Data Stewardship and Curation Practices in AI-Driven Genomics and Automated Microscopy Image Analysis for High-Throughput Screening Studies: Promoting Robust and Ethical AI Applications
Keywords: Data Stewardship; AI-Driven Genomics; Microscopy Image Analysis; High-Throughput Screening; Ethical AI Applications
TL;DR: My paper explores best practices in data stewardship and curation for AI-driven genomics and automated microscopy, emphasizing robust and ethical AI applications in high-throughput screening studies.
Abstract: The increasing adoption of AI and next-generation sequencing (NGS) has revolutionized genomics and high-throughput screening (HTS), transforming how cellular processes and disease mechanisms are understood. However, these advancements generate vast datasets requiring effective data stewardship and curation practices to maintain data integrity, privacy, and accessibility. This review consolidates existing knowledge on key aspects, including data governance, quality management, privacy measures, ownership, access control, accountability, traceability, curation frameworks, and storage systems. Major challenges such as managing biases, ensuring data quality, and securing privacy are highlighted. Advanced cryptographic techniques, federated learning, and blockchain technology are proposed as strategic solutions, emphasizing standards compliance, ethical oversight, and tailored access control frameworks. Effective data stewardship is vital for advancing AI-driven genomics and microscopy research. Stakeholders must prioritize robust data governance and privacy measures to ensure data integrity and ethical use. Collaborative efforts should focus on developing transparent data-sharing policies and interoperable platforms to foster innovation and advance research practices. The study promotes collaboration among researchers, robust data governance, privacy and security, clear policies, and educational initiatives to prepare future researchers.
Submission Number: 10
Loading