Added skip-option

bin/schavott

@@ -41,9 +41,9 @@ def parse_arguments():
                         help='''Which scaffolder to use.''')
     parser.add_argument('--sspace_path', '-p',
                         help='Path to SSPACE (Only for scaffolding)')
-    parser.add_argument('--min_read_length', '-l', default=5000,
+    parser.add_argument('--min_read_length', '-l', default=0,
                         help='''Minimum read length from MinION to use.''')
-    parser.add_argument('--min_quality', '-q', default=9,
+    parser.add_argument('--min_quality', '-q', default=0,
                         help='''Minimum quality for reads from MinION to use.''')
     parser.add_argument('--watch', '-w', required=True,
                         help='Directory to watch for fast5 files')
@@ -53,6 +53,8 @@ def parse_arguments():
                         choices=['time', 'reads'],
                         help='''Use timer or read count.\
                         [reads]''')
+    parser.add_argument('--skip', '-j',
+                        help='''Skips the first j read of the sequencing''')
     parser.add_argument('--intensity', '-i', default=100,
                         help='''How often the scaffolding process should run.\
                         If run mode is set to reads, scaffolding will run\

move_fast5.py

@@ -26,7 +26,7 @@
 times = times.sort_values(["moveTimes"])
 # Create a list with all filenames in the dataframe
 path = list(times['filename'])
-
+print(times["unix_timestamp_end"])
 # Wait until each read is completed, then move it to the output_path
 prev_time = 0
 print("Start copying files to " + output_path)

schavott/MainApp.py

@@ -8,18 +8,22 @@
 import schavott.Assembler
 
 class MainApp(object):
+    # TODO: Add switch to discard xx number of reads in the beginning
+    # to avoid reads from wrong organism in the scaffolding.
     def __init__(self, args):
         self.readQue = []
         self.reads = []
         self.passCounter = 0
         self.failCounter = 0
         self.runMode = args.run_mode
+        self.skip = args.skip
+        self.skip_counter = 0
         self.output = args.output
         self.plot = args.plot
         self.triggerMode = args.trigger_mode
         # Will be added to argument list
         self.readLengths = []
-        self.minQuality = args.min_quality
+        self.minQuality = int(args.min_quality)
         self.minLength = int(args.min_read_length)
         self._reset_timer()
         self._set_intensity(args.intensity)
@@ -53,36 +57,40 @@ def __init__(self, args):
     def open_read(self, filePath):
         """Open downloaded fast5"""
         # Try to read fast5 file.
-        try:
-            head, tail = os.path.split(filePath)
-            root, ext = os.path.splitext(tail)
-            read = schavott.ReadData.ReadData(filePath)
-            self.add_read(read)
-            if read.get_twod():
-                self.readLengths.append(read.get_length())
-                if read.get_quality() >= self.minQuality and read.get_length() >= self.minLength:
-                    read.set_pass()
-                    with open(os.path.join(self.output, "reads_fasta", root) + '.fasta', 'w') as f:
-                        f.write(str(read.get_fasta()))
-                    f.close()
-            self.update_counter(read)
-            #print("PassCounter: " + str(self.passCounter))
-            #print("FailCounter: " + str(self.failCounter))
-            #print("Reads not possible to open: " + str(len(self.readQue)))
-        except AttributeError:
-            self.add_to_readQue(filePath)
-
-
-
-        # If the file is not completly downloaded or corrupt
-
+        self.skip_counter += 1
+        if self.skip_counter > self.skip:
+            try:
+                head, tail = os.path.split(filePath)
+                root, ext = os.path.splitext(tail)
+                read = schavott.ReadData.ReadData(filePath)
+                self.add_read(read)
+                # Change if statement to if read.get_twod(): to use 2D reads, depricated from ONT.
+                if False:
+                    self.readLengths.append(read.get_length())
+                    if read.get_quality() >= self.minQuality and read.get_length() >= self.minLength:
+                        read.set_pass()
+                        with open(os.path.join(self.output, "reads_fasta", root) + '.fasta', 'w') as f:
+                            f.write(str(read.get_fasta()))
+                        f.close()
+                        self.update_counter(read)
+                    else:
+                        self.readLengths.append(read.get_length_1d())
+                        if read.get_quality_1d() >= self.minQuality and read.get_length_1d() >= self.minLength:
+                        read.set_pass()
+                        with open(os.path.join(self.output, "reads_fasta", root) + '.fasta', 'w') as f:
+                            f.write(str(read.get_fasta_1d()))
+                        f.close()
+                        self.update_counter(read)
+            except AttributeError:
+                self.add_to_readQue(filePath)
 
     def add_read(self, read):
         self.reads.append(read)
 
