In [1]:

from trnlib.omeORM import *
from pandas import *

from numpy import array
from sqlalchemy import func

from IPython.core.display import HTML

ome = Session()

In [37]:

direct_reg = read_table('arcA_ChIP_expression.txt', index_col=0)

In [38]:

HTML(direct_reg.to_html())

Out[38]:

	Function	Fold_change	occupancy_change_σ70_-O2_O2	ArcA_TSS_distance	Previous_ArcA-P_Binding	Previous_effect
operon
pdhR-aceEF-lpdA	DNA-binding transcriptional dual regulator; Py...	3.2	-	-167 to -146,-27 to -7	NaN	NaN
lpdA	Lipoamide Dehydrogenase	6.1	-	-38 to -6	[16]	[16,17]
acnB	aconitate hydratase 2	13.7	-	-57 to -19	NaN	[42]
gcd	glucose dehydrogenase	20	NC	-2 to 30	NaN	NaN
fadE	acyl-CoA dehydrogenase	17.5	-	4 to 35	[18]	[18]
betIBA	glycine betaine biosynthesis	4.4	-	42 to 88	NaN	[19]
betT	choline BCCT transporter	5.9	-	-18 to 25	NaN	[19]
mhpR	3HPP DNA-binding transcriptional activator	23.9	ND	-23 to 9	NaN	NaN
cyoABCDE	cytochrome bo terminal oxidase	64.9	-	-231 to -189,-38 to -7	NaN	[13,17,20]
tesB	thioesterase II	2.3	NC	-123 to -104	NaN	NaN
ybaY	predicted outer membrane lipoprotein	6.4	NC	-18 to 3**	NaN	NaN
ylaC	predicted inner membrane protein	7.7	-	-95 to -75	NaN	NaN
cstA	peptide transporter induced by carbon starvation	21.5	-	-44 to -24	NaN	NaN
gltA	citrate synthase	7.1	-	-68 to -37	[12,23]	[13,17,21]
sdhCDAB-sucABCD	succinate dehydrogenase; succinyl-CoA synthetase	133.5	-	-71 to -18	[12,23]	[13,17,22-25]
ybiU	predicted protein	2.4	ND	no TSS	NaN	NaN
bssR	regulator of biofilm formation	3.2	+	-69 to -49**	NaN	NaN
potFGHI	putrescine ABC transporter	2.6	-	-139 to -108	NaN	[17]
clpA	ATP-dependent protease specificity component a...	3.7	-	-43 to -1	NaN	NaN
putA	fused DNA-binding transcriptional regulator to...	30.8	-	-45 to -15	NaN	NaN
putP	proline:sodium symporter	2.4	-	-15 to 9*	NaN	NaN
phoH	ATP-binding protein	25.3	-	-80 to -21*	NaN	[13]
csgD	DNA-binding transcriptional dual regulator	3	-	-51 to -21	NaN	[13]
icdA	isocitrate dehydrogenase	4	-	-12 to 21*	[26]	[13,17,26]
ycgZ-ymgA-ariR-ymgC	predicted protein	2.4	-	-209 to -167**	NaN	NaN
ompW	outer membrane protein	3.3	ND	-8 to 13	NaN	NaN
puuA	glutamate-putrescine ligase	15.3	-	no TSS	NaN	[27]
puuDR	γ-glutamyl-γ-aminobutyrate hydrolase;DNA-bindi...	10.6	-	-70 to -28	NaN	[27]
ynaJ	predicted inner membrane protein	3.4	-	-12 to +9**	NaN	NaN
feaR	DNA-binding transcriptional activator	2.1	-	no TSS	NaN	NaN
aldA	aldehyde dehydrogenase A	36.1	-	-10 to 33	[28]	[13]
ydcI	predicted DNA-binding transcriptional regulator	15.9	-	-20 to 12	NaN	NaN
yncD	predicted iron outer membrane transporter	2.5	-	-39 to -8**	NaN	NaN
yncE	conserved protein	2.6	-	-125 to -94	NaN	NaN
ydgC	hypothetical protein	2	+	260 to 281**	NaN	NaN
fumC	fumarase C	8.4	NC	no TSS	NaN	[29]
fumA	fumarase A	26	ND	-35 to 9	NaN	[29]
astCADBE	acetylornithine transaminase, catabolic to s...	10.6	-	-22 to 22*	NaN	NaN
msrB	methionine sulfoxide reductase B	11.6	+	-28 to -8**	NaN	NaN
fadD-sroD	fatty acyl-CoA synthetase	3.2	ND	-16 to 16	[18]	[13]
yehDCBA	predicted fimbrial-like adhesin protein	5.4	ND	no TSS	NaN	NaN
mglBAC	methyl-galactoside ABC transporter	29.2	-	-42 to -22	NaN	NaN
cirA	outer membrane receptor involved in uptake of ...	5.2	ND	NaN	NaN	NaN
yeiQ	predicted dehydrogenase, NAD-dependent	3.1	ND	-2 to 41**	NaN	NaN
yejG	predicted protein	11.9	-	-26 to 18	NaN	NaN
mqo	malate:quinone oxidoreductase	31.8	-	-39 to -8**	NaN	[30]
nuoABCEFGHIJKLMN	NADH:ubiquinone oxidoreductase 1	2.7e	-	-178 to -146 (-351 to 319), 57 to 77 (-117 to ...	NaN	[14,17]
argT-hisJQMP	lysine to arginine to ornithine ABC transporter	22.6	-	-14 to 29**	NaN	NaN
fadIJ	anaerobic fatty acid oxidation complex	10.2	-	-26 to -6	[18]	[18]
fadL	long-chain fatty acid outer membrane transporter	2.8	-	-60 to -29	[18]	[18]
maeB	malate dehydrogenase (oxaloacetate-decarboxyla...	4.9	-	-49 to -7**	NaN	NaN
ndk	nucleoside diphosphate kinase	8.2	-	-63 to -43	NaN	[13]
hcaR	DNA-binding transcriptional activator	6.8	-	-12 to 20	NaN	[40]
trxC	thioredoxin 2	2.7	NC	-32 to 16*	NaN	NaN
kgtP	α-ketoglutarate MFS transporter	8.8	-	189 to 220**	NaN	[13]
glcDEFGBA	glycolate and glyoxylate degradation	7.1	-	-121 to -90	[31]	[13,31]
glcC	transcriptional dual regulator	9.8	-	-40 to -9	[31]	[13,31]
ygjG	putrescine aminotransferase to diamine trans...	5.5	-	NaN	NaN	NaN
fadH	2,4-dienoyl-CoA reductase	3.1	ND	8 to 28	[18]	[18,32]
mdh	malate dehydrogenase	8.8	+	-64 to -33	[18]	[13,17,18,33]
kefGB-yheV	protein required for KefB activity;KefB potass...	2.8	-	-27 to 16**	NaN	[13]
nudE	ADP-sugar pyrophosphorylase	2.6	-	-72 to -51**	NaN	NaN
ugpBAECQ	glycerol-3-P ABC transporter	8.2	-	-2 to 30	NaN	NaN
yhjE	YhjE MFS transporter	3.2	-	-178 to -158**	NaN	NaN
dctA	DctA dicarboxylate DAACS transporter	15.3	-	-72 to 4*	NaN	[34]
lldPRD	L-lactate permease;transcriptional repressor;L...	5	-	-49 to -7	[12]	[13]
nepI	MFS ribonucleoside transporter	2.1	-	-51 to -31	NaN	NaN
yifK	APC transporter	2.4	-	NaN	NaN	NaN
fadBA	fatty acid oxidation complex	27.2	-	-50 to -9	[18]	[13,18]
fdoGHI-fdhE	formate dehydrogenase-O	6	-	-60 to -29**	NaN	NaN
sthA	pyridine nucleotide transhydrogenase, soluble	18.3	-	-36 to -5	NaN	NaN
rsd	stationary phase protein, binds sigma 70 RNA p...	2.8	-	-18 to 8	NaN	NaN
acs-yjcH-actP	acetyl-CoA synthetase;SSS transporter	57.5	-	-34 to 3*	NaN	NaN
yjiR	putative regulator	2.9	-	-43 to -23**	NaN	NaN
ybcW	predicted protein	-2.6	+	no TSS	NaN	NaN
appY	DNA-binding transcriptional activator	-4.6	+	-275 to -221	NaN	[39]
ybfA	predicted protein	-3.2	+	-136 to -94	NaN	NaN
hyaABCDEF	hydrogenase 1	-3.7	+	-18 to 3	[35]	[17,37,38]
oppA	oligopeptide ABC transporter	-2.1	+	-376 to -356, -230 to -210	NaN	[17]
feoABC	ferrous iron transporter	-3.7	NC	-191 to -171	NaN	NaN
slp-dctR	outer membrane lipoprotein;predicted DNA-bindi...	-4	+	-472 to -452	NaN	NaN
gadE-mdtEF	DNA-binding transcriptional activator;multidru...	-11.4	+	-112 to -92	NaN	[36]
gadXW	DNA-binding transcriptional dual regulator	-3.1	+	-226 to -195	NaN	[17]
adiC	arginine:agmatine antiporter	-8	+	-124 to -104	NaN	NaN
fnrS	small regulatory RNA	-	+	-155 to -102	NaN	[9]

