sorted files

RECETOX · Oct 27, 2023 · cf3ed09 · cf3ed09
1 parent ac70bfd
commit cf3ed09
Show file tree

Hide file tree

Showing 15 changed files with 251,070 additions and 216,551 deletions.
diff --git a/analysis/R_scripts/match_spectra.R b/analysis/R_scripts/match_spectra.R
@@ -33,31 +33,22 @@ match_spectra <- function(reference_file, simulated_file, output_file, ppm = 5)
   write.table(matched_spectra_df, file = paste(output_file,"filterNA",sep = '_'), sep = "\t", quote = FALSE, row.names = FALSE)
 }
 
-base_path <- 'analysis/data'
+# matching for all peaks
+reference_file_all_peaks <- file.path('analysis/data/experimental/RECETOX_GC-EI_MS_20201028.msp')
+simulated_file_all_peaks <- file.path('analysis/data/filtered/simulated_matchms_filter_1%I_all_peaks.msp')
 
-reference_file <- file.path(base_path, 'experimental/RECETOX_GC-EI_MS_20201028_matchms_filter_top5.msp')
-simulated_file <- file.path(base_path, 'filtered/1%/Galaxy29-[matchms_filtering_on_data_27]_1%_tp5.msp')
 match_spectra(
-  reference_file,
-  simulated_file,
-  file.path(base_path, 'outputs/matchspectra_R/metaboannotation_top5.tsv')
+  reference_file_all_peaks,
+  simulated_file_all_peaks,
+  file.path('analysis/data/output_matching/metaboannotation/metaboannotation_NA_to_zeros_all_peaks.tsv')
 )
 
-# match_spectra(
-#   file.path(base_path, "experimental/RECETOX_GC-EI_MS_20201028_norm_matchms.msp"),
-#   file.path(base_path, 'filtered/matchms_filtering_default_filter_1%_all_peaks.msp'),
-#   file.path(base_path, 'outputs/matchspectra_R/match_1%/metaboannotation_all_peaks_zeros_temp.tsv')
-# )
-
-# reference_file <- file.path(base_path, "experimental/problematic_spectra.msp")
-# simulated_file <- file.path(base_path, 'filtered/problematic_predicted.msp')
-# match_spectra(
-#   reference_file,
-#   query_file,
-#   file.path(base_path, 'outputs/matchspectra_R/problematic_scores.tsv')
-# )
-# match_spectra(
-#   file.path(base_path, "experimental/RECETOX_GC-EI_MS_20201028.msp"),
-#   file.path(base_path, 'filtered/matchms_filtering_default_filter_1%_all_peaks.msp'),
-#   file.path(base_path, 'outputs/matchspectra_R/match_1%/matchSpectra_results_source_1%_all_peaks.tsv')
-# )
+# matching for top5 peaks. query and reference were filtered to top5 peaks.
+reference_file_top5 <- file.path('analysis/data/experimental/RECETOX_GC-EI_MS_20201028_matchms_filter_top5.msp')
+simulated_file_top5 <- file.path('analysis/data/filtered/simulated_matchms_filter_1%I_top5.msp')
+
+match_spectra(
+  reference_file_top5,
+  simulated_file_top5,
+  file.path('analysis/data/output_matching/metaboannotation/metaboannotation_NA_to_zeros_top5.tsv')
+)
diff --git a/...tered/matchms_filtering_1%I_all_peaks.msp → ...imulated_matchms_filter_1%I_all_peaks.msp b/...tered/matchms_filtering_1%I_all_peaks.msp → ...imulated_matchms_filter_1%I_all_peaks.msp
diff --git a/...ta/filtered/matchms_filtering_1%I_tp5.msp → ...red/simulated_matchms_filter_1%I_top5.msp b/...ta/filtered/matchms_filtering_1%I_tp5.msp → ...red/simulated_matchms_filter_1%I_top5.msp
diff --git a/...matter_on_data_61]_tol1%_1%_all_peaks.tsv → ...atchms/matchms_tol_0.01_1%I_all_peaks.tsv b/...matter_on_data_61]_tol1%_1%_all_peaks.tsv → ...atchms/matchms_tol_0.01_1%I_all_peaks.tsv
diff --git a/analysis/data/output_matching/matchms/matchms_tol_0.01_1%I_top5.tsv b/analysis/data/output_matching/matchms/matchms_tol_0.01_1%I_top5.tsv
diff --git a/analysis/data/output_matching/metaboannotation/metaboannotation_NA_to_zeros_all_peaks.tsv b/analysis/data/output_matching/metaboannotation/metaboannotation_NA_to_zeros_all_peaks.tsv
diff --git a/...data/output_matching/metaboannotation/metaboannotation_NA_to_zeros_all_peaks_filterNA.tsv b/...data/output_matching/metaboannotation/metaboannotation_NA_to_zeros_all_peaks_filterNA.tsv
diff --git a/...ra_R/metaboannotation_top5_with_zeros.tsv → ...ion/metaboannotation_NA_to_zeros_top5.tsv b/...ra_R/metaboannotation_top5_with_zeros.tsv → ...ion/metaboannotation_NA_to_zeros_top5.tsv
diff --git a/...ectra_R/metaboannotation_top5_NA_to_0.tsv → ...oannotation_NA_to_zeros_top5_filterNA.tsv b/...ectra_R/metaboannotation_top5_NA_to_0.tsv → ...oannotation_NA_to_zeros_top5_filterNA.tsv
diff --git a/analysis/data/outputs/matchspectra_R/match_1%/matchSpectra_results_source_1%_all_peaks.tsv b/analysis/data/outputs/matchspectra_R/match_1%/matchSpectra_results_source_1%_all_peaks.tsv
diff --git a/...is/data/outputs/matchspectra_R/match_1%/matchSpectra_results_source_1%_all_peaks_norm.tsv b/...is/data/outputs/matchspectra_R/match_1%/matchSpectra_results_source_1%_all_peaks_norm.tsv
diff --git a/analysis/data/outputs/matchspectra_R/match_1%/matchms_top5_comparison_with_zeros.tsv b/analysis/data/outputs/matchspectra_R/match_1%/matchms_top5_comparison_with_zeros.tsv
diff --git a/analysis/data/outputs/matchspectra_R/match_1%/metaboannotation_all_peaks_zeros.tsv b/analysis/data/outputs/matchspectra_R/match_1%/metaboannotation_all_peaks_zeros.tsv
diff --git a/analysis/data/outputs/matchspectra_R/match_1%/metaboannotation_all_peaks_zeros_temp.tsv b/analysis/data/outputs/matchspectra_R/match_1%/metaboannotation_all_peaks_zeros_temp.tsv
diff --git a/codes/ls_lima_formatter.sh b/codes/ls_lima_formatter.sh
@@ -0,0 +1,22 @@
+#!/bin/sh
+
+# Check if the filename argument is provided
+if [ -z "$1" ]; then
+  echo "Usage: $0 <filename>"
+  exit 1
+fi
+
+# Replace multiple spaces with a single space
+sed -E "s,[[:space:]]+, ,g" "$1" > "$1.tmp"
+
+# Remove lines containing 'IONMODE' and 'CHARGE'
+grep -v 'IONMODE\|CHARGE' "$1.tmp" > "$1.tmp1"
+
+# Replace 'COMPOUND_NAME' with 'NAME'
+sed 's/COMPOUND_NAME/NAME/g' "$1.tmp1" > "$1.tmp2"
+
+# Move the final file to the original filename
+mv "$1.tmp2" "$1"
+
+# Remove temporary files
+rm -f "$1.tmp" "$1.tmp1"