Abstract
In the field of cancer genomics, the broad availability of genetic information offered by next-generation sequencing technologies and rapid growth in biomedical publication has led to the advent of the big-data era. Integration of artificial intelligence (AI) approaches such as machine learning, deep learning, and natural language processing (NLP) to tackle the challenges of scalability and high dimensionality of data and to transform big data into clinically actionable knowledge is expanding and becoming the foundation of precision medicine. In this paper, we review the current status and future directions of AI application in cancer genomics within the context of workflows to integrate genomic analysis for precision cancer care. The existing solutions of AI and their limitations in cancer genetic testing and diagnostics such as variant calling and interpretation are critically analyzed. Publicly available tools or algorithms for key NLP technologies in the literature mining for evidence-based clinical recommendations are reviewed and compared. In addition, the present paper highlights the challenges to AI adoption in digital healthcare with regard to data requirements, algorithmic transparency, reproducibility, and real-world assessment, and discusses the importance of preparing patients and physicians for modern digitized healthcare. We believe that AI will remain the main driver to healthcare transformation toward precision medicine, yet the unprecedented challenges posed should be addressed to ensure safety and beneficial impact to healthcare.
Highlights
Is artificial intelligence (AI) going to take over the world as pictured in the sci-fi movies? It has famously beaten the best-performing human beings in competitions such as Jeopardy, AlphaGo, etc., and is crawling into our daily life without notice
Autonomous vehicles, smart homes, chat bots, individualized marketing, fraud detection, and high-frequency automated trading are some examples of AI empowering humans to live in a more efficient and personalized way
Healthcare, an industry that is long governed by medical professionals, is benefitting from AI
Summary
Is artificial intelligence (AI) going to take over the world as pictured in the sci-fi movies? It has famously beaten the best-performing human beings in competitions such as Jeopardy, AlphaGo, etc., and is crawling into our daily life without notice. Different variant scientists among companies, research groups, and hospitals can introduce bias due to subjectivity in curation criteria, adherence to Standardized Operating Procedures and training To address these limitations, organizations are working to build and standardize multi-step protocols for variant classification such as the American College of Medical Genetics and Genomics and the Association for Molecular Pathology (ACMG-AMP), who, in 2015, published a series of guidelines for the interpretation of germline genetic variants for genes causative of hereditary human disorders (Richards et al 2015). Besides standard variant detection paradigms, Google’s DeepVariant transforms a variant calling problem into an image recognition problem by converting a BAM file into images similar to genome browser snapshots and calls the variants based on likelihoods, using the Inception Tensor Flow framework which was originally developed for image classification (Going Deeper with Convolutions 2014) Another recent study successfully applied ML on sequencing data from multiple regions of a tumor to identify and learn growth patterns as accurate predictors for tumor progression (Caravagna et al 2018). The logistic regression model demonstrated the best performance with only 1% false negativity and 2% false positivity, which is comparable to human decisions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
