QLTI-07. COLLABORATIVE RESEARCH SUITE FOR GENOMIC ANALYSIS, DATA REPORTING AND WORKFLOW CUSTOMISATION

Abstract The genomic analysis pipeline involves multiple stages, including data extraction, transformation, and loading (ETL), exploratory data analysis (EDA), machine learning (ML) modeling, and reporting. The ETL stage involves data profiling and quality control measures to ensure data integrity and consistency. The EDA stage employs statistical and visualization methods to understand data distribution, identify patterns, and detect anomalies. Machine learning modelling involves supervised classification techniques, such as logistic regression and support vector machines (SVMs), to predict tumour classification and develop gene signatures. Unsupervised classification techniques, such as K-means clustering and Hierarchical clustering, identify patterns and relationships in genomic data. Quality metrics evaluate data completeness, accuracy, and consistency, ensuring data reliability and validity. The integration of data science techniques into a comprehensive framework can be achieved with the development of Application Dashboards that provide real-time insights into genomic data across every stage of the analysis pipeline. This enables clinical researchers and bioinformaticians to make informed decisions quickly, improving turn-around time and accelerating the discovery of new insights. In contrast to conventional methods of using stand-alone scripts, these dashboards offer a reusable and scalable solution, allowing for easy modification and adaptation to new datasets and analysis pipelines, thereby reducing development effort and increasing productivity. The dashboards constitute a centralized platform for data visualization, exploration, and analysis, facilitating collaboration and communication among research team members. With customizable and interactive visualizations, users can explore genomic data from multiple dimensions and the integration of multiple sources, including genomic and transcriptomic data. The technologies used to power this Research suite include Streamlit for Web App development, Python for data analysis, Opensearch for data storage and other utility libraries for reporting.