Merge pull request #599 from CCMS-UCSD/classic_networking_linkouts_lc…

…_browser Classic networking linkouts lc browser
CCMS-UCSD · Aug 23, 2020 · f05b3df · f05b3df
2 parents a5ae96d + e15acf6
commit f05b3df
Show file tree

Hide file tree

Showing 7 changed files with 97 additions and 3 deletions.
diff --git a/metabolomics-snets-v2/metabolomics-snets-v2/binding.xml b/metabolomics-snets-v2/metabolomics-snets-v2/binding.xml
@@ -47,6 +47,12 @@
 	</bind>
 
 
+	<bind action="filesummary" tool="filesummary">
+        <inputAsRequirement port="spec" requirement="spec"/>
+        <inputAsRequirement port="workflowParameters" requirement="workflowParameters"/>
+        <productionToOutput port="filestatsresults" production="result"/>
+    </bind>
+
 
 
 	<bind action="searchlibraryparamgeneration_specnets" tool="LibrarySearchParamGeneration_specnets">
@@ -330,6 +336,12 @@
 		<query name="task" valueRef="@task"/>
 		<contentQuery name="content"/>
 		<compression type="zip"/>
+
+
+		<upload port="filestatsresults" type="file">
+			<query name="resource" value="filestatsresults"/>
+		</upload>
+
 		<upload port="clusterinfo" type="file">
 			<query name="resource" value="clusterinfo"/>
 		</upload>

diff --git a/metabolomics-snets-v2/metabolomics-snets-v2/flow.xml b/metabolomics-snets-v2/metabolomics-snets-v2/flow.xml
@@ -35,6 +35,14 @@
         <output port="input_file_validation_flag"           object="input_file_validation_flag"/>
     </action>
 
+    <!-- File Summary -->
+    <object name="filestatsresults"/>
+    <action name="filesummary">
+        <input port="spec" collection="inputspectra"/>
+        <input port="workflowParameters" object="workflowParameters"/>
+        <output port="filestatsresults" object="filestatsresults"/>
+    </action>
+
 
     <!-- Library Search -->
     <collection name="paramsgen_specnets"/>
@@ -317,6 +325,8 @@
 
 
     <action name="end">
+        <input port="filestatsresults" object="filestatsresults"/>
+
         <!-- Library Search -->
         <input port="result_specnets" object="result_specnets"/>
         <input port="result_specnets_DB" object="result_specnets_DB"/>

diff --git a/metabolomics-snets-v2/metabolomics-snets-v2/result.xml b/metabolomics-snets-v2/metabolomics-snets-v2/result.xml
@@ -704,6 +704,33 @@
     </block>
 
 
+    <!-- File Summary -->
+    <view id="file_summary" label="File Summaries" group="Default Molecular Networking Results Views">
+        <blockRef id="main" type="file_summary"/>
+    </view>
+
+    <block id="file_summary" type="table">
+        <data>
+            <source type="file" name="filestatsresults/"/>
+            <parsers>
+                <parser type="sortedTabular" sortBy="full_CCMS_path" operator="ascending"/>
+            </parsers>
+        </data>
+        <row>
+            <column label="View Chromatogram" type="genericurlgenerator" width="5">
+                <parameter name="URLBASE" value="http://dorresteintesthub.ucsd.edu:6548"/>
+                <parameter name="REQUESTPARAMETER=usi" value="mzspec:GNPS:TASK-{task}-f.[full_CCMS_path]:scan:1"/>
+                <parameter name="LABEL" value="View LCMS Chromatogram (Beta)"/>
+            </column>
+            <column type="text" field="full_CCMS_path" label="Filename" width="10"/>
+            <column type="text" field="Vendor" label="Vendor" width="10"/>
+            <column type="text" field="Model" label="Model" width="10"/>
+            <column type="integer" field="MS1s" label="MS1 Count" width="3"/>
+            <column type="integer" field="MS2s" label="MS2 Count" width="3"/>
+        </row>
+    </block>
+
+
 
 
 
