INTEGRATING ARTIFICIAL INTELLIGENCE AND DATA SCIENCE FOR BIOINFORMATICS: METHODS, TOOLS, AND RESEARCH APPLICATIONS

Abstract

Artificial intelligence (AI) and data science are providing scalable computational frameworks for extracting insight from increasingly large and complex biological datasets. Methods from machine learning (ML), deep learning (DL), and large language modeling now support tasks ranging from multi-omics integration and variant interpretation to protein-structure prediction and accelerated antimicrobial discovery. Deep learning approaches have produced near-experimental accuracy in protein structure prediction, while DNA-specialized large language models (LLMs) extend sequence interpretation across regulatory and structural contexts (Jumper et al., 2021; Varadi et al., 2024; Wang et al., 2025). In antimicrobial resistance (AMR) research, ML systems enable rapid resistance classification, surveillance, and candidate prioritization for novel therapeutics (Ali et al., 2023; Bilal et al., 2025; Santos-Júnior et al., 2024). Explainable AI (XAI) and rigorous data curation are essential for trustworthy deployment in research and clinical settings (Budhkar et al., 2025; Martínez-Agüero et al., 2022). This chapter synthesizes contemporary methods, tools, and representative applications to guide students in bioinformatics, biotechnology, microbiology, and computational biology toward reproducible, evidence-based practice.