radaniba

from BeautifulSoup import BeautifulSoup
import urllib
import xlwt
wb = xlwt.Workbook()
ws = wb.add_sheet('a test sheet')
f = urllib.urlopen("http://www.ebi.ac.uk/Tools/services/web/blastresult.ebi?tool=ncbiblast&jobId=ncbiblast-I20120714-161017-0108-80986175-pg&context=nucleotide")
html = f.read()
soup = BeautifulSoup(html)
#print soup.prettify()
#print soup

radaniba

### IMPORTS
 
require 'roo'
require 'pp'
 
### IMPLEMENTATION ###
 
# A Excel spreadsheet reader that can clean up column names and convert data.
#
# Assumptions: The data is read off the first sheet of the workbook. The sheet

radaniba

###### 1. explore sequence composition of human genome
library(BSgenome)
available.genomes()
library(BSgenome.Hsapiens.UCSC.hg18)
 
### get sequence for chromosome 1
Seq=Hsapiens[["chr1"]]
Seq # shows some summaries
Seq=unmasked(Seq)  ## remove the mask
 

radaniba

#!perl -w
#
#   A client showing how to use Bio::Biblio module, a module for
#   accessing and querying a bibliographic repository.
#   It also shows how to use modules Bio::Biblio::IO::medlinexml
#   Bio::Biblio::IO::medline2ref which converts XML MEDLINE
#   citations into a simple hash table and into full Perl objects.
#
#   It has many options in order to cover as many methods as
#   possible.  Because of that, it can be also used as a fully

radaniba

#5. Add accession numbers and sequences to the tree -- now we're using PhyloXML's extra features.

from Bio.Phylo import PhyloXML
 
# Make a lookup table for sequences
lookup = dict((rec.id, str(rec.seq)) for rec in best_seqs)
 
for clade in egfr_tree.get_terminals():
    key = clade.name
    accession = PhyloXML.Accession(key, 'NCBI')

radaniba

#!/usr/bin/perl -w

# oligos.pl
# Create and analyze an overlapping series of oligos
# WI Bioinformatics course - Feb 2002 - Lecture 5
# WI Bioinformatics course - Revised - Sep 2003 
# Example of input taken as multiple arguments 

# Check input and give info if arguments are missing
if (! $ARGV[3])

radaniba

#! /usr/local/bin/perl -w

# Homemade Genbank report parser using regular expressions.
# Once desired data is captured, it can be printed in any format.
# WI Bioinformatics course - Feb 2002 - Lecture 6

$gb_report = "genbank_sample.txt";

open (GB, $gb_report) || die "cannot open $gb_report for reading: $!";

radaniba

#!/usr/local/bin/perl -w

# Parsing BLAST reports with BioPerl's Bio::Tools::BPlite module
# WI Bioinformatics course - Feb 2002 - Lecture 6

# See documentation at http://www.bioperl.org/Core/POD/Bio/Tools/BPlite.html

use Bio::Tools::BPlite;

# Prompt the user for the file name if it's not an argument

radaniba

#!/usr/bin/perl -w

# patscan_batch.pl
# Run patscan on all seqs in a folder
# Can be easily modified to run any command on every sequence in a folder
# WI Bioinformatics course - Feb 2002 - Lecture 5
# Revised - Sep 2003 
################  User-supplied variables  #############

# Directory of sequences

radaniba

#If you deal with a large quantity of gene IDs (such as the ones produced by microarray analysis), annotating them is important if you want to determine their potential biological meaning. However, a lot of annotation systems are only web-based, or do not work with Python. 

#Thanks to the Entrez module it is possible to annotate batches of Entrez Gene IDs without trouble, using the "retrieve_ids" function provided below.

#This example assumes you have a list of Entrez Gene IDs. Note: they should be stored as strings, rather than integers, even if they are numbers.

import sys
 
from Bio import Entrez