Skip to content

Instantly share code, notes, and snippets.

@steve-federowicz
Last active August 29, 2015 13:56
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save steve-federowicz/7cceedba73982c0ae995 to your computer and use it in GitHub Desktop.
Save steve-federowicz/7cceedba73982c0ae995 to your computer and use it in GitHub Desktop.
Figure generation code
{
"metadata": {
"name": ""
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"from trnlib.omeORM import *\n",
"from sqlalchemy import func\n",
"from IPython.core import display\n",
"from IPython.core.display import HTML\n",
"from numpy import random, average\n",
"from pandas import *\n",
"\n",
"import pymongo\n",
"import simplejson as json\n",
"import math\n",
"import os\n",
"\n",
"\n",
"ome = Session()\n",
"connection = pymongo.Connection()\n",
"\n",
"db_gff = connection.gff_database\n",
"gff_data = db_gff.gff_data\n",
"\n",
"anaerobic = ome.query(Condition).filter_by(carbon_source='glucose',eacceptor='anaerobic').first()\n",
"nitrate = ome.query(Condition).filter_by(carbon_source='glucose',eacceptor='NO3').first()\n",
"\n",
"def html_table(matrix):\n",
" table = '<table border=\"1\">\\n'\n",
" for row in matrix:\n",
" table += '<tr>'\n",
" for entry in row: table += '<td>'+str(entry)+'</td>'\n",
" table += '</tr>'\n",
" table += '</table>'\n",
" return HTML(table)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"def get_chip_data(target = 'ArcA', carbon_source = 'glucose', nitrogen_source = 'NH4Cl', eacceptor = 'anaerobic', replicates = [1,2,3],\\\n",
" leftpos = 0, rightpos = 200, strand = ['+','-'], value = 0.0):\n",
" condition = ome.query(Condition).filter(and_(Condition.carbon_source == carbon_source, Condition.nitrogen_source == nitrogen_source,\\\n",
" Condition.eacceptor == eacceptor)).first()\n",
" gff_exp_wids = [x[0] for x in ome.query(GFFExperiment.wid).filter(and_(GFFExperiment.target == target, GFFExperiment.condition == condition,\\\n",
" GFFExperiment.replicate.in_(replicates))).all()]\n",
" probes = []\n",
" for probe in gff_data.find({\"$and\": \n",
" [{\"leftpos\" : {\"$gte\": leftpos}}, \n",
" {\"rightpos\": {\"$lte\": rightpos}}, \n",
" {\"strand\": {\"$in\" : strand}},\n",
" {\"value\": {\"$gte\": value}},\n",
" {\"experiment_wid\": {\"$in\" : gff_exp_wids}}\n",
" ]}): \n",
" probes.append(probe)\n",
" return probes\n",
"\n",
"\n",
"\n",
"def nimblegen_AUC(signals):\n",
" AUC = 0\n",
" a = signals.pop(0)\n",
" b = signals.pop(0)\n",
" if a < b: AUC = (a+b)-a/2\n",
" elif a > b: AUC = (a+b)-b/2\n",
" elif a == b: AUC = (a+b)-a/2\n",
" a = b\n",
" sumval = 0\n",
" for b in signals:\n",
" sumval+=b\t\n",
" if a < b:\n",
" AUC += b-a/2\n",
" elif a > b:\n",
" AUC += b/2\n",
" else:\n",
" AUC += b-a/2\n",
" a = b\n",
" return AUC\n"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"cpge = ChipPeakGeneExpression\n",
"data = {}\n",
"data2 = {}\n",
"for target,eacceptor in [('ArcA','anaerobic'),('ArcA','NO3'),('Fnr','anaerobic'),('Fnr','NO3')]:\n",
" for x in ome.query(cpge).filter(and_(cpge.target == target, cpge.eacceptor == eacceptor)).all():\n",
" #ChIP_value = nimblegen_AUC([y['value'] for y in get_chip_data(target = x.target, eacceptor = x.eacceptor, \n",
" # leftpos = x.leftpos, rightpos = x.rightpos)])\n",
" ChIP_value = 1.\n",
" if x.target1 != 'wt': inv = -1.0\n",
" else: inv = 1\n",
" try: \n",
" \n",
" if x.fdr < .05: data[x.gene_name][(target+' '+eacceptor)] = x.fold_change*inv\n",
" data2[x.gene_name][(target+' '+eacceptor)] = ChIP_value\n",
" except:\n",
" try: data[x.gene_name]\n",
" except: \n",
" data[x.gene_name] = {'ArcA anaerobic':0.1,'ArcA NO3':0.1,'Fnr anaerobic':0.1,'Fnr NO3':0.1}\n",
" data2[x.gene_name] = {'ArcA anaerobic':0.1,'ArcA NO3':0.1,'Fnr anaerobic':0.1,'Fnr NO3':0.1}\n",
" if x.fdr < .05: data[x.gene_name][target+' '+eacceptor] = x.fold_change*inv\n",
" data2[x.gene_name][(target+' '+eacceptor)] = ChIP_value\n",
" \n",
" \n",
"data_frame = DataFrame(data)\n",
"data_frame2 = DataFrame(data2)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"def write_heatmap_json(genes, name):\n",
" \n",
" name_map = {}\n",
" for gene_name in genes:\n",
" x = ome.query(TU.name).filter(TU.genes.contains(ome.query(Gene).filter_by(name=gene_name).first())).first()[0]\n",
" if x == '': x = gene_name\n",
" name_map[gene_name] = x\n",
" \n",
" data_json = json.dumps({\"genes\":[{\"name\": name_map[gene_name] , \"data\": list(data_frame[gene_name].values), \n",
