biopy_multi_class.py

# ~/devel/pyDev/biopy_multi_class.py
# pastebin.com/wNRGXJeM

# renamed the file: "HPA88HDJ016-Alignment.xml" to "blast_output.xml" and used it as the database being parsed.
FILE_INPUT = open("blast_output.xml")   #   // set FILE_INPUT equal to the contents of blast_output.xml.
MINIMUM_INT = 20    #   // set MINIMUM_INT to 20 (threshold integer)
from Bio.Blast import NCBIXML   #   // import the specialty module NCBXML from Bio.Blast.
PARSE_FILE = NCBIXML.parse(FILE_INPUT)  # // use the parse() function, from the NCBIXML module, on FILE_INPUT and set PARSE_FILE as the result. we now will use PARSE_FILE as our iterator.
READ_LINE = PARSE_FILE.next()   #   // tells the PARSE_FILE iterator to use the next() method to parse each line into the READ_LINE variable.

# though commented heavily, this script is fully executable. the intention of writing the script in this way was
# so that various sections of the code could be commented and uncommented to show various results when executed.
# it was my hope that writing a script in this fashion would help you determine the various data sets and how they
# can be displayed and manipulated.

""" [UNCOMMENT FOR EXECUTION]
for READ_LINE in PARSE_FILE:    # for each line in PARSE_FILE, begin to loop.
    for alignment in READ_LINE.alignments:  #   // for each alignment value in the alignments class, begin nested loop.
        for hsp in alignment.hsps:  #   // for each hsp value in the hsps class, begin the second nested loop.
            if hsp.identities > MINIMUM_INT:    #   // if the value of the each record's identities field is greater than MINIMUM_INT execute the following.
                print '\n***Seperator*** \n\n ALIGNMENT_TITLE: ', alignment.title
                print 'ALIGNMENT_LENGTH: ', alignment.length
                print 'HSP_SCORE: ', hsp.score
                print 'HSP_BITS: ', hsp.bits
                print 'HSP_EXPECT: ', hsp.expect
                print 'HSP_NUM_ALIGNMENTS: ', hsp.num_alignments
                print 'HSP_IDENTITIES: ', hsp.identities
                print 'HSP_POSITIVES: ', hsp.positives
                print 'HSP_GAPS: ', hsp.gaps
                print 'HSP_STRAND: ', hsp.strand
                print 'HSP_FRAME: ', hsp.frame
                print 'HSP_QUERY: ', hsp.query[0:75] + '...'
                print 'HSP_QUERY_START: ', hsp.query_start
                print 'HSP_MATCH: ', hsp.match[0:75] + '...'
                print 'HSP_SBJCT: ', hsp.sbjct[0:75] + '...'
                print 'HSP_SBJCT_START: ', hsp.sbjct_start
[UNCOMMENT FOR EXECUTION] """

""" [UNCOMMENT FOR EXECUTION]
above is an example of how a parser could be written to parse and print each value contained in the HSP and Alignment classes.
the snippet of code written below is one way to set 're-usable' variables for eash record parsed.
while this is not necessary it may be helpful if trying to format the output.

                ALIGNMENT_TITLE  = alignment.title
                ALIGNMENT_LENGTH  = alignment.length
                HSP_SCORE  = hsp.score
                HSP_BITS  = hsp.bits
                HSP_EXPECT  = hsp.expect
                HSP_NUM_ALIGNMENTS  = hsp.num_alignments
                HSP_IDENTITIES  = hsp.identities
                HSP_POSITIVES  = hsp.positives
                HSP_GAPS  = hsp.gaps
                HSP_STRAND  = hsp.strand
                HSP_FRAME  = hsp.frame
                HSP_QUERY  = hsp.query
                HSP_QUERY_START  = hsp.query_start
                HSP_MATCH  = hsp.match
                HSP_SBJCT  = hsp.sbjct
                HSP_SBJCT_START  = hsp.sbjct_start
[UNCOMMENT FOR EXECUTION] """

""" [UNCOMMENT FOR EXECUTION]
if you wanted to look inside another class contained in the database such as the description class,
you could something like the function below.

FILE_INPUT = open("blast_output.xml")
MINIMUM_INT = 20
from Bio.Blast import NCBIXML
PARSE_FILE = NCBIXML.parse(FILE_INPUT)
READ_LINE = PARSE_FILE.next()
for READ_LINE in PARSE_FILE:
    for description in READ_LINE.descriptions:  #   // for loop through each line contained in the Description class.
        print '\n***Seperator***\n\nDESCRIPTION_TITLE: ', description.title #   // seperator to show loop begining and end points, also print each description title.
        print 'DESCRIPTION_SCORE: ', description.score #    // print the description's score.
        print 'DESCRIPTION_E: ', description.e  #   // print the description's E. Whatever that might be.
        print 'DESCRIPTION_NUM_ALIGNMENTS: ', description.num_alignments    # // print description's num_alignments.

        DESC_TITLE  = str(description.title)    #   // set DESC_TITLE equal to the description's title.
        DESC_SCORE  = str(description.score)    #   // set DESC_SCORE equal to the description's score.
        DESC_E  = str(description.e)    #   // set DESC_E equal to the description's E...
        DESC_NUM_ALIGN  = str(description.num_alignments)   #   // set DESC_NUM_ALIGN equal to the description's num_alignments.
[UNCOMMENT FOR EXECUTION]"""