danielecook

# This is an auto-generated Django model module.
# You'll have to do the following manually to clean this up:
#     * Rearrange models' order
#     * Make sure each model has one field with primary_key=True
# Feel free to rename the models, but don't rename db_table values or field names.
#
# Also note: You'll have to insert the output of 'django-admin.py sqlcustom [appname]'
# into your database.
#
# I made the following changes to the models generated using inspectdb

danielecook

"""
Daniel E. Cook 2013 
(danielecook.com)

This script takes a csv containing authors and associated Pubmed identifiers (PMIDs) of their publications and outputs a formatted html document of their publications.
The first row of the csv should contain the authors, and each row below their publications (as PMIDs). If you put something other than a PMID in it will simply be outputted -
so you can add publications that might not be in pubmed or that you want to display in a certain way.

This script might be useful for individuals who maintains publication lists for researchers at a university, for instance. 

danielecook

from pprint import pprint as pp
from Bio import Entrez

Entrez.email = "[email protected]"

def pull_line(var_set,line):
 	"""
	This function parses data from lines in one of three ways:

	1.) Pulls variables out of a particular line when defined as "variablename=[value]" - uses a string to find the variable.

danielecook

# Downloading pub tables. Requires wget. Can be installed using home brew for mac
# More information is available here: http://brew.sh/

mkdir ../data/

# Download Files
wget  --timestamping --directory-prefix='../data/' 'http://hgdownload.cse.ucsc.edu/goldenPath/hgFixed/database/pubsArticle.txt.gz'
wget  --timestamping --directory-prefix='../data/' 'http://hgdownload.cse.ucsc.edu/goldenPath/hgFixed/database/pubsMarkerAnnot.txt.gz'
## wget  --timestamping --directory-prefix='../data/' 'http://hgdownload.cse.ucsc.edu/goldenPath/hgFixed/database/pubsSequenceAnnot.txt.gz'

danielecook

#!/usr/bin/env

# Requires wget - can be installed using homebrew if you are on a mac.

## Installation Variables ##
CHADO_DB_USERNAME=""
CHADO_DB_PASS="" 
CHADO_DB_NAME="chado"
PATH_TO_PSQL="/Applications/Postgres.app/Contents/MacOS/bin/psql" # I use a special application for mac, for convenience.

danielecook

# Note: Requires mysqldb; install using:
# pip install MySQL-python
from MySQLdb.constants import FIELD_TYPE
import _mysql

db = None

def fetch_gene_coordinates(gene_name,build):
	global db # db is global to prevent reconnecting.
	if db is None:

danielecook

# Extract all worksheets form an excel file and export as individual CSVs
# Install xlrd with 'pip install xlrd'
# Thanks to Boud from http://stackoverflow.com/questions/10802417/how-to-save-an-excel-worksheet-as-csv-from-python-unix

import xlrd
import csv

# Open the workbook
x = xlrd.open_workbook('excel_file.xlsx')

danielecook

import xlrd # pip install xlrd
import csv
import os

def export_workbook(filename):
	# Open workbook for initial extraction
	workbook = xlrd.open_workbook(filename)
	filename = os.path.splitext(filename)[0] # Remove extension
	if not os.path.exists(filename):
			os.makedirs(filename)

danielecook

# Download KEGG Data (Pathways)
#==============================#
# Download select files from UCSC (hg19)

for var in keggPathway KeggMapDesc knownGene kgXref
do
wget --timestamping --directory-prefix test 'ftp://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/$var.txt.gz'
gunzip kegg/$var.txt.gz
done

danielecook

#! /usr/local/bin/Python
import sqlite3
import os
import glob
import time
import sqlalchemy
from sqlalchemy import Table, Column, Index, Integer, String, Float, MetaData, ForeignKey
from sqlalchemy import create_engine
import datetime