" \"data2\": list(data_frame2[gene_name].values)}\n",
" for gene_name in genes],\n",
" \"headers\":[{\"name\" : \"ArcA anaerobic\"},{\"name\" : \"ArcA NO3\"},{\"name\" : \"Fnr anaerobic\"},{\"name\" : \"Fnr NO3\"}]})\n",
"\n",
" try: os.remove(name+'.json')\n",
" except: None\n",
" open(name+'.json','w').write(data_json)\n",
" \n",
" \n",
"data_frame = data_frame.reindex_axis(Index(['ArcA anaerobic', 'ArcA NO3', 'Fnr anaerobic', 'Fnr NO3'], dtype=object), axis=0)\n",
"data_frame2 = data_frame2.reindex_axis(Index(['ArcA anaerobic', 'ArcA NO3', 'Fnr anaerobic', 'Fnr NO3'], dtype=object), axis=0)\n",
"\n",
"write_heatmap_json(flatten_to_genes(catabolism_tu),'catabolism')\n",
"write_heatmap_json(flatten_to_genes(anabolism_tu),'anabolism')\n",
"write_heatmap_json(flatten_to_genes(chemiosmosis_tu),'chemiosmosis')\n"
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"%%timeit\n",
"nimblegen_AUC([x['value'] for x in get_chip_data(leftpos=449500,rightpos=452000,replicates=[1,2,3],strand=['+','-'])])/6"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"1 loops, best of 3: 713 ms per loop\n"
]
}
],
"prompt_number": 29
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"def flatten_to_genes(category):\n",
" genes = []\n",
" for x in category: \n",
" for y in category[x]:\n",
" try: \n",
" for z in category[x][y]: genes.append(z)\n",
" except:\n",
" genes.append(y)\n",
" return genes\n",
" "
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"genes = flatten_to_genes(catabolism_tu)\n",
"name_map = {}\n",
"for gene_name in genes:\n",
" x = ome.query(TU.name).filter(TU.genes.contains(ome.query(Gene).filter_by(name=gene_name).first())).first()[0]\n",
" if x == '': x = gene_name\n",
" name_map[gene_name] = x\n",
"name_map"
],
"language": "python",
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'catabolism_tu' is not defined",
"output_type": "pyerr",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-5-b706e81067c2>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mgenes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mflatten_to_genes\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcatabolism_tu\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mname_map\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mgene_name\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mgenes\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mome\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mquery\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mTU\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfilter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mTU\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgenes\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcontains\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mome\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mquery\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mGene\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfilter_by\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mgene_name\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfirst\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfirst\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mx\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m''\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgene_name\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mNameError\u001b[0m: name 'catabolism_tu' is not defined"
]
}
],
"prompt_number": 5
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"catabolism = {\n",
" \"transport\": {\n",
" \"carbohydrate\": ['mglA','mglB','mglC','ugpB','ugpA','ugpE','ugpC','kgtP','dcuA','focA',\n",
" 'uraA','ptsG','lldP','exuT'],\n",
" \"amino_acid\": ['metQ','metI','metN','aroP','dppA','dppB','dppB','dppC','dppD','dppF',\n",
" 'oppA','oppB','oppC','oppD','oppF','sstT','hisJ','hisQ',\n",
" 'hisM','hisP','potF','potG','potH','potI','potA','potB','potC','potD',\n",
" 'argT','cycA','putP','tyrP','gabP'],\n",
" \"nucleotides\": ['nupC'],\n",
" \"lipids\": ['fadL']\n",
" },\n",
" \"recycling\": {\n",
" \"carbohydrate\": ['envC','mltA','pldA','ugpQ','arnA','manA','paaK','mhpC','mhpF'],\n",
" \"amino_acid\": ['clpA','clpS','rnpA','pepN','pepQ','ybiS','yhbU','ygjG','gcvA','gcvB',\n",
" 'glpG','pepT','astC','astD','astE'],\n",
" \"lipids\": ['fadI','fadJ','fadD','fadE','fadB','fadA','fadH'],\n",
" \"nucleotides\": ['xseA','csrB']\n",
