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
4290 - Characterization of the mechanism of action and efficacy of MEN1611 (PA799), a novel PI3K inhibitor, in breast cancer preclinical models.
Presenter: Alessio Fiascarelli
Session: Poster Display session 3
Resources:
Abstract
2167 - Neat-1: culprit lnRNA tying PIG-C, MSLN, CD80 in TNBC
Presenter: Nada Hussein
Session: Poster Display session 3
Resources:
Abstract
1829 - A novel RAF/MEK inhibitor CH5126766 in phase 1 clinical trial has an effectiveness in the combination with eribulin for the treatment of triple negative breast cancer
Presenter: Hisako Ono
Session: Poster Display session 3
Resources:
Abstract
4357 - Identification of a stemness-related gene panel associated with BET inhibition in triple negative breast cancer
Presenter: Eva Galan-Moya
Session: Poster Display session 3
Resources:
Abstract
5163 - Preclinical Evaluation targeting both IGF1R and IR in Triple Negative Breast Cancer
Presenter: Alex Eustace
Session: Poster Display session 3
Resources:
Abstract
832 - Monospecific antibody targeting of CDH11 inhibits epithelial-to-mesenchymal transition and represses cancer stem cell-like phenotype by up-regulating miR-335 in metastatic breast cancer, in vitro and in vivo.
Presenter: Jia-Hong Chen
Session: Poster Display session 3
Resources:
Abstract
3781 - Pharmacological screening with Chk1 inhibitors identify synergistic agents to overcome resistance to platinums in basal breast and ovarian cancer
Presenter: Ana Lucia Sanabria
Session: Poster Display session 3
Resources:
Abstract
3275 - Comparison of 11 circulating miRNAs and CA125 kinetics in ovarian cancer during first line treatment: data from the randomized CHIVA trial (a GINECO-GCIG study)
Presenter: Patrick Robelin
Session: Poster Display session 3
Resources:
Abstract
3391 - Inhibiting Ehmt2 and Ezh2 histone methyltransferases alters the immune microenvironment in a Trp53-/- murine ovarian cancer model
Presenter: Pavlina Spiliopoulou
Session: Poster Display session 3
Resources:
Abstract
3839 - Fenofibrate impairs pro-tumorigenic potential of cancer stem cell-like cells within drug-resistant prostate cancer cell populations.
Presenter: Tomasz Wróbel
Session: Poster Display session 3
Resources:
Abstract