Abstract
BackgroundGenetic information is becoming more readily available and is increasingly being used to predict patient cancer types as well as their subtypes. Most classification methods thus far utilize somatic mutations as independent features for classification and are limited by study power. We aim to develop a novel method to effectively explore the landscape of genetic variants, including germline variants, and small insertions and deletions for cancer type prediction.ResultsWe proposed DeepCues, a deep learning model that utilizes convolutional neural networks to unbiasedly derive features from raw cancer DNA sequencing data for disease classification and relevant gene discovery. Using raw whole-exome sequencing as features, germline variants and somatic mutations, including insertions and deletions, were interactively amalgamated for feature generation and cancer prediction. We applied DeepCues to a dataset from TCGA to classify seven different types of major cancers and obtained an overall accuracy of 77.6%. We compared DeepCues to conventional methods and demonstrated a significant overall improvement (p < 0.001). Strikingly, using DeepCues, the top 20 breast cancer relevant genes we have identified, had a 40% overlap with the top 20 known breast cancer driver genes.ConclusionOur results support DeepCues as a novel method to improve the representational resolution of DNA sequencings and its power in deriving features from raw sequences for cancer type prediction, as well as discovering new cancer relevant genes.
Highlights
Genetic information is becoming more readily available and is increasingly being used to predict patient cancer types as well as their subtypes
In a pilot study utilizing 4174 samples across seven major cancer types from The Cancer Genome Atlas (TCGA), we were able to achieve an accuracy of 77.6% in predicting cancer types using the raw tumor sequences
Germline and somatic mutations from 4174 samples across seven major cancer types were obtained from the TCGA [29]
Summary
Genetic information is becoming more readily available and is increasingly being used to predict patient cancer types as well as their subtypes. While many methods attempted to address the complex mutational heterogeneity in cancer, driver gene identification still remains a challenge due to the limited capability in integrating other genome components for integrative study [4,5,6,7,8] Other genome components, such as nonsense mutations of insertions and deletions, as well as germline variation, were largely ignored in the past but have been recently highlighted to play a significant role for cancer development [9,10,11]. Due to the limitation of analysis power, methods including Bayesian classifier [13], regression models [14, 15], and KNN [16] are not optimal in handling such high-dimensional features interactively To circumvent these challenges, labor intensive feature engineering using prior knowledge need to be performed prior to modeling [17]. Recent examples of exploring the application of CNNs within raw sequencing data include DeepBind [25], DanQ [26], DeepSEA [27], DeepCpG [28]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
