Changes to test the pipeline with generating indexes and bigbed files…

…. Required including the type of the bed file that was being indexed

process_bed.py

@@ -36,6 +36,7 @@
 
     from dummy_pycompss import *
 
+from tool import bed_indexer
 
 # ------------------------------------------------------------------------------
 
@@ -78,10 +79,18 @@ def run(self, file_ids, metadata):
         chrom_file = file_ids[1]
         hdf5_file = file_ids[2]
         assembly = metadata["assembly"]
+        file_id = metadata["file_id"]
+        bed_type = metadata["bed_type"]
+
+        meta_data = {
+            "file_id" : b_file,
+            "bed_type" : bed_type,
+            "assembly" : assembly
+        }
 
         # Bed Indexer
-        b = tool.bedIndexerTool(self.configuration)
-        bb, h5_idx = b.run((bed_file, chrom_file, hdf5_file), {'assembly' : assembly})
+        b = bed_indexer.bedIndexerTool()
+        bb, h5_idx = b.run((bed_file, chrom_file, hdf5_file), meta_data)
 
         return (bb, h5_idx)
 
@@ -97,14 +106,16 @@ def run(self, file_ids, metadata):
     parser.add_argument("--chrom", help="Matching chrom.size file")
     parser.add_argument("--bed_file", help="Bed file to get indexed")
     parser.add_argument("--h5_file", help="Location of HDF5 index file")
+    parser.add_argument("--bed_type", help="Type of Bed file bedN[+P]", default=None)
 
     # Get the matching parameters from the command line
     args = parser.parse_args()
 
     assembly = args.assembly
     chrom_size_file = args.chrom
     bed_file = args.bed_file
-    h5_file = args.h5_file
+    hdf5_file = args.h5_file
+    bed_type = args.bed_type
 
     pb = process_bed()
 
@@ -118,19 +129,26 @@ def run(self, file_ids, metadata):
 
 
     #2. Register the data with the DMP
-    da = dmp()
+    da = dmp(test=True)
 
     print(da.get_files_by_user("test"))
 
     cs_file = da.set_file("test", chrom_size_file, "tsv", "ChIP-seq", "", None)
     b_file = da.set_file("test", bed_file, "bed", "Assembly", "", None)
-    h5_file = da.set_file("test", h5_file, "hdf5", "index", "", None)
+    h5_file = da.set_file("test", hdf5_file, "hdf5", "index", "", None)
 
     print(da.get_files_by_user("test"))
 
     # 3. Instantiate and launch the App
-    from basic_modules import WorkflowApp
-    app = WorkflowApp()
-    results = app.launch(process_bed, [b_file, cs_file, h5_file], {"assembly" : assembly})
+    #from basic_modules import WorkflowApp
+    #app = WorkflowApp()
+    #results = app.launch(process_bed, [b_file, cs_file, h5_file], {"assembly" : assembly})
+
+    metadata = {
+        "file_id" : b_file,
+        "bed_type" : bed_type,
+        "assembly" : assembly
+    }
+    results = pb.run([bed_file, chrom_size_file, hdf5_file], metadata)
 
     print(da.get_files_by_user("test"))

tool/bed_indexer.py

@@ -82,7 +82,7 @@ def bedsort(self, file_bed, file_sorted_bed):
 
 
     @task(file_sorted_bed=FILE_IN, file_chrom=FILE_IN, file_bb=FILE_OUT)
-    def bed2bigbed(self, file_bed, file_chrom, file_bb):
+    def bed2bigbed(self, file_sorted_bed, file_chrom, file_bb):
         """
         BED to BigBed converter
         
@@ -255,7 +255,7 @@ def run(self, input_files, metadata):
                 Location of chrom.size file
             hdf5_file : str
                 Location of the HDF5 index file
-        meta_data : list
+        metadata : list
             file_id : str
                 file_id used to identify the original bed file
             assembly : str
@@ -285,17 +285,17 @@ def run(self, input_files, metadata):
         hdf5_file  = input_files[2]
 
         bed_sorted_name = bed_file.split("/")
-        bed_sorted_name[-1].replace('.bed', '.sorted.bed')
+        bed_sorted_name[-1] = bed_sorted_name[-1].replace('.bed', '.sorted.bed')
         bed_sorted_file = '/'.join(bed_sorted_name)
 
         bb_name = bed_file.split("/")
-        bb_name[-1].replace('.bed', '.bb')
+        bb_name[-1] = bb_name[-1].replace('.bed', '.bb')
         bb_file = '/'.join(bb_name)
 
-        assembly = meta_data['assembly']
-        
+        assembly = metadata['assembly']
+
         # handle error
-        if not self.bedsorted(bed_file, bed_sorted_file):
+        if not self.bedsort(bed_file, bed_sorted_file):
             output_metadata.set_exception(
                 Exception(
                     "bedsorted: Could not process files {}, {}.".format(*input_files)))
@@ -305,7 +305,7 @@ def run(self, input_files, metadata):
                 Exception(
                     "bed2bigbed: Could not process files {}, {}.".format(*input_files)))
 
-        if not self.bed2hdf5(file_id, assembly, bed_file, hdf5_file):
+        if not self.bed2hdf5(metadata['file_id'], assembly, bed_file, hdf5_file):
             output_metadata.set_exception(
                 Exception(
                     "bed2hdf5: Could not process files {}, {}.".format(*input_files)))