" },\n",
" \"glycolysis\": ['fsaA','dhaK','dhaL','dhaM','gapA','gpmM','eno','pykA','aceE','aceF',\n",
" 'adhE','lpd','acs'],\n",
" \"TCA\": ['gltA','acnB','icd','sucA','sucB','sucC','sucD','sdhA',\n",
" 'sdhB','sdhC','sdhD','frdA','frdB','frdC','frdD','fumA',\n",
" 'fumB','mdh','glcD','glcB','glcG','aldA'],\n",
" \"accessory\": ['thiE','thiF','thiG','thiH','thiS'],\n",
" \"regulators\": {\n",
" \"carbohydrate\": ['lldR','aer','mhpR','caiF','puuR','pdhR','glcC']\n",
" }\n",
" }"
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"anabolism = {\n",
" \"macromolecular_synthesis\": ['nrdA','nrdB','ndk','nudE','nudJ','upp','nrdD','nrdG','ung',\n",
" 'dbpA','rimP','rplY','rpsU','ddlA'],\n",
" \"biosynthesis\": {\n",
" \"nucleotides\": ['sthA','pntA','pntB','pncB','purA','guaA','guaB','ravA',\n",
" 'viaA','katG','pyrD','purM','purN'],\n",
" \"amino_acids\": ['carA','carB','thiC','thrA','thrB','thrC','gabD','gabT',\n",
" 'speA','puuA','puuD','putA','mhpD','mhpE','glpE','gltB',\n",
" 'gltD','gltF','argG'],\n",
" \"lipids\": ['acpP','tpx']\n",
" },\n",
" \"regulators\": ['bssR','rcsB','rcsD','uspA','uspB','uspF','rho','nusA','infA','infB','rutR']\n",
" }\n",
" "
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"chemiosmosis = {\n",
" \"ETC\": {\n",
" \"dehydrogenases\": ['fdnH','fdnI','fdoG','fdoH','fdoI','hybC','hybO','glpD',\n",
" 'hybA','hybB','hybD','hybE','hybF','hybG','nuoA','nuoB',\n",
" 'nuoC','nuoE','nuoF','nuoG','nuoH','nuoI','nuoJ','nuoK',\n",
" 'nuoL','nuoM','nuoN','ndh','lldD','mdh','sdhA','sdhB','sdhC','sdhD'],\n",
" \"oxidoreductases\": ['lhgO','mqo','frdA','frdB','frdC','frdD','dmsA','dmsB','dmsC',\n",
" 'ynfE','ynfF','ynfG','ynfH','nirB','nirD','nirC','nrfA',\n",
" 'nrfB','nrfC','nrfD','nrfF','narG','narH','narI','cyoA','cyoB',\n",
" 'cyoC','cyoD','cyoE','cydA','cydB','hcr'],\n",
" \"accessory\": ['dmsD','ynjE','moaA','moaB','moaC','moaD','moaE','fhuF',\n",
" 'nikA','nikB','nikC','nikD','nikE','hcp','dsbB','msrB','glpE']\n",
" },\n",
" \"fermentation\": ['pflB','yfiD','pta','ackA','adhE','focA'],\n",
" \"ion_pumps\": ['hemG','feoA','feoB','feoC','dcuA','dcuB','osmY','cydD','cydC',\n",
" 'ompC','ompW','pitA','kdpC','narK','narJ','cirA','gsiA',\n",
" 'gsiB','gsiC','gsiD','mntH'],\n",
" \"motility\": ['flhC','flhD'],\n",
" \"regulators\": ['gadX','gadW','nikR','rstA','rstB','narX','narL','glpR']\n",
" }\n",
" \n",
" "
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"ome.query(Gene.info).filter_by(name='yghB').all()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "pyout",
"prompt_number": 52,
"text": [
"[(u'conserved inner membrane protein')]"
]
}
],
"prompt_number": 52
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"b = [x.bnum+'\\t'+x.gene_name for x in ome.query(cpge).join(Gene, Gene.bnum == cpge.bnum).filter(Gene.info.ilike('%membrane%')).filter(and_(cpge.target.in_(['ArcA','Fnr']), cpge.fdr < .05)).filter(not_(cpge.gene_name.in_(a))).order_by(cpge.gene_name).all()]"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 60
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"for x in b: print x"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"b1445\tydcX\n",
"b1750\tydjX\n",
"b1752\tydjZ\n",
"b1929\tyedE\n",
"b2295\tyfbV\n",
"b2298\tyfcC\n",
"b3009\tyghB\n",
"b3485\tyhhJ\n",
"b3964\tyijD\n",
"b4068\tyjcH\n",
"b4068\tyjcH\n",
"b4176\tyjeT\n",
"b1332\tynaJ\n",
"b3002\tyqhA\n"
]
}
],
"prompt_number": 61
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"a = flatten_to_genes(catabolism)+flatten_to_genes(anabolism)+flatten_to_genes(chemiosmosis)\n",
"cpge = ChipPeakGeneExpression\n",
"ome.query(cpge).filter(and_(cpge.target.in_(['ArcA','Fnr']), cpge.fdr < .05)).filter(not_(cpge.gene_name.in_(a))).order_by(cpge.gene_name).all()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 9,
"text": [
