Logo Search packages:      
Sourcecode: python-biopython version File versions  Download package

Record.py

00001 """Hold GenBank data in a straightforward format.

classes:
o Record - All of the information in a GenBank record.
o Reference - hold reference data for a record.
o Feature - Hold the information in a Feature Table.
o Qualifier - Qualifiers on a Feature.
"""
# local stuff
import Bio.GenBank

00012 def _wrapped_genbank(information, indent, wrap_space = 1, split_char = " "):
    """Write a line of GenBank info that can wrap over multiple lines.

    This takes a line of information which can potentially wrap over
    multiple lines, and breaks it up with carriage returns and
    indentation so it fits properly into a GenBank record.

    Arguments:

    o information - The string holding the information we want
    wrapped in GenBank method.

    o indent - The indentation on the lines we are writing.

    o wrap_space - Whether or not to wrap only on spaces in the
    information.

    o split_char - A specific character to split the lines on. By default
    spaces are used.
    """
    info_length = Record.GB_LINE_LENGTH - indent

    if wrap_space:
        info_parts = information.split(split_char)
    else:
        cur_pos = 0
        info_parts = []
        while cur_pos < len(information):
            info_parts.append(information[cur_pos: cur_pos + info_length])
            cur_pos += info_length
            
    # first get the information string split up by line
    output_parts = []
    cur_part = ""
    for info_part in info_parts:
        if len(cur_part) + 1 + len(info_part) > info_length:
            if cur_part:
                if split_char != " ":
                    cur_part += split_char
                output_parts.append(cur_part)
            cur_part = info_part
        else:
            if cur_part == "":
                cur_part = info_part
            else:
                cur_part += split_char + info_part

    # add the last bit of information to the output
    if cur_part:
        output_parts.append(cur_part)

    # now format the information string for return
    output_info = output_parts[0] + "\n"
    for output_part in output_parts[1:]:
        output_info += " " * indent + output_part + "\n"

    return output_info            
        
00070 def _indent_genbank(information, indent):
    """Write out information with the specified indent.

    Unlike _wrapped_genbank, this function makes no attempt to wrap
    lines -- it assumes that the information already has newlines in the
    appropriate places, and will add the specified indent to the start of
    each line.
    """
    # split the info into lines based on line breaks
    info_parts = information.split("\n")

    # the first line will have no indent
    output_info = info_parts[0] + "\n"
    for info_part in info_parts[1:]:
        output_info += " " * indent + info_part + "\n"

    return output_info

00088 class Record:
    """Hold GenBank information in a format similar to the original record.

    The Record class is meant to make data easy to get to when you are
    just interested in looking at GenBank data.

    Attributes:
    o locus - The name specified after the LOCUS keyword in the GenBank
    record. This may be the accession number, or a clone id or something else.
    o size - The size of the record.
    o residue_type - The type of residues making up the sequence in this
    record. Normally something like RNA, DNA or PROTEIN, but may be as
    esoteric as 'ss-RNA circular'.
    o data_file_division - The division this record is stored under in
    GenBank (ie. PLN -> plants; PRI -> humans, primates; BCT -> bacteria...)
    o date - The date of submission of the record, in a form like '28-JUL-1998'
    o accession - list of all accession numbers for the sequence.
    o nid - Nucleotide identifier number.
    o pid - Proteint identifier number
    o version - The accession number + version (ie. AB01234.2)
    o db_source - Information about the database the record came from
    o gi - The NCBI gi identifier for the record.
    o keywords - A list of keywords related to the record.
    o segment - If the record is one of a series, this is info about which
    segment this record is (something like '1 of 6').
    o source - The source of material where the sequence came from.
    o organism - The genus and species of the organism (ie. 'Homo sapiens')
    o taxonomy - A listing of the taxonomic classification of the organism,
    starting general and getting more specific.
    o references - A list of Reference objects.
    o comment - Text with any kind of comment about the record.
    o features - A listing of Features making up the feature table.
    o base_counts - A string with the counts of bases for the sequence.
    o origin - A string specifying info about the origin of the sequence.
    o sequence - A string with the sequence itself.
    o contig - A string of location information for a CONTIG in a RefSeq
    file.
    """
    # constants for outputting GenBank information
    GB_LINE_LENGTH = 79
    GB_BASE_INDENT = 12
    GB_FEATURE_INDENT = 21
    GB_INTERNAL_INDENT = 2
    GB_OTHER_INTERNAL_INDENT = 3
    GB_FEATURE_INTERNAL_INDENT = 5
    GB_SEQUENCE_INDENT = 9

