Merge pull request #146 from ypriverol/master

Fixed some errors introduced before in #PR 44

requirements.txt

@@ -4,3 +4,4 @@ pandas_schema
 pytest
 requests
 pyyaml
+numpy

sdrf_pipelines/maxquant/maxquant.py

@@ -73,7 +73,7 @@ def guess_tmt(self, lt, label_list=None):
                     lt = lt + "TMT2plex-Lys" + i.replace("TMT", "") + ","
         return lt
 
-    def extractTMT_info(self, label="TMT2", mods=None):
+    def extract_tmt_info(self, label="TMT2", mods=None):
         lt = ""
         label_list = sorted(label)
         label_head = [re.search(r"TMT(\d+)plex-", i).group(1) for i in mods if "TMT" in i]
@@ -1350,7 +1350,7 @@ def maxquant_convert(
         root.appendChild(intensityPredictionsFile)
 
         minPepLen = doc.createElement("minPepLen")
-        if "min_peptide_length" in file2params and len(file2params["min_peptide_length"]) > 0::
+        if "min_peptide_length" in file2params and len(file2params["min_peptide_length"]) > 0:
             tparam = file2params["min_peptide_length"]
             first = list(tparam.values())[0]
             minPepLen.appendChild(doc.createTextNode(first))
@@ -1368,7 +1368,7 @@ def maxquant_convert(
         root.appendChild(psmFdrCrosslink)
 
         peptideFdr = doc.createElement("peptideFdr")
-        if "ident_fdr_peptide" in file2params and len(file2params["ident_fdr_peptide"]) > 0::
+        if "ident_fdr_peptide" in file2params and len(file2params["ident_fdr_peptide"]) > 0:
             tparam = file2params["ident_fdr_peptide"]
             first = list(tparam.values())[0]
             warning_message = "overwriting peptide FDR using the value in the sdrf file"
@@ -1382,7 +1382,7 @@ def maxquant_convert(
         root.appendChild(peptideFdr)
 
         proteinFdr = doc.createElement("proteinFdr")
-        if "ident_fdr_protein" in file2params and len(file2params["ident_fdr_protein"]) > 0::
+        if "ident_fdr_protein" in file2params and len(file2params["ident_fdr_protein"]) > 0:
             tparam = file2params["ident_fdr_protein"]
             first = list(tparam.values())[0]
             warning_message = "overwriting protein FDR using the value in the sdrf file"
@@ -1396,7 +1396,7 @@ def maxquant_convert(
         root.appendChild(proteinFdr)
 
         siteFdr = doc.createElement("siteFdr")
-        if "ident_fdr_psm" in file2params and len(file2params["ident_fdr_psm"]) > 0::
+        if "ident_fdr_psm" in file2params and len(file2params["ident_fdr_psm"]) > 0:
             tparam = file2params["ident_fdr_psm"]
             first = list(tparam.values())[0]
             warning_message = "overwriting PSM FDR using the value in the sdrf file"
@@ -1422,7 +1422,7 @@ def maxquant_convert(
         root.appendChild(useNormRatiosForOccupancy)
 
         minPeptides = doc.createElement("minPeptides")
-        if "min_num_peptides" in file2params and len(file2params["min_num_peptides"]) > 0::
+        if "min_num_peptides" in file2params and len(file2params["min_num_peptides"]) > 0:
             tparam = file2params["min_num_peptides"]
             first = list(tparam.values())[0]
             minPeptides.appendChild(doc.createTextNode(first))
@@ -1504,7 +1504,7 @@ def maxquant_convert(
         root.appendChild(compositionPrediction)
 
         quantMode = doc.createElement("quantMode")
-        if "protein_inference" in file2params and len(file2params["protein_inference"]) > 0::
+        if "protein_inference" in file2params and len(file2params["protein_inference"]) > 0:
             tparam = file2params["protein_inference"]
             first = list(tparam.values())[0]
             if first == "unique":

sdrf_pipelines/openms/openms.py

@@ -191,10 +191,12 @@ def openms_convert(
 
         # load sdrf file
         sdrf = pd.read_table(sdrf_file)
+        null_cols = sdrf.columns[sdrf.isnull().any()]
         if sdrf.isnull().values.any():
             raise Exception(
                 "Encountered empty cells while reading SDRF."
-                " Please check your file, e.g. for too many column headers or empty fields"
+                "Please check your file, e.g. for too many column headers or empty fields"
+                "Columns with empty values: {}".format(list(null_cols))
             )
         sdrf = sdrf.astype(str)
         sdrf.columns = map(str.lower, sdrf.columns)  # convert column names to lower-case
@@ -968,7 +970,8 @@ def save_search_settings_to_file(self, output_filename, sdrf, f2c):
                 acquisition_method = "Data-Dependent Acquisition"
             else:
                 acquisition_method = row["comment[proteomics data acquisition method]"]
-                acquisition_method = acquisition_method.split(";")[0].split("=")[1]
+                if len(acquisition_method.split(";")) > 1:
+                    acquisition_method = acquisition_method.split(";")[0].split("=")[1]
 
             if raw in raws:
                 continue

sdrf_pipelines/parse_sdrf.py

@@ -27,7 +27,8 @@
 @click.group(context_settings=CONTEXT_SETTINGS)
 def cli():
     """
-    This is the main tool that gives access to all commands to convert SDRF files into pipelines specific configuration files
+    This is the main tool that gives access to all commands to convert SDRF files into pipelines specific configuration
+    files.
     """
     pass