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
5383 - A pilot trial to investigate the impact of a personalised self-management lifestyle programme using mobile technology on the health and wellbeing of cancer survivors
Presenter: Mary Grace Kelly
Session: Poster Display session 3
Resources:
Abstract
5084 - The BRIGHTLIGHT national survey of the impact of specialist teenage and young adult cancer care on caregivers’ information and support needs
Presenter: Rachel Taylor
Session: Poster Display session 3
Resources:
Abstract
4328 - Life beyond cancer: Occupational health care service support in returning work experienced by cancer survivals
Presenter: Minna Nurmi
Session: Poster Display session 3
Resources:
Abstract
3337 - Investigating the factors related to primary caregivers' burden in oncology patients in Greece
Presenter: Ourania Govina
Session: Poster Display session 3
Resources:
Abstract
3387 - Factors Influencing the Level of Emotional Support from Nurses Perceived by Patients Undergoing Haematopoietic Stem Cell Transplantation in Protective Isolation
Presenter: Michela Piredda
Session: Poster Display session 3
Resources:
Abstract
935 - Progressive Muscle Relaxation and Guided Imagery Techniques and the Way of Coping of Parents of Children with Malignancies: A randomized controlled trial
Presenter: Tsitsi Theologia
Session: Poster Display session 3
Resources:
Abstract
3457 - Pharmacist and Nurse Led Melanoma Immunotherapy Clinic
Presenter: Dharmisha Chauhan
Session: Poster Display session 3
Resources:
Abstract
5160 - Measuring the impact of the Irish Cancer Society's Cancer Information Services
Presenter: Aileen McHale
Session: Poster Display session 3
Resources:
Abstract
4297 - It's Great to Talk
Presenter: Noreen Andersen
Session: Poster Display session 3
Resources:
Abstract
4444 - Impact of Burn-Out Syndrome in Oncology personnel and its improvement through specific interventions
Presenter: Inmaculada Ortega
Session: Poster Display session 3
Resources:
Abstract