Introduction

mlomix is a bioinformatics that accepts gene expression feature counts and/or DNA methylation data (beta matrices or raw IDAT files) together with the corresponding classes for each sample, and processes the data for machine learning classification for e.g. cancers.

It comes bundled with configs for pre-processing inference data for classification using PALLAS10k (Pan Acute Leukemia Learning and Subtyping), a multi-modal classifier used to predict subtypes of pediatric acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML).

Usage

Input samplesheet

First, prepare a samplesheet with your input data that looks as follows:

samplesheet.csv:

sample,dataset,gex_feature_counts_file
CONTROL_REP1,201009_A00123_0045_AHT2LMDSXX,/path/to/CONTROL_REP1.txt

Full documentation on the samplesheet columns is here.

Running the pipeline

If you are new to Nextflow and nf-core, please refer to this page on how to set-up Nextflow. Make sure to test your setup with -profile test before running the workflow on actual data.

Now, you can run the pipeline using:

nextflow run mlomix \
   -profile <local/docker/singularity/.../institute> \
   --input samplesheet.csv \
   --outdir <OUTDIR>

To pre-process data for inference using the PALLAS classifier, run:

nextflow run mlomix \
   -profile <local/docker/singularity/.../institute> \
   --input samplesheet.csv \
   --outdir <OUTDIR> \
   --classifier_name pallas \
   --classifier_version 1.0.0

Citations

This pipeline uses code and infrastructure developed and maintained by the nf-core initative, and reused here under the MIT license.

The nf-core framework for community-curated bioinformatics pipelines.

Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen.

Nat Biotechnol. 2020 Feb 13. doi: 10.1038/s41587-020-0439-x.

In addition, references of tools and data used in this pipeline are as follows: