AnnaTSW0609

import re 
import os.path
import time 

# start = time. time()


def MeSH_DB(data_folder): 

# Source: https://www.nlm.nih.gov/mesh/2019/download/2019New_Mesh_Tree_Hierarchy.txt

AnnaTSW0609

## Assignment 1 analysis script 

library(GEOquery)

## getting the decompressed GEO series 
gse <- getGEO(filename='data/GSE50697_family.soft') # data already downloaded to local file in the interest of time
names(GSMList(gse)) # getting the name of the samples in the dataset 

for (gsm in GSMList(gse)) { # this is the condition we are interested in: whether we have miR-203 or not
  print(Meta(gsm)[['characteristics_ch1']])

AnnaTSW0609

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE Query>
<Query  virtualSchemaName = "plants_mart" formatter = "TSV" header = "0" uniqueRows = "0" count = "" datasetConfigVersion = "0.6" >
			
	<Dataset name = "athaliana_eg_gene" interface = "default" >
		<Filter name = "with_interpro" excluded = "0"/>
		<Attribute name = "ensembl_gene_id" />
		<Attribute name = "ensembl_transcript_id" />
		<Attribute name = "ensembl_peptide_id" />
		<Attribute name = "interpro" />

AnnaTSW0609

import os
import sqlite3
import json

from biothings import config
from biothings.utils.hub_db import IDatabase
from biothings.utils.dotfield import parse_dot_fields
from biothings.utils.dataload import update_dict_recur
from biothings.utils.common import json_serial

AnnaTSW0609

import os.path
import copy
from biothings.utils.common import SubStr
from biothings.utils.dataload import tab2dict, tab2list, value_convert, normalized_value, \
                                     list2dict, dict_nodup, dict_attrmerge, tab2dict_iter

        
def _not_LRG(ld):
    return not ld[1].startswith("LRG_")

AnnaTSW0609

import sys
import os
import time
from ftplib import FTP
import requests

import biothings, config
biothings.config_for_app(config)

from biothings.utils.common import timesofar, safewfile, is_int

AnnaTSW0609

Data = [] # Create an empty dictionary 
import re
with open("testfile_PantherDB.txt", "r+") as testfile:
     for line in testfile:
         # Creating the items for the reference gene
         # The four lines below creates 1a (name of the species specific database)
         # and 1b (the ID for that gene in the ss database
         split_list = re.split("[| \t \n]", line)
         ESID= split_list [1]
         ESID_title_break = re.split("[=]", ESID)