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
3349 - Interplay between miR-17-5p and MALAT-1 Shapes The Cytokine Storm in Triple Negative Breast Cancer (TNBC) Tumor Microenvironment
Presenter: Raghda Soliman
Session: Poster Display session 3
Resources:
Abstract
4014 - Clinical verification on the relationship between lipid metabolism and the immune microenvironment of breast cancer
Presenter: Wataru Goto
Session: Poster Display session 3
Resources:
Abstract
4158 - The clinical and transcriptional signatures of human CD204 reveal an applicable marker for tumor associated macrophage in breast cancer
Presenter: Yunjie He
Session: Poster Display session 3
Resources:
Abstract
5392 - Activated effector T cells co-expressing multiple inhibitory receptors (IRs) are enriched in the tumor immune microenvironment in high grade serous ovarian cancer (HGSOC)
Presenter: Alice Bergamini
Session: Poster Display session 3
Resources:
Abstract
2617 - Oncolytic reovirus as a new anti-tumor strategy in castration resistant prostate cancer
Presenter: Yunlim Kim
Session: Poster Display session 3
Resources:
Abstract
2995 - Dysregulation of helper T lymphocytes in esophageal squamous cell carcinoma (ESCC) patients is highly associated with aberrant production of miR-21
Presenter: Ali Memarian
Session: Poster Display session 3
Resources:
Abstract
3597 - Myeloid derived suppressor cells but not regulatory T cells are associated with adaptive immunity and clinical outcomes in anal squamous cell carcinoma
Presenter: Christophe Borg
Session: Poster Display session 3
Resources:
Abstract
3430 - Evaluation of immune responses among responders (R) and non-responders (non-R) in a humanized mouse model with colorectal cancer (CRC) xenografts treated with combination immunotherapy
Presenter: Juan Marín Jiménez
Session: Poster Display session 3
Resources:
Abstract
1995 - ¬¬Advanced melanoma patients with high CD16+ macrophages have better response and survival to anti-PD-1 based immunotherapy
Presenter: Hansol Lee
Session: Poster Display session 3
Resources:
Abstract
3988 - Basal NK activity and early Treg function inhibition predicts Nivolumab responsiveness in metastatic renal cancer patients (REVOLUTION) trial.
Presenter: Sara Santagata
Session: Poster Display session 3
Resources:
Abstract