Skip to main content

Framework of AI for Genome Analysis

Harnessing AI in the analysis of high-dimensional genomic data for accelerated biomarker discovery and enhanced genomic sequence annotations.

As genomic research becomes more complex and data-rich, artificial intelligence (AI) has emerged as a crucial tool for processing and analysing high-dimensional genomic data, accelerating biomarker discovery, and enhancing genomic sequence annotations. Despite the increasing application of AI in genomic research, challenges persist, particularly regarding the integration of biomedical knowledge into algorithm development. As a fruit of the preliminary investigation of this project, we reviewed high-quality AI-driven genomic studies from the past five years (Figure 1) and identified the current research issues and challenges (Figures 2 and 3). 

Literature review framework and AI-driven biomedical genomics categories.

Figure 1: Literature review framework and AI-driven biomedical genomics categories.

Figure 2: The hierarchical topic tree of AI-driven genomic studies

Figure 2: The hierarchical topic tree of AI-driven genomic studies,

Figure 3. The incorporation of genomic data and AI techniques profiled by current research

Figure 3: The incorporation of genomic data and AI techniques profiled by current research.

The paper titled Artificial intelligence-driven biomedical genomics was published on Knowledge-based Systems (2023). It summarizes six subsets of AI techniques used frequently in AI-driven genomic studies and specifies their applications in disease detection, prediction, diagnosis and treatment. Furthermore, challenges regarding contemporary AI-driven genomic research are concluded.

Figure 4. A mind map of the AI techniques and biomedical topics reviewed

Figure 4: A mind map of the AI techniques and biomedical topics reviewed.

The key contributions of this paper are:

  1. Presents a timely review of AI applications in biomedical genomics over the past five years, emphasizing the contributions of AI in enhancing disease prediction, diagnosis, and treatment.
  2. Devises a literature search framework for biomedical analysis using advanced bibliometric methods.
  3. Identifies challenges in contemporary AI-driven genomic research and proposes potential solutions.
  4. Serves as the training material for researchers, physicians, and industry partners who are interested in the convergence of AI and genomics, providing fundamental knowledge and the latest applications in this field.

Read the full paper (https://doi.org/10.1016/j.knosys.2023.110937).