update pacbio_qc

src/jflow/config_reader.py

@@ -18,6 +18,7 @@
 import os
 import sys
 import inspect
+import logging
 
 from ConfigParser import ConfigParser, NoOptionError
 

src/jflow/parameter.py

@@ -191,8 +191,8 @@ class MultipleParameters(object):
         else:
             try:
                 value = self.types[parts[0]](parts[1])
-            except:
-                raise argparse.ArgumentTypeError("invalid " + self.types[parts[0]].__name__ + " value: '" + parts[1] + "' for sub parameter '" + parts[0] + "'")
+            except Exception, e:
+                raise argparse.ArgumentTypeError("invalid " + self.types[parts[0]].__name__ + " value: '" + parts[1] + "' for sub parameter '" + parts[0] + "' - " + str(e))
             
             if self.choices[parts[0]] != None:
                 if value not in self.choices[parts[0]]:

src/ng6/ng6workflow.py

@@ -210,8 +210,8 @@ class NG6Workflow (BasicNG6Workflow):
         
     def __add_sample_parameters__(self):
         self.add_multiple_parameter_list("input_sample", "Definition of a sample", flag="--sample", required = True, group="Sample description")
-        self.add_parameter("sample_id", "The uniq identifier of the sample", add_to = "input_sample")
-        self.add_parameter("sample_name", "A descriptive name for the sample", add_to = "input_sample")
+        self.add_parameter("sample_id", "The uniq identifier of the sample", type="nospacestr", add_to = "input_sample")
+        self.add_parameter("sample_name", "A descriptive name for the sample", type="nospacestr", add_to = "input_sample")
         self.add_parameter("sample_description", "A brief description of the sample", add_to = "input_sample")
         self.add_parameter("type", "Read orientation and type", choices = Sample.AVAILABLE_TYPES, default='se', add_to = "input_sample")
         self.add_parameter("insert_size", "Insert size for paired end reads", type = int, add_to = "input_sample")

ui/nG6/pi1/analyzes/Adaptorcleaner.js

@@ -30,7 +30,7 @@ $(function () {
 	
     $('a[data-toggle="tab"]').on('shown', function () {
         if ($(this).attr("href") == "#adaptor") {
-        	var oTable = $('#adaptor-table').dataTable();
+        	var oTable = $('#adaptor-table').DataTable();
         	oTable.fnDraw();
         	oTable.fnAdjustColumnSizing();
         }

ui/nG6/pi1/analyzes/RS_Subreads.js

@@ -23,7 +23,7 @@
 
 $(function () {
 
-	var udateTableStatus = function($elmt){
+	var updateTableStatus = function($elmt){
 		var table = $("#rs_subreads_datatable").DataTable();
 		var column = table.column($elmt.attr('data-column')) ;
 		column.visible($elmt[0].checked );
@@ -31,12 +31,12 @@ $(function () {
 	
 	$('#rs_subreads_datatable').on( 'draw.dt', function () {
 		$(':checkbox.toogle-vis').each(function(e){
-			udateTableStatus($(this));
+			updateTableStatus($(this));
 		});
 	});
 	
 	$(':checkbox.toogle-vis').change(function(e) {
-		udateTableStatus($(this));
+		updateTableStatus($(this));
 	});
 	
 	$(':checkbox#view_all_metrics').change(function(e) {
@@ -126,6 +126,10 @@ $(function () {
 			$("#ng6modal").modal();
 		}
     }) ;
+    
+    $(':checkbox.toogle-vis').each(function(e){
+		updateTableStatus($(this));
+	});
 	
 });
 

ui/nG6/pi1/analyzes/RS_Subreads.tpl

@@ -18,6 +18,10 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 {extends file='AnalysisTemplate.tpl'}
 
 {block name=results_title} Reports {/block}
+
+{block name=nav_menu_downloads}{/block}
+{block name=tab_content_downloads}{/block}
+
 {block name=results}
     
