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
4900 - Molecular profiling and prognostic significance of TP53 mutations in Diffuse Large B Cell Lymphoma: identifying a high-risk subgroup
Presenter: Yuan-Kai Shi
Session: Poster Display session 3
Resources:
Abstract
3809 - Differential expression of various miRNAs in Pediatric Cytogenetically Normal Acute Myeloid Leukemia (CN-AML)
Presenter: Vikas Gaur
Session: Poster Display session 3
Resources:
Abstract
4750 - Circulating tumour cells in head and neck and non-small cell lung cancer
Presenter: Kenneth O'Byrne
Session: Poster Display session 3
Resources:
Abstract
3704 - OX40/OX40L protein expression in Non-small cell lung cancer and its role in clinical outcome and relationships with other immune biomarkers
Presenter: Xiaoshen Zhang
Session: Poster Display session 3
Resources:
Abstract
2235 - Effect of Serum Survivin on Survival among Non-Small Cell Lung Cancer Patients; NCI Experience
Presenter: Reham Rashed
Session: Poster Display session 3
Resources:
Abstract
2788 - Enhanced performance of prognostic estimation from TCGA RNAseq data using transfer learning.
Presenter: Helene Vanacker
Session: Poster Display session 3
Resources:
Abstract
4689 - Analysis of Circulating Tumor DNA for Early Relapse Detection in Stage III Colorectal Cancer After Adjuvant Chemotherapy
Presenter: Samuel Jacobs
Session: Poster Display session 3
Resources:
Abstract
1454 - Ascites-derived circulating microRNAs as potential diagnostic biomarkers of gastric cancer-associated malignant ascites
Presenter: Hye Sook Han
Session: Poster Display session 3
Resources:
Abstract
5574 - Results from TRIO030, a Pre-Surgical Tissue-Acquisition Study to Evaluate Molecular Alterations in Human Breast Cancer Tissue Following Short-Term Exposure to the Androgen Receptor Antagonist Darolutamide
Presenter: Hsiao-Wang Chen
Session: Poster Display session 3
Resources:
Abstract
1787 - JMJD2A is a novel epigenetic factor of chemotherapeutic susceptibility in gastric cancer
Presenter: Yasushi Sato
Session: Poster Display session 3
Resources:
Abstract