API Reference¶

Data Model¶

`ClusterType`	An immutable storage for the type of a gene cluster.
`Strand`	A flag to declare on which DNA strand a gene is located.
`Domain`	A conserved region within a protein.
`Protein`	A sequence of amino-acids translated from a gene.
`Gene`	A nucleotide sequence coding a protein.
`Cluster`	A sequence of contiguous genes.
`ClusterTable`	A table storing condensed information from several clusters.
`FeatureTable`	A table storing condensed domain annotations from different genes.

ORF Extraction¶

`ORFFinder`	An abstract base class to provide a generic ORF finder.
`PyrodigalFinder`	An `ORFFinder` that uses the Pyrodigal bindings to Prodigal.

Domain Annotation¶

A domain annotator that uses pyhmmer.

BGC Detection¶

A wrapper for sklearn_crfsuite.CRF to work with the GECCO data model.

BGC Extraction¶

ClusterRefiner

A post-processor to extract contiguous clusters from CRF predictions.

Type Prediction¶

`TypeBinarizer`	A `MultiLabelBinarizer` working with `ClusterType` instances.
`TypeClassifier`	A wrapper to predict the type of a `Cluster`.

InterPro Metadata¶

`InterPro`	A subset of the InterPro database exposing domain metadata.
`InterProEntry`	A single entry in the InterPro database.