     def update_counter(self, read):
         if read.get_pass():
             self.passCounter += 1
+            print('Reads: ' + str(self.passCounter))
             self.run_scaffold()
         else:
             self.failCounter += 1

schavott/ReadData.py

@@ -8,17 +8,24 @@ def __init__(self, filePath):
         self.open_read(filePath)
         self.passQuality = False
         self.twod = False
+        self.oned = False
+        self.set_time()
+        self.set_1d()
+        self.set_length_1d()
+        self.set_quality_1d()
+        self.set_fastq_1d()
+        self.set_fasta_1d()
         self.set_2d()
         self.set_length()
         self.set_quality()
-        self.set_time()
         self.set_fastq()
         self.set_fasta()
         self.close_read()
 
     def open_read(self, path):
         try:
             self._fast5 = h5py.File(path)
+            #print('Read: ' + path)
         except IOError:
             print('File was not possible to open')
 
@@ -27,17 +34,40 @@ def close_read(self):
         self._fast5.close()
 
     def set_2d(self):
-
         try:
             self._fast5['Analyses']['Basecall_2D_000']['BaseCalled_2D']
             self.twod = True
+            #print('Has 2D')
         except:
-            print('1D')
+            print('No 2D sequence')
+
+    def set_1d(self):
+        try:
+            self._fast5['Analyses']['Basecall_1D_000']['BaseCalled_template']
+            self.oned = True
+        except:
+            print('No template sequence')
+
+    def set_length_1d(self):
+        if self.oned:
+            self.length_1d = self._fast5['Analyses']['Basecall_1D_000']['Summary']['basecall_1d_template'].attrs['sequence_length']
+            #print('Read length (template): ' + str(self.length_1d))
+
+    def set_fastq_1d(self):
+        if self.oned:
+            self.fastq_1d = str(np.array(self._fast5['Analyses']['Basecall_1D_000']['BaseCalled_template']['Fastq']))
+
+    def set_fasta_1d(self):
+        if self.oned:
+            raw_fasta = self.fastq_1d.split('\n')[:2]
+            header = '>' + raw_fasta[0][3:] + '\n'
+            seq = raw_fasta[1] + '\n'
+            self.fasta_1d = header + seq
 
     def set_length(self):
         if self.twod:
             self.length = self._fast5['Analyses']['Basecall_2D_000']['Summary']['basecall_2d'].attrs['sequence_length']
-            #print('Read length: ' + str(self.length))
+            #print('Read length (2d): ' + str(self.length))
 
     def set_fastq(self):
         if self.twod:
@@ -56,14 +86,18 @@ def set_time(self):
         for key in self._fast5['Raw']['Reads'].keys():
             startSample = self._fast5['Raw']['Reads'][key].attrs['start_time']
             durationSample = self._fast5['Raw']['Reads'][key].attrs['duration']
-        self.startTime = datetime.datetime.fromtimestamp(int(expStartTime) + float(startSample)/samplingRate + float(durationSample)/samplingRate)
-        #self.startTime = datetime.datetime.now().time()
+        #self.startTime = datetime.datetime.fromtimestamp(int(expStartTime) + float(startSample)/samplingRate + float(durationSample)/samplingRate)
+        self.startTime = datetime.datetime.now().time()
 
     def set_quality(self):
         if self.twod:
             self.quality = self._fast5['Analyses']['Basecall_2D_000']['Summary']['basecall_2d'].attrs['mean_qscore']
             #print('Read quality:' + str(self.quality))
 
+    def set_quality_1d(self):
+        if self.oned:
+            self.quality_1d = self._fast5['Analyses']['Basecall_1D_000']['Summary']['basecall_1d_template'].attrs['mean_qscore']
+
     def set_pass(self):
         self.passQuality = True
 
@@ -88,5 +122,17 @@ def get_time(self):
     def get_twod(self):
         return self.twod
 
+    def get_oned(self):
+        return self.oend
+
+    def get_quality_1d(self):
+        return self.quality_1d
+
+    def get_length_1d(self):
+        return self.length_1d
 
+    def get_fastq_1d(self):
+        return self.fastq_1d
 
+    def get_fasta_1d(self):
+        return self.fasta_1d

schavott/Scaffold.py

@@ -57,8 +57,8 @@ def run_sspace(self, passCounter):
         self._create_single_fasta()
         # Run SSPACE without alignment step
         args = ['perl', self.sspacePath, '-c', self.contigPath,
-                '-p', self.npReads, '-i', '70', '-a', '1500', '-g' '-5000',
-                '-b', outdir]
+                '-p', self.npReads, '-i', '70', '-b', outdir, '-g', '-5000', '-t', '18']
+        print(args)
 
         process = subprocess.Popen(args, stdin=subprocess.PIPE,
                                    stdout=subprocess.PIPE)