Harvard:Biophysics 101/2007/Notebook:Resmi Charalel/2007-5-3

Progress

In class on Tuesday and afterwards, Cynthia and I worked together to completely parse out the mesh terms (all as well as just the major) and increase the efficiency of our individual codes. We were able to slightly increase the efficiency of our look-up methods, but we are still working on how to search through PubMed only one time, so that the search is much faster (and we do not have any code for this latter part as of yet). The non-redundant parts were then combined to produce the code below, which returns mesh terms from two main sources (outlined below).

I have also been working on the documentation of our program and its functions. I am still working on updating this documentation as the fully compiled code comes together. So, I will continue to work on this past tomorrow, so that it is complete and as up-to-date as possible.

Annotation

• The following code combines the work that both Cynthia and I have done to return mesh terms (all mesh terms as well as just the major mesh terms) that are derived from two sources:
  • 1) From parsing OMIM for PMIDs and returning meshterms of these PMIDs
  • 2) By searching PubMed for rs number and returning meshterms of the articles returned in the search

Code

from Bio.EUtils import DBIdsClient
import xml.dom.minidom
from xml.dom.minidom import parse, parseString

# C-style struct to pass parameters
class PubmedID:
        pass

# queries the database and returns all info in an XML format
def omim_snp_search(dnsnp_id):
        client = DBIdsClient.DBIdsClient()
        query = client.search(dnsnp_id, "omim")
        records = [i.efetch(rettype="xml") for i in query]
        return records

# basic text extraction from XML; based on http://docs.python.org/lib/dom-example.html
def get_text(node_list):
    rc = ""
    for node in node_list:
        if node.nodeType == node.TEXT_NODE:
            rc = rc + node.data
    return rc

def extract_allelic_variant_pmid(str):
    dom = parseString(str)
    pmids = dom.getElementsByTagName("Mim-reference")
    if len(pmids) == 0:
        return
    ids = []
    for p in pmids:
        i = PubmedID()
        i.pmid = get_text(p.getElementsByTagName("Mim-reference_pubmedUID")[0].childNodes)
        ids.append(i.pmid)
    return ids

from Bio import PubMed
from Bio import Medline
import string

# parses a mesh term to remove * and /
def parse_term(str, bool):
    parsed_term = str
    if(bool):
        parsed_term = parsed_term.replace('*', )
    if str.find('/') != -1:
       parsed_term = parsed_term.replace('/', ' ')
    return parsed_term

# parses list of mesh terms
# returns embedded list, one with all terms and one major  terms
def parse_mesh(list):
    all_mesh_terms = []
    major_mesh_terms = []
    mesh_term = 
    for i in range(len(list)):
        major = False
        if list[i].find('*') == -1:
            mesh_term = parse_term(list[i], major)
            all_mesh_terms.append(mesh_term)
        else:
            major = True
            mesh_term = parse_term(list[i], major)
            major_mesh_terms.append(mesh_term)
            all_mesh_terms.append(mesh_term)
    all_mesh = [all_mesh_terms, major_mesh_terms]
    return all_mesh


rec_parser = Medline.RecordParser()
medline_dict = PubMed.Dictionary(parser = rec_parser)

all_mesh = []
all_mesh_terms = []
major_mesh_terms = []

for i in omim_snp_search("rs11200638"):
        p = extract_allelic_variant_pmid(i.read())
        if p != None:
               # for s in p:
               #         print p[0]
                        cur_record = medline_dict[p[0]]
         #   print '\n', cur_record.title, cur_record.authors, cur_record.source
                        mesh_headings = cur_record.mesh_headings
                        if len(mesh_headings) != 0:
                            all_mesh = parse_mesh(mesh_headings)
                            all_mesh_terms.extend(all_mesh[0])
                            major_mesh_terms.extend(all_mesh[1])

print '\n', "All mesh terms from OMIM PMIDs:  ", all_mesh_terms, '\n', "Major mesh terms from OMIM PMIDs:  ", major_mesh_terms

article_ids = PubMed.search_for("rs11200638")

all_mesh = []
all_mesh_terms = []
major_mesh_terms = []
for did in article_ids[0:5]:
    cur_record = medline_dict[did]
    #print '\n', cur_record.title, cur_record.authors, cur_record.source
    mesh_headings = cur_record.mesh_headings
    if len(mesh_headings) != 0:
        all_mesh = parse_mesh(mesh_headings)
        all_mesh_terms.extend(all_mesh[0])
        major_mesh_terms.extend(all_mesh[1])

print '\n', "All mesh terms from rs number:  ", all_mesh_terms, '\n', "Major mesh terms from rs number:  ", major_mesh_terms

#rest of code returns review articles on topic of interest by searching pubmed
disease = "Age-related Macular Degeneration" #should put a.name here when combined with Xiaodi's previous code
search_term = "Review[ptyp] "+disease
#print search_term

review_ids = PubMed.search_for(search_term)

count = 1

for did in review_ids[0:3]:
    cur_record = medline_dict[did]
    print '\n', count, ')  ', string.rstrip(cur_record.title), cur_record.authors, string.strip(cur_record.source)
    count=count+1