    BASE_FORMAT = "%-" + str(GB_BASE_INDENT) + "s"
    INTERNAL_FORMAT = " " * GB_INTERNAL_INDENT + "%-" + \
                      str(GB_BASE_INDENT - GB_INTERNAL_INDENT) + "s"
    OTHER_INTERNAL_FORMAT = " " * GB_OTHER_INTERNAL_INDENT + "%-" + \
                            str(GB_BASE_INDENT - GB_OTHER_INTERNAL_INDENT) + \
                            "s"

    BASE_FEATURE_FORMAT = "%-" + str(GB_FEATURE_INDENT) + "s"
    INTERNAL_FEATURE_FORMAT = " " * GB_FEATURE_INTERNAL_INDENT + "%-" + \
                              str(GB_FEATURE_INDENT -
                                  GB_FEATURE_INTERNAL_INDENT) + "s"
    SEQUENCE_FORMAT = "%" + str(GB_SEQUENCE_INDENT) + "s"
    
    def __init__(self):
        self.locus = ''
        self.size = ''
        self.residue_type = ''
        self.data_file_division = ''
        self.date = ''
        self.definition = ''
        self.accession = []
        self.nid = ''
        self.pid = ''
        self.version = ''
        self.db_source = ''
        self.gi = ''
        self.keywords = []
        self.segment = ''
        self.source = ''
        self.organism = ''
        self.taxonomy = []
        self.references = []
        self.comment = ''
        self.features = []
        self.base_counts = ''
        self.origin = ''
        self.sequence = ''
        self.contig = ''
        self.primary=[]

00175     def __str__(self):
        """Provide a GenBank formatted output option for a Record.

        The objective of this is to provide an easy way to read in a GenBank
        record, modify it somehow, and then output it in 'GenBank format.'
        We are striving to make this work so that a parsed Record that is
        output using this function will look exactly like the original
        record.

        Much of the output is based on format description info at:

        ftp://ncbi.nlm.nih.gov/genbank/gbrel.txt
        """
        output = self._locus_line()
        output += self._definition_line()
        output += self._accession_line()
        output += self._version_line()
        output += self._nid_line()
        output += self._pid_line()
        output += self._keywords_line()
        output += self._db_source_line()
        output += self._segment_line()
        output += self._source_line()
        output += self._organism_line()
        for reference in self.references:
            output += str(reference)
        output += self._comment_line()
        output += self._features_line()
        for feature in self.features:
            output += str(feature)
        output += self._base_count_line()
        output += self._origin_line()
        output += self._sequence_line()
        output += self._contig_line()
        output += "//"
        return output
            
00212     def _locus_line(self):
        """Provide the output string for the LOCUS line.
        """
        output = "LOCUS"
        output += " " * 7 # 6-12 spaces
        output += "%-9s" % self.locus
        output += " " # 22 space
        output += "%7s" % self.size
        if self.residue_type.find("PROTEIN") >= 0:
            output += " aa"
        else:
            output += " bp "

        # treat circular types differently, since they'll have long residue
        # types
        if self.residue_type.find("circular") >= 0:
             output += "%17s" % self.residue_type
        # second case: ss-DNA types of records
        elif self.residue_type.find("-") >= 0:
            output += "%7s" % self.residue_type
            output += " " * 10 # spaces for circular
        else:
            output += " " * 3 # spaces for stuff like ss-
            output += "%-4s" % self.residue_type
            output += " " * 10 # spaces for circular

        output += " " * 2
        output += "%3s" % self.data_file_division
        output += " " * 7 # spaces for 56-63
        output += "%11s" % self.date
        output += "\n"
        return output

00245     def _definition_line(self):
        """Provide output for the DEFINITION line.
        """
        output = Record.BASE_FORMAT % "DEFINITION"
        output += _wrapped_genbank(self.definition, Record.GB_BASE_INDENT)
        return output

00252     def _accession_line(self):
        """Output for the ACCESSION line.
        """
        output = Record.BASE_FORMAT % "ACCESSION"

        acc_info = ""
        for accession in self.accession:
            acc_info += "%s " % accession
        # strip off an extra space at the end
        acc_info = acc_info.rstrip()
        output += _wrapped_genbank(acc_info, Record.GB_BASE_INDENT)
        
        return output

00266     def _version_line(self):
        """Output for the VERSION line.
        """
        output = Record.BASE_FORMAT % "VERSION"
        output += self.version
        output += "  GI:"
        output += "%s\n" % self.gi
        return output

00275     def _nid_line(self):
        """Output for the NID line. Use of NID is obsolete in GenBank files.
        """
        if self.nid:
            output = Record.BASE_FORMAT % "NID"
            output += "%s\n" % self.nid
        else:
            output = ""
        return output

