SeqOptPlot

class SeqOptPlot(*, verbose=False)[source]

Plotting class for SeqOpt (Sequence Optimizer) results [Breimann24a].

Visualizes the Pareto front produced by SeqOpt.run(): a 2-D objective scatter colored by non-dominated rank, and the per-generation hypervolume convergence trace.

Every plotting method returns a (fig, ax) pair (a thin tuple subclass): unpack as fig, ax = .... For backward compatibility, the returned object also forwards attribute access to ax.

Warning

Experimental. This class is part of the new v1.1.0 protein-design/optimization layer and is under active development; its API (signatures, defaults, return objects) may change between minor releases without the usual deprecation cycle. Pin a version if you depend on the current behaviour.

Added in version 1.1.0.

Parameters:: verbose (bool)

Methods

`convergence`(history, *[, figsize])	Plot per-generation convergence: hypervolume, spread and per-objective best.
`genealogy`(df_pareto, *[, ax, figsize, ...])	Mutational-lineage tree of the variants, rooted at the wild-type.
`hypervolume`(trajectory, *[, ax, figsize])	Plot the per-generation hypervolume convergence trace.
`mutation_map`(df_pareto, *[, ax, figsize, ...])	Heatmap of substitution enrichment across the Pareto front (position x amino acid).
`parallel_coordinates`(df_pareto, objectives, *)	Parallel-coordinates plot of a Pareto front over any number of objectives.
`pareto_front`(df_pareto, x, y, *[, z, ax, ...])	Scatter two (or three) objectives of a Pareto front.

__init__(*, verbose=False)[source]

Parameters:: verbose (bool, default=False) – If True, verbose outputs are enabled.