Clarify instructions

Molmed · Sep 18, 2024 · 74c6039 · 74c6039
1 parent 1913632
commit 74c6039
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -2,22 +2,23 @@
 
 ## About
 
-ALLIUM (ALL subtype Identification Using Machine learning) is a multimodal classifier of molecular subtypes in pediatric acute lymphoblastic leukemia, using DNA methylation (DNAm) and gene expression (GEX) data.
+ALLIUM (ALL subtype Identification Using Machine learning) is a multimodal classifier of molecular subtypes in pediatric acute lymphoblastic leukemia, using DNA methylation (DNAm) and gene expression (GEX) data. The reference genome used by this model is Homo_sapiens.GRCh38.103.
 
 ## Modules
 
 This repository contains:
 - the ALLIUM models
 - GEX and DNAm prediction clients
 - data preprocessing helpers
+- metadata generation helpers (use only if changing reference genome versions)
 - test data
 
 ## Pre-requisites
 General:
 - Python 3.8+
 - Conda
 
-For preprocessing data only:
+For regenerating metadata for a different reference genome:
 - R 4.4.1 or later, and renv
 
 You may need to install additional libraries depending on your operating system.

diff --git a/src/preprocessing/1_download_ref.py → src/metadata_generation/1_download_ref.py b/src/preprocessing/1_download_ref.py → src/metadata_generation/1_download_ref.py
diff --git a/src/preprocessing/2_parse_ref.r → src/metadata_generation/2_parse_ref.r b/src/preprocessing/2_parse_ref.r → src/metadata_generation/2_parse_ref.r