WorMachine: machine learning-based phenotypic analysis tool for worms

New Software for phenotypic high-throughput analysis of C.Elegans Microscope Images
WorMachine: machine learning-based phenotypic analysis tool for worms

A link to the paper in BMC Biology can be found here.

Also, we created a short demo video for the software:

Caenorhabditis elegans nematodes are powerful model organisms, yet quantification of visible phenotypes is still often labor-intensive, biased, and error-prone. Particularly, evolution research requires numerous samples, which make manual analysis extremely strenuous. 

Hence, we developed WorMachine, a MATLAB-based image analysis software that utilized cutting-edge techniques from deep & machine learning, and consists of three steps:

  1. Automated identification of C. elegans worms in microscope images.
  2. Extraction of morphological features and quantification of fluorescent signals
  3. Machine learning techniques for high-level analysis.

We examined the power of WorMachine using five separate representative assays: supervised classification of binary-sex phenotype, scoring continuous-sexual phenotypes, quantifying the effects of two different RNA interference treatments, and measuring intracellular protein aggregation.

WorMachine is suitable for analysis of a variety of evolutionary questions and provides an accurate and reproducible analysis tool for measuring diverse phenotypes. It serves as a “quick and easy,” convenient, high-throughput, and automated solution for nematode research. We hope you find it helpful for your research needs, and are happy to be of service for any questions or comments.