liveBook · Manning

Epistasis

Epistasis is the interaction among variables or mutations whereby the effect of one depends on the states of others.

How 2 Manning books explain it

Build AI Drug Discovery Pipelines

Epistasis is the dependence of a mutation's effect on the presence of other mutations in the same sequence.

How it is used
Uses epistasis to motivate checking combined protein mutations rather than relying on individual mutation scores.
How deep it goes
Explains a model-based plausibility check for mutation combinations but stops short of establishing biological effects.
Examples
Illustrates three individually promising antibody framework mutations evaluated together against the wild-type sequence.
What you can do after
Evaluate combined variants using ESM-2 pseudo-perplexity while recognizing that sequence plausibility does not establish biological function.

Read how Build AI Drug Discovery Pipelines explains epistasis →

Advanced Algorithms and Data Structures

Epistasis is the degree to which variables in an optimization problem interact so that changing one variable affects the values or constraints of others.

How it is used
Guides the choice between genetic algorithms and simulated annealing by revealing how strongly optimization variables interact.
How deep it goes
Explains epistasis through variable dependencies, constraints, and examples, then stops short of formal measurement.
Examples
Uses knapsack, traveling salesperson, house design, and vertex cover to contrast independent, coupled, and constraint-linked variables.
What you can do after
Evaluate optimization methods by comparing epistasis and testing genetic algorithms against simulated annealing on smaller instances.

Read how Advanced Algorithms and Data Structures explains epistasis →

Related concepts

Questions about epistasis

What is epistasis?

Epistasis is the interaction among variables or mutations whereby the effect of one depends on the states of others.

Which Manning books explain epistasis?

Build AI Drug Discovery Pipelines and Advanced Algorithms and Data Structures.

What is the difference between epistasis and gradient descent?

Epistasis is the interaction among variables or mutations whereby the effect of one depends on the states of others. Gradient descent is an iterative optimization method that updates parameters in the direction opposite an objective function’s gradient to reduce the objective’s value.

What is epistasis a kind of?

Epistasis is a kind of variable interaction. Variable interaction is the dependence in an optimization problem whereby the value or constraints of one variable are affected by another variable.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.