From da4eceaaea5cebff2e1efbebc0c486d8ecf6a12f Mon Sep 17 00:00:00 2001
From: Pavankumar Videm <pavanvidem@gmail.com>
Date: Fri, 10 Jan 2025 15:00:30 +0100
Subject: [PATCH] Update README and annotation, and fix params according to
 their datatypes

---
 ...gle-cell-RNA-seq-data-with-Scanpy-tests.yml | 18 +++++++++---------
 ...-of-single-cell-RNA-seq-data-with-Scanpy.ga |  4 ++--
 workflows/scRNAseq/scanpy-clustering/README.md |  4 +++-
 3 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/workflows/scRNAseq/scanpy-clustering/Preprocessing-and-Clustering-of-single-cell-RNA-seq-data-with-Scanpy-tests.yml b/workflows/scRNAseq/scanpy-clustering/Preprocessing-and-Clustering-of-single-cell-RNA-seq-data-with-Scanpy-tests.yml
index a9afaf629..e7a031d4f 100644
--- a/workflows/scRNAseq/scanpy-clustering/Preprocessing-and-Clustering-of-single-cell-RNA-seq-data-with-Scanpy-tests.yml
+++ b/workflows/scRNAseq/scanpy-clustering/Preprocessing-and-Clustering-of-single-cell-RNA-seq-data-with-Scanpy-tests.yml
@@ -12,17 +12,17 @@
       class: File
       location: https://zenodo.org/record/3581213/files/matrix.mtx
       filetype: mtx
-    Minimum number of cells expressed: '3'
+    Minimum number of cells expressed: 3
     Input is from Cell Ranger v2 or earlier versions: true
-    Mitochondrial genes start with pattern: MT-
-    Minimum number of genes expressed: '200'
-    Maximum number of genes expressed: '2500'
-    Number of neighbours for computing neighborhood graph: '10'
-    Number of PCs to use for computing neighborhood graph: '10'
-    Louvain resolution: '0.45'
+    Mitochondrial genes start with pattern: 'MT-'
+    Minimum number of genes expressed: 200
+    Maximum number of genes expressed: 2500
+    Number of neighbours for computing neighborhood graph: 10
+    Number of PCs to use for computing neighborhood graph: 10
+    Louvain resolution: 0.45
     Manually annotate celltypes?: true
-    Annotate louvain clusters with these cell types: CD4+ T, CD14+, B, CD8+ T, FCGR3A+,
-      NK, Dendritic, Megakaryocytes
+    Annotate louvain clusters with these cell types: 'CD4+ T, CD14+, B, CD8+ T, FCGR3A+,
+      NK, Dendritic, Megakaryocytes'
   outputs:
     Anndata with Celltype Annotation:
       asserts:
diff --git a/workflows/scRNAseq/scanpy-clustering/Preprocessing-and-Clustering-of-single-cell-RNA-seq-data-with-Scanpy.ga b/workflows/scRNAseq/scanpy-clustering/Preprocessing-and-Clustering-of-single-cell-RNA-seq-data-with-Scanpy.ga
index 758fc6b41..7cc03ba49 100644
--- a/workflows/scRNAseq/scanpy-clustering/Preprocessing-and-Clustering-of-single-cell-RNA-seq-data-with-Scanpy.ga
+++ b/workflows/scRNAseq/scanpy-clustering/Preprocessing-and-Clustering-of-single-cell-RNA-seq-data-with-Scanpy.ga
@@ -1,6 +1,6 @@
 {
     "a_galaxy_workflow": "true",
-    "annotation": "Single-cell RNA-seq workflow with Scanpy and Anndata. Based on the 3k PBMC clustering tutorial from Scanpy.",
+    "annotation": "Single-cell RNA-seq workflow with Scanpy and Anndata. Based on the 3k PBMC clustering tutorial from Scanpy. It takes count matrix, barcodes and feature files as input and creates an Anndata object out of them. It then performs QC and filters for lowly expressed genes and cells. Then the data is normalized and scaled. Then PCs are computed to further cluster using louvain algorithm. It also generated various plots of clustering colored with highly ranked genes.",
     "comments": [],
     "creator": [
         {
@@ -21,7 +21,7 @@
         {
             "class": "Person",
             "identifier": "0000-0001-9852-1987",
-            "name": "B\u00e9r\u00e9nice Batut"
+            "name": "Bérénice Batut"
         }
     ],
     "format-version": "0.1",
diff --git a/workflows/scRNAseq/scanpy-clustering/README.md b/workflows/scRNAseq/scanpy-clustering/README.md
index 9bdab2c0f..78e0fdd74 100644
--- a/workflows/scRNAseq/scanpy-clustering/README.md
+++ b/workflows/scRNAseq/scanpy-clustering/README.md
@@ -1,5 +1,7 @@
 # Preprocessing and Clustering of Single-cell RNA-seq Data with Scanpy
 
+This workflow follows Scanpy legacy workflow [clustering 3k PBMCs](https://scanpy.readthedocs.io/en/stable/tutorials/basics/clustering-2017.html). For more details on concepts and parameters, please refer to the equivalent Galaxy-based [tutorial](https://training.galaxyproject.org/training-material/topics/single-cell/tutorials/scrna-scanpy-pbmc3k/tutorial.html).
+
 ## Inputs
 
 ### Input datasets
@@ -35,4 +37,4 @@
 ## Outputs
 
 - Final output is an Anndata object with annotations of louvain clusters.
-- Some informative plots from QC to the end results
\ No newline at end of file
+- Some informative plots from QC to the end results