Skip to main content
Python Software Foundation 20th Year Anniversary Fundraiser  Donate today!

Machine Learning for Genomic

Project description


GenoML is an Automated Machine Learning (AutoML) for Genomic. This is the core package of GenoML. this repo is under development, please report any issues (bug, performance, documentation) on the GenoML issues page.

Here are some quick "get started" exmaples, please checkout the additional options and details in the Usage and CLI. In general, use linux or mac with python > 3.5 for best results.



pip install genoml

Train the ML model

You can use the IPDGC (International Parkinson's Disease Genomics Consortium) test data. This data is a simulation of the genetic and clinical data used for Parkinson's diagnosis in previous publications. You can find it at IPDGC example data.

Download and unzip data:


To train, run:

genoml-train --geno-prefix=./exampleData/training --pheno-file=./exampleData/training.pheno --model-dir=./exampleModel

Final tuned model and performance metrics are stored in the --model-dir directory.

Using the trained ML model for inference

genoml-inference --model-dir=./exampleModel --valid-dir=./exampleData --valid-geno-prefix=./exampleData/validation --valid-pheno-file=./exampleData/validation.pheno

Valdiation results and model performance metrics are stored in the --valid-dir directory.

For debugging purposes, include the -v or -vvv flags at the end of a command.

Report issues

Please report any issue or suggestions on the GenoML issues page.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for genoml, version 1.0.4
Filename, size File type Python version Upload date Hashes
Filename, size genoml-1.0.4-py3-none-any.whl (250.7 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size genoml-1.0.4.tar.gz (78.8 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page