00285     def _pid_line(self):
        """Output for PID line. Presumedly, PID usage is also obsolete.
        """
        if self.pid:
            output = Record.BASE_FORMAT % "PID"
            output += "%s\n" % self.pid
        else:
            output = ""
        return output

00295     def _keywords_line(self):
        """Output for the KEYWORDS line.
        """
        output = ""
        if len(self.keywords) >= 0:
            output +=  Record.BASE_FORMAT % "KEYWORDS"
            keyword_info = ""
            for keyword in self.keywords:
                keyword_info += "%s; " % keyword
            # replace the ; at the end with a period
            keyword_info = keyword_info[:-2]
            keyword_info += "."
            
            output += _wrapped_genbank(keyword_info,
                                       Record.GB_BASE_INDENT)

        return output

00313     def _db_source_line(self):
        """Output for DBSOURCE line.
        """
        if self.db_source:
            output = Record.BASE_FORMAT % "DBSOURCE"
            output += "%s\n" % self.db_source
        else:
            output = ""
        return output

00323     def _segment_line(self):
        """Output for the SEGMENT line.
        """
        output = ""
        if self.segment:
            output += Record.BASE_FORMAT % "SEGMENT"
            output += _wrapped_genbank(self.segment, Record.GB_BASE_INDENT)
        return output

00332     def _source_line(self):
        """Output for SOURCE line on where the sample came from.
        """
        output = Record.BASE_FORMAT % "SOURCE"
        output += _wrapped_genbank(self.source, Record.GB_BASE_INDENT)
        return output
    
00339     def _organism_line(self):
        """Output for ORGANISM line with taxonomy info.
        """
        output = Record.INTERNAL_FORMAT % "ORGANISM"
        output += "%s\n" % self.organism
        output += " " * Record.GB_BASE_INDENT
        taxonomy_info = ""
        for tax in self.taxonomy:
            taxonomy_info += "%s; " % tax
        # replace the ; at the end with a period
        taxonomy_info = taxonomy_info[:-2]
        taxonomy_info += "."
        output += _wrapped_genbank(taxonomy_info, Record.GB_BASE_INDENT)

        return output
            
00355     def _comment_line(self):
        """Output for the COMMENT lines.
        """
        output = ""
        if self.comment:
            output += Record.BASE_FORMAT % "COMMENT"
            output += _indent_genbank(self.comment,
                                      Record.GB_BASE_INDENT)
        return output

00365     def _features_line(self):
        """Output for the FEATURES line.
        """
        output = ""
        if len(self.features) > 0:
            output += Record.BASE_FEATURE_FORMAT % "FEATURES"
            output += "Location/Qualifiers\n"
        return output

00374     def _base_count_line(self):
        """Output for the BASE COUNT line with base information.
        """
        output = ""
        if self.base_counts:
            output += Record.BASE_FORMAT % "BASE COUNT  "
            # split up the base counts into their individual parts
            count_parts = self.base_counts.split(" ")
            while '' in count_parts:
                count_parts.remove('')
            # deal with the standard case, with a normal origin line
            # like: 474 a    356 c    428 g    364 t
            if len(count_parts) % 2 == 0:
                while len(count_parts) > 0:
                    count_info = count_parts.pop(0)
                    count_type = count_parts.pop(0)

                    output += "%7s %s" % (count_info, count_type)
            # deal with ugly ORIGIN lines like:
            # 1311257 a2224835 c2190093 g1309889 t
            # by just outputting the raw information
            else:
                output += self.base_counts
            output += "\n"
        return output

00400     def _origin_line(self):
        """Output for the ORIGIN line
        """
        output = ""
        # only output the ORIGIN line if we have a sequence
        if self.sequence:
            output += Record.BASE_FORMAT % "ORIGIN"
            if self.origin:
                output += _wrapped_genbank(self.origin,
                                           Record.GB_BASE_INDENT)
            else:
                output += "\n"
        return output

00414     def _sequence_line(self):
        """Output for all of the sequence.
        """
        output = ""
        if self.sequence:
            cur_seq_pos = 0
            while cur_seq_pos < len(self.sequence):
                output += Record.SEQUENCE_FORMAT % str(cur_seq_pos + 1)

                for section in range(6):
                    start_pos = cur_seq_pos + section * 10
                    end_pos = start_pos + 10
                    seq_section = self.sequence[start_pos:end_pos]
                    output += " %s" % seq_section.lower()

                    # stop looping if we are out of sequence
                    if end_pos > len(self.sequence):
                        break
                
                output += "\n"
                cur_seq_pos += 60
        return output

00437     def _contig_line(self):
        """Output for CONTIG location information from RefSeq.
        """
        output = ""
        if self.contig:
            output += Record.BASE_FORMAT % "CONTIG"
            output += _wrapped_genbank(self.contig,
                                       Record.GB_BASE_INDENT, split_char = ',')
        return output

00447 class Reference:
    """Hold information from a GenBank reference.

