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
3117 - A modified Edmonton Symptom Assessment Scale for assessing symptoms in one day chemotherapy clinic
Presenter: Anjuleta Kampitsi
Session: Poster Display session 3
Resources:
Abstract
6058 - Level of physical activity and nutritional status in cancer patients with fatigue: an exploratory cross-sectional study
Presenter: Patrick Jahn
Session: Poster Display session 3
Resources:
Abstract
1980 - Catheter related necrotizing fascitiis in haematological patients. Case report and implications for nursing
Presenter: Arianna Rosich Soteras
Session: Poster Display session 3
Resources:
Abstract
3984 - Everyday life with Long-term Chemotherapy Induced Peripheral Neuropathy among Patient in Adjuvant Treatment for Colorectal Cancer – a Multi Methods Study
Presenter: Marlene Jensen
Session: Poster Display session 3
Resources:
Abstract
2202 - Scalp cooler is effective in reducing chemotherapy-induced alopecia among breast cancer patients : a single institution experience
Presenter: Emilia Gianotti
Session: Poster Display session 3
Resources:
Abstract
5942 - Nursing management of fatigue in cancer patients: mixed methods study
Presenter: Angela Tolotti
Session: Poster Display session 3
Resources:
Abstract
2930 - Awareness of Nursing Students about the Warning Signs of Cancer
Presenter: Hatice Yakar
Session: Poster Display session 3
Resources:
Abstract
2978 - Assessment of quality of life in patients with cancer and diabetes 2 in Northern Greece.
Presenter: STYLIANI MICHALOPOULOU
Session: Poster Display session 3
Resources:
Abstract
3400 - Radiation dose variables related to the causes of skin toxicities in women with breast cancer: a study proposal
Presenter: EULALIA PUJOL
Session: Poster Display session 3
Resources:
Abstract
2156 - How should the symptoms be managed after breast cancer surgery? An example of mobile app
Presenter: AYDANUR AYDIN
Session: Poster Display session 3
Resources:
Abstract