"[ChipPeakGeneExpression: Fnr (activator) for Gene: arcA (b4401) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.58, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: arcA (b4401) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change -5.15, fdr=3.04e-08),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: arcA (b4401) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 11.27, fdr=1.35e-07),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: argR (b3237) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.42, fdr=4.33e-03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: betI (b0313) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 1.39, fdr=2.03e-04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: caiA (b0039) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.39, fdr=0.04),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: csiD (b2659) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -2.32, fdr=1.26e-04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: cspA (b3556) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.48, fdr=0.03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: cysG (b3368) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.47, fdr=0.04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: dnaG (b3066) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.39, fdr=5.33e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: fabD (b1092) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.19, fdr=8.42e-04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: fabF (b1095) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.43, fdr=0.03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: fabG (b1093) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.12, fdr=0.04),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: fnr (b1334) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 10.95, fdr=2.35e-06),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: fnr (b1334) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 3.32, fdr=1.88e-05),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: folE (b2153) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.48, fdr=3.40e-04),\n",
" ChipPeakGeneExpression: Fnr (repressor) for Gene: groL (b4143) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change -0.45, fdr=0.02),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: hsdM (b4349) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.34, fdr=0.03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: hsdR (b4350) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 5.08, fdr=7.97e-04),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: hsdS (b4348) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.50, fdr=7.83e-03),\n",
" ChipPeakGeneExpression: Fnr (repressor) for Gene: iraP (b0382) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change -2.32, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: ispH (b0029) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.35, fdr=2.95e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: leuD (b0071) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.21, fdr=0.03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: leuL (b0075) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.76, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: macA (b0878) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.59, fdr=7.29e-03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: mcbA (b0806) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.68, fdr=0.02),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: metV (b2816) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 0.80, fdr=0.02),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: metW (b2815) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 0.86, fdr=2.87e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: metZ (b2814) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 0.78, fdr=5.61e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: micF (b4439) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.64, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: mutM (b3635) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.63, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: phoH (b1020) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 4.48, fdr=9.38e-08),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: pnp (b3164) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.24, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: pnp (b3164) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.12, fdr=0.04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: pnp (b3164) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.12, fdr=0.04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: psrD (b4418) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.39, fdr=8.82e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: rbfA (b3167) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.32, fdr=6.93e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: