Пример #1
0
    def __init__(self, config, parent=True):
        if parent:
            SeqLib.__init__(self, config)
        self.wt_dna = None
        self.wt_protein = None
        self.aligner = None
        self.aligner_cache = None

        try:
            self.set_wt(config['wild type']['sequence'], 
                        coding=config['wild type']['coding'])
            if 'align variants' in config:
                if config['align variants']:
                    self.aligner = Aligner()
                    self.aligner_cache = dict()

        except KeyError as key:
            raise EnrichError("Missing required config value '{key}'".format(key), 
                              self.name)

        if 'reference offset' in config['wild type']:
            try:
                self.reference_offset = int(config['wild type']
                                                  ['reference offset'])
            except ValueError:
                raise EnrichError("Invalid reference offset value", self.name)
        else:
            self.reference_offset = 0

        self.df_dict['variants'] = None
Пример #2
0
    def __init__(self, config, parent=True):
        if parent:
            SeqLib.__init__(self, config)
        self.wt_dna = None
        self.wt_protein = None
        self.aligner = None
        self.aligner_cache = None

        try:
            self.set_wt(config['wild type']['sequence'],
                        coding=config['wild type']['coding'])
            if 'align variants' in config:
                if config['align variants']:
                    self.aligner = Aligner()
                    self.aligner_cache = dict()

        except KeyError as key:
            raise EnrichError(
                "Missing required config value '{key}'".format(key), self.name)

        if 'reference offset' in config['wild type']:
            try:
                self.reference_offset = int(
                    config['wild type']['reference offset'])
            except ValueError:
                raise EnrichError("Invalid reference offset value", self.name)
        else:
            self.reference_offset = 0

        self.df_dict['variants'] = None
Пример #3
0
    def __init__(self, config, barcodevariant=False):
        self.barcodevariant = barcodevariant
        if not self.barcodevariant:
            SeqLib.__init__(self, config)
        try:
            if 'forward' in config['fastq'] and 'reverse' in config['fastq']:
                raise EnrichError("Multiple FASTQ files specified", self.name)
            elif 'forward' in config['fastq']:
                self.reads = config['fastq']['forward']
                self.revcomp_reads = False
            elif 'reverse' in config['fastq']:
                self.reads = config['fastq']['reverse']
                self.revcomp_reads = True
            else:
                raise KeyError("'forward' or 'reverse'")

            if 'start' in config['fastq']:
                self.bc_start = config['fastq']['start']
            else:
                self.bc_start = 1
            if 'length' in config['fastq']:
                self.bc_length = config['fastq']['length']
            else:
                self.bc_length = 2147483647  # longer than any read... for now

            if 'min count' in config['barcodes']:
                self.min_count = config['barcodes']['min count']
            else:
                self.min_count = 0

            self.set_filters(config['filters'], {
                'min quality': 0,
                'avg quality': 0,
                'chastity': False
            })
        except KeyError as key:
            raise EnrichError(
                "Missing required config value {key}".format(key=key),
                self.name)

        try:
            check_fastq(self.reads)
        except IOError as fqerr:
            raise EnrichError("FASTQ file error: {error}".format(error=fqerr),
                              self.name)

        self.df_dict['barcodes'] = None
        if self.min_count > 0:
            self.df_dict['barcodes_low_abundance'] = None
Пример #4
0
    def __init__(self, config, barcodevariant=False):
        self.barcodevariant = barcodevariant
        if not self.barcodevariant:
            SeqLib.__init__(self, config)
        try:
            if 'forward' in config['fastq'] and 'reverse' in config['fastq']:
                raise EnrichError("Multiple FASTQ files specified", self.name)
            elif 'forward' in config['fastq']:
                self.reads = config['fastq']['forward']
                self.revcomp_reads = False
            elif 'reverse' in config['fastq']:
                self.reads = config['fastq']['reverse']
                self.revcomp_reads = True
            else:
                raise KeyError("'forward' or 'reverse'")

            if 'start' in config['fastq']:
                self.bc_start = config['fastq']['start']
            else:
                self.bc_start = 1
            if 'length' in config['fastq']:
                self.bc_length = config['fastq']['length']
            else:
                self.bc_length = 2147483647 # longer than any read... for now

            if 'min count' in config['barcodes']:
                self.min_count = config['barcodes']['min count']
            else:
                self.min_count = 0

            self.set_filters(config['filters'], {'min quality' : 0,
                                      'avg quality' : 0,
                                      'chastity' : False})
        except KeyError as key:
            raise EnrichError("Missing required config value {key}".format(key=key), self.name)

        try:
            check_fastq(self.reads)
        except IOError as fqerr:
            raise EnrichError("FASTQ file error: {error}".format(error=fqerr), self.name)

        self.df_dict['barcodes'] = None
        if self.min_count > 0:
            self.df_dict['barcodes_low_abundance'] = None
Пример #5
0
    def __init__(self, config, parent=True):
        if parent:
            SeqLib.__init__(self, config)
        try:
            if "forward" in config["fastq"] and "reverse" in config["fastq"]:
                raise EnrichError("Multiple FASTQ files specified", self.name)
            elif "forward" in config["fastq"]:
                self.reads = config["fastq"]["forward"]
                self.revcomp_reads = False
            elif "reverse" in config["fastq"]:
                self.reads = config["fastq"]["reverse"]
                self.revcomp_reads = True
            else:
                raise KeyError("'forward' or 'reverse'")

            if "start" in config["fastq"]:
                self.bc_start = config["fastq"]["start"]
            else:
                self.bc_start = 1
            if "length" in config["fastq"]:
                self.bc_length = config["fastq"]["length"]
            else:
                self.bc_length = 2147483647  # longer than any read... for now

            if "min count" in config["barcodes"]:
                self.min_count = config["barcodes"]["min count"]
            else:
                self.min_count = 0

            self.set_filters(config["filters"], {"min quality": 0, "avg quality": 0, "chastity": False})
        except KeyError as key:
            raise EnrichError("Missing required config value %s" % key, self.name)

        try:
            check_fastq(self.reads)
        except IOError as fqerr:
            raise EnrichError("FASTQ file error: %s" % fqerr, self.name)

        self.counts["barcodes"] = None