ml-from-omics

KO | EN

gitlite — search

#python #hacktoberfest #llm #android #rust #linux #macos #awesome #kubernetes #awesome-list #vue #ios #mcp #openai

(★ 15)

Code required to reproduce results from the book chapter "Machine learning from omics data" (Springer Protocols, 2021)

ml-from-omics Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Machine learning from omics data

This repository contains the code required to reproduce all results and figures presented in the book chapter "Machine learning from omics data" (Springer Protocols, 2021).

**This is an updated version of the [original code](https://github.com/Evotec-Bioinformatics/ml-from-omics/tree/original_code). It uses a newer Python version, more recent dependencies and Optuna for hyper-parameter search.**

## Instructions

First, install Python 3.10.10 (newer versions may also work) and then clone this repository. Next, install the dependencies using pip (preferably in a new virtualenv):

````shell
pip install -r requirements.txt
````

Optionally, set the number of processes to use during the hyper-parameter search. The default is 4. If you use SLURM, this will be done automatically.

````shell
export SLURM_CPUS_ON_NODE=20
````

Now, you can `cd src/` and train the models:
````shell
python main.py
````

This will take a while. Note, that this script will also download and extract all required datasets and thus needs about 41 GB of disk space. Afterwards generate all four figures by calling:

````shell
python create_plots.py
````

Neither the SVM nor UMAP are fully deterministic methods. Hence, minor deviations from the published results are to be expected.

ml-from-omics

ml-from-omics Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

ml-from-omics

ml-from-omics Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README