An AI Driven Enhanced Bioinformatics Pipelines in DevOps Environment
DOI:
https://doi.org/10.26438/ijcse/v13i2.124135Keywords:
Artificial Intelligence, Bioinformatics, DevOps, Machine Learning, Deep Learning, Data Analysis, Pipelines, Scalability, ReproducibilityAbstract
The implementation of AI methods into DevOps pipelines within bioinformatics has several effects: Initially, it liberates researchers’ time as it provides for automation of simple and repetitive procedures like data pre-processing and feature extraction. Secondly deployment of AI models can be done at scale as the data can be processed in parallel and distributed fashion. This helps to enhance the rate of processing large amounts of information and the efficiency of functioning. In addition, the integration of AI into the models has been proven to increase the high predictive and classifying effectiveness of bioinformatics results gained from specimens. This paper also showed that AI with aspects of DevOps exists in the field of bioinformatics, and they aid in such approaches’ fine working. For example, in the process of protein-protein interactions, gene functions and diseases, machine learning models have been employed to give reliable forecasts. Machine learning algorithms such as deep learning have been applied to find disease subtypes from genomic data, hence leading to precision medicine. Now, due to NLP, great knowledge from huge amounts of scientific literature can be effectively exploited to generate new biological hypotheses. However, there are issues that are yet to be solved with regard to this aspect of research findings. The most evident one can be named as the absence of definite procedures and methods for the proper incorporation of AI into DevOps frameworks in bioinformatics. More importantly, there is a need to standardize practice to allow the replication of findings and increase the visibility of the analysis that is done through the use of Artificial Intelligence. Also, bioinformatics is an active area of research which experiences the setting of new technologies and data types regularly. This construes a need for constant invention and interdisciplinary efforts, especially at the intersection in-between biology, computer science, and statistics.
References
[1] Xiaotian Hu et al., “Deep learning frameworks for protein–protein interaction prediction,” Computational and Structural Biotechnology Journal, Vol.20, pp.3223-3233, 2022. https://doi.org/10.1016/j.csbj.2022.06.025
[2] Runpu Chen, Deep-learning approach to identifying cancer subtypes using high-dimensional genomic data, Bioinformatics. Mar; Vol.36, Issue.5, pp.1476–1483, 2020. https://doi.org/10.1093/bioinformatics/btz769
[3] Jeremy Leipzig, A review of bioinformatic pipeline frameworks, Briefings in Bioinformatics, May, Vol.18, Issue.3, pp.530–536, 2017. https://doi.org/10.1093/bib/bbw020
[4] Miller D, Arias O, Burstein D. GeNLP: a web tool for NLP-based exploration and prediction of microbial gene function. Bioinformatics. Feb 1; Vol.40, Issue.2, 2024. doi: https://doi.org/10.1093/bioinformatics/btae034
[5] Alan T. Bull, The Paradigm Shift: Bioinformatics, Microbial Diversity and Bioprospecting, 2023. https://doi.org/10.1128/9781555817770.part5
[6] Kevin G. Libuit, Accelerating bioinformatics implementation in public health Open Access, 2023. https://doi.org/10.1099/mgen.0.001051
[7] Bioinformatics Pipeline & Tips For Faster Iterations, weka, 2022.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
