geometricus

Fast, structure-based, alignment-free protein embedding


Keywords
alignment-free, feature-engineering, invariant-features, machine-learning, protein-structure, proteins
License
MIT
Install
pip install geometricus==0.3.0

Documentation

PyPI version DOI

Geometricus Represents Protein Structures as Shape-mers derived from Moment Invariants

A structure-based, alignment-free embedding approach for proteins. Can be used as input to machine learning algorithms.

See the documentation.

Installation

Geometricus is a Python (3.7+) package with NumPy, SciPy, Numba and ProDy as dependencies.

Install with pip install geometricus

Usage

See the Getting Started page for example usage.

Publications

Janani Durairaj, Mehmet Akdel, Dick de Ridder, Aalt D J van Dijk, Geometricus represents protein structures as shape-mers derived from moment invariants, Bioinformatics, Volume 36, Issue Supplement_2, December 2020, Pages i718–i725, https://doi.org/10.1093/bioinformatics/btaa839

Janani Durairaj, Mehmet Akdel, Dick de Ridder, Aalt D.J. van Dijk, Fast and adaptive protein structure representations for machine learning, bioRxiv 2021.04.07.438777; doi: https://doi.org/10.1101/2021.04.07.438777