douglas McNeel
Session: Poster Display session 3
Resources:
Abstract
4327 - Impact of germline mutations in Homologous Recombination (HR) genes on the response to Radium-223 for metastatic castration resistant prostate cancer (mCRPC)
Presenter: Elena Castro
Session: Poster Display session 3
Resources:
Abstract
3600 - Serum biomarkers of bone metabolism in metastatic castration-resistant prostate cancer (mCRPC) patients (pts) treated with Radium-223 (Ra223): Results from a prospective multicentre study
Presenter: Nuria Romero Laorden
Session: Poster Display session 3
Resources:
Abstract
3742 - Prognostic value of tumor suppression genes (TP53, PTEN, Rb) in metastatic hormone sensitive prostate cancer
Presenter: Miguel Gonzalez Velez
Session: Poster Display session 3
Resources:
Abstract
2643 - Germline sequencing of advanced prostate cancer patients in the BARCODE2 trial
Presenter: Sarah Benafif
Session: Poster Display session 3
Resources:
Abstract
4349 - Impact of treatment sequence in patients (pts) with metastatic castration-resistant prostate cancer (mCRPC): data from the prospective PROREPAIR-B study.
Presenter: Carlo Cattrini
Session: Poster Display session 3
Resources:
Abstract
3301 - Implications of Single Nucleotide Polymorphisms (SNPs) in Androgen Related-Genes in Outcome of metastatic castration-resistant prostate cancer (mCRPC) patients treated with Abiraterone (Abi) and Enzalutamide (Enza)
Presenter: Isabel Aragon
Session: Poster Display session 3
Resources:
Abstract
2275 - Activating mutations in AKT1/PIK3CA are associated with poor clinical outcomes in metastatic prostate cancer (mPC)
Presenter: Simon Fu
Session: Poster Display session 3
Resources:
Abstract