Abstract Background: Genomics is expected to transform oncology clinical practice. However, converting genomic data into clinically actionable information is a daunting task. Genomic high-throughput technologies produce massive amounts of raw data, and its complexity presents a formidable challenge for clinical adoption. While algorithms exist to convert genomic data into meaningful biological information, they are geared towards the bioinformatics expert user, lack clinical annotation and interpretation, and are not addressing the needs of clinical experts. Furthermore, the main problem is that sequencing results should not be treated like a test as they are geared towards precision diagnostics which require patient clinical data. Methods: We present PAPAyA, a genome informatics platform that provides an overall solution to the genomic data overload which includes analysis of whole transcriptome and exome data, secure storage and management of this data and the interactive presentation of patient genome information in a contextualized manner. It is a continuum of analytics and user experiences with deep understanding of the clinical questions and the workflow. PAPAyA is a framework for hosting multiple genome informatics applications that bring information that is Connected, Digital and in Real Time. Connected in many dimensions - across hospital systems, across time, across many hospitals and their affiliates. Digital means retrievable (without complicated SQL queries) not just stored bits across modalities (genomics is a single vertical that pulls other information towards precise treatment). Real time means up to date ACTGs get converted into actionable information fast, and get to the right clinical expert without manual actions and printing reports. The framework sits on top of a digital health platform that offers core capabilities such as: persisting data and provisioning service (elastic computing), security, auditing, business workflow engine, reports service, user management service, patient identity service, provider registry service. At its core, PAPAyA provides full pipelines that analyze genomic high-throughput data, and further extract and prioritize clinically-meaningful information from the patient's genome. Furthermore, PAPAyA enables storage and secure management of this complex data which allows clinicians to query the data in a clinical action-oriented framework, as opposed to data aggregation and reporting framework. Results: We demonstrate the usability of PAPAyA using public data from TCGA breast cancer cohort. We show the utility of executing in-silico assays applied on RNAseq data, such as ER/PR/Her2, differential expression of long-noncoding RNAs, gene fusions, subtyping, hypoxia index, and other known signatures from the biomedical literature. In parallel, we annotate full exomes in order to find clinically relevant information for variants of unknown significance as well as variants with known disease and response phenotype using biological, functional, and clinical annotation resources. Conclusion: We have implemented an automated open learning system for processing genomic data to aid in clinical decision making. We already started the pilot phase and clinical evaluation with key academic collaborators. Citation Format: Nilanjana Banerjee, Konstantin Volyanskyy, Vartika Agrawal, Yong Mao, Yee-Him Cheung, Sitharthan Kamalakaran, Laurens Boekhorst, Arjan Claassen, Nevenka Dimitrova. PAPAyA – The genome informatics framework for oncology applications and other clinical domains [abstract]. In: Proceedings of the Thirty-Seventh Annual CTRC-AACR San Antonio Breast Cancer Symposium: 2014 Dec 9-13; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2015;75(9 Suppl):Abstract nr P4-08-02.
Read full abstract