From d21a7207d61fb8ba5601a5ea361f3c4e72bf5f43 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Thu, 12 Jun 2025 18:08:21 -0400
Subject: [PATCH 01/45] Changes for metamorpheus #1

---
 .github/workflows/benchmark.yml    |   4 +-
 benchmark/benchmark_Metamorpheus.R |  76 ++++++++++++++++++++
 benchmark/config.slurm             |   2 +-
 benchmark/metamorpheus_Process.R   |  41 +++++++++++
 benchmark/scriptController.json    |  15 ++++
 metamorpheus_code.R                | 112 +++++++++++++++++++++++++++++
 6 files changed, 247 insertions(+), 3 deletions(-)
 create mode 100644 benchmark/benchmark_Metamorpheus.R
 create mode 100644 benchmark/metamorpheus_Process.R
 create mode 100644 metamorpheus_code.R

diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
index f8d9dcf0..73a9ce73 100644
--- a/.github/workflows/benchmark.yml
+++ b/.github/workflows/benchmark.yml
@@ -3,8 +3,8 @@ name: Run Simple R Script on HPC via Slurm
 on:
   push:
     branches:
-      # - feature/multiple-scripts
-      - devel
+      - feature/metamorpheus-scripts
+      # - devel
 
 jobs:
   Benchmarking-pipeline:
diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
new file mode 100644
index 00000000..356a0b6f
--- /dev/null
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -0,0 +1,76 @@
+library(MSstatsConvert)
+library(MSstats)
+library(tidyverse)
+
+source("metamorpheus_Process.R")
+
+config <- fromJSON("scriptController.json", simplifyVector = FALSE)
+
+dataset_config <- config$datasets[["DDA-Solivais2024-Metamorpheus_NoMBR_LFQ"]]
+dataset_config <- as.list(dataset_config)
+
+cat("Processing Dataset:", dataset_config$name, "\n")
+cat("Dataset File Path:", dataset_config$file, "\n")
+
+filePath = dataset_config$parent + "/" + dataset_config$data
+annotPath = dataset_config$parent + "/"
+
+input = data.table::fread(file.path(filePath, "QuantifiedPeaks.tsv"))
+annot = data.table::fread(file.path(annotPath, "annotation.csv"))
+
+input = input %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
+input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
+
+protein_mappings = data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
+protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
+
+input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
+
+output = MetamorpheusToMSstatsFormat(input, annot)
+
+data_process_tasks <- list(
+  list(
+    label = "Data process with Normalized Data",
+    result = function() dataProcess(msstats_format, featureSubset = "topN", n_top_feature = 20)
+  ),
+  list(
+    label = "Data process with Normalization and MBImpute False",
+    result = function() dataProcess(msstats_format, featureSubset = "topN", n_top_feature = 20, MBimpute = FALSE)
+  ),
+  list(
+    label = "Data process without Normalization",
+    result = function() dataProcess(msstats_format, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20)
+  ),
+  list(
+    label = "Data process without Normalization with MBImpute False",
+    result = function() dataProcess(msstats_format, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20, MBimpute = FALSE)
+  ),
+  list(
+    label = "Data process without Normalization and Imputation On for all features",
+    result = function() dataProcess(msstats_format, featureSubset = "all", normalization = "FALSE", MBimpute = FALSE)
+  ),
+  list(
+    label = "Data process without Normalization and Imputation On for top3 features",
+    result = function() dataProcess(msstats_format, featureSubset = "top3", normalization = "FALSE", MBimpute = FALSE)
+  )
+)
+    
+start_time <- Sys.time()
+
+num_cores <- detectCores() - 1 
+
+summarized_results <- mclapply(data_process_tasks, function(task) {
+  list(label = task$label, summarized = task$result())
+}, mc.cores = num_cores)	
+
+
+results_list <- mclapply(summarized_results, function(res) {
+  calculate_Metrics(res$summarized, protein_mappings, res$label)
+}, mc.cores = num_cores)
+
+
+final_results <- do.call(rbind, results_list)
+end_time <- Sys.time()
+total_time <- end_time - start_time
+print(final_results)
+print(paste("Total Execution Time:", total_time))
\ No newline at end of file
diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 28332e1a..054b7f17 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -27,7 +27,7 @@ remotes::install_github('Vitek-Lab/MSstats', ref = 'devel', lib = Sys.getenv('R_
 remotes::install_github('Vitek-Lab/MSstatsConvert', ref = 'master', lib = Sys.getenv('R_LIBS_USER')); \
 install.packages(c('dplyr', 'stringr', 'ggplot2'), lib = Sys.getenv('R_LIBS_USER'), repos = 'https://cloud.r-project.org')"
 
-R_SCRIPTS=("benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R")
+R_SCRIPTS=("benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R", "benchmark_Metamorpheus.R")
 
 for script in "${R_SCRIPTS[@]}"; do
     echo "Executing script: $script" >> job_output.txt  
diff --git a/benchmark/metamorpheus_Process.R b/benchmark/metamorpheus_Process.R
new file mode 100644
index 00000000..b1efae31
--- /dev/null
+++ b/benchmark/metamorpheus_Process.R
@@ -0,0 +1,41 @@
+calculate_Metrics(QuantData, Label, protein_mappings){
+
+    # dataProcessPlots(QuantData, "QCPlot", which.Protein = "allonly", address = FALSE, isPlotly = TRUE)
+
+    comparison <- matrix(c(-1,0,0,0,1, # 3x
+                        -1,0,0,1,0, # 2.5x
+                        -1,0,1,0,0, # 2x
+                        -1,1,0,0,0),nrow=4,byrow = TRUE) # 1.5x
+                        
+    row.names(comparison) <- c("E-A", "D-A", "C-A", "B-A")
+    groups = levels(QuantData$ProteinLevelData$GROUP)
+    colnames(comparison) <- groups[order(as.numeric(groups))]
+    model <- groupComparison(contrast.matrix=comparison, data=QuantData,
+                                    use_log_file = FALSE)
+                    
+                                    
+                                    
+    ecoli_proteins = protein_mappings %>% filter(Organism == "Escherichia coli (strain K12)")
+    model$ComparisonResult = model$ComparisonResult %>% mutate(ecoli = Protein %in% ecoli_proteins$`Protein Groups`)
+
+
+    e_group = model$ComparisonResult %>% filter(Label == "B-A") %>% filter(is.na(issue))
+
+    ecoli = e_group %>% filter(ecoli == TRUE)
+
+    # hist(ecoli$log2FC)
+
+    ecoli = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == TRUE)
+    human = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == FALSE)
+    FDR = nrow(human) / (nrow(ecoli) + nrow(human))
+
+    cat(label, FDR, "\n")
+
+    results <- data.frame(
+    Label = label,
+    FDR = fdr
+  )
+  
+  return(results)
+
+}
\ No newline at end of file
diff --git a/benchmark/scriptController.json b/benchmark/scriptController.json
index 9b6cbc06..d1a10a78 100644
--- a/benchmark/scriptController.json
+++ b/benchmark/scriptController.json
@@ -31,6 +31,21 @@
           "type": "significant"
         }
       }
+    },
+    "DDA-Solivais2024-Metamorpheus_NoMBR_LFQ": {
+      "name": "DDA-Solivais2024-Metamorpheus_NoMBR_LFQ",
+      "parent": "/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current",
+      "data":"FlashLFQ_NoNormalization_NoPIP",
+      "samples": {
+        "Human": {
+          "pattern": "_HUMAN$",
+          "type": "insignificant"
+        },
+        "Ecoli": {
+          "pattern": "_ECOLI$",
+          "type": "significant"
+        }
+      }
     }
   }
 }
\ No newline at end of file
diff --git a/metamorpheus_code.R b/metamorpheus_code.R
new file mode 100644
index 00000000..fa0c12c1
--- /dev/null
+++ b/metamorpheus_code.R
@@ -0,0 +1,112 @@
+library(MSstatsConvert)
+library(MSstats)
+library(tidyverse)
+
+
+# No MBR
+input_no_mbr = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/QuantifiedPeaks.tsv")
+
+
+
+annot_no_mbr = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/annotation.csv")
+
+
+input_no_mbr = input_no_mbr %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
+input_no_mbr = input_no_mbr %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
+protein_mappings = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/QuantifiedProteins.tsv")
+protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
+input_no_mbr = input_no_mbr %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
+
+
+# input_no_mbr$`Protein Group` = ifelse(
+#   input_no_mbr$`Protein Group` %in% ecoli$`Protein Groups`, 
+#   paste(input_no_mbr$`Protein Group`, "|ECOLI", sep = ""), 
+#   paste(input_no_mbr$`Protein Group`, "|HUMAN", sep = ""))
+# write.csv(input_no_mbr, "QuantifiedPeaks.csv", row.names = FALSE)
+
+
+output_no_mbr = MetamorpheusToMSstatsFormat(input_no_mbr, annot_no_mbr)
+QuantData_no_mbr = dataProcess(output_no_mbr, normalization = FALSE)
+
+dataProcessPlots(QuantData_no_mbr, "QCPlot", which.Protein = "allonly", address = FALSE, isPlotly = TRUE)
+
+comparison <- matrix(c(-1,0,0,0,1, # 3x
+                       -1,0,0,1,0, # 2.5x
+                       -1,0,1,0,0, # 2x
+                       -1,1,0,0,0),nrow=4,byrow = TRUE) # 1.5x
+
+
+row.names(comparison) <- c("E-A", "D-A", "C-A", "B-A")
+groups = levels(QuantData_no_mbr$ProteinLevelData$GROUP)
+colnames(comparison) <- groups[order(as.numeric(groups))]
+model_no_mbr <- groupComparison(contrast.matrix=comparison, data=QuantData_no_mbr,
+                                use_log_file = FALSE)
+
+library(tidyverse)
+ecoli_proteins = protein_mappings %>% filter(Organism == "Escherichia coli (strain K12)")
+model_no_mbr$ComparisonResult = model_no_mbr$ComparisonResult %>% mutate(ecoli = Protein %in% ecoli_proteins$`Protein Groups`)
+
+e_group_no_mbr = model_no_mbr$ComparisonResult %>% filter(Label == "B-A") %>% filter(is.na(issue))
+ecoli_no_mbr = e_group_no_mbr %>% filter(ecoli == TRUE)
+hist(ecoli_no_mbr$log2FC)
+
+ecoli_no_mbr = e_group_no_mbr %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == TRUE)
+human_no_mbr = e_group_no_mbr %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == FALSE)
+FDR_no_mbr = nrow(human_no_mbr) / (nrow(ecoli_no_mbr) + nrow(human_no_mbr))
+
+cat("FDR no MBR", FDR_no_mbr, "\n")
+
+# With MBR
+library(MSstatsConvert)
+library(MSstats)
+library(tidyverse)
+input = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_v1.0_NoNormalization_wPIP/QuantifiedPeaks.tsv")
+annot = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/annotation.csv")
+
+input = input %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
+input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
+
+protein_mappings = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_v1.0_NoNormalization_wPIP/QuantifiedProteins.tsv")
+protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
+input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
+
+# input$`Protein Group` = ifelse(
+#   input$`Protein Group` %in% ecoli$`Protein Groups`,
+#   paste(input$`Protein Group`, "|ECOLI", sep = ""),
+#   paste(input$`Protein Group`, "|HUMAN", sep = ""))
+# write.csv(input, "QuantifiedPeaks-MBR.csv", row.names = FALSE)
+
+
+output = MetamorpheusToMSstatsFormat(input, annot)
+QuantData = dataProcess(output, normalization = FALSE)
+
+dataProcessPlots(QuantData, "QCPlot", which.Protein = "allonly", address = FALSE, isPlotly = TRUE)
+
+comparison <- matrix(c(-1,0,0,0,1, # 3x
+                       -1,0,0,1,0, # 2.5x
+                       -1,0,1,0,0, # 2x
+                       -1,1,0,0,0),nrow=4,byrow = TRUE) # 1.5x
+row.names(comparison) <- c("E-A", "D-A", "C-A", "B-A")
+groups = levels(QuantData$ProteinLevelData$GROUP)
+colnames(comparison) <- groups[order(as.numeric(groups))]
+model <- groupComparison(contrast.matrix=comparison, data=QuantData,
+                         use_log_file = FALSE)
+
+library(tidyverse)
+ecoli_proteins = protein_mappings %>% filter(Organism == "Escherichia coli (strain K12)")
+model$ComparisonResult = model$ComparisonResult %>% mutate(ecoli = Protein %in% ecoli_proteins$`Protein Groups`)
+
+e_group = model$ComparisonResult %>% filter(Label == "B-A") %>% filter(is.na(issue))
+ecoli = e_group %>% filter(ecoli == TRUE)
+hist(ecoli$log2FC)
+
+ecoli = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == TRUE)
+human = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == FALSE)
+FDR = nrow(human) / (nrow(ecoli) + nrow(human))
+
+
+cat("FDR MBR", FDR, "\n")
+# FDR no MBR seems to be lower than that of FDR with MBR (except for E-A label), but it's not by a wide margin.  
+# When normalization was enabled, FDR spiked to 38% without MBR and 58% with MBR.
+# When we set adj.pvalue to 0.01, FDR without MBR does better, but not by much.
+# Less proteins detected as significant with MBR disabled.
\ No newline at end of file

From eaee20e470f0d2208baca05244477d11a0e72022 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Thu, 12 Jun 2025 20:31:54 -0400
Subject: [PATCH 02/45] Added changes for metamorpheus no mbr file

