Skip to content

fix(starfish110): missing patch #770

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
branfosj merged 2 commits into from
Jan 28, 2026
Merged

fix(starfish110): missing patch #770

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
21b9f86
fix(starfish110): missing patch
Jan 28, 2026
2c75928
fix(starfish110): missing patch
Jan 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
122 changes: 122 additions & 0 deletions ...figs/s/starfish/starfish-1.1.0_added-utility-script-for-concatenating-annotate-outp.patch
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,122 @@
diff --git a/aux/process_annotate_output.sh b/aux/process_annotate_output.sh
new file mode 100644
index 0000000..a339d4e
--- a/dev/null
+++ b/aux/process_annotate_output.sh
@@ -0,0 +1,112 @@
+#!/bin/bash
+
+# Utility script for combining filt and filt_intersect output from starfish annotate
+# across multiple independent runs
+
+# Function to display help menu
+display_help() {
+ echo "Usage: $0 [OPTIONS]"
+ echo ""
+ echo "Utility script for combining filt and filt_intersect output from starfish annotate"
+ echo ""
+ echo "Options:"
+ echo " -i, --input FILE Input TSV file with genome codes in the first field (required)"
+ echo " -a, --analysis PREFIX Path to root analysis directory containing an output directory for each genome (required)"
+ echo " -o, --output PREFIX Path and Prefix for output files (required)"
+ echo " -h, --help Display this help menu"
+ echo ""
+ echo "Example:"
+ echo " $0 -i ome2assembly.txt -a starfish_run1 -o all_annotations"
+}
+
+# Initialize variables
+INPUT_FILE=""
+ANALYSIS_PREFIX=""
+OUTPUT_PREFIX=""
+HELP=false
+
+# Parse command-line arguments
+while [[ $# -gt 0 ]]; do
+ key="$1"
+ case $key in
+ -i|--input)
+ INPUT_FILE="$2"
+ shift 2
+ ;;
+ -a|--analysis)
+ ANALYSIS_PREFIX="$2"
+ shift 2
+ ;;
+ -o|--output)
+ OUTPUT_PREFIX="$2"
+ shift 2
+ ;;
+ -h|--help)
+ HELP=true
+ shift
+ ;;
+ *)
+ echo "Unknown option: $1"
+ display_help
+ exit 1
+ ;;
+ esac
+done
+
+# Display help or validate required arguments
+if [[ "$HELP" = true ]] || [ -z "$INPUT_FILE" ] || [ -z "$ANALYSIS_PREFIX" ] || [ -z "$OUTPUT_PREFIX" ]; then
+ display_help
+ exit 1
+fi
+
+output_gff=${OUTPUT_PREFIX}.gff
+output_ids=${OUTPUT_PREFIX}.ids
+output_fas=${OUTPUT_PREFIX}.fas
+
+# Check if the input file exists
+if [ ! -f "$INPUT_FILE" ]; then
+ echo "Error: Input file $INPUT_FILE does not exist."
+ exit 1
+fi
+
+# Initialize counters
+count_filt_intersect=0
+count_filt=0
+count_none=0
+
+# Clear the output file or create it if it doesn't exist
+> "$output_gff"
+> "$output_ids"
+> "$output_fas"
+
+# Read each genome code from the input file
+while IFS=$'\t' read -r genome_code rest_of_line || [ -n "$genome_code" ]; do
+
+ # Trim any potential whitespace from the genome code
+ genome_code=$(echo "$genome_code" | xargs)
+
+ # Define the directory name based on the genome code
+ dir_name="${ANALYSIS_PREFIX}/$genome_code"
+
+ # Check for 'filt_intersect' file first
+ if [ -f "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt_intersect.ids" ]; then
+ cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt_intersect.ids" >> "$output_ids"
+ cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt_intersect.fas" >> "$output_fas"
+ cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt_intersect.gff" >> "$output_gff"
+ ((count_filt_intersect++))
+ elif [ -f "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt.ids" ]; then
+ # If 'filt_intersect' doesn't exist, use 'filt' file
+ cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt.ids" >> "$output_ids"
+ cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt.fas" >> "$output_fas"
+ cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt.gff" >> "$output_gff"
+ ((count_filt++))
+ else
+ echo "No 'filt_intersect' or 'filt' file found for genome code: $genome_code"
+ ((count_none++))
+ fi
+done < "$INPUT_FILE"
+
+echo "Total genomes with 'filt_intersect' files: $count_filt_intersect"
+echo "Total genomes with 'filt' files: $count_filt"
+echo "Total genomes with no files: $count_none"
+echo "Processing complete"
\ No newline at end of file
--
2.43.7

34 changes: 34 additions & 0 deletions easyconfigs/s/starfish/starfish-1.1.0_bug-fix.patch
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
diff --git a/aux/process_annotate_output.sh b/aux/process_annotate_output.sh
old mode 100644
new mode 100755
index a339d4e..6375eba
--- a/aux/process_annotate_output.sh
+++ b/aux/process_annotate_output.sh
@@ -89,16 +89,16 @@ while IFS=$'\t' read -r genome_code rest_of_line || [ -n "$genome_code" ]; do
dir_name="${ANALYSIS_PREFIX}/$genome_code"

# Check for 'filt_intersect' file first
- if [ -f "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt_intersect.ids" ]; then
- cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt_intersect.ids" >> "$output_ids"
- cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt_intersect.fas" >> "$output_fas"
- cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt_intersect.gff" >> "$output_gff"
+ if ls "${dir_name}/${genome_code}"*".filt_intersect.ids" &> /dev/null; then
+ cat "${dir_name}/${genome_code}"*"filt_intersect.ids" >> "$output_ids"
+ cat "${dir_name}/${genome_code}"*"filt_intersect.fas" >> "$output_fas"
+ cat "${dir_name}/${genome_code}"*"filt_intersect.gff" >> "$output_gff"
((count_filt_intersect++))
- elif [ -f "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt.ids" ]; then
+ elif ls "${dir_name}/${genome_code}"*".filt.ids" &> /dev/null; then
# If 'filt_intersect' doesn't exist, use 'filt' file
- cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt.ids" >> "$output_ids"
- cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt.fas" >> "$output_fas"
- cat "${dir_name}/${genome_code}.${ANALYSIS_PREFIX}.filt.gff" >> "$output_gff"
+ cat "${dir_name}/${genome_code}"*"filt.ids" >> "$output_ids"
+ cat "${dir_name}/${genome_code}"*"filt.fas" >> "$output_fas"
+ cat "${dir_name}/${genome_code}"*"filt.gff" >> "$output_gff"
((count_filt++))
else
echo "No 'filt_intersect' or 'filt' file found for genome code: $genome_code"
--
2.43.7