     {assign var="analyse_results_sorted" value=$analyse_results|@ksort}
@@ -57,7 +61,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
                             <li>
                                 <div class="checkbox">
                                     <label>
-                                      <input type="checkbox" data-column="{$data_col}" class="toogle-vis"/> {$head}
+                                      <input type="checkbox" data-column="{$data_col}" class="toogle-vis" checked/> {$head}
                                     </label>
                                 </div>
                             </li>
@@ -146,7 +150,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 			    <tr>
 				    <th rowspan="2"><center><input type="checkbox" id="chk_all_sample"/></center></th>
 				    {assign var="nb_samples" value=$analyse_results|@count - 1 }
-				    <th class="string-sort" rowspan="2" id="th_id_1"><center>SMRT Cell ID {if $nb_samples > 1 }({$nb_samples}){/if}</center></th>
+				    <th class="string-sort" rowspan="2" id="th_id_1"><center>Sample {if $nb_samples > 1 }({$nb_samples}){/if}</center></th>
 				
 				    {if $metrics['loading']}
 				        <th colspan="{$loading_stats_count}"><center>Loading report</center></th>

ui/nG6/pi1/analyzes/RunAssembly.js

@@ -30,19 +30,19 @@ $(function () {
 		
     $('a[data-toggle="tab"]').on('shown', function () {
         if ($(this).attr("href") == "#contigs") {
-        	var oTable = $('#contigs-table').dataTable();
+        	var oTable = $('#contigs-table').DataTable();
         	oTable.fnDraw();
         	oTable.fnAdjustColumnSizing();
         } else if ($(this).attr("href") == "#isogroups") {
-        	var oTable = $('#isogroups-table').dataTable();
+        	var oTable = $('#isogroups-table').DataTable();
         	oTable.fnDraw();
         	oTable.fnAdjustColumnSizing();
         } else if ($(this).attr("href") == "#isotigs") {
-        	var oTable = $('#isotigs-table').dataTable();
+        	var oTable = $('#isotigs-table').DataTable();
         	oTable.fnDraw();
         	oTable.fnAdjustColumnSizing();
         } else if ($(this).attr("href") == "#ace") {
-        	var oTable = $('#ace-table').dataTable();
+        	var oTable = $('#ace-table').DataTable();
         	oTable.fnDraw();
         	oTable.fnAdjustColumnSizing();
         }

ui/nG6/pi1/class.tx_nG6_pi1.php

@@ -369,10 +369,6 @@ class tx_nG6_pi1 extends tslib_pibase {
 				
 					// Try to process the analyse template
 					try {
-						if (file_exists(t3lib_extMgm::extPath($this->extKey).'pi1/analyzes/'.$analyse['class'].'.js')) {
-							$GLOBALS['TSFE']->additionalHeaderData[$this->prefixId] .= '
-							<script type="text/javascript" src="'.t3lib_extMgm::siteRelPath($this->extKey).'pi1/analyzes/'.$analyse['class'].'.js"></script>';
-						}
 						$GLOBALS['TSFE']->additionalHeaderData[$this->prefixId] .= '
 						<script type="text/javascript" src="'.t3lib_extMgm::siteRelPath($this->extKey).'res/js/tx_nG6_pi1_analysis.js"></script>
 						<script type="text/javascript" src="'.t3lib_extMgm::siteRelPath($this->extKey).'res/js/jquery.venny.min.js"></script>
@@ -386,6 +382,12 @@ class tx_nG6_pi1 extends tslib_pibase {
 						<script type="text/javascript" src="'.t3lib_extMgm::siteRelPath($this->extKey).'res/js/jquery.jstree.min.js"></script>
 						<script type="text/javascript" src="'.t3lib_extMgm::siteRelPath($this->extKey).'res/js/d3-3.4.4.min.js"></script>
 						<link type="text/css" rel="stylesheet" media="screen" href="'.t3lib_extMgm::siteRelPath($this->extKey).'res/css/unitip.css"/>';
+						
+						if (file_exists(t3lib_extMgm::extPath($this->extKey).'pi1/analyzes/'.$analyse['class'].'.js')) {
+							$GLOBALS['TSFE']->additionalHeaderData[$this->prefixId] .= '
+							<script type="text/javascript" src="'.t3lib_extMgm::siteRelPath($this->extKey).'pi1/analyzes/'.$analyse['class'].'.js"></script>';
+						}
+						
 						return $smarty->fetch($analyse['class'].'.tpl');
 					} catch (Exception $e) {
 						return 'No template found for class ' . $analyse['class'];