---
 benchmark/benchmark_Metamorpheus.R | 22 +++++++++++++---------
 benchmark/metamorpheus_Process.R   |  4 ++--
 2 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 356a0b6f..41c27e59 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -1,6 +1,7 @@
 library(MSstatsConvert)
 library(MSstats)
 library(tidyverse)
+library(parallel)
 
 source("metamorpheus_Process.R")
 
@@ -10,14 +11,17 @@ dataset_config <- config$datasets[["DDA-Solivais2024-Metamorpheus_NoMBR_LFQ"]]
 dataset_config <- as.list(dataset_config)
 
 cat("Processing Dataset:", dataset_config$name, "\n")
-cat("Dataset File Path:", dataset_config$file, "\n")
 
-filePath = dataset_config$parent + "/" + dataset_config$data
-annotPath = dataset_config$parent + "/"
+filePath <- file.path(dataset_config$parent, dataset_config$data)
+annotPath <- dataset_config$parent
 
 input = data.table::fread(file.path(filePath, "QuantifiedPeaks.tsv"))
 annot = data.table::fread(file.path(annotPath, "annotation.csv"))
 
+
+cat("Dataset File Path:", filePath, "\n")
+cat("Dataset File Path:", annotPath, "\n")
+
 input = input %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
 input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
 
@@ -31,27 +35,27 @@ output = MetamorpheusToMSstatsFormat(input, annot)
 data_process_tasks <- list(
   list(
     label = "Data process with Normalized Data",
-    result = function() dataProcess(msstats_format, featureSubset = "topN", n_top_feature = 20)
+    result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20)
   ),
   list(
     label = "Data process with Normalization and MBImpute False",
-    result = function() dataProcess(msstats_format, featureSubset = "topN", n_top_feature = 20, MBimpute = FALSE)
+    result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20, MBimpute = FALSE)
   ),
   list(
     label = "Data process without Normalization",
-    result = function() dataProcess(msstats_format, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20)
+    result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20)
   ),
   list(
     label = "Data process without Normalization with MBImpute False",
-    result = function() dataProcess(msstats_format, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20, MBimpute = FALSE)
+    result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20, MBimpute = FALSE)
   ),
   list(
     label = "Data process without Normalization and Imputation On for all features",
-    result = function() dataProcess(msstats_format, featureSubset = "all", normalization = "FALSE", MBimpute = FALSE)
+    result = function() dataProcess(output, featureSubset = "all", normalization = "FALSE", MBimpute = FALSE)
   ),
   list(
     label = "Data process without Normalization and Imputation On for top3 features",
-    result = function() dataProcess(msstats_format, featureSubset = "top3", normalization = "FALSE", MBimpute = FALSE)
+    result = function() dataProcess(output, featureSubset = "top3", normalization = "FALSE", MBimpute = FALSE)
   )
 )
     
diff --git a/benchmark/metamorpheus_Process.R b/benchmark/metamorpheus_Process.R
index b1efae31..9954d3eb 100644
--- a/benchmark/metamorpheus_Process.R
+++ b/benchmark/metamorpheus_Process.R
@@ -1,4 +1,4 @@
-calculate_Metrics(QuantData, Label, protein_mappings){
+calculate_Metrics <- function(QuantData, protein_mappings, label){
 
     # dataProcessPlots(QuantData, "QCPlot", which.Protein = "allonly", address = FALSE, isPlotly = TRUE)
 
@@ -33,7 +33,7 @@ calculate_Metrics(QuantData, Label, protein_mappings){
 
     results <- data.frame(
     Label = label,
-    FDR = fdr
+    FDR = FDR
   )
   
   return(results)

From b09fae246ab9748b920f7bbf46a609660281494a Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 13 Jun 2025 15:28:12 -0400
Subject: [PATCH 03/45] Explorer Migration Changes #1

---
 .github/workflows/benchmark.yml | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
index 73a9ce73..c3c1c917 100644
--- a/.github/workflows/benchmark.yml
+++ b/.github/workflows/benchmark.yml
@@ -21,24 +21,24 @@ jobs:
         mkdir -p ~/.ssh
         touch ~/.ssh/id_rsa
         chmod 600 ~/.ssh/id_rsa
-        echo "${{ secrets.SSH_PRIVATE_KEY }}" > ~/.ssh/id_rsa
-        ssh-keyscan -H login-00.discovery.neu.edu >> ~/.ssh/known_hosts || exit 1
+        echo "${{ secrets.SSH_PRIVATE_KEY_EXPLORER }}" > ~/.ssh/id_rsa
+        ssh-keyscan -H login.explorer.northeastern.edu >> ~/.ssh/known_hosts || exit 1
 
     - name: Transfer Files to HPC
       run: |
-        scp -O benchmark/benchmark_Dowell2021-HEqe408_LFQ.R benchmark/benchmark_Puyvelde2022-HYE5600735_LFQ.R benchmark/scriptController.json benchmark/calculateMetrics.R benchmark/config.slurm raina.ans@login-00.discovery.neu.edu:/work/VitekLab/Projects/Benchmarking || exit 1
+        scp -O benchmark/benchmark_Dowell2021-HEqe408_LFQ.R benchmark/benchmark_Puyvelde2022-HYE5600735_LFQ.R benchmark/scriptController.json benchmark/calculateMetrics.R benchmark/config.slurm raina.ans@login.explorer.northeastern.edu:/work/VitekLab/Projects/Benchmarking || exit 1
 
     - name: Submit Slurm Job and Capture Job ID
       id: submit_job
       run: |
-        ssh raina.ans@login-00.discovery.neu.edu "cd /work/VitekLab/Projects/Benchmarking && sbatch config.slurm" | tee slurm_job_id.txt 
+        ssh raina.ans@login.explorer.northeastern.edu "cd /work/VitekLab/Projects/Benchmarking && sbatch config.slurm" | tee slurm_job_id.txt 
         slurm_job_id=$(grep -oP '\d+' slurm_job_id.txt) 
         echo "Slurm Job ID is $slurm_job_id"
         echo "slurm_job_id=$slurm_job_id" >> $GITHUB_ENV  
 
     - name: Monitor Slurm Job
       run: |
-        ssh raina.ans@login-00.discovery.neu.edu "
+        ssh raina.ans@login.explorer.northeastern.edu "
           while squeue -j ${{ env.slurm_job_id }} | grep -q ${{ env.slurm_job_id }}; do
             echo 'Job Id : ${{ env.slurm_job_id }} is still running...'
             sleep 10
@@ -48,8 +48,8 @@ jobs:
 
     - name: Fetch Output
       run: |
-        scp -O raina.ans@login-00.discovery.neu.edu:/work/VitekLab/Projects/Benchmarking/job_output.txt job_output.txt
-        scp -O raina.ans@login-00.discovery.neu.edu:/work/VitekLab/Projects/Benchmarking/job_error.txt job_error.txt
+        scp -O raina.ans@login.explorer.northeastern.edu:/work/VitekLab/Projects/Benchmarking/job_output.txt job_output.txt
+        scp -O raina.ans@login.explorer.northeastern.edu:/work/VitekLab/Projects/Benchmarking/job_error.txt job_error.txt
 
     - name: Upload Output as Artifact
       uses: actions/upload-artifact@v4

From f5927d8a31399fc2189c4c25bc20a03e85d0198d Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 13 Jun 2025 15:35:01 -0400
Subject: [PATCH 04/45] Path correction

---
 .github/workflows/benchmark.yml | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
index c3c1c917..8e4e730a 100644
--- a/.github/workflows/benchmark.yml
+++ b/.github/workflows/benchmark.yml
@@ -26,12 +26,12 @@ jobs:
 
     - name: Transfer Files to HPC
       run: |
-        scp -O benchmark/benchmark_Dowell2021-HEqe408_LFQ.R benchmark/benchmark_Puyvelde2022-HYE5600735_LFQ.R benchmark/scriptController.json benchmark/calculateMetrics.R benchmark/config.slurm raina.ans@login.explorer.northeastern.edu:/work/VitekLab/Projects/Benchmarking || exit 1
+        scp -O benchmark/benchmark_Dowell2021-HEqe408_LFQ.R benchmark/benchmark_Puyvelde2022-HYE5600735_LFQ.R benchmark/scriptController.json benchmark/calculateMetrics.R benchmark/config.slurm raina.ans@login.explorer.northeastern.edu:/projects/VitekLab/Projects/Benchmarking || exit 1
 
     - name: Submit Slurm Job and Capture Job ID
       id: submit_job
       run: |
-        ssh raina.ans@login.explorer.northeastern.edu "cd /work/VitekLab/Projects/Benchmarking && sbatch config.slurm" | tee slurm_job_id.txt 
+        ssh raina.ans@login.explorer.northeastern.edu "cd /projects/VitekLab/Projects/Benchmarking && sbatch config.slurm" | tee slurm_job_id.txt 
         slurm_job_id=$(grep -oP '\d+' slurm_job_id.txt) 
         echo "Slurm Job ID is $slurm_job_id"
         echo "slurm_job_id=$slurm_job_id" >> $GITHUB_ENV  
@@ -48,8 +48,8 @@ jobs:
 
     - name: Fetch Output
       run: |
-        scp -O raina.ans@login.explorer.northeastern.edu:/work/VitekLab/Projects/Benchmarking/job_output.txt job_output.txt
-        scp -O raina.ans@login.explorer.northeastern.edu:/work/VitekLab/Projects/Benchmarking/job_error.txt job_error.txt
+        scp -O raina.ans@login.explorer.northeastern.edu:/projects/VitekLab/Projects/Benchmarking/job_output.txt job_output.txt
+        scp -O raina.ans@login.explorer.northeastern.edu:/projects/VitekLab/Projects/Benchmarking/job_error.txt job_error.txt
 
     - name: Upload Output as Artifact
       uses: actions/upload-artifact@v4

From 8bd37a9d733e7e925f37a5112bdcf0354727bd57 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 13 Jun 2025 16:14:00 -0400
Subject: [PATCH 05/45] Transfer all benchmark files - Correction

---
 .github/workflows/benchmark.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
index 8e4e730a..eb958b1a 100644
--- a/.github/workflows/benchmark.yml
+++ b/.github/workflows/benchmark.yml
@@ -26,7 +26,7 @@ jobs:
 
     - name: Transfer Files to HPC
       run: |
-        scp -O benchmark/benchmark_Dowell2021-HEqe408_LFQ.R benchmark/benchmark_Puyvelde2022-HYE5600735_LFQ.R benchmark/scriptController.json benchmark/calculateMetrics.R benchmark/config.slurm raina.ans@login.explorer.northeastern.edu:/projects/VitekLab/Projects/Benchmarking || exit 1
+        scp -r benchmark raina.ans@login.explorer.northeastern.edu:/projects/VitekLab/Projects/Benchmarking || exit 1
 
     - name: Submit Slurm Job and Capture Job ID
       id: submit_job

From 71f62f46b826ab4ed498c984ee26e65a55a681d7 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 13 Jun 2025 17:46:23 -0400
Subject: [PATCH 06/45] Changes for benchmark folder

---
 .github/workflows/benchmark.yml | 6 +++---
 benchmark/config.slurm          | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
index eb958b1a..47296677 100644
--- a/.github/workflows/benchmark.yml
+++ b/.github/workflows/benchmark.yml
@@ -31,7 +31,7 @@ jobs:
     - name: Submit Slurm Job and Capture Job ID
       id: submit_job
       run: |
-        ssh raina.ans@login.explorer.northeastern.edu "cd /projects/VitekLab/Projects/Benchmarking && sbatch config.slurm" | tee slurm_job_id.txt 
+        ssh raina.ans@login.explorer.northeastern.edu "cd /projects/VitekLab/Projects/Benchmarking/benchmark && sbatch config.slurm" | tee slurm_job_id.txt 
         slurm_job_id=$(grep -oP '\d+' slurm_job_id.txt) 
         echo "Slurm Job ID is $slurm_job_id"
         echo "slurm_job_id=$slurm_job_id" >> $GITHUB_ENV  
@@ -48,8 +48,8 @@ jobs:
 
     - name: Fetch Output
       run: |
-        scp -O raina.ans@login.explorer.northeastern.edu:/projects/VitekLab/Projects/Benchmarking/job_output.txt job_output.txt
-        scp -O raina.ans@login.explorer.northeastern.edu:/projects/VitekLab/Projects/Benchmarking/job_error.txt job_error.txt
+        scp -O raina.ans@login.explorer.northeastern.edu:/projects/VitekLab/Projects/Benchmarking/benchmark/job_output.txt job_output.txt
+        scp -O raina.ans@login.explorer.northeastern.edu:/projects/VitekLab/Projects/Benchmarking/benchmark/job_error.txt job_error.txt
 
     - name: Upload Output as Artifact
       uses: actions/upload-artifact@v4
diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 054b7f17..6f1e7545 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -1,6 +1,6 @@
 #!/bin/bash
 #SBATCH --job-name=msstats_benchmark_job_updated
-#SBATCH --chdir=/work/VitekLab/Projects/Benchmarking/
+#SBATCH --chdir=/work/VitekLab/Projects/Benchmarking/benchmark
 #SBATCH --output=job_output.txt
 #SBATCH --error=job_error.txt
 #SBATCH --open-mode=append

From d2275bd5d5e363c63c3e55edc23a3e489cb13315 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 13 Jun 2025 20:08:46 -0400
Subject: [PATCH 07/45] Changes for path correction in slurm file

