Skip to main content
PyCon US is happening May 14th-22nd in Pittsburgh, PA USA.  Learn more

Find residues with sidechains in a specific region

Project description

Visible Residues

Last release Python version Documentation Test status Test coverage Last commit

This is an extension module implementing one performance-critical function used to create a machine learning dataset of 3D images of macromolecules with labeled amino acid identities. Specifically, the function accepts a dataframe of atoms in the image, then samples a fixed number of residues whose sidechains are likely to be mostly within the image. To avoid biasing the samples based on the specific sidechains involved (e.g. glycine has a smaller sidechain than arginine, so it might be sampled more often if the actual sidechain was considered), this "within the image" determination is based entirely on backbone coordinates.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page