ui/nG6/res/js/tx_nG6_pi1_analysis.js

@@ -197,7 +197,7 @@ $(function () {
 	
     	// Build dataTable
     	if ($(this).children("tbody").children("tr").children("td:has(input:checkbox)").length > 0) {
-			$(this).dataTable({
+			$(this).DataTable({
 				"scrollX"		: "90%",
 				"sScrollXInner"	: "100%",
 	  			"order"		: [[1, 'desc']],
@@ -205,7 +205,7 @@ $(function () {
 				"columnDefs": [ { "orderable": false, "targets":  0  } ]
 		  	});
 	  	} else {
-		    $(this).dataTable({
+		    $(this).DataTable({
 		    	"scrollX"		: "90%",
 				"sScrollXInner"	: "100%",
 	  			"order"		: [[1, 'desc']],

workflows/pacbio_qc/__init__.py

@@ -18,7 +18,6 @@
 from ng6.ng6workflow import NG6Workflow
 from ng6.utils import Utils
 
-
 class PacBioQualityCheck (NG6Workflow):
     
     def get_name(self):
@@ -31,9 +30,15 @@ class PacBioQualityCheck (NG6Workflow):
         self.add_parameter("nb_threads", "Number of threads to use for fastqc. Each thread will be allocated 250MB of memory.", default=3)
     
     def process(self):
+        sample_names = []
+        infiles = []
+        for sample in self.samples :
+            sample_names.append( sample.name )
+            infiles.append(sample.reads1[0])
+            
         add_pacbio_raw_file = self.add_component("AddPacBioRawFiles", [self.runobj, self.get_all_reads()])
-        h5tofastq =  self.add_component("H5toFastq", [self.get_all_reads()])
+        h5tofastq =  self.add_component("H5toFastq", [sample_names, infiles])
         fastqc = self.add_component("FastQC", [h5tofastq.output_fastqs, False, False, "fastqc.tar.gz", self.nb_threads], parent = h5tofastq)
-        self.add_component("RS_Subreads", [self.get_all_reads()])
+        self.add_component("RS_Subreads", [sample_names, infiles])
                     
         
\ No newline at end of file

workflows/pacbio_qc/components/h5tofastq.py

@@ -44,10 +44,10 @@ def h5_to_fastq(input_file, fastqfile):
 
 class H5toFastq (Analysis):
     
-    def define_parameters(self, input_files):
+    def define_parameters(self, sample_names, input_files):
+        self.add_parameter_list("sample_names", "sample names, each sample name must correspond to an input file", default=sample_names, required=True)
         self.add_input_file_list( "input_files", "Input pacbio bas.h5 files", default=input_files, file_format = h5file, required=True)
-        items = [os.path.basename(os.path.splitext(os.path.splitext(filename)[0])[0]) for filename in self.input_files]
-        self.add_output_file_list( 'output_fastqs', "Output fastq files", pattern="{basename_woext}.fastq.gz", file_format="fastq", items=items)
+        self.add_output_file_list( 'output_fastqs', "Output fastq files", pattern="{basename_woext}.fastq.gz", file_format="fastq", items=self.sample_names)
 
     def process(self):
         convertion = PythonFunction(h5_to_fastq, cmd_format="{EXE} {IN} {OUT}")
@@ -55,7 +55,7 @@ class H5toFastq (Analysis):
         
     def define_analysis(self):
         self.name = "H5toFastq"
-        self.description = "Convert pacbio bas.h5 to fastq files"
+        self.description = "Extract subreads of pacbio bas.h5 files to fastq files"
         self.software = "Python"
         self.options = ""
     

workflows/pacbio_qc/components/rs_subreads.py

@@ -73,13 +73,27 @@ def rs_subreads(inputfile, componentdir, smrtpipe, fofnToSmrtpipeInput, min_subr
     # run smrtpipe
     subprocess.check_call("%s --output=%s --params=%s  xml:%s >> %s"%(smrtpipe, outputdir, settings_xml, inputs_xml,stdout), shell = True)
 