---
 benchmark/config.slurm          | 2 +-
 benchmark/scriptController.json | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 6f1e7545..20cf2114 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -1,6 +1,6 @@
 #!/bin/bash
 #SBATCH --job-name=msstats_benchmark_job_updated
-#SBATCH --chdir=/work/VitekLab/Projects/Benchmarking/benchmark
+#SBATCH --chdir=/projects/VitekLab/Projects/Benchmarking/benchmark
 #SBATCH --output=job_output.txt
 #SBATCH --error=job_error.txt
 #SBATCH --open-mode=append
diff --git a/benchmark/scriptController.json b/benchmark/scriptController.json
index d1a10a78..3881cf05 100644
--- a/benchmark/scriptController.json
+++ b/benchmark/scriptController.json
@@ -2,7 +2,7 @@
   "datasets": {
     "DDA-Puyvelde2022-HYE5600735_LFQ": {
       "name": "DDA-Puyvelde2022-HYE5600735_LFQ",
-      "file": "/work/VitekLab/Data/MS/Benchmarking/DDA-Puyvelde2022/DDA-Puyvelde2022-HYE5600735_LFQ/FragPipe/TOP0/MSstats_fixed.csv",
+      "file": "/projects/VitekLab/Data/MS/Benchmarking/DDA-Puyvelde2022/DDA-Puyvelde2022-HYE5600735_LFQ/FragPipe/TOP0/MSstats_fixed.csv",
       "samples": {
         "Human": {
           "pattern": "_HUMAN$",
@@ -20,7 +20,7 @@
     },
     "DDA-Dowell2021-HEqe408_LFQ": {
       "name": "DDA-Dowell2021-HEqe408_LFQ",
-      "file": "/work/VitekLab/Data/MS/Benchmarking/DDA-Dowell2021-HEqe408_LFQ/FragPipe/TOP0/MSstats.csv",
+      "file": "/projects/VitekLab/Data/MS/Benchmarking/DDA-Dowell2021-HEqe408_LFQ/FragPipe/TOP0/MSstats.csv",
       "samples": {
         "Human": {
           "pattern": "_HUMAN$",

From 7300bcc7bd2595e88477ee8bf2d9273f550eeb9d Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Sat, 14 Jun 2025 13:12:09 -0400
Subject: [PATCH 08/45] Removed wrong character in script

---
 benchmark/config.slurm | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 20cf2114..6956f8c4 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -8,8 +8,7 @@
 #SBATCH --ntasks=1              # Number of tasks (one process)
 #SBATCH --cpus-per-task=8      # Use 8 CPU cores for the task
 #SBATCH --mem=256G              # Request 256GB of memory
-#SBATCH --partition=short       # Use the 'short' partition (or change as needed)
-
+#SBATCH --partition=short       
 module load R-geospatial
 
 module load gcc/11.1.0
@@ -27,7 +26,7 @@ remotes::install_github('Vitek-Lab/MSstats', ref = 'devel', lib = Sys.getenv('R_
 remotes::install_github('Vitek-Lab/MSstatsConvert', ref = 'master', lib = Sys.getenv('R_LIBS_USER')); \
 install.packages(c('dplyr', 'stringr', 'ggplot2'), lib = Sys.getenv('R_LIBS_USER'), repos = 'https://cloud.r-project.org')"
 
-R_SCRIPTS=("benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R", "benchmark_Metamorpheus.R")
+R_SCRIPTS=("benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R" "benchmark_Metamorpheus.R")
 
 for script in "${R_SCRIPTS[@]}"; do
     echo "Executing script: $script" >> job_output.txt  

From 79e0a2d7407cc11165013ea2b4eca4c43d0ac219 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Mon, 16 Jun 2025 17:09:06 -0400
Subject: [PATCH 09/45] Changes for gcc added

---
 benchmark/config.slurm | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 6956f8c4..4a4877a0 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -9,13 +9,12 @@
 #SBATCH --cpus-per-task=8      # Use 8 CPU cores for the task
 #SBATCH --mem=256G              # Request 256GB of memory
 #SBATCH --partition=short       
-module load R-geospatial
+module load R
 
-module load gcc/11.1.0
-module load cmake/3.23.2
+module load cmake/3.30.2
 
 export LC_ALL=C
-export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.2-geospatial
+export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4
 
 
 mkdir -p $R_LIBS_USER

From 434c1c0150e69181cdbfb92d96fdb064ca5e623d Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Tue, 17 Jun 2025 10:38:27 -0400
Subject: [PATCH 10/45] Changing back R-LIBS_User env in config

---
 benchmark/config.slurm | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 4a4877a0..fd6b010e 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -14,7 +14,7 @@ module load R
 module load cmake/3.30.2
 
 export LC_ALL=C
-export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4
+export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.2-geospatial
 
 
 mkdir -p $R_LIBS_USER

From 83958b8e1b05e0024a5f123270abae932659c304 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Tue, 17 Jun 2025 14:29:34 -0400
Subject: [PATCH 11/45] changes done to fix env

---
 benchmark/benchmark_Metamorpheus.R | 3 ++-
 benchmark/config.slurm             | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 41c27e59..0d224bcc 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -1,7 +1,8 @@
 library(MSstatsConvert)
 library(MSstats)
-library(tidyverse)
+library(stringr)
 library(parallel)
+library(jsonlite)
 
 source("metamorpheus_Process.R")
 
diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index fd6b010e..4a4877a0 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -14,7 +14,7 @@ module load R
 module load cmake/3.30.2
 
 export LC_ALL=C
-export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.2-geospatial
+export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4
 
 
 mkdir -p $R_LIBS_USER

From bf4938d25dd5e8c2e422c976f8aa0089e7aec3fa Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Tue, 17 Jun 2025 15:00:44 -0400
Subject: [PATCH 12/45] Changes for failing package

---
 benchmark/config.slurm | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 4a4877a0..500aef0d 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -19,8 +19,7 @@ export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4
 
 mkdir -p $R_LIBS_USER
 
-module load R
-Rscript -e "if (!requireNamespace('remotes', quietly = TRUE)) install.packages('remotes', lib = Sys.getenv('R_LIBS_USER'), repos = 'https://cloud.r-project.org'); \
+Rscript -e "if (!requireNamespace('remotes', quietly = TRUE)) install.packages(c('remotes', 'nloptr'), lib = Sys.getenv('R_LIBS_USER'), repos = 'https://cloud.r-project.org'); \
 remotes::install_github('Vitek-Lab/MSstats', ref = 'devel', lib = Sys.getenv('R_LIBS_USER')); \
 remotes::install_github('Vitek-Lab/MSstatsConvert', ref = 'master', lib = Sys.getenv('R_LIBS_USER')); \
 install.packages(c('dplyr', 'stringr', 'ggplot2'), lib = Sys.getenv('R_LIBS_USER'), repos = 'https://cloud.r-project.org')"

From 6b784f1c8cde5034c557b93121622f481bd502e2 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Tue, 17 Jun 2025 15:41:41 -0400
Subject: [PATCH 13/45] Added changes for path

---
 benchmark/config.slurm | 1 +
 1 file changed, 1 insertion(+)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 500aef0d..1a6cee9a 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -14,6 +14,7 @@ module load R
 module load cmake/3.30.2
 
 export LC_ALL=C
+export LD_LIBRARY_PATH=/shared/EL9/explorer/R/4.4.1/lib64/R/lib:$LD_LIBRARY_PATH
 export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4
 
 

From 959d271d3dd6f77a7e4bb9f372340352db6a9e35 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Tue, 17 Jun 2025 16:55:28 -0400
Subject: [PATCH 14/45] Changes added for nolptr

---
 benchmark/config.slurm | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 1a6cee9a..175c4cc5 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -20,10 +20,17 @@ export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4
 
 mkdir -p $R_LIBS_USER
 
-Rscript -e "if (!requireNamespace('remotes', quietly = TRUE)) install.packages(c('remotes', 'nloptr'), lib = Sys.getenv('R_LIBS_USER'), repos = 'https://cloud.r-project.org'); \
-remotes::install_github('Vitek-Lab/MSstats', ref = 'devel', lib = Sys.getenv('R_LIBS_USER')); \
-remotes::install_github('Vitek-Lab/MSstatsConvert', ref = 'master', lib = Sys.getenv('R_LIBS_USER')); \
-install.packages(c('dplyr', 'stringr', 'ggplot2'), lib = Sys.getenv('R_LIBS_USER'), repos = 'https://cloud.r-project.org')"
+Rscript -e "
+if (!requireNamespace('remotes', quietly = TRUE)) install.packages('remotes', lib = Sys.getenv('R_LIBS_USER'), repos = 'https://cloud.r-project.org');
+for (pkg in c('dplyr', 'stringr', 'ggplot2')) {
+  if (!requireNamespace(pkg, quietly = TRUE)) {
+    install.packages(pkg, lib = Sys.getenv('R_LIBS_USER'), repos = 'https://cloud.r-project.org')
+  }
+}
+remotes::install_github('Vitek-Lab/MSstats', ref = 'devel', lib = Sys.getenv('R_LIBS_USER'));
+remotes::install_github('Vitek-Lab/MSstatsConvert', ref = 'master', lib = Sys.getenv('R_LIBS_USER'));
+"
+
 
 R_SCRIPTS=("benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R" "benchmark_Metamorpheus.R")
 

From 138c802f2ffbe693db5809a03fc45904cefa5b48 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Tue, 17 Jun 2025 17:46:15 -0400
Subject: [PATCH 15/45] Changes for Library path

---
 benchmark/config.slurm | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 175c4cc5..dc677982 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -14,8 +14,8 @@ module load R
 module load cmake/3.30.2
 
 export LC_ALL=C
-export LD_LIBRARY_PATH=/shared/EL9/explorer/R/4.4.1/lib64/R/lib:$LD_LIBRARY_PATH
 export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4
+export LD_LIBRARY_PATH=/shared/EL9/explorer/R/4.4.1/lib64/R/lib:/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH
 
 
 mkdir -p $R_LIBS_USER

From 1980ad92658cf53623817a0de88511fcf7c6b6d1 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Tue, 17 Jun 2025 20:00:37 -0400
Subject: [PATCH 16/45] Added changes for POC #1

---
 benchmark/config.slurm | 50 ++++++++++++++++++++++++++----------------
 1 file changed, 31 insertions(+), 19 deletions(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index dc677982..42d6da0e 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -4,40 +4,52 @@
 #SBATCH --output=job_output.txt
 #SBATCH --error=job_error.txt
 #SBATCH --open-mode=append
-#SBATCH --time=01:00:00         # Set the maximum run time
-#SBATCH --ntasks=1              # Number of tasks (one process)
-#SBATCH --cpus-per-task=8      # Use 8 CPU cores for the task
-#SBATCH --mem=256G              # Request 256GB of memory
-#SBATCH --partition=short       
-module load R
+#SBATCH --time=01:00:00
+#SBATCH --ntasks=1
+#SBATCH --cpus-per-task=8
+#SBATCH --mem=256G
+#SBATCH --partition=short
 
+module load R
 module load cmake/3.30.2
 
 export LC_ALL=C
 export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4
-export LD_LIBRARY_PATH=/shared/EL9/explorer/R/4.4.1/lib64/R/lib:/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH
 
+export LD_LIBRARY_PATH=/shared/EL9/explorer/R/4.4.1/lib64/R/lib:/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH
 
 mkdir -p $R_LIBS_USER
 
-Rscript -e "
-if (!requireNamespace('remotes', quietly = TRUE)) install.packages('remotes', lib = Sys.getenv('R_LIBS_USER'), repos = 'https://cloud.r-project.org');
-for (pkg in c('dplyr', 'stringr', 'ggplot2')) {
-  if (!requireNamespace(pkg, quietly = TRUE)) {
-    install.packages(pkg, lib = Sys.getenv('R_LIBS_USER'), repos = 'https://cloud.r-project.org')
-  }
+echo "Running ldd on preprocessCore.so" >> job_output.txt
+ldd $(find ~/R -name preprocessCore.so | head -n 1) >> job_output.txt 2>> job_error.txt
+echo "Running ldd on nloptr.so" >> job_output.txt
+ldd $(find ~/R -name nloptr.so | head -n 1) >> job_output.txt 2>> job_error.txt
+
+Rscript -e '
+.libPaths("/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4")
+Sys.unsetenv("R_LIBS")
+cat("R version: ", R.version$version.string, "\n")
+cat(".libPaths():\n"); print(.libPaths())
+
+if (!requireNamespace("remotes", quietly = TRUE))
+    install.packages("remotes", repos = "https://cloud.r-project.org")
+
+for (pkg in c("dplyr", "stringr", "ggplot2")) {
+    if (!requireNamespace(pkg, quietly = TRUE)) {
+        install.packages(pkg, repos = "https://cloud.r-project.org")
+    }
 }
-remotes::install_github('Vitek-Lab/MSstats', ref = 'devel', lib = Sys.getenv('R_LIBS_USER'));
-remotes::install_github('Vitek-Lab/MSstatsConvert', ref = 'master', lib = Sys.getenv('R_LIBS_USER'));
-"
 
+remotes::install_github("Vitek-Lab/MSstats", ref = "devel")
+remotes::install_github("Vitek-Lab/MSstatsConvert", ref = "master")
+'
 
