Exemple #1
0
 def convert(filename):
     info = io.get_file_info(filename)
     ok = selection.matches('type-fastq:[compression-none/compression-gzip/compression-bzip2]', info)
     if ok:
         return filename            
     result_name = tempname()
     with open(result_name,'wb') as f:
         for name, seq, qual in io.read_sequences(filename, qualities='required'):
             io.write_fastq(f, name, seq, qual)
     return result_name
Exemple #2
0
 def convert(filename):
     info = io.get_file_info(filename)
     ok = selection.matches(
         'type-fastq:[compression-none/compression-gzip/compression-bzip2]',
         info)
     if ok:
         return filename
     result_name = tempname()
     with open(result_name, 'wb') as f:
         for name, seq, qual in io.read_sequences(
                 filename, qualities='required'):
             io.write_fastq(f, name, seq, qual)
     return result_name
Exemple #3
0
    def run(self):
        f = self.begin_output()

        for filename in self.filenames:
            info = io.get_file_info(filename)

            any = False

            name = os.path.splitext(os.path.split(filename)[1])[0]

            if info.matches('sequences'):
                total = 0
                total_length = 0
                for seq in io.read_sequences(filename, qualities=True):
                    total += 1
                    total_length += len(seq[1])
                print >> f, grace.datum(name, 'sequences', total)
                print >> f, grace.datum(name, 'total bases', total_length)
                if total:
                    print >> f, grace.datum(name, 'average length',
                                            float(total_length) / total)
                print >> f
                any = True

            if info.matches('annotations'):
                total = 0
                counts = {}
                for item in annotation.read_annotations(filename, "/"):
                    total += 1
                    counts[item.type] = counts.get(item.type, 0) + 1

                print >> f, grace.datum(name, 'features', total)
                for key in sorted(counts):
                    print >> f, grace.datum(name, key + ' features',
                                            counts[key])
                print >> f
                any = True

            if info.matches('type-vcf'):
                reader_f = io.open_possibly_compressed_file(filename)
                reader = vcf.Reader(reader_f)
                n = 0
                for item in reader:
                    n += 1
                print >> f, grace.datum(name, 'variants', n)
                any = True

            if not any:
                raise grace.Error('Don\'t know what to do with ' + filename)

        self.end_output(f)
Exemple #4
0
    def run(self):
        f = self.begin_output()
    
        for filename in self.filenames:
            info = io.get_file_info(filename)
            
            any = False
            
            name = os.path.splitext(os.path.split(filename)[1])[0]
            
            if info.matches('sequences'):
                total = 0
                total_length = 0
                for seq in io.read_sequences(filename, qualities=True):
                    total += 1
                    total_length += len(seq[1])
                print >> f, grace.datum(name, 'sequences', total)
                print >> f, grace.datum(name, 'total bases', total_length)
                if total:
                    print >> f, grace.datum(name, 'average length', float(total_length)/total)
                print >> f
                any = True
            
            if info.matches('annotations'):
                total = 0
                counts = { }
                for item in annotation.read_annotations(filename):
                    total += 1
                    counts[item.type] = counts.get(item.type,0)+1
                                
                print >> f, grace.datum(name, 'features', total)
                for key in sorted(counts):
                    print >> f, grace.datum(name, key + ' features', counts[key])
                print >> f
                any = True
            
            if info.matches('type-vcf'):
                reader_f = io.open_possibly_compressed_file(filename)
                reader = vcf.Reader(reader_f)
                n = 0
                for item in reader:
                    n += 1
                print >> f, grace.datum(name, 'variants', n)
                any = True
            
            if not any:
                raise grace.Error('Don\'t know what to do with ' + filename)

        self.end_output(f)