rbfA (b3167) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.11, fdr=0.03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: recF (b3700) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.46, fdr=0.03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: recF (b3700) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.64, fdr=0.03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: ribF (b0025) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.12, fdr=8.16e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: rplU (b3186) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.23, fdr=0.04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: rpmA (b3185) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.45, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: rpmB (b3637) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.21, fdr=0.04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: rpmG (b3636) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.37, fdr=0.03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: rpmH (b3703) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.24, fdr=0.03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: rpmH (b3703) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.15, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: rpsO (b3165) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.36, fdr=0.05),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: rpsO (b3165) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.36, fdr=0.05),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: rpsT (b0023) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.52, fdr=0.01),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: secG (b3175) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.46, fdr=7.54e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: secG (b3175) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.56, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: suhB (b2533) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.44, fdr=0.01),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: thrL (b0001) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 1.12, fdr=0.03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: truB (b3166) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.65, fdr=4.29e-03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: uxaC (b3092) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.75, fdr=0.03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: xthA (b1749) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.28, fdr=0.03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: ybfA/EG11521 (b0699) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 2.00, fdr=5.20e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: ybfA/EG11521 (b0699) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change -0.85, fdr=6.61e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: ybhK/G6402 (b0780) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.74, fdr=3.21e-04),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: ybiU/G6424 (b0821) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -1.84, fdr=4.21e-04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: ybjX/G6460 (b0877) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 1.03, fdr=4.82e-04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: yceD/EG11119 (b1088) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.24, fdr=0.01),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ydcX/G6756 (b1445) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.75, fdr=0.02),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ydfZ/G6815 (b1541) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 12.27, fdr=2.55e-10),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ydfZ/G6815 (b1541) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 10.15, fdr=1.16e-03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: ydgC/G6863 (b1607) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -1.54, fdr=1.71e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ydhW/G6900 (b1672) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 0.97, fdr=0.05),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ydhY/G6902 (b1674) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 1.42, fdr=4.14e-04),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ydjX/G6945 (b1750) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 