 R_SCRIPTS=("benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R" "benchmark_Metamorpheus.R")
 
 for script in "${R_SCRIPTS[@]}"; do
-    echo "Executing script: $script" >> job_output.txt  
+    echo "Executing script: $script" >> job_output.txt
     Rscript "$script" >> job_output.txt 2>> job_error.txt
-    wait  
-    echo "Finished executing script: $script" >> job_output.txt  
+    wait
+    echo "Finished executing script: $script" >> job_output.txt
     echo -e "\n\n"
 done
\ No newline at end of file

From 331ba24b3dc72b74ecad75a3d34e7689a88082b6 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Tue, 17 Jun 2025 23:24:38 -0400
Subject: [PATCH 17/45] Added symlink of error package in our directory

---
 benchmark/config.slurm | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 42d6da0e..f66bd5ab 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -16,7 +16,10 @@ module load cmake/3.30.2
 export LC_ALL=C
 export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4
 
-export LD_LIBRARY_PATH=/shared/EL9/explorer/R/4.4.1/lib64/R/lib:/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH
+mkdir -p $HOME/lib_fix
+ln -sf /shared/EL9/explorer/R/4.4.1/lib64/R/lib/libRlapack.so $HOME/lib_fix/libRlapack.so
+
+export LD_LIBRARY_PATH=$HOME/lib_fix:/shared/EL9/explorer/R/4.4.1/lib64/R/lib:/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH
 
 mkdir -p $R_LIBS_USER
 
@@ -28,7 +31,6 @@ ldd $(find ~/R -name nloptr.so | head -n 1) >> job_output.txt 2>> job_error.txt
 Rscript -e '
 .libPaths("/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4")
 Sys.unsetenv("R_LIBS")
-cat("R version: ", R.version$version.string, "\n")
 cat(".libPaths():\n"); print(.libPaths())
 
 if (!requireNamespace("remotes", quietly = TRUE))

From 5c497f47b57a92539eee57f847543766c3573a6f Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Wed, 18 Jun 2025 13:15:49 -0400
Subject: [PATCH 18/45] Changes for slurm

---
 benchmark/config.slurm | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index f66bd5ab..2e7f78d6 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -15,13 +15,12 @@ module load cmake/3.30.2
 
 export LC_ALL=C
 export R_LIBS_USER=/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4
+mkdir -p $R_LIBS_USER
 
 mkdir -p $HOME/lib_fix
-ln -sf /shared/EL9/explorer/R/4.4.1/lib64/R/lib/libRlapack.so $HOME/lib_fix/libRlapack.so
-
-export LD_LIBRARY_PATH=$HOME/lib_fix:/shared/EL9/explorer/R/4.4.1/lib64/R/lib:/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH
+ln -sf /shared/EL9/explorer/R/4.4.1/lib64/R/lib/libRlapack.so $HOME/lib_fix/libRlapack.so.3
 
-mkdir -p $R_LIBS_USER
+export LD_LIBRARY_PATH=$HOME/lib_fix:/shared/EL9/explorer/R/4.4.1/lib64/R/lib:/usr/lib64:$LD_LIBRARY_PATH
 
 echo "Running ldd on preprocessCore.so" >> job_output.txt
 ldd $(find ~/R -name preprocessCore.so | head -n 1) >> job_output.txt 2>> job_error.txt
@@ -36,6 +35,8 @@ cat(".libPaths():\n"); print(.libPaths())
 if (!requireNamespace("remotes", quietly = TRUE))
     install.packages("remotes", repos = "https://cloud.r-project.org")
 
+install.packages("nloptr", type = "source", repos = "https://cloud.r-project.org")
+
 for (pkg in c("dplyr", "stringr", "ggplot2")) {
     if (!requireNamespace(pkg, quietly = TRUE)) {
         install.packages(pkg, repos = "https://cloud.r-project.org")

From d78a1e9b2a2875b233ea44e20d0e2c6575cf8bee Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Wed, 18 Jun 2025 18:20:49 -0400
Subject: [PATCH 19/45] Changes for lesser RAM

---
 benchmark/config.slurm | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 2e7f78d6..9ed27a4c 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -7,7 +7,7 @@
 #SBATCH --time=01:00:00
 #SBATCH --ntasks=1
 #SBATCH --cpus-per-task=8
-#SBATCH --mem=256G
+#SBATCH --mem=128G
 #SBATCH --partition=short
 
 module load R

From 4917efe59e8f2ccc291a59d2aec838b5b2661aa6 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Wed, 18 Jun 2025 18:59:35 -0400
Subject: [PATCH 20/45] Changes for MSStats Convert added

---
 benchmark/config.slurm | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 9ed27a4c..4b071c44 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -42,9 +42,8 @@ for (pkg in c("dplyr", "stringr", "ggplot2")) {
         install.packages(pkg, repos = "https://cloud.r-project.org")
     }
 }
-
+BiocManager::install(c("MSstatsConvert", "preprocessCore"), force = TRUE)
 remotes::install_github("Vitek-Lab/MSstats", ref = "devel")
-remotes::install_github("Vitek-Lab/MSstatsConvert", ref = "master")
 '
 
 R_SCRIPTS=("benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R" "benchmark_Metamorpheus.R")

From 90ca387c43d231e6a21b73990798880910f30187 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Wed, 18 Jun 2025 19:50:25 -0400
Subject: [PATCH 21/45] Changes for MSStats

---
 benchmark/config.slurm | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 4b071c44..8eab27e7 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -43,7 +43,7 @@ for (pkg in c("dplyr", "stringr", "ggplot2")) {
     }
 }
 BiocManager::install(c("MSstatsConvert", "preprocessCore"), force = TRUE)
-remotes::install_github("Vitek-Lab/MSstats", ref = "devel")
+remotes::install_github("Vitek-Lab/MSstats", ref = "devel", force = TRUE)
 '
 
 R_SCRIPTS=("benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R" "benchmark_Metamorpheus.R")

From 09cacfae1b9092e15c3b6d152649ca811bb624aa Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Wed, 18 Jun 2025 21:03:21 -0400
Subject: [PATCH 22/45] Changes for Script with fix

---
 benchmark/config.slurm | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 8eab27e7..fce5d7ef 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -50,7 +50,7 @@ R_SCRIPTS=("benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE56007
 
 for script in "${R_SCRIPTS[@]}"; do
     echo "Executing script: $script" >> job_output.txt
-    Rscript "$script" >> job_output.txt 2>> job_error.txt
+    stdbuf -oL -eL Rscript "$script" >> job_output.txt 2>> job_error.txt
     wait
     echo "Finished executing script: $script" >> job_output.txt
     echo -e "\n\n"

From e0472b9f30a13c55e1a0f999adf929d7ad684e51 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Wed, 18 Jun 2025 21:21:52 -0400
Subject: [PATCH 23/45] Changes to debug output

---
 benchmark/benchmark_Metamorpheus.R | 34 +++++++++++++++++++++++++-----
 benchmark/config.slurm             |  1 -
 2 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 0d224bcc..9d01d53d 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -68,13 +68,37 @@ summarized_results <- mclapply(data_process_tasks, function(task) {
   list(label = task$label, summarized = task$result())
 }, mc.cores = num_cores)	
 
+cat("Summarized Results:\n")
+print(str(summarized_results))
+flush.console()
+
+
+results_list <- lapply(summarized_results, function(res) {
+  cat("Processing result for:", res$label, "\n")
+  flush.console()
+  out <- tryCatch({
+    calculate_Metrics(res$summarized, protein_mappings, res$label)
+  }, error = function(e) {
+    message("Error in calculate_Metrics for ", res$label, ": ", e$message)
+    NULL
+  })
+  print(str(out))
+  flush.console()
+  out
+})
+
+cat("Results List structure:\n")
+print(str(results_list))
+flush.console()
+
+final_results <- tryCatch({
+  do.call(rbind, results_list)
+}, error = function(e) {
+  message("Error during rbind: ", e$message)
+  NULL
+})
 
-results_list <- mclapply(summarized_results, function(res) {
-  calculate_Metrics(res$summarized, protein_mappings, res$label)
-}, mc.cores = num_cores)
 
-
-final_results <- do.call(rbind, results_list)
 end_time <- Sys.time()
 total_time <- end_time - start_time
 print(final_results)
diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index fce5d7ef..92d8ad03 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -3,7 +3,6 @@
 #SBATCH --chdir=/projects/VitekLab/Projects/Benchmarking/benchmark
 #SBATCH --output=job_output.txt
 #SBATCH --error=job_error.txt
-#SBATCH --open-mode=append
 #SBATCH --time=01:00:00
 #SBATCH --ntasks=1
 #SBATCH --cpus-per-task=8

From 2d8e3b3ad4ba3077b107655f3dfee33e053ea91d Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Wed, 18 Jun 2025 21:32:51 -0400
Subject: [PATCH 24/45] Change for Script order

---
 benchmark/config.slurm | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index 92d8ad03..a4f7d4a9 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -45,7 +45,7 @@ BiocManager::install(c("MSstatsConvert", "preprocessCore"), force = TRUE)
 remotes::install_github("Vitek-Lab/MSstats", ref = "devel", force = TRUE)
 '
 
-R_SCRIPTS=("benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R" "benchmark_Metamorpheus.R")
+R_SCRIPTS=("benchmark_Metamorpheus.R" "benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R")
 
 for script in "${R_SCRIPTS[@]}"; do
     echo "Executing script: $script" >> job_output.txt

From 73e6bcc582f7500454b236662761a7c20a874268 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Wed, 18 Jun 2025 22:00:29 -0400
Subject: [PATCH 25/45] Changes to see file print

---
 benchmark/benchmark_Metamorpheus.R | 114 ++++++++++++++++-------------
 benchmark/config.slurm             |   7 +-
 2 files changed, 63 insertions(+), 58 deletions(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 9d01d53d..54005d5a 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -6,89 +6,97 @@ library(jsonlite)
 
 source("metamorpheus_Process.R")
 
-config <- fromJSON("scriptController.json", simplifyVector = FALSE)
+options(echo = TRUE)
 
+config <- fromJSON("scriptController.json", simplifyVector = FALSE)
 dataset_config <- config$datasets[["DDA-Solivais2024-Metamorpheus_NoMBR_LFQ"]]
 dataset_config <- as.list(dataset_config)
 
 cat("Processing Dataset:", dataset_config$name, "\n")
-
 filePath <- file.path(dataset_config$parent, dataset_config$data)
 annotPath <- dataset_config$parent
+cat("File Path:", filePath, "\n")
+cat("Annotation Path:", annotPath, "\n")
+flush.console()
+
+input <- data.table::fread(file.path(filePath, "QuantifiedPeaks.tsv"))
+cat("Input loaded: ", nrow(input), " rows\n")
+flush.console()
 
-input = data.table::fread(file.path(filePath, "QuantifiedPeaks.tsv"))
-annot = data.table::fread(file.path(annotPath, "annotation.csv"))
+annot <- data.table::fread(file.path(annotPath, "annotation.csv"))
+cat("Annotation loaded: ", nrow(annot), " rows\n")
+flush.console()
 
+# Filters
+input <- input %>% filter(!str_detect(`Protein Group`, ";"))
+cat("Post semicolon filter: ", nrow(input), " rows\n")
+input <- input %>% filter(!str_detect(`Protein Group`, "DECOY"))
+cat("Post DECOY filter: ", nrow(input), " rows\n")
+flush.console()
 
-cat("Dataset File Path:", filePath, "\n")
-cat("Dataset File Path:", annotPath, "\n")
+protein_mappings <- data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
+cat("Protein mappings loaded: ", nrow(protein_mappings), " rows\n")
+protein_mappings <- protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
+cat("Post organism filter: ", nrow(protein_mappings), " rows\n")
+flush.console()
 
-input = input %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
-input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
+input <- input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
+cat("Post protein group mapping filter: ", nrow(input), " rows\n")
+flush.console()
 
-protein_mappings = data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
-protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
+output <- tryCatch({
+  MetamorpheusToMSstatsFormat(input, annot)
+}, error = function(e) {
+  message("Error in MetamorpheusToMSstatsFormat: ", e$message)
+  NULL
+})
+cat("MSstats format complete\n")
+flush.console()
 
-input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
+if (is.null(output)) stop("Output is NULL, aborting")
 
-output = MetamorpheusToMSstatsFormat(input, annot)
+# DEBUG: check structure
+cat("Structure of MSstats formatted output:\n")
+print(str(output))
+flush.console()
 
 data_process_tasks <- list(
-  list(
-    label = "Data process with Normalized Data",
-    result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20)
-  ),
-  list(
-    label = "Data process with Normalization and MBImpute False",
-    result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20, MBimpute = FALSE)
-  ),
-  list(
-    label = "Data process without Normalization",
-    result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20)
-  ),
-  list(
-    label = "Data process without Normalization with MBImpute False",
-    result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20, MBimpute = FALSE)
-  ),
-  list(
-    label = "Data process without Normalization and Imputation On for all features",
-    result = function() dataProcess(output, featureSubset = "all", normalization = "FALSE", MBimpute = FALSE)
-  ),
-  list(
-    label = "Data process without Normalization and Imputation On for top3 features",
-    result = function() dataProcess(output, featureSubset = "top3", normalization = "FALSE", MBimpute = FALSE)
-  )
+  list(label = "Normalized", result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20)),
+  list(label = "Norm + MBimpute=FALSE", result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20, MBimpute = FALSE)),
+  list(label = "No Norm", result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20)),
+  list(label = "No Norm + MBimpute=FALSE", result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20, MBimpute = FALSE)),
+  list(label = "No Norm + Impute all", result = function() dataProcess(output, featureSubset = "all", normalization = "FALSE", MBimpute = FALSE)),
+  list(label = "No Norm + Impute top3", result = function() dataProcess(output, featureSubset = "top3", normalization = "FALSE", MBimpute = FALSE))
 )
-    
-start_time <- Sys.time()
 