@@ -1096,6 +1123,12 @@
                 <parameter name="REQUESTPARAMETER=filename" value="[Original_Path]"/>
                 <parameter name="LABEL" value="View Global Metadata"/>
             </column>
+            <column label="View Chromatogram" type="genericurlgenerator" width="5">
+                <parameter name="URLBASE" value="http://dorresteintesthub.ucsd.edu:6548"/>
+                <parameter name="REQUESTPARAMETER=usi" value="mzspec:GNPS:TASK-{task}-[Original_Path]:scan:1"/>
+                <parameter name="REQUESTPARAMETER=xicmz" value="[parent mass]"/>
+                <parameter name="LABEL" value="View LCMS Chromatogram (Beta)"/>
+            </column>
             <column type="text" field="AllFiles" label="Filename" width="10"/>
             <column type="integer" field="ScanNumber" label="Scan" width="3"/>
             <column type="float" field="sum(precursor intensity)" label="Precursor Int" precision="3"/>

diff --git a/metabolomics-snets-v2/metabolomics-snets-v2/tool.xml b/metabolomics-snets-v2/metabolomics-snets-v2/tool.xml
@@ -1,4 +1,31 @@
 <toolset>
+
+    <!-- File Summary -->
+    <pathSet base="anaconda3/bin">
+        <toolPath tool="filesummary" path="python" />
+    </pathSet>
+    <pathSet base="$base/scripts">
+        <pathVar name="msaccess.file" path="msaccess"/>
+        <pathVar name="filesummary.script" path="filesummary.py"/>
+    </pathSet>
+
+    <tool name="filesummary">
+        <require name="spec" type="folder"/>
+        <require name="parameter" type="file"/>
+        <require name="workflowParameters" type="file"/>
+        <produce name="result" type="file" naming="explicit" extension="tsv"/>
+
+        <execution env="binary" argConvention="adhoc">
+            <arg pathRef="filesummary.script"/>
+            <arg valueRef="spec"/>
+            <arg valueRef="workflowParameters"/>
+            <arg valueRef="result"/>
+            <arg pathRef="msaccess.file"/>
+        </execution>
+    </tool>
+
+
+
     <!-- MSClustering -->
 
     <pathSet base="$base">

diff --git a/metabolomics-snets-v2/tools/metabolomicsnetsv2/scripts/filesummary.py b/metabolomics-snets-v2/tools/metabolomicsnetsv2/scripts/filesummary.py
@@ -0,0 +1 @@
+../../../../molecular-librarysearch-v2/tools/molecularsearch/filesummary.py
diff --git a/metabolomics-snets-v2/tools/metabolomicsnetsv2/scripts/msaccess b/metabolomics-snets-v2/tools/metabolomicsnetsv2/scripts/msaccess
@@ -0,0 +1 @@
+../../../../molecular-librarysearch-v2/tools/molecularsearch/msaccess
diff --git a/molecular-librarysearch-v2/tools/molecularsearch/filesummary.py b/molecular-librarysearch-v2/tools/molecularsearch/filesummary.py
@@ -13,7 +13,8 @@
 import ming_parallel_library
 import csv
 import re
-
+import pandas as pd
+import glob
 
 def summary_wrapper(search_param_dict):
     summary_files(search_param_dict["spectrum_file"], search_param_dict["tempresults_folder"], search_param_dict["args"])
@@ -85,15 +86,24 @@ def main():
 
         #print(result_list)
         #full_result_list += result_list
-
+
+    used_files = set()
     for result_object in full_result_list:
         mangled_name = os.path.basename(result_object["Filename"])
         full_path = mangled_mapping[mangled_name]
         result_object["full_CCMS_path"] = full_path
+        used_files.add(full_path)
 
-    ming_fileio_library.write_list_dict_table_data(full_result_list, args.result_file)
+    for mangled_name in spectra_files:
+        full_path = mangled_mapping[os.path.basename(mangled_name)]
+        if full_path in used_files:
+            continue
 
+        output_dict = {}
+        output_dict["full_CCMS_path"] = full_path
+        full_result_list.append(output_dict)
 
+    pd.DataFrame(full_result_list).to_csv(args.result_file, sep="\t", index=False)