    Attributes:
    o number - The number of the reference in the listing of references.
    o bases - The bases in the sequence the reference refers to.
    o authors - String with all of the authors.
    o consrtm - Consortium the authors belong to. 
    o title - The title of the reference.
    o journal - Information about the journal where the reference appeared.
    o medline_id - The medline id for the reference.
    o pubmed_id - The pubmed_id for the reference.
    o remark - Free-form remarks about the reference.
    """
    def __init__(self):
        self.number = ''
        self.bases = ''
        self.authors = ''
        self.consrtm = ''
        self.title = ''
        self.journal = ''
        self.medline_id = ''
        self.pubmed_id = ''
        self.remark = ''

    def __str__(self):
        output = self._reference_line()
        output += self._authors_line()
        output += self._consrtm_line()
        output += self._title_line()
        output += self._journal_line()
        output += self._medline_line()
        output += self._pubmed_line()
        output += self._remark_line()
        
        return output

00484     def _reference_line(self):
        """Output for REFERENCE lines.
        """
        output = Record.BASE_FORMAT % "REFERENCE"
        if self.number:
            if self.bases:
                output += "%-3s" % self.number
                output += "%s" % self.bases
            else:
                output += "%s" % self.number

        output += "\n"
        return output

00498     def _authors_line(self):
        """Output for AUTHORS information.
        """
        output = ""
        if self.authors:
            output += Record.INTERNAL_FORMAT % "AUTHORS"
            output += _wrapped_genbank(self.authors, Record.GB_BASE_INDENT)
        return output

00507     def _consrtm_line(self):
        """Output for CONSRTM information.
        """
        output = ""
        if self.consrtm:
            output += Record.INTERNAL_FORMAT % "CONSRTM"
            output += _wrapped_genbank(self.consrtm, Record.GB_BASE_INDENT)
        return output

00516     def _title_line(self):
        """Output for TITLE information.
        """
        output = ""
        if self.title:
            output += Record.INTERNAL_FORMAT % "TITLE"
            output += _wrapped_genbank(self.title, Record.GB_BASE_INDENT)
        return output

00525     def _journal_line(self):
        """Output for JOURNAL information.
        """
        output = ""
        if self.journal:
            output += Record.INTERNAL_FORMAT % "JOURNAL"
            output += _wrapped_genbank(self.journal, Record.GB_BASE_INDENT)
        return output

00534     def _medline_line(self):
        """Output for MEDLINE information.
        """
        output = ""
        if self.medline_id:
            output += Record.INTERNAL_FORMAT % "MEDLINE"
            output += self.medline_id + "\n"
        return output
    
00543     def _pubmed_line(self):
        """Output for PUBMED information.
        """
        output = ""
        if self.pubmed_id:
            output += Record.OTHER_INTERNAL_FORMAT % "PUBMED"
            output += self.pubmed_id + "\n"
        return output
    
00552     def _remark_line(self):
        """Output for REMARK information.
        """
        output = ""
        if self.remark:
            output += Record.INTERNAL_FORMAT % "REMARK"
            output += _wrapped_genbank(self.remark, Record.GB_BASE_INDENT)
        return output
    
00561 class Feature:
    """Hold information about a Feature in the Feature Table of GenBank record.

    Attributes:
    o key - The key name of the featue (ie. source)
    o location - The string specifying the location of the feature.
    o qualfiers - A listing Qualifier objects in the feature.
    """
    def __init__(self):
        self.key = ''
        self.location = ''
        self.qualifiers = []

    def __str__(self):
        output = Record.INTERNAL_FEATURE_FORMAT % self.key
        output += _wrapped_genbank(self.location, Record.GB_FEATURE_INDENT,
                                   split_char = ',')
        for qualifier in self.qualifiers:
            output += " " * Record.GB_FEATURE_INDENT
            
            # determine whether we can wrap on spaces
            space_wrap = 1
            for no_space_key in \
                Bio.GenBank._BaseGenBankConsumer.remove_space_keys:
                if qualifier.key.find(no_space_key) >= 0:
                    space_wrap = 0
            
            output += _wrapped_genbank(qualifier.key + qualifier.value,
                                       Record.GB_FEATURE_INDENT, space_wrap)
        return output

00592 class Qualifier:
    """Hold information about a qualifier in a GenBank feature.

    Attributes:
    o key - The key name of the qualifier (ie. /organism=)
    o value - The value of the qualifier ("Dictyostelium discoideum").
    """
    def __init__(self):
        self.key = ''
        self.value = ''

Generated by  Doxygen 1.6.0   Back to index