Tariq, Usman ORCID: https://orcid.org/0000-0001-7672-1187, Ahmed, Irfan
ORCID: https://orcid.org/0000-0001-5648-388X, Khan, Muhammad Attique
ORCID: https://orcid.org/0000-0002-6347-4890 and Bashir, Ali Kashif
ORCID: https://orcid.org/0000-0003-2601-9327
(2025)
Bridging biosciences and deep learning for revolutionary discoveries: a comprehensive review.
IAES International Journal of Artificial Intelligence (IJ-AI), 14 (2).
pp. 867-883.
ISSN 2089-4872
|
Published Version
Available under License Creative Commons Attribution Share Alike. Download (723kB) | Preview |
Abstract
Deep learning (DL), a pivotal artificial intelligence (AI) innovation, has dramatically transformed biosciences, aligning with the surge in complex data volumes to foster notable progress across disciplines such as genomics, genetics, and drug discovery. DL's precision and efficiency outmatch conventional methods, propelling advancements in biomedical imaging and disease marker identification. Despite its success, DL's integration into broader bioscience areas encounters hurdles including data scarcity, interpretability challenges, computational demands, and the necessity for ethical and regulatory considerations. Overcoming these obstacles is vital for DL to achieve its transformative potential fully. This review explores into DL's expanding role in biosciences, critically examining areas ripe for DL application and highlighting underexplored opportunities. It provides an insightful analysis of the algorithms that form the backbone of DL in biosciences, offering a thorough understanding of their capabilities. Ultimately, this paper aims to equip biotechnologists and researchers with the knowledge to leverage DL effectively, thereby enhancing the analysis of complex bioscience data and contributing to the field's future advancements.
Impact and Reach
Statistics
Additional statistics for this dataset are available via IRStats2.