liveBook · Manning

Target identification

As explained in Build AI Drug Discovery Pipelines

Target discovery is the identification of biological entities and disease relationships that may support new therapeutic hypotheses.

Target identification finds a biological molecule associated with a disease mechanism and worth modulating therapeutically. Selecting the target focuses later design on compounds that bind it and alter its activity. section 1.4.1

The choice is rarely obvious because disease biology may be only partly understood. Computational systems can assemble and rank candidate targets from scientific literature or multi-omics data, but human experts must scrutinize the evidence and validate whether modulation could limit disease progression. section 1.4.1 section 13.4

Target identification sits at the beginning of the early discovery workflow:

  • Identify or select a disease-associated biomolecule. section 1.4
  • Validate the target’s relationship to disease and its therapeutic potential. section 1.4.1
  • Discover active compounds through virtual screening or high-throughput screening. section 1.4.1
  • Advance promising hits through lead identification and lead optimization, including potency, selectivity, safety, and ADMET considerations. section 1.5

From disease mechanism to target

For disease X, a target is a biomolecule linked to an underlying mechanism. A compound that binds the target resembles a key fitting a lock, but binding may change enzyme shape and function. Unintended binding to other biomolecules creates an off-target effect. TNIK in idiopathic pulmonary fibrosis illustrates a stronger case of computationally emerging biology because it had little prior disease literature and no selective inhibitors. section 1.4.1 section 13.4

Figure 1.11 We can breakdown drug design into target identification and validation, hit discovery, hit-to-lead (lead identification), lead optimization, and preclinical development. Once a drug candidate has progressed to the drug development stage, it will need to pass multiple phases of clinical trials testing safety and efficacy prior to submission to and review by the FDA and launch to market.

Use the pipeline diagram to distinguish target identification and validation from hit discovery, lead optimization, preclinical development, and later clinical development. section 1.4

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains selection, validation, computational prioritization, and expert scrutiny, but stops short of detailed target-validation methods.
Examples
Uses disease X, the lock-and-key analogy, off-target effects, and TNIK research in idiopathic pulmonary fibrosis.
What it assumes
Assumes a disease mechanism may be partly known and teaches target, hit, off-target effect, and validation terminology from practical examples.
What you can do after
Evaluate candidate targets and understand how validated targets direct compound discovery and later optimization.
How it connects
Connects target validation with hit discovery, virtual screening, high-throughput screening, lead optimization, ADMET, and clinical translation.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.