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
3524 - Cabazitaxel For Octogenarian Patients With Metastatic Castration-Resistant Prostate Cancer (MCRPC).
Presenter: Paolo Tralongo
Session: Poster Display session 3
Resources:
Abstract
5637 - External Validation of a Prognostic Score in First-Line Metastastic Castration-Resistant Prostate Cancer (mCRPC)
Presenter: David Lorente
Session: Poster Display session 3
Resources:
Abstract
3228 - Treatment outcomes of 3rd treatment in a real-world metastatic castration resistant prostate cancer (mCRPC) population: results from the Dutch CAPRI-registry
Presenter: Jessica Notohardjo
Session: Poster Display session 3
Resources:
Abstract
4695 - Pelvic lymph node dissection and its extent on survival benefit in prostate cancer patients with a risk of lymph node invasion>5%: a propensity score matching analysis from SEER database
Presenter: Junru Chen
Session: Poster Display session 3
Resources:
Abstract
4438 - Multi-institutional evaluation of therapeutic management for oligometastatic cancer prostate recurrence with choline-PET/CT
Presenter: Morgane Guibert-broudic
Session: Poster Display session 3
Resources:
Abstract
4574 - Safety of new androgen receptor inhibitors (ARi) in patients with nonmetastatic castration-resistant prostate cancer (nmCRPC): a network meta-analysis of randomized controlled trials (RCT)
Presenter: Amelia Altavilla
Session: Poster Display session 3
Resources:
Abstract
3816 - Real-world use of radium-223 for treatment of metastatic castration resistant-prostate cancer (mCRPC): results from the Dutch CAPRI registry
Presenter: Malou Kuppen
Session: Poster Display session 3
Resources:
Abstract
5180 - A phase 2a study of radium-223 dichloride (Ra-223) alone or in combination with abiraterone acetate or enzalutamide in metastatic castration-resistant prostate cancer (mCRPC)
Presenter: Daniel Petrylak
Session: Poster Display session 3
Resources:
Abstract
1067 - Adding ADT to PSMA-PET/CT-guided SBRT for oligometastatic prostate cancer improves distant progression-free survival
Presenter: Carole Mercier
Session: Poster Display session 3
Resources:
Abstract
5529 - Safety and efficacy of Ac-225-PSMA-617 in metastatic castration resistant prostate cancer (mCRPC) after failure of Lu-177-PSMA
Presenter: Robert Tauber
Session: Poster Display session 3
Resources:
Abstract