+start_time <- Sys.time()
 num_cores <- detectCores() - 1 
 
-summarized_results <- mclapply(data_process_tasks, function(task) {
+# Debug: Use lapply instead of mclapply
+summarized_results <- lapply(data_process_tasks, function(task) {
+  cat("Running task:", task$label, "\n")
+  flush.console()
   list(label = task$label, summarized = task$result())
-}, mc.cores = num_cores)	
+})
 
-cat("Summarized Results:\n")
-print(str(summarized_results))
+cat("Completed summarization tasks\n")
 flush.console()
 
-
 results_list <- lapply(summarized_results, function(res) {
   cat("Processing result for:", res$label, "\n")
   flush.console()
-  out <- tryCatch({
-    calculate_Metrics(res$summarized, protein_mappings, res$label)
+  tryCatch({
+    out <- calculate_Metrics(res$summarized, protein_mappings, res$label)
+    print(str(out))
+    flush.console()
+    out
   }, error = function(e) {
     message("Error in calculate_Metrics for ", res$label, ": ", e$message)
     NULL
   })
-  print(str(out))
-  flush.console()
-  out
 })
 
-cat("Results List structure:\n")
-print(str(results_list))
+cat("All metrics calculated\n")
 flush.console()
 
 final_results <- tryCatch({
@@ -98,8 +106,10 @@ final_results <- tryCatch({
   NULL
 })
 
-
 end_time <- Sys.time()
 total_time <- end_time - start_time
+
+cat("Final Results:\n")
 print(final_results)
-print(paste("Total Execution Time:", total_time))
\ No newline at end of file
+print(paste("Total Execution Time:", total_time))
+flush.console()
diff --git a/benchmark/config.slurm b/benchmark/config.slurm
index a4f7d4a9..5b4d610d 100644
--- a/benchmark/config.slurm
+++ b/benchmark/config.slurm
@@ -21,11 +21,6 @@ ln -sf /shared/EL9/explorer/R/4.4.1/lib64/R/lib/libRlapack.so $HOME/lib_fix/libR
 
 export LD_LIBRARY_PATH=$HOME/lib_fix:/shared/EL9/explorer/R/4.4.1/lib64/R/lib:/usr/lib64:$LD_LIBRARY_PATH
 
-echo "Running ldd on preprocessCore.so" >> job_output.txt
-ldd $(find ~/R -name preprocessCore.so | head -n 1) >> job_output.txt 2>> job_error.txt
-echo "Running ldd on nloptr.so" >> job_output.txt
-ldd $(find ~/R -name nloptr.so | head -n 1) >> job_output.txt 2>> job_error.txt
-
 Rscript -e '
 .libPaths("/home/raina.ans/R/x86_64-pc-linux-gnu-library/4.4")
 Sys.unsetenv("R_LIBS")
@@ -45,7 +40,7 @@ BiocManager::install(c("MSstatsConvert", "preprocessCore"), force = TRUE)
 remotes::install_github("Vitek-Lab/MSstats", ref = "devel", force = TRUE)
 '
 
-R_SCRIPTS=("benchmark_Metamorpheus.R" "benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R")
+R_SCRIPTS=("benchmark_Dowell2021-HEqe408_LFQ.R" "benchmark_Puyvelde2022-HYE5600735_LFQ.R" "benchmark_Metamorpheus.R" )
 
 for script in "${R_SCRIPTS[@]}"; do
     echo "Executing script: $script" >> job_output.txt

From 244d42f09622060484120d2ec1c2a86148907089 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Wed, 18 Jun 2025 23:43:34 -0400
Subject: [PATCH 26/45] Corrections added for metamorpheus script file

---
 benchmark/benchmark_Metamorpheus.R | 147 +++++++++++------------------
 1 file changed, 56 insertions(+), 91 deletions(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 54005d5a..41c27e59 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -1,115 +1,80 @@
 library(MSstatsConvert)
 library(MSstats)
-library(stringr)
+library(tidyverse)
 library(parallel)
-library(jsonlite)
 
 source("metamorpheus_Process.R")
 
-options(echo = TRUE)
-
 config <- fromJSON("scriptController.json", simplifyVector = FALSE)
+
 dataset_config <- config$datasets[["DDA-Solivais2024-Metamorpheus_NoMBR_LFQ"]]
 dataset_config <- as.list(dataset_config)
 
 cat("Processing Dataset:", dataset_config$name, "\n")
+
 filePath <- file.path(dataset_config$parent, dataset_config$data)
 annotPath <- dataset_config$parent
-cat("File Path:", filePath, "\n")
-cat("Annotation Path:", annotPath, "\n")
-flush.console()
-
-input <- data.table::fread(file.path(filePath, "QuantifiedPeaks.tsv"))
-cat("Input loaded: ", nrow(input), " rows\n")
-flush.console()
-
-annot <- data.table::fread(file.path(annotPath, "annotation.csv"))
-cat("Annotation loaded: ", nrow(annot), " rows\n")
-flush.console()
-
-# Filters
-input <- input %>% filter(!str_detect(`Protein Group`, ";"))
-cat("Post semicolon filter: ", nrow(input), " rows\n")
-input <- input %>% filter(!str_detect(`Protein Group`, "DECOY"))
-cat("Post DECOY filter: ", nrow(input), " rows\n")
-flush.console()
-
-protein_mappings <- data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
-cat("Protein mappings loaded: ", nrow(protein_mappings), " rows\n")
-protein_mappings <- protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
-cat("Post organism filter: ", nrow(protein_mappings), " rows\n")
-flush.console()
-
-input <- input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
-cat("Post protein group mapping filter: ", nrow(input), " rows\n")
-flush.console()
-
-output <- tryCatch({
-  MetamorpheusToMSstatsFormat(input, annot)
-}, error = function(e) {
-  message("Error in MetamorpheusToMSstatsFormat: ", e$message)
-  NULL
-})
-cat("MSstats format complete\n")
-flush.console()
-
-if (is.null(output)) stop("Output is NULL, aborting")
-
-# DEBUG: check structure
-cat("Structure of MSstats formatted output:\n")
-print(str(output))
-flush.console()
+
+input = data.table::fread(file.path(filePath, "QuantifiedPeaks.tsv"))
+annot = data.table::fread(file.path(annotPath, "annotation.csv"))
+
+
+cat("Dataset File Path:", filePath, "\n")
+cat("Dataset File Path:", annotPath, "\n")
+
+input = input %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
+input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
+
+protein_mappings = data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
+protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
+
+input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
+
+output = MetamorpheusToMSstatsFormat(input, annot)
 
 data_process_tasks <- list(
-  list(label = "Normalized", result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20)),
-  list(label = "Norm + MBimpute=FALSE", result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20, MBimpute = FALSE)),
-  list(label = "No Norm", result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20)),
-  list(label = "No Norm + MBimpute=FALSE", result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20, MBimpute = FALSE)),
-  list(label = "No Norm + Impute all", result = function() dataProcess(output, featureSubset = "all", normalization = "FALSE", MBimpute = FALSE)),
-  list(label = "No Norm + Impute top3", result = function() dataProcess(output, featureSubset = "top3", normalization = "FALSE", MBimpute = FALSE))
+  list(
+    label = "Data process with Normalized Data",
+    result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20)
+  ),
+  list(
+    label = "Data process with Normalization and MBImpute False",
+    result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20, MBimpute = FALSE)
+  ),
+  list(
+    label = "Data process without Normalization",
+    result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20)
+  ),
+  list(
+    label = "Data process without Normalization with MBImpute False",
+    result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20, MBimpute = FALSE)
+  ),
+  list(
+    label = "Data process without Normalization and Imputation On for all features",
+    result = function() dataProcess(output, featureSubset = "all", normalization = "FALSE", MBimpute = FALSE)
+  ),
+  list(
+    label = "Data process without Normalization and Imputation On for top3 features",
+    result = function() dataProcess(output, featureSubset = "top3", normalization = "FALSE", MBimpute = FALSE)
+  )
 )
-
+    
 start_time <- Sys.time()
+
 num_cores <- detectCores() - 1 
 
-# Debug: Use lapply instead of mclapply
-summarized_results <- lapply(data_process_tasks, function(task) {
-  cat("Running task:", task$label, "\n")
-  flush.console()
+summarized_results <- mclapply(data_process_tasks, function(task) {
   list(label = task$label, summarized = task$result())
-})
-
-cat("Completed summarization tasks\n")
-flush.console()
-
-results_list <- lapply(summarized_results, function(res) {
-  cat("Processing result for:", res$label, "\n")
-  flush.console()
-  tryCatch({
-    out <- calculate_Metrics(res$summarized, protein_mappings, res$label)
-    print(str(out))
-    flush.console()
-    out
-  }, error = function(e) {
-    message("Error in calculate_Metrics for ", res$label, ": ", e$message)
-    NULL
-  })
-})
-
-cat("All metrics calculated\n")
-flush.console()
-
-final_results <- tryCatch({
-  do.call(rbind, results_list)
-}, error = function(e) {
-  message("Error during rbind: ", e$message)
-  NULL
-})
+}, mc.cores = num_cores)	
 
+
+results_list <- mclapply(summarized_results, function(res) {
+  calculate_Metrics(res$summarized, protein_mappings, res$label)
+}, mc.cores = num_cores)
+
+
+final_results <- do.call(rbind, results_list)
 end_time <- Sys.time()
 total_time <- end_time - start_time
-
-cat("Final Results:\n")
 print(final_results)
-print(paste("Total Execution Time:", total_time))
-flush.console()
+print(paste("Total Execution Time:", total_time))
\ No newline at end of file

From 462925f9d136129d2d8bfb667fbfc077b5bfdf8a Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Thu, 19 Jun 2025 00:43:21 -0400
Subject: [PATCH 27/45] Rerun metamorpheus benchmark

---
 benchmark/benchmark_Metamorpheus.R | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 41c27e59..da5ceb5b 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -1,7 +1,8 @@
 library(MSstatsConvert)
 library(MSstats)
-library(tidyverse)
 library(parallel)
+library(stringr)
+library(jsonlite)
 
 source("metamorpheus_Process.R")
 

From 1b962cf23b3b4c6c17b1a55826a4423312961df1 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Thu, 19 Jun 2025 00:58:29 -0400
Subject: [PATCH 28/45] Changes for library

---
 benchmark/benchmark_Metamorpheus.R | 1 +
 1 file changed, 1 insertion(+)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index da5ceb5b..e57b3b7d 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -3,6 +3,7 @@ library(MSstats)
 library(parallel)
 library(stringr)
 library(jsonlite)
+library(dplyr)
 
 source("metamorpheus_Process.R")
 

From f0ec62156bc92ed64371fa54774567ebeb7e2eab Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Thu, 19 Jun 2025 14:51:39 -0400
Subject: [PATCH 29/45] Changes for MBR

---
 benchmark/benchmark_Metamorpheus.R | 138 +++++++++++++++--------------
 benchmark/scriptController.json    |  15 ++++
 2 files changed, 88 insertions(+), 65 deletions(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index e57b3b7d..33bb366d 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -6,77 +6,85 @@ library(jsonlite)
 library(dplyr)
 
 source("metamorpheus_Process.R")
-
 config <- fromJSON("scriptController.json", simplifyVector = FALSE)
 
-dataset_config <- config$datasets[["DDA-Solivais2024-Metamorpheus_NoMBR_LFQ"]]
-dataset_config <- as.list(dataset_config)
-
-cat("Processing Dataset:", dataset_config$name, "\n")
-
-filePath <- file.path(dataset_config$parent, dataset_config$data)
-annotPath <- dataset_config$parent
-
-input = data.table::fread(file.path(filePath, "QuantifiedPeaks.tsv"))
-annot = data.table::fread(file.path(annotPath, "annotation.csv"))
-
-
-cat("Dataset File Path:", filePath, "\n")
-cat("Dataset File Path:", annotPath, "\n")
-
-input = input %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
-input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
-
-protein_mappings = data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
-protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
-
-input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
-
-output = MetamorpheusToMSstatsFormat(input, annot)
-
-data_process_tasks <- list(
-  list(
-    label = "Data process with Normalized Data",
-    result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20)
-  ),
-  list(
-    label = "Data process with Normalization and MBImpute False",
-    result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20, MBimpute = FALSE)
-  ),
-  list(
-    label = "Data process without Normalization",
-    result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20)
-  ),
-  list(
-    label = "Data process without Normalization with MBImpute False",
-    result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20, MBimpute = FALSE)
-  ),
-  list(
-    label = "Data process without Normalization and Imputation On for all features",
-    result = function() dataProcess(output, featureSubset = "all", normalization = "FALSE", MBimpute = FALSE)
-  ),
-  list(
-    label = "Data process without Normalization and Imputation On for top3 features",
-    result = function() dataProcess(output, featureSubset = "top3", normalization = "FALSE", MBimpute = FALSE)
+runBenchmarkForMetaMorpheusData <- function(datasetPath, config) {
+
+  dataset_config <- config$datasets[[datasetPath]]
+  dataset_config <- as.list(dataset_config)
+
+  cat("Processing Dataset:", dataset_config$name, "\n")
+
+  filePath <- file.path(dataset_config$parent, dataset_config$data)
+  annotPath <- dataset_config$parent
+
+  input = data.table::fread(file.path(filePath, "QuantifiedPeaks.tsv"))
+  annot = data.table::fread(file.path(annotPath, "annotation.csv"))
+
+
+  cat("Dataset File Path:", filePath, "\n")
+  cat("Annotation File Path:", annotPath, "\n")
+
+  input = input %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
+  input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
+
+  protein_mappings = data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
+  protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
+
+  input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
+
+  output = MetamorpheusToMSstatsFormat(input, annot)
+
+  data_process_tasks <- list(
+    list(
+      label = "Data process with Normalized Data",
+      result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20)
+    ),
+    list(
+      label = "Data process with Normalization and MBImpute False",
+      result = function() dataProcess(output, featureSubset = "topN", n_top_feature = 20, MBimpute = FALSE)
+    ),
+    list(
+      label = "Data process without Normalization",
+      result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20)
+    ),
+    list(
+      label = "Data process without Normalization with MBImpute False",
+      result = function() dataProcess(output, featureSubset = "topN", normalization = "FALSE", n_top_feature = 20, MBimpute = FALSE)
+    ),
+    list(
+      label = "Data process without Normalization and Imputation On for all features",
+      result = function() dataProcess(output, featureSubset = "all", normalization = "FALSE", MBimpute = FALSE)
+    ),
+    list(
+      label = "Data process without Normalization and Imputation On for top3 features",
+      result = function() dataProcess(output, featureSubset = "top3", normalization = "FALSE", MBimpute = FALSE)
+    )
   )
-)
-    
-start_time <- Sys.time()
+      
+  start_time <- Sys.time()
+
+  num_cores <- detectCores() - 1 
+
+  summarized_results <- mclapply(data_process_tasks, function(task) {
+    list(label = task$label, summarized = task$result())
+  }, mc.cores = num_cores)	
+
+
+  results_list <- mclapply(summarized_results, function(res) {
+    calculate_Metrics(res$summarized, protein_mappings, res$label)
+  }, mc.cores = num_cores)
 