4.50, fdr=2.10e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ydjY/G6946 (b1751) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 5.56, fdr=7.03e-04),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ydjZ/G6947 (b1752) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 4.43, fdr=6.84e-06),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yeaD/G6966 (b1780) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 1.40, fdr=0.04),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yeaD/G6966 (b1780) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 1.19, fdr=4.80e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yecH/G7036 (b1906) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 5.85, fdr=1.47e-05),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yecH/G7036 (b1906) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 4.39, fdr=2.35e-03),\n",
" ChipPeakGeneExpression: Fnr (repressor) for Gene: yedE/EG11660 (b1929) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change -1.12, fdr=4.91e-03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yeiG/EG12026 (b2154) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.34, fdr=4.68e-03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yejG/EG12042 (b2181) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 6.12, fdr=2.05e-09),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yejG/EG12042 (b2181) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -4.00, fdr=3.62e-04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: yfbM/G7179 (b2272) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.72, fdr=0.01),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yfbV/G7189 (b2295) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 0.65, fdr=1.37e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yfcC/G7190 (b2298) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 2.85, fdr=1.29e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yfcZ/G7214 (b2343) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 1.02, fdr=6.26e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yfcZ/G7214 (b2343) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 1.89, fdr=4.46e-03),\n",
" ChipPeakGeneExpression: Fnr (repressor) for Gene: yffL/G7273 (b2443) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.95, fdr=0.01),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yffS/G7280 (b2450) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.32, fdr=3.95e-03),\n",
" ChipPeakGeneExpression: Fnr (repressor) for Gene: yffS/G7280 (b2450) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change -0.32, fdr=0.04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: yfiF/EG11786 (b2581) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change -0.26, fdr=0.04),\n",
" ChipPeakGeneExpression: Fnr (repressor) for Gene: yghA/EG11292 (b3003) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.95, fdr=0.03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yghB/EG11824 (b3009) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 1.12, fdr=8.67e-04),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: ygjD/EG11171 (b3064) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.31, fdr=0.04),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yhbS/G7650 (b3156) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 1.13, fdr=3.50e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yhbS/G7650 (b3156) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 0.41, fdr=0.01),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yhbT/G7651 (b3157) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 2.02, fdr=7.04e-07),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yhbT/G7651 (b3157) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.47, fdr=0.01),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yhbV/G7653 (b3159) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 6.60, fdr=2.11e-05),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: yhgE/G7745 (b3402) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.73, fdr=1.53e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: yhhJ/EG11767 (b3485) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.36, fdr=0.05),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yhjE/EG12249 (b3523) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 3.75, fdr=4.63e-05),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yhjE/EG12249 (b3523) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -1.92, fdr=2.22e-04),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yiaG/EG12624 (b3555) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.32, fdr=0.02),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yibN/EG12295 (b3611) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 0.75, fdr=1.01e-03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yieE/EG11722 (b3712) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.40, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yigI/EG11467 (b3820) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 5.06, fdr=2.67e-12),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yigZ/EG11484 (b3848) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.41, fdr=1.46e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: yijD/EG11395 (b3964) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.48, fdr=4.27e-03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yjcH/EG11943 (b4068) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -4.58, fdr=5.88e-04),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yjcH/EG11943 (b4068) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 3.12, fdr=7.31e-05),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yjeT/G7844 (b4176) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.67, fdr=0.03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yjiR/G7936 (b4340) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -1.88, fdr=1.42e-03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: ynaJ/G6668 (b1332) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 4.05, fdr=6.36e-06),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yncD/G6762 (b1451) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -2.16, fdr=1.06e-03),\n",
" ChipPeakGeneExpression: ArcA (repressor) for Gene: yncE/G6763 (b1452) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -4.65, fdr=1.43e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ynfK/G6851 (b1593) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 3.91, fdr=1.22e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ynfK/G6851 (b1593) on Condition: C:glucose, N:NH4Cl, e:anaerobic (fold change 5.05, fdr=2.09e-06),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ynjA/G6948 (b1753) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 1.97, fdr=1.30e-03),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ynjB/G6949 (b1754) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 2.14, fdr=9.41e-04),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ynjC/G6950 (b1755) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 3.02, fdr=2.29e-04),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: ynjD/G6951 (b1756) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 2.26, fdr=2.11e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: ypdA/G7243 (b2380) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.66, fdr=6.12e-03),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: ypdB/G7244 (b2381) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.45, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: ypdC/G7245 (b2382) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.39, fdr=0.02),\n",
" ChipPeakGeneExpression: ArcA (activator) for Gene: yqcA/G7448 (b2790) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.36, fdr=0.04),\n",
" ChipPeakGeneExpression: Fnr (activator) for Gene: yqgC/G7522 (b2940) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change 0.47, fdr=0.03),\n",
" ChipPeakGeneExpression: Fnr (repressor) for Gene: yqhA/G7559 (b3002) on Condition: C:glucose, N:NH4Cl, e:NO3 (fold change -0.36, fdr=0.02)]"
]
}
],
"prompt_number": 9
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"catabolism_tu = {\n",
" \"transport\": {\n",
" \"carbohydrate\": ['mglB','ugpE','kgtP','lldP','exuT','focA','uraA','ptsG','dcuA'],\n",
" \"amino_acid\": ['potB','metN','aroP','dppD','oppF','sstT','hisJ','potF','argT',\n",
" 'cycA','putP','gabP','tyrP'],\n",
" \"nucleotides\": ['nupC'],\n",
" \"lipids\": ['fadL']\n",
" },\n",
" \"recycling\": {\n",
" \"carbohydrate\": ['envC','mltA','pldA','ugpQ','mhpF','arnA'],\n",
" \"amino_acid\": ['clpA','ygjG','pepN','pepQ','ybiS','yhbU','rnpA','gcvA','gcvB',\n",
" 'astC',],\n",
" \"lipids\": ['fadJ','fadD','fadE','fadB','fadH']\n",
" },\n",
" \"glycolysis\": ['dhaK','gapA','gpmM','pykA','aceE',\n",
" 'adhE','lpd','acs'],\n",