+
+def extract_metrics(inputfile):
+    import h5py
+    import os
+    
+    from workflows.pacbio_qc.lib.pacbiolib import PacbioH5Reader
+    
+    reader = PacbioH5Reader(inputfile)
+    for baxh5 in reader.bash5.parts :
+        h5 = h5py.File(baxh5,'r')
+        metrics = h5['PulseData']['BaseCalls']['ZMWMetrics'] 
+    
+
 class RS_Subreads (Analysis):
     """
         implementation of pacbio RS_Subreads.1 protocol
         This module filters reads based on a minimum subread length, polymerase read quality and polymerase read length
     """
     
-    def define_parameters(self, input_files, min_subreads_length = 50, polymerase_read_qual = 75.0, polymerase_read_length = 50):
+    def define_parameters(self, sample_names, input_files, min_subreads_length = 50, polymerase_read_qual = 75.0, polymerase_read_length = 50):
+        self.add_parameter_list("sample_names", "sample names, each sample name must correspond to an input file", default=sample_names, required=True)
         self.add_input_file_list( "input_files", "Input pacbio bas.h5 files", default=input_files, file_format = h5file, required=True)
         self.add_parameter("min_subreads_length", "Subreads shorter than this value (in base pairs) are filtered out and excluded from analysis", default=min_subreads_length, type='int')
         self.add_parameter("polymerase_read_qual", "Polymerase reads with lower quality than this value are filtered out and excluded from analysis", default=polymerase_read_qual, type='float')
@@ -109,8 +123,9 @@ class RS_Subreads (Analysis):
         metrics = []
         
         for i,samplefile in enumerate(self.input_files) :
-            sample = os.path.basename(os.path.splitext(os.path.splitext(samplefile)[0])[0])
-            sample_outdir = os.path.join(self.output_directory, sample)
+            sample = self.sample_names[i]
+            sdir = os.path.basename(os.path.splitext(os.path.splitext(samplefile)[0])[0])
+            sample_outdir = os.path.join(self.output_directory, sdir)
             
             # loading 
             jsonfile = os.path.join(sample_outdir, 'results', 'filter_reports_loading.json')

workflows/pacbio_qc/data/pacbio_qc.conf

@@ -33,5 +33,6 @@ pacbio demo workflow
 Demo project
 
 --sample
+sample-name=Pacbio_sample
 read1=workflows/pacbio_qc/data/primary/lambda_v210/Analysis_Results/m130802_062611_ethan_c100542982550000001823084811241306_s1_p0.bas.h5
 

workflows/pacbio_qc/lib/pacbiolib.py

@@ -59,7 +59,7 @@ class PacbioH5Reader(object):
         return (np.clip(a, 0, 93).astype(np.uint8) + 33).tostring()  
 
     def __iter__(self):
-        for zmwRead in self.bash5.reads():
+        for zmwRead in self.bash5.subreads():
             yield Sequence(zmwRead.readName, zmwRead.readName, zmwRead.basecalls(), self.asciiFromQvs(zmwRead.QualityValue()))
 
 def h5file(ifile):

workflows/types.py

@@ -112,6 +112,11 @@ def email(val):
     
     return val
 
+def nospacestr(val):
+    if re.search(r"\s+", val):
+        raise argparse.ArgumentTypeError("The string value '%s' must not contain spaces" % val)
+    return val
+    
 def samplemetadata(metadata):
     key, val =  metadata.split(':', 2) 
     if not (key and val) :