-num_cores <- detectCores() - 1 
 
-summarized_results <- mclapply(data_process_tasks, function(task) {
-  list(label = task$label, summarized = task$result())
-}, mc.cores = num_cores)	
+  final_results <- do.call(rbind, results_list)
+  end_time <- Sys.time()
+  total_time <- end_time - start_time
+  print(final_results)
+  print(paste("Total Execution Time:", total_time))
 
+}
 
-results_list <- mclapply(summarized_results, function(res) {
-  calculate_Metrics(res$summarized, protein_mappings, res$label)
-}, mc.cores = num_cores)
 
 
-final_results <- do.call(rbind, results_list)
-end_time <- Sys.time()
-total_time <- end_time - start_time
-print(final_results)
-print(paste("Total Execution Time:", total_time))
\ No newline at end of file
+runBenchmarkForMetaMorpheusData("DDA-Solivais2024-Metamorpheus_MBR_LFQ", config)
+runBenchmarkForMetaMorpheusData("DDA-Solivais2024-Metamorpheus_NoMBR_LFQ", config)
\ No newline at end of file
diff --git a/benchmark/scriptController.json b/benchmark/scriptController.json
index 3881cf05..449c667a 100644
--- a/benchmark/scriptController.json
+++ b/benchmark/scriptController.json
@@ -46,6 +46,21 @@
           "type": "significant"
         }
       }
+    },
+    "DDA-Solivais2024-Metamorpheus_MBR_LFQ": {
+      "name": "DDA-Solivais2024-Metamorpheus_MBR_LFQ",
+      "parent": "/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current",
+      "data":"FlashLFQ_v1.0_NoNormalization_wPIP",
+      "samples": {
+        "Human": {
+          "pattern": "_HUMAN$",
+          "type": "insignificant"
+        },
+        "Ecoli": {
+          "pattern": "_ECOLI$",
+          "type": "significant"
+        }
+      }
     }
   }
 }
\ No newline at end of file

From ec9fe42548eeae08f00dafbcd2cf44664d58e4cf Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 13:15:14 -0400
Subject: [PATCH 30/45] Changes for calculate metrics

---
 benchmark/metamorpheus_Process.R | 84 +++++++++++++++++---------------
 1 file changed, 45 insertions(+), 39 deletions(-)

diff --git a/benchmark/metamorpheus_Process.R b/benchmark/metamorpheus_Process.R
index 9954d3eb..cd6c4fba 100644
--- a/benchmark/metamorpheus_Process.R
+++ b/benchmark/metamorpheus_Process.R
@@ -1,41 +1,47 @@
-calculate_Metrics <- function(QuantData, protein_mappings, label){
-
-    # dataProcessPlots(QuantData, "QCPlot", which.Protein = "allonly", address = FALSE, isPlotly = TRUE)
-
-    comparison <- matrix(c(-1,0,0,0,1, # 3x
-                        -1,0,0,1,0, # 2.5x
-                        -1,0,1,0,0, # 2x
-                        -1,1,0,0,0),nrow=4,byrow = TRUE) # 1.5x
-                        
-    row.names(comparison) <- c("E-A", "D-A", "C-A", "B-A")
-    groups = levels(QuantData$ProteinLevelData$GROUP)
-    colnames(comparison) <- groups[order(as.numeric(groups))]
-    model <- groupComparison(contrast.matrix=comparison, data=QuantData,
-                                    use_log_file = FALSE)
-                    
-                                    
-                                    
-    ecoli_proteins = protein_mappings %>% filter(Organism == "Escherichia coli (strain K12)")
-    model$ComparisonResult = model$ComparisonResult %>% mutate(ecoli = Protein %in% ecoli_proteins$`Protein Groups`)
-
-
-    e_group = model$ComparisonResult %>% filter(Label == "B-A") %>% filter(is.na(issue))
-
-    ecoli = e_group %>% filter(ecoli == TRUE)
-
-    # hist(ecoli$log2FC)
-
-    ecoli = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == TRUE)
-    human = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == FALSE)
-    FDR = nrow(human) / (nrow(ecoli) + nrow(human))
-
-    cat(label, FDR, "\n")
-
-    results <- data.frame(
-    Label = label,
-    FDR = FDR
+calculate_Metrics <- function(QuantData, protein_mappings, task_label, alpha = 0.05) {
+  comparison <- matrix(
+    c(-1,0,0,0,1,   # E-A
+      -1,0,0,1,0,   # D-A
+      -1,0,1,0,0,   # C-A
+      -1,1,0,0,0),  # B-A
+    nrow = 4, byrow = TRUE
+  )
+  rownames(comparison) <- c("E-A", "D-A", "C-A", "B-A")
+  groups <- levels(QuantData$ProteinLevelData$GROUP)
+  colnames(comparison) <- groups[order(as.numeric(groups))]
+
+  model <- groupComparison(
+    contrast.matrix = comparison,
+    data = QuantData,
+    use_log_file = FALSE
   )
-  
-  return(results)
 
-}
\ No newline at end of file
+  ecoli_ids <- protein_mappings %>%
+    filter(Organism == "Escherichia coli (strain K12)") %>%
+    pull(`Protein Groups`)
+
+  comp <- model$ComparisonResult %>%
+    mutate(ecoli = Protein %in% ecoli_ids) %>%
+    filter(is.na(issue))
+
+  labels <- unique(comp$Label)
+  result_rows <- lapply(labels, function(lbl) {
+    df <- comp %>% filter(Label == lbl)
+    sig <- df %>% filter(adj.pvalue < alpha)
+
+    tp <- sig %>% filter(ecoli) %>% nrow()
+    fp <- sig %>% filter(!ecoli) %>% nrow()
+    tot <- tp + fp
+    fdr <- if (tot > 0) fp / tot else NA_real_
+
+    data.frame(
+      Task       = task_label,
+      Comparison = lbl,
+      FDR        = fdr,
+      stringsAsFactors = FALSE
+    )
+  })
+
+  results <- do.call(rbind, result_rows)
+  return(results)
+}

From c7e7b60728d6d638cd9e0d338184dad7c6ac076d Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 14:07:53 -0400
Subject: [PATCH 31/45] All PR comments resolved

---
 benchmark/benchmark_Metamorpheus.R |   4 +-
 benchmark/metamorpheus_Process.R   |   6 +-
 metamorpheus_code.R                | 112 -----------------------------
 3 files changed, 6 insertions(+), 116 deletions(-)
 delete mode 100644 metamorpheus_code.R

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 33bb366d..4003d207 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -29,7 +29,9 @@ runBenchmarkForMetaMorpheusData <- function(datasetPath, config) {
   input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
 
   protein_mappings = data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
-  protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
+  valid_organisms <- unique(input$Organism)
+
+  protein_mappings = protein_mappings %>% filter(Organism %in% valid_organisms)
 
   input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
 
diff --git a/benchmark/metamorpheus_Process.R b/benchmark/metamorpheus_Process.R
index cd6c4fba..dcf7fce1 100644
--- a/benchmark/metamorpheus_Process.R
+++ b/benchmark/metamorpheus_Process.R
@@ -20,13 +20,13 @@ calculate_Metrics <- function(QuantData, protein_mappings, task_label, alpha = 0
     filter(Organism == "Escherichia coli (strain K12)") %>%
     pull(`Protein Groups`)
 
-  comp <- model$ComparisonResult %>%
+  filtered_results <- model$ComparisonResult %>%
     mutate(ecoli = Protein %in% ecoli_ids) %>%
     filter(is.na(issue))
 
-  labels <- unique(comp$Label)
+  labels <- unique(filtered_results$Label)
   result_rows <- lapply(labels, function(lbl) {
-    df <- comp %>% filter(Label == lbl)
+    df <- filtered_results %>% filter(Label == lbl)
     sig <- df %>% filter(adj.pvalue < alpha)
 
     tp <- sig %>% filter(ecoli) %>% nrow()
diff --git a/metamorpheus_code.R b/metamorpheus_code.R
deleted file mode 100644
index fa0c12c1..00000000
--- a/metamorpheus_code.R
+++ /dev/null
@@ -1,112 +0,0 @@
-library(MSstatsConvert)
-library(MSstats)
-library(tidyverse)
-
-
-# No MBR
-input_no_mbr = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/QuantifiedPeaks.tsv")
-
-
-
-annot_no_mbr = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/annotation.csv")
-
-
-input_no_mbr = input_no_mbr %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
-input_no_mbr = input_no_mbr %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
-protein_mappings = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/QuantifiedProteins.tsv")
-protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
-input_no_mbr = input_no_mbr %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
-
-
-# input_no_mbr$`Protein Group` = ifelse(
-#   input_no_mbr$`Protein Group` %in% ecoli$`Protein Groups`, 
-#   paste(input_no_mbr$`Protein Group`, "|ECOLI", sep = ""), 
-#   paste(input_no_mbr$`Protein Group`, "|HUMAN", sep = ""))
-# write.csv(input_no_mbr, "QuantifiedPeaks.csv", row.names = FALSE)
-
-
-output_no_mbr = MetamorpheusToMSstatsFormat(input_no_mbr, annot_no_mbr)
-QuantData_no_mbr = dataProcess(output_no_mbr, normalization = FALSE)
-
-dataProcessPlots(QuantData_no_mbr, "QCPlot", which.Protein = "allonly", address = FALSE, isPlotly = TRUE)
-
-comparison <- matrix(c(-1,0,0,0,1, # 3x
-                       -1,0,0,1,0, # 2.5x
-                       -1,0,1,0,0, # 2x
-                       -1,1,0,0,0),nrow=4,byrow = TRUE) # 1.5x
-
-
-row.names(comparison) <- c("E-A", "D-A", "C-A", "B-A")
-groups = levels(QuantData_no_mbr$ProteinLevelData$GROUP)
-colnames(comparison) <- groups[order(as.numeric(groups))]
-model_no_mbr <- groupComparison(contrast.matrix=comparison, data=QuantData_no_mbr,
-                                use_log_file = FALSE)
-
-library(tidyverse)
-ecoli_proteins = protein_mappings %>% filter(Organism == "Escherichia coli (strain K12)")
-model_no_mbr$ComparisonResult = model_no_mbr$ComparisonResult %>% mutate(ecoli = Protein %in% ecoli_proteins$`Protein Groups`)
-
-e_group_no_mbr = model_no_mbr$ComparisonResult %>% filter(Label == "B-A") %>% filter(is.na(issue))
-ecoli_no_mbr = e_group_no_mbr %>% filter(ecoli == TRUE)
-hist(ecoli_no_mbr$log2FC)
-
-ecoli_no_mbr = e_group_no_mbr %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == TRUE)
-human_no_mbr = e_group_no_mbr %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == FALSE)
-FDR_no_mbr = nrow(human_no_mbr) / (nrow(ecoli_no_mbr) + nrow(human_no_mbr))
-
-cat("FDR no MBR", FDR_no_mbr, "\n")
-
-# With MBR
-library(MSstatsConvert)
-library(MSstats)
-library(tidyverse)
-input = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_v1.0_NoNormalization_wPIP/QuantifiedPeaks.tsv")
-annot = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/annotation.csv")
-
-input = input %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
-input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
-
-protein_mappings = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_v1.0_NoNormalization_wPIP/QuantifiedProteins.tsv")
-protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
-input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
-
-# input$`Protein Group` = ifelse(
-#   input$`Protein Group` %in% ecoli$`Protein Groups`,
-#   paste(input$`Protein Group`, "|ECOLI", sep = ""),
-#   paste(input$`Protein Group`, "|HUMAN", sep = ""))
-# write.csv(input, "QuantifiedPeaks-MBR.csv", row.names = FALSE)
-
-
-output = MetamorpheusToMSstatsFormat(input, annot)
-QuantData = dataProcess(output, normalization = FALSE)
-
-dataProcessPlots(QuantData, "QCPlot", which.Protein = "allonly", address = FALSE, isPlotly = TRUE)
-
-comparison <- matrix(c(-1,0,0,0,1, # 3x
-                       -1,0,0,1,0, # 2.5x
-                       -1,0,1,0,0, # 2x
-                       -1,1,0,0,0),nrow=4,byrow = TRUE) # 1.5x
-row.names(comparison) <- c("E-A", "D-A", "C-A", "B-A")
-groups = levels(QuantData$ProteinLevelData$GROUP)
-colnames(comparison) <- groups[order(as.numeric(groups))]
-model <- groupComparison(contrast.matrix=comparison, data=QuantData,
-                         use_log_file = FALSE)
-
-library(tidyverse)
-ecoli_proteins = protein_mappings %>% filter(Organism == "Escherichia coli (strain K12)")
-model$ComparisonResult = model$ComparisonResult %>% mutate(ecoli = Protein %in% ecoli_proteins$`Protein Groups`)
-
-e_group = model$ComparisonResult %>% filter(Label == "B-A") %>% filter(is.na(issue))
-ecoli = e_group %>% filter(ecoli == TRUE)
-hist(ecoli$log2FC)
-
-ecoli = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == TRUE)
-human = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == FALSE)
-FDR = nrow(human) / (nrow(ecoli) + nrow(human))
-
-
-cat("FDR MBR", FDR, "\n")
-# FDR no MBR seems to be lower than that of FDR with MBR (except for E-A label), but it's not by a wide margin.  
-# When normalization was enabled, FDR spiked to 38% without MBR and 58% with MBR.
-# When we set adj.pvalue to 0.01, FDR without MBR does better, but not by much.
-# Less proteins detected as significant with MBR disabled.
\ No newline at end of file