" \"TCA\": ['gltA','acnB','icd','sucD','sdhC','frdD','fumA','mdh','glcD','aldA'],\n",
" \"accessory\": ['thiE'],\n",
" \"regulators\": {\n",
" \"carbohydrate\": ['aer','lldR','mhpR','glcC','puuR','pdhR','caiF']\n",
" }\n",
" }"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 9
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"anabolism_tu = {\n",
" \"macromolecular_synthesis\": ['ndk','nudE','nrdA','nrdD','upp','ung','dbpA','rimP','rplY','rpsU','ddlA'],\n",
" \"biosynthesis\": {\n",
" \"nucleotides\": ['sthA','pntB','pncB','purA','purN','guaB','ravA','katG','pyrD'],\n",
" \"amino_acids\": ['carA','thiC','gabT','puuD','putA','mhpD','thrA','gltB','argG','speA'],\n",
" \"lipids\": ['tpx']\n",
" \n",
" },\n",
" \"regulators\": ['uspA','uspB','bssR','uspF','rcsD','rho','nusA','infA','infB']\n",
" }\n",
" "
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 10
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"chemiosmosis_tu = {\n",
" \"ETC\": {\n",
" \"dehydrogenases\": ['fdnI','fdoG','hybO','nuoH','lldD','mdh','sdhC'],\n",
" \"oxidoreductases\": ['lhgO','mqo','frdD','dmsA','ynfE','nirD','nrfB','narH','cyoA','cydA','hcr'],\n",
" \"accessory\": ['msrB','glpE','fhuF','ynjE','moaD','nikB','hcp','dsbB']\n",
" },\n",
" \"fermentation\": ['pflB','yfiD','pta','ackA','adhE','focA'],\n",
" \"ion_pumps\": ['hemG','dcuB','cydD','ompC','kdpC','pitA','narK','narJ',\n",
" 'osmY','cirA','feoB','mntH','gsiD'],\n",
" \"motility\": ['flhD'],\n",
" \"regulators\": ['gadW','glpR','narL','nikR','rstA']\n",
" }\n",
" \n",
" \n",
" "
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 11
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"['fdnH','fdnI','fdoG','fdoH','fdoI','hybC','hybO',\n",
" 'hybA','hybB','nuoA','nuoB','nuoC','nuoD','nuoE','nuoF',\n",
" 'nuoG','nuoH','nuoI','nuoJ','nuoK','nuoL','nuoM','nuoN',\n",
" 'ndh','lldD','mdh','sdhA','sdhB','sdhC','sdhD'],\n",
"\n",
"['hemG','feoA','feoB','dcuA','dcuB','osmY','cydD','cydC',\n",
" 'ompC','ompW','pitA','kdpC','kdpD','kdpE'],"
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"avg_peak_width = average([x[0] for x in ome.query(ChipPeakGene.rightpos-ChipPeakGene.leftpos).\n",
" group_by(ChipPeakGene.leftpos, ChipPeakGene.rightpos).all()])\n",
"width_aucs = []\n",
"for y in [[x-(avg_peak_width/2),x+(avg_peak_width/2)] for x in random.randint(0,4.6e6,1000)]:\n",
" width_aucs.append(nimblegen_AUC([z['value'] for z in get_chip_data(leftpos=y[0],rightpos=y[1])])/6)"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 20
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"len(chem_genes+cat_genes+ana_genes)"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "pyout",
"prompt_number": 36,
"text": [
"192"
]
}
],
"prompt_number": 36
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"a = flatten_to_genes(catabolism)+flatten_to_genes(anabolism)+flatten_to_genes(chemiosmosis)\n",
"unknown = ['yncD','yncE','rpmA','yciC','yciB','yecH','ypdC','ypdB','yfaL','eno','yjjY',\n",
" 'yhjE','ynjB','ynjA','mutM','pck','rpmG','plsX','rpmF','ypdA','gmhB','yibN',\n",
" 'ynjC','yejG','yfiF','ynjD','ybfA','yceI','mcbA','yqcC','yffL','yffS','ydcX',\n",
" 'ileS','ychE','fkpB','rbbA','yrfF','ybiT','ydgH','rmf','phnJ','metV','metW',\n",
" 'nohB','yddG','aqpZ','yhjE','yfbM','ydjY','ydjZ','ydjX','yceD','yfcC','yfcZ',\n",
" 'yfbV','fsaA','yhgE','yieE','ygjD','yjcH','ssrA','yhiL','slyA','yjeH','yffR',\n",
" 'yghB','ynaJ','ybiU','rplU','ydgC','yeaD','yhiI','paaH','yhiL','phoH','ydhY',\n",
" 'yhiN','metK','yccA','trmJ','yijD','rpoD','uspC','yfdZ','rimO','lpcA','metZ',\n",
" 'yqgB','ybjX','yhbS','yhbT','ybjD','yhbV','yiaG','yjiR','ynfK','ybhK','yqhA',\n",
" 'yghA','ydhI','yqgC','yhhJ','yqcA','yjeT','yigI','ydhY','yedE','csiD']\n",
"redox_exotic = ['yieF']\n",
"unexpressed = ['rhoL','pyrG','avtA','lspA','rhlB','ydhJ','trkH','rnpB','anmK','phnD','phnO',\n",
" 'leuL','leuA','leuB','leuC','leuD','ydcY','rluE','paaJ','ubiC','iaaA','caiB',\n",
" 'kup','asd','fabR','truC','trxA','rutG','fabH','dnaA','dnaN']\n",
"unrelated = ['hsdM']\n",
"contamination = ['fabD','fabG','psrD']\n",
"print data_frame.index\n",
"table = []\n",
"for x in set(data_frame.columns).difference(set(a+unknown+redox_exotic+unexpressed+unrelated+contamination)): \n",
" gene = ome.query(Gene).filter_by(name=x).first()\n",
" table.append((gene._repr_html_(),data_frame[x].values,gene.info))\n",
"html_table(table)\n"
],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment