fix: Remove large dataset error on the rSPR entry (#177)

* RSPR approx and exact scripts * Add functional documentation and update support threshold * Fix rspr argument * Use clustering information from rSPR * Generate cluster heatmap * Revert "Generate cluster heatmap" This reverts commit f00f491. * Revert "Use clustering information from rSPR" This reverts commit ee043b3. * Expect path to the csv containing gene tree paths in rspr approx * refactor: Accept samplesheet as input in rspr_approx --------- Co-authored-by: KARTIK KAKADIYA <20909285+ktkakadiya@users.noreply.github.com> Co-authored-by: ktkakadiya <99840261+ktkakadiya@users.noreply.github.com>
beiko-lab · Nov 22, 2023 · 9a119b4 · 9a119b4
1 parent b22988b
commit 9a119b4
Show file tree

Hide file tree

Showing 5 changed files with 21 additions and 15 deletions.
diff --git a/bin/rspr_approx.py b/bin/rspr_approx.py
@@ -29,7 +29,7 @@ def parse_args(args=None):
     parser = argparse.ArgumentParser(description=Description, epilog=Epilog)
     parser.add_argument("-c", "--core", dest="CORE_TREE", help="Core tree")
     parser.add_argument(
-        "-a", "--acc", dest="GENE_TREES", nargs="+", help="Gene tree list"
+        "-a", "--acc", dest="GENE_TREES", help="Gene tree samplesheet path"
     )
     parser.add_argument(
         "-ann",
@@ -98,15 +98,15 @@ def root_tree(input_path, output_path):
 ### FUNCTION ROOT_TREE
 ### Root all the unrooted input trees in directory
 ### core_tree: path of the core tree
-### gene_trees: input gene tree directory path
+### gene_trees: path of the csv file containing all the gene tree paths
 ### output_dir: output directory path
 ### results: dataframe of the results to store tree size
 ### merge_pair: boolean to check whether to merge coer tree and gene tree in a single file
 ### RETURN path of the rooted gene trees directory
 #####################################################################
 
 
-def root_trees(core_tree, gene_trees, output_dir, results, merge_pair=False):
+def root_trees(core_tree, gene_trees_path, output_dir, results, merge_pair=False):
     print("Rooting trees")
     #'''
     reference_tree = core_tree
@@ -119,8 +119,9 @@ def root_trees(core_tree, gene_trees, output_dir, results, merge_pair=False):
     )
     refer_content, refer_tree_size = root_tree(reference_tree, rooted_reference_tree)
 
+    df_gene_trees = pd.read_csv(gene_trees_path)
     rooted_gene_trees_path = os.path.join(output_dir, "rooted_gene_trees")
-    for filename in gene_trees:
+    for filename in df_gene_trees["path"]:
         basename = Path(filename).name
         rooted_gene_tree_path = os.path.join(rooted_gene_trees_path, basename)
         gene_content, gene_tree_size = root_tree(filename, rooted_gene_tree_path)

diff --git a/modules/local/rspr/approx.nf b/modules/local/rspr/approx.nf
@@ -29,7 +29,7 @@ process RSPR_APPROX {
     """
     rspr_approx.py \\
         --core $core_tree \\
-        --acc \$(cat $gene_tree_list) \\
+        --acc $gene_tree_list \\
         --annotation $annotation \\
         -o approx \\
         --min_rspr_distance $min_rspr_distance \\

diff --git a/subworkflows/local/rspr.nf b/subworkflows/local/rspr.nf
@@ -6,17 +6,11 @@ workflow RSPR {
 
     take:
         core_tree
-        gene_trees
+        gene_tree_sheet
         annotation
 
     main:
 
-        gene_trees
-            .flatten()
-            .map{it -> it.toString() }
-            .collectFile(name: 'gene_tree_paths.txt', newLine: true)
-            .set{ gene_tree_sheet }
-
         RSPR_APPROX (
             core_tree,
             gene_tree_sheet,

diff --git a/subworkflows/local/rspr_input_check.nf b/subworkflows/local/rspr_input_check.nf
@@ -4,8 +4,6 @@ workflow RSPR_INPUT_CHECK {
 
     main:
     samplesheet
-        .splitCsv(header: true)
-        .map { it -> get_sample_info_rspr(it.path) }
         .set { trees }
 
     emit:

diff --git a/workflows/arete.nf b/workflows/arete.nf
@@ -231,9 +231,22 @@ workflow ARETE {
         }
 
         if (params.run_rspr) {
+            PHYLOGENOMICS.out.gene_trees
+                .flatten()
+                .map{it -> it.toString() }
+                .collectFile(newLine: true) { item ->
+                    ["${item}.txt",
+                    "sample,path\n" + item + ',' + item ]
+                }
+                .set { individual_sheets }
+
+            individual_sheets
+                .collectFile(name: 'gene_tree_paths.txt', skip:1 , keepHeader: true)
+                .set{ gene_tree_sheet }
+
             RSPR (
                 PHYLOGENOMICS.out.core_tree,
-                PHYLOGENOMICS.out.gene_trees,
+                gene_tree_sheet,
                 ANNOTATE_ASSEMBLIES.out.annotation
             )
         }