1. Explore - How AI Understands Biology?

1.1 Biology as Data: From Living Systems to Digital Information

Biology traditionally focuses on the study of living systems such as cells, tissues, organs, organisms, and ecosystems. With the rapid development of digital technologies, these living systems are increasingly represented as data that can be stored, processed, and analyzed by computers.

From the perspective of Artificial Intelligence:

  • DNA is represented as long sequences of letters (A, T, C, G), e.g., AI analyzes sequences to predict regulatory motifs or splice sites.
  • Proteins are described as chains of amino acids and 3D structures, e.g., the AlphaFold model determines a protein's 3D shape from its sequence, enabling the design of new proteins for drugs.
  • Microscopic images become pixel-based visual data.
    Biological interactions are transformed into networks and models, e.g., gene regulatory networks where AI identifies "who regulates what" among genes and signaling molecules.​

AI systems do not directly observe life; instead, they work with digital representations of biological processes. By processing large volumes of biological data, AI can identify relationships and patterns that are difficult or impossible for humans to detect manually.

Key idea for students:

From AI’s perspective, biology becomes a combination of information, structure, and relationships.