From d8bcb034d7d4e96fbd8825fd17ee5a16973003e2 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 14:41:24 -0400
Subject: [PATCH 32/45] Fix Bug : Unique comparisons not visible

---
 benchmark/metamorpheus_Process.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/benchmark/metamorpheus_Process.R b/benchmark/metamorpheus_Process.R
index dcf7fce1..e167dbe2 100644
--- a/benchmark/metamorpheus_Process.R
+++ b/benchmark/metamorpheus_Process.R
@@ -24,7 +24,7 @@ calculate_Metrics <- function(QuantData, protein_mappings, task_label, alpha = 0
     mutate(ecoli = Protein %in% ecoli_ids) %>%
     filter(is.na(issue))
 
-  labels <- unique(filtered_results$Label)
+  labels <- rownames(comparison)
   result_rows <- lapply(labels, function(lbl) {
     df <- filtered_results %>% filter(Label == lbl)
     sig <- df %>% filter(adj.pvalue < alpha)

From ba65d2d8e5c32c743d0083078a5672a9c1abed0c Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 15:18:44 -0400
Subject: [PATCH 33/45] Changes reverted

---
 benchmark/benchmark_Metamorpheus.R |   4 +-
 benchmark/metamorpheus_Process.R   |   6 +-
 metamorpheus_code.R                | 112 +++++++++++++++++++++++++++++
 3 files changed, 116 insertions(+), 6 deletions(-)
 create mode 100644 metamorpheus_code.R

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 4003d207..33bb366d 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -29,9 +29,7 @@ runBenchmarkForMetaMorpheusData <- function(datasetPath, config) {
   input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
 
   protein_mappings = data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
-  valid_organisms <- unique(input$Organism)
-
-  protein_mappings = protein_mappings %>% filter(Organism %in% valid_organisms)
+  protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
 
   input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
 
diff --git a/benchmark/metamorpheus_Process.R b/benchmark/metamorpheus_Process.R
index e167dbe2..cd6c4fba 100644
--- a/benchmark/metamorpheus_Process.R
+++ b/benchmark/metamorpheus_Process.R
@@ -20,13 +20,13 @@ calculate_Metrics <- function(QuantData, protein_mappings, task_label, alpha = 0
     filter(Organism == "Escherichia coli (strain K12)") %>%
     pull(`Protein Groups`)
 
-  filtered_results <- model$ComparisonResult %>%
+  comp <- model$ComparisonResult %>%
     mutate(ecoli = Protein %in% ecoli_ids) %>%
     filter(is.na(issue))
 
-  labels <- rownames(comparison)
+  labels <- unique(comp$Label)
   result_rows <- lapply(labels, function(lbl) {
-    df <- filtered_results %>% filter(Label == lbl)
+    df <- comp %>% filter(Label == lbl)
     sig <- df %>% filter(adj.pvalue < alpha)
 
     tp <- sig %>% filter(ecoli) %>% nrow()
diff --git a/metamorpheus_code.R b/metamorpheus_code.R
new file mode 100644
index 00000000..fa0c12c1
--- /dev/null
+++ b/metamorpheus_code.R
@@ -0,0 +1,112 @@
+library(MSstatsConvert)
+library(MSstats)
+library(tidyverse)
+
+
+# No MBR
+input_no_mbr = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/QuantifiedPeaks.tsv")
+
+
+
+annot_no_mbr = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/annotation.csv")
+
+
+input_no_mbr = input_no_mbr %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
+input_no_mbr = input_no_mbr %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
+protein_mappings = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/QuantifiedProteins.tsv")
+protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
+input_no_mbr = input_no_mbr %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
+
+
+# input_no_mbr$`Protein Group` = ifelse(
+#   input_no_mbr$`Protein Group` %in% ecoli$`Protein Groups`, 
+#   paste(input_no_mbr$`Protein Group`, "|ECOLI", sep = ""), 
+#   paste(input_no_mbr$`Protein Group`, "|HUMAN", sep = ""))
+# write.csv(input_no_mbr, "QuantifiedPeaks.csv", row.names = FALSE)
+
+
+output_no_mbr = MetamorpheusToMSstatsFormat(input_no_mbr, annot_no_mbr)
+QuantData_no_mbr = dataProcess(output_no_mbr, normalization = FALSE)
+
+dataProcessPlots(QuantData_no_mbr, "QCPlot", which.Protein = "allonly", address = FALSE, isPlotly = TRUE)
+
+comparison <- matrix(c(-1,0,0,0,1, # 3x
+                       -1,0,0,1,0, # 2.5x
+                       -1,0,1,0,0, # 2x
+                       -1,1,0,0,0),nrow=4,byrow = TRUE) # 1.5x
+
+
+row.names(comparison) <- c("E-A", "D-A", "C-A", "B-A")
+groups = levels(QuantData_no_mbr$ProteinLevelData$GROUP)
+colnames(comparison) <- groups[order(as.numeric(groups))]
+model_no_mbr <- groupComparison(contrast.matrix=comparison, data=QuantData_no_mbr,
+                                use_log_file = FALSE)
+
+library(tidyverse)
+ecoli_proteins = protein_mappings %>% filter(Organism == "Escherichia coli (strain K12)")
+model_no_mbr$ComparisonResult = model_no_mbr$ComparisonResult %>% mutate(ecoli = Protein %in% ecoli_proteins$`Protein Groups`)
+
+e_group_no_mbr = model_no_mbr$ComparisonResult %>% filter(Label == "B-A") %>% filter(is.na(issue))
+ecoli_no_mbr = e_group_no_mbr %>% filter(ecoli == TRUE)
+hist(ecoli_no_mbr$log2FC)
+
+ecoli_no_mbr = e_group_no_mbr %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == TRUE)
+human_no_mbr = e_group_no_mbr %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == FALSE)
+FDR_no_mbr = nrow(human_no_mbr) / (nrow(ecoli_no_mbr) + nrow(human_no_mbr))
+
+cat("FDR no MBR", FDR_no_mbr, "\n")
+
+# With MBR
+library(MSstatsConvert)
+library(MSstats)
+library(tidyverse)
+input = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_v1.0_NoNormalization_wPIP/QuantifiedPeaks.tsv")
+annot = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/annotation.csv")
+
+input = input %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
+input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
+
+protein_mappings = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_v1.0_NoNormalization_wPIP/QuantifiedProteins.tsv")
+protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
+input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
+
+# input$`Protein Group` = ifelse(
+#   input$`Protein Group` %in% ecoli$`Protein Groups`,
+#   paste(input$`Protein Group`, "|ECOLI", sep = ""),
+#   paste(input$`Protein Group`, "|HUMAN", sep = ""))
+# write.csv(input, "QuantifiedPeaks-MBR.csv", row.names = FALSE)
+
+
+output = MetamorpheusToMSstatsFormat(input, annot)
+QuantData = dataProcess(output, normalization = FALSE)
+
+dataProcessPlots(QuantData, "QCPlot", which.Protein = "allonly", address = FALSE, isPlotly = TRUE)
+
+comparison <- matrix(c(-1,0,0,0,1, # 3x
+                       -1,0,0,1,0, # 2.5x
+                       -1,0,1,0,0, # 2x
+                       -1,1,0,0,0),nrow=4,byrow = TRUE) # 1.5x
+row.names(comparison) <- c("E-A", "D-A", "C-A", "B-A")
+groups = levels(QuantData$ProteinLevelData$GROUP)
+colnames(comparison) <- groups[order(as.numeric(groups))]
+model <- groupComparison(contrast.matrix=comparison, data=QuantData,
+                         use_log_file = FALSE)
+
+library(tidyverse)
+ecoli_proteins = protein_mappings %>% filter(Organism == "Escherichia coli (strain K12)")
+model$ComparisonResult = model$ComparisonResult %>% mutate(ecoli = Protein %in% ecoli_proteins$`Protein Groups`)
+
+e_group = model$ComparisonResult %>% filter(Label == "B-A") %>% filter(is.na(issue))
+ecoli = e_group %>% filter(ecoli == TRUE)
+hist(ecoli$log2FC)
+
+ecoli = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == TRUE)
+human = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == FALSE)
+FDR = nrow(human) / (nrow(ecoli) + nrow(human))
+
+
+cat("FDR MBR", FDR, "\n")
+# FDR no MBR seems to be lower than that of FDR with MBR (except for E-A label), but it's not by a wide margin.  
+# When normalization was enabled, FDR spiked to 38% without MBR and 58% with MBR.
+# When we set adj.pvalue to 0.01, FDR without MBR does better, but not by much.
+# Less proteins detected as significant with MBR disabled.
\ No newline at end of file

From 423b485d0c0ad5c6fa2000607cf2ae652f62466b Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 15:39:12 -0400
Subject: [PATCH 34/45] Removed unnecessary file

---
 metamorpheus_code.R | 112 --------------------------------------------
 1 file changed, 112 deletions(-)
 delete mode 100644 metamorpheus_code.R

