From 459b4d2053f3252b0a93d3878b6b53c8a828a650 Mon Sep 17 00:00:00 2001
From: Philipbear <philipxsp@hotmail.com>
Date: Mon, 16 Sep 2024 11:17:02 -0700
Subject: [PATCH] bug fix

---
 bin/create_library/merge_df.py     | 4 +++-
 bin/create_library/summarize_df.py | 3 ++-
 workflowinput.yaml                 | 8 ++++----
 3 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/bin/create_library/merge_df.py b/bin/create_library/merge_df.py
index f29eca0..2eb3bef 100755
--- a/bin/create_library/merge_df.py
+++ b/bin/create_library/merge_df.py
@@ -1,11 +1,13 @@
 import pandas as pd
 
 
-def merge_compound_feature_tables(compound_df, feature_df, mz_da=0.002, mz_ppm=10):
+def merge_compound_feature_tables(compound_df, feature_df, mz_ppm=10):
     """
     Merge compound DataFrame with feature table based on m/z values.
     """
 
+    mz_da = 200 * mz_ppm / 1e6
+
     # Create empty list to store matches
     matches = []
 
diff --git a/bin/create_library/summarize_df.py b/bin/create_library/summarize_df.py
index a56580d..b596575 100644
--- a/bin/create_library/summarize_df.py
+++ b/bin/create_library/summarize_df.py
@@ -27,7 +27,8 @@ def summarize_df(df):
         # for INCHI_AUX
         isomer_inchi_ls = df.loc[mask, 'inchi_adduct'].unique().tolist()
         # remove the current inchi_adduct
-        isomer_inchi_ls.remove(row['inchi_adduct'])
+        if row['inchi_adduct'] in isomer_inchi_ls:
+            isomer_inchi_ls.remove(row['inchi_adduct'])
         row['isomer_inchis'] = ';'.join(isomer_inchi_ls)
 
         mask2 = df['SMILES_adduct'] == row['SMILES_adduct']
diff --git a/workflowinput.yaml b/workflowinput.yaml
index ceb6776..7950429 100644
--- a/workflowinput.yaml
+++ b/workflowinput.yaml
@@ -2,7 +2,7 @@ workflowname: reverse_metabolomics_create_library_workflow
 workflowdescription: This is to create MS/MS libraries for reverse metabolomics.
 workflowlongdescription: This is the workflow to create a tsv library from a set of mzML files and compound csv files. The tsv file is ready to be uploaded to GNPS library. 
   A template for the compound csv file can be found [here](https://docs.google.com/spreadsheets/d/14VoG20s6C8GaoWk1fodWFzg2Ao8p9UuRcvuW7rgiEnA/edit?usp=sharing).
-workflowversion: "2024.09.16"
+workflowversion: "2024.09.16.2"
 workflowfile: nf_workflow.nf
 workflowautohide: false
 adminonly: false
@@ -63,9 +63,9 @@ parameterlist:
       formvalue: "full"
       options:
         - value: "simple"
-          display: "Positive: M+H, M+Na, M+NH4 | Negative: M-H"
+          display: "Positive: M+H, M+Na, M+NH4 || Negative: M-H"
         - value: "full"
-          display: "Positive: M+H, M+Na, M+NH4, M+K, M+H-H2O, M+H-2H2O, M+H-3H2O | Negative: M-H, M+FA, M+Ac, M+Cl, M+Br, M-H-H2O"
+          display: "Positive: M+H, M+Na, M+NH4, M+K, M+H-H2O, M+H-2H2O, M+H-3H2O || Negative: M-H, M+FA, M+Ac, M+Cl, M+Br, M-H-H2O"
 
     - displayname: Core Adduct Filter
       paramtype: select
@@ -76,5 +76,5 @@ parameterlist:
           display: "True"
         - value: "0"
           display: "False"
-      tooltip: "One chemical can have multiple candidate peaks in the LC-MS run. If true, candidate peaks without core adducts will be excluded. Core adducts: M+H, M+NH4, M+H-H2O, M+H-2H2O; M-H"
+      tooltip: "One chemical can have multiple candidate peaks in the LC-MS run. If true, candidate peaks without core adducts will be excluded. Core adducts: M+H, M+NH4, M+H-H2O, M+H-2H2O || M-H"