diff --git a/metamorpheus_code.R b/metamorpheus_code.R
deleted file mode 100644
index fa0c12c1..00000000
--- a/metamorpheus_code.R
+++ /dev/null
@@ -1,112 +0,0 @@
-library(MSstatsConvert)
-library(MSstats)
-library(tidyverse)
-
-
-# No MBR
-input_no_mbr = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/QuantifiedPeaks.tsv")
-
-
-
-annot_no_mbr = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/annotation.csv")
-
-
-input_no_mbr = input_no_mbr %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
-input_no_mbr = input_no_mbr %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
-protein_mappings = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/QuantifiedProteins.tsv")
-protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
-input_no_mbr = input_no_mbr %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
-
-
-# input_no_mbr$`Protein Group` = ifelse(
-#   input_no_mbr$`Protein Group` %in% ecoli$`Protein Groups`, 
-#   paste(input_no_mbr$`Protein Group`, "|ECOLI", sep = ""), 
-#   paste(input_no_mbr$`Protein Group`, "|HUMAN", sep = ""))
-# write.csv(input_no_mbr, "QuantifiedPeaks.csv", row.names = FALSE)
-
-
-output_no_mbr = MetamorpheusToMSstatsFormat(input_no_mbr, annot_no_mbr)
-QuantData_no_mbr = dataProcess(output_no_mbr, normalization = FALSE)
-
-dataProcessPlots(QuantData_no_mbr, "QCPlot", which.Protein = "allonly", address = FALSE, isPlotly = TRUE)
-
-comparison <- matrix(c(-1,0,0,0,1, # 3x
-                       -1,0,0,1,0, # 2.5x
-                       -1,0,1,0,0, # 2x
-                       -1,1,0,0,0),nrow=4,byrow = TRUE) # 1.5x
-
-
-row.names(comparison) <- c("E-A", "D-A", "C-A", "B-A")
-groups = levels(QuantData_no_mbr$ProteinLevelData$GROUP)
-colnames(comparison) <- groups[order(as.numeric(groups))]
-model_no_mbr <- groupComparison(contrast.matrix=comparison, data=QuantData_no_mbr,
-                                use_log_file = FALSE)
-
-library(tidyverse)
-ecoli_proteins = protein_mappings %>% filter(Organism == "Escherichia coli (strain K12)")
-model_no_mbr$ComparisonResult = model_no_mbr$ComparisonResult %>% mutate(ecoli = Protein %in% ecoli_proteins$`Protein Groups`)
-
-e_group_no_mbr = model_no_mbr$ComparisonResult %>% filter(Label == "B-A") %>% filter(is.na(issue))
-ecoli_no_mbr = e_group_no_mbr %>% filter(ecoli == TRUE)
-hist(ecoli_no_mbr$log2FC)
-
-ecoli_no_mbr = e_group_no_mbr %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == TRUE)
-human_no_mbr = e_group_no_mbr %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == FALSE)
-FDR_no_mbr = nrow(human_no_mbr) / (nrow(ecoli_no_mbr) + nrow(human_no_mbr))
-
-cat("FDR no MBR", FDR_no_mbr, "\n")
-
-# With MBR
-library(MSstatsConvert)
-library(MSstats)
-library(tidyverse)
-input = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_v1.0_NoNormalization_wPIP/QuantifiedPeaks.tsv")
-annot = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_NoNormalization_NoPIP/annotation.csv")
-
-input = input %>% filter(!str_detect(`Protein Group`, ";")) # remove multiple protein group in same cell
-input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
-
-protein_mappings = data.table::fread("/projects/VitekLab/Data/MS/Benchmarking/DDA-Solivais2024_Metamorpheus/Current/FlashLFQ_v1.0_NoNormalization_wPIP/QuantifiedProteins.tsv")
-protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
-input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
-
-# input$`Protein Group` = ifelse(
-#   input$`Protein Group` %in% ecoli$`Protein Groups`,
-#   paste(input$`Protein Group`, "|ECOLI", sep = ""),
-#   paste(input$`Protein Group`, "|HUMAN", sep = ""))
-# write.csv(input, "QuantifiedPeaks-MBR.csv", row.names = FALSE)
-
-
-output = MetamorpheusToMSstatsFormat(input, annot)
-QuantData = dataProcess(output, normalization = FALSE)
-
-dataProcessPlots(QuantData, "QCPlot", which.Protein = "allonly", address = FALSE, isPlotly = TRUE)
-
-comparison <- matrix(c(-1,0,0,0,1, # 3x
-                       -1,0,0,1,0, # 2.5x
-                       -1,0,1,0,0, # 2x
-                       -1,1,0,0,0),nrow=4,byrow = TRUE) # 1.5x
-row.names(comparison) <- c("E-A", "D-A", "C-A", "B-A")
-groups = levels(QuantData$ProteinLevelData$GROUP)
-colnames(comparison) <- groups[order(as.numeric(groups))]
-model <- groupComparison(contrast.matrix=comparison, data=QuantData,
-                         use_log_file = FALSE)
-
-library(tidyverse)
-ecoli_proteins = protein_mappings %>% filter(Organism == "Escherichia coli (strain K12)")
-model$ComparisonResult = model$ComparisonResult %>% mutate(ecoli = Protein %in% ecoli_proteins$`Protein Groups`)
-
-e_group = model$ComparisonResult %>% filter(Label == "B-A") %>% filter(is.na(issue))
-ecoli = e_group %>% filter(ecoli == TRUE)
-hist(ecoli$log2FC)
-
-ecoli = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == TRUE)
-human = e_group %>% filter(adj.pvalue < 0.05) %>% filter(ecoli == FALSE)
-FDR = nrow(human) / (nrow(ecoli) + nrow(human))
-
-
-cat("FDR MBR", FDR, "\n")
-# FDR no MBR seems to be lower than that of FDR with MBR (except for E-A label), but it's not by a wide margin.  
-# When normalization was enabled, FDR spiked to 38% without MBR and 58% with MBR.
-# When we set adj.pvalue to 0.01, FDR without MBR does better, but not by much.
-# Less proteins detected as significant with MBR disabled.
\ No newline at end of file

From 7485d9519545cbed3c56d885a66d3d4709b25f1d Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 15:58:48 -0400
Subject: [PATCH 35/45] Changes for variable name correction

---
 benchmark/metamorpheus_Process.R | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/benchmark/metamorpheus_Process.R b/benchmark/metamorpheus_Process.R
index cd6c4fba..dcf7fce1 100644
--- a/benchmark/metamorpheus_Process.R
+++ b/benchmark/metamorpheus_Process.R
@@ -20,13 +20,13 @@ calculate_Metrics <- function(QuantData, protein_mappings, task_label, alpha = 0
     filter(Organism == "Escherichia coli (strain K12)") %>%
     pull(`Protein Groups`)
 
-  comp <- model$ComparisonResult %>%
+  filtered_results <- model$ComparisonResult %>%
     mutate(ecoli = Protein %in% ecoli_ids) %>%
     filter(is.na(issue))
 
-  labels <- unique(comp$Label)
+  labels <- unique(filtered_results$Label)
   result_rows <- lapply(labels, function(lbl) {
-    df <- comp %>% filter(Label == lbl)
+    df <- filtered_results %>% filter(Label == lbl)
     sig <- df %>% filter(adj.pvalue < alpha)
 
     tp <- sig %>% filter(ecoli) %>% nrow()

From 4fb9d062ba3722fa7d2bd0795bf630c9c2adecaf Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 16:09:05 -0400
Subject: [PATCH 36/45] Variable rename revert

---
 benchmark/metamorpheus_Process.R | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/benchmark/metamorpheus_Process.R b/benchmark/metamorpheus_Process.R
index dcf7fce1..cd6c4fba 100644
--- a/benchmark/metamorpheus_Process.R
+++ b/benchmark/metamorpheus_Process.R
@@ -20,13 +20,13 @@ calculate_Metrics <- function(QuantData, protein_mappings, task_label, alpha = 0
     filter(Organism == "Escherichia coli (strain K12)") %>%
     pull(`Protein Groups`)
 
-  filtered_results <- model$ComparisonResult %>%
+  comp <- model$ComparisonResult %>%
     mutate(ecoli = Protein %in% ecoli_ids) %>%
     filter(is.na(issue))
 
-  labels <- unique(filtered_results$Label)
+  labels <- unique(comp$Label)
   result_rows <- lapply(labels, function(lbl) {
-    df <- filtered_results %>% filter(Label == lbl)
+    df <- comp %>% filter(Label == lbl)
     sig <- df %>% filter(adj.pvalue < alpha)
 
     tp <- sig %>% filter(ecoli) %>% nrow()

From 9fc6a86663a801a259f4503c86ffb9593b590cf8 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 17:52:11 -0400
Subject: [PATCH 37/45] PR feedbacks

---
 benchmark/metamorpheus_Process.R | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/benchmark/metamorpheus_Process.R b/benchmark/metamorpheus_Process.R
index cd6c4fba..035d45a9 100644
--- a/benchmark/metamorpheus_Process.R
+++ b/benchmark/metamorpheus_Process.R
@@ -20,13 +20,13 @@ calculate_Metrics <- function(QuantData, protein_mappings, task_label, alpha = 0
     filter(Organism == "Escherichia coli (strain K12)") %>%
     pull(`Protein Groups`)
 
-  comp <- model$ComparisonResult %>%
+  filtered_comparison_result <- model$ComparisonResult %>%
     mutate(ecoli = Protein %in% ecoli_ids) %>%
     filter(is.na(issue))
 
-  labels <- unique(comp$Label)
+  labels <- unique(filtered_comparison_result$Label)
   result_rows <- lapply(labels, function(lbl) {
-    df <- comp %>% filter(Label == lbl)
+    df <- filtered_comparison_result %>% filter(Label == lbl)
     sig <- df %>% filter(adj.pvalue < alpha)
 
     tp <- sig %>% filter(ecoli) %>% nrow()

From 8518c44a9a3d84b2f4bccd43e776fcf234e6a119 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 18:10:59 -0400
Subject: [PATCH 38/45] Changes for Unique Organisms

---
 benchmark/benchmark_Metamorpheus.R | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 33bb366d..95e855b7 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -29,7 +29,11 @@ runBenchmarkForMetaMorpheusData <- function(datasetPath, config) {
   input = input %>% filter(!str_detect(`Protein Group`, "DECOY")) # remove decoys
 
   protein_mappings = data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
-  protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
+
+  valid_organisms <- unique(input$Organism)
+
+  protein_mappings = protein_mappings %>%
+    filter(Organism %in% valid_organisms)
 
   input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
 

From 8eefbff3faceee1f0b6416f5ee72ee95225d1d65 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 18:23:07 -0400
Subject: [PATCH 39/45] Changes for protein_mappings

---
 benchmark/benchmark_Metamorpheus.R | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 95e855b7..57c12be4 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -35,6 +35,8 @@ runBenchmarkForMetaMorpheusData <- function(datasetPath, config) {
   protein_mappings = protein_mappings %>%
     filter(Organism %in% valid_organisms)
 
+  print(protein_mappings)
+
   input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
 
   output = MetamorpheusToMSstatsFormat(input, annot)

From a9fbe803e52384f03b6951e69c32d0ecf0644cf7 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 18:50:55 -0400
Subject: [PATCH 40/45] Correction for Organism column

---
 benchmark/benchmark_Metamorpheus.R | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 57c12be4..3fd8c313 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -31,6 +31,10 @@ runBenchmarkForMetaMorpheusData <- function(datasetPath, config) {
   protein_mappings = data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
 
   valid_organisms <- unique(input$Organism)
+  
+  if (is.null(valid_organisms) || length(valid_organisms) == 0) {
+    valid_organisms <- unique(input$`Organism.y`)
+  }
 
   protein_mappings = protein_mappings %>%
     filter(Organism %in% valid_organisms)

From 3be70e4534fe3b51b54ee38af72acdda7458b359 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Fri, 15 Aug 2025 19:02:45 -0400
Subject: [PATCH 41/45] Organisms

---
 benchmark/benchmark_Metamorpheus.R | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 3fd8c313..5c8040d8 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -31,11 +31,13 @@ runBenchmarkForMetaMorpheusData <- function(datasetPath, config) {
   protein_mappings = data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
 
   valid_organisms <- unique(input$Organism)
-  
+
   if (is.null(valid_organisms) || length(valid_organisms) == 0) {
     valid_organisms <- unique(input$`Organism.y`)
   }
 
+  print("Organisms")
+  print(valid_organisms)
   protein_mappings = protein_mappings %>%
     filter(Organism %in% valid_organisms)
 

From 85a41cde6878f0b34cd518df0646b9af8a2825af Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Mon, 18 Aug 2025 11:57:28 -0400
Subject: [PATCH 42/45] Changes for organisms column

---
 benchmark/benchmark_Metamorpheus.R | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 5c8040d8..5e43ba08 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -35,7 +35,8 @@ runBenchmarkForMetaMorpheusData <- function(datasetPath, config) {
   if (is.null(valid_organisms) || length(valid_organisms) == 0) {
     valid_organisms <- unique(input$`Organism.y`)
   }
-
+  
+  print(colnames(input))
   print("Organisms")
   print(valid_organisms)
   protein_mappings = protein_mappings %>%

From c4c0c86724fca9e1aa3f5e383f0a3ede737f37da Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Mon, 18 Aug 2025 12:34:05 -0400
Subject: [PATCH 43/45] Reverted changes

---
 benchmark/benchmark_Metamorpheus.R | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 5e43ba08..7d3cf645 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -30,17 +30,7 @@ runBenchmarkForMetaMorpheusData <- function(datasetPath, config) {
 
   protein_mappings = data.table::fread(file.path(filePath, "QuantifiedProteins.tsv"))
 
-  valid_organisms <- unique(input$Organism)
-
-  if (is.null(valid_organisms) || length(valid_organisms) == 0) {
-    valid_organisms <- unique(input$`Organism.y`)
-  }
-  
-  print(colnames(input))
-  print("Organisms")
-  print(valid_organisms)
-  protein_mappings = protein_mappings %>%
-    filter(Organism %in% valid_organisms)
+  protein_mappings = protein_mappings %>% filter(Organism %in% c("Escherichia coli (strain K12)", "Homo sapiens"))
 
   print(protein_mappings)
 

From f6ac63e219077da570d83a904345f8cf0e374be8 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Mon, 18 Aug 2025 13:13:26 -0400
Subject: [PATCH 44/45] Added new arguments

---
 benchmark/benchmark_Metamorpheus.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 7d3cf645..460c6ec4 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -36,7 +36,7 @@ runBenchmarkForMetaMorpheusData <- function(datasetPath, config) {
 
   input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
 
-  output = MetamorpheusToMSstatsFormat(input, annot)
+  output = MetamorpheusToMSstatsFormat(input, annot, removeFewMeasurements = FALSE, removeProtein_with1Feature = FALSE)
 
   data_process_tasks <- list(
     list(

From 90cf018acd2c26c6a2db72ed01d81070cbc2c3f6 Mon Sep 17 00:00:00 2001
From: Anshuman Raina <raina.ans@northeastern.edu>
Date: Mon, 18 Aug 2025 15:01:31 -0400
Subject: [PATCH 45/45] Removed params

---
 benchmark/benchmark_Metamorpheus.R | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/benchmark/benchmark_Metamorpheus.R b/benchmark/benchmark_Metamorpheus.R
index 460c6ec4..7d3cf645 100644
--- a/benchmark/benchmark_Metamorpheus.R
+++ b/benchmark/benchmark_Metamorpheus.R
@@ -36,7 +36,7 @@ runBenchmarkForMetaMorpheusData <- function(datasetPath, config) {
 
   input = input %>% filter(`Protein Group` %in% protein_mappings$`Protein Groups`)
 
-  output = MetamorpheusToMSstatsFormat(input, annot, removeFewMeasurements = FALSE, removeProtein_with1Feature = FALSE)
+  output = MetamorpheusToMSstatsFormat(input, annot)
 
   data_process_tasks <- list(
     list(