In [49]:

cpge = ChipPeakTUGeneExpression
for operon in direct_reg.index:
    if operon in discrepancies.keys() or operon in mapping_errors.keys(): continue
    if not ome.query(cpge).filter_by(target='ArcA').filter(and_(cpge.gene_name.ilike(operon[0:3]+'%'), cpge.fdr < .05)).all():
        print operon

In [76]:

aa = AllAnalysis
ome.query(aa).filter(and_(or_(aa.target1 == 'delta-arcA', aa.target2 == 'delta-arcA'),\
                          or_(aa.target1 == 'wt', aa.target2 == 'wt'), aa.fdr < 1, aa.gene_name.ilike('fnrS%'),\
                          or_(and_(aa.eacceptor1 == 'anaerobic', aa.eacceptor2 == 'anaerobic'),\
                              and_(aa.eacceptor1 == 'NO3', aa.eacceptor2 == 'NO3'),\
                              and_(aa.eacceptor1 == 'O2', aa.eacceptor2 == 'O2')))).all()

Out[76]:

[]

In [42]:

cpge = ChipPeakGeneExpression
ome.query(cpge).filter(and_(cpge.fdr < .05, cpge.gene_name.ilike('app%'))).all()

Out[42]:

[]

In [47]:

discrepancies = {
                 'gcd': 'very weak, insignificant peak, diff expressed',\
                 'tesB': '3 significant out of 12 same as ybaY, diff expressed in NO3',\
                 'ybaY': '3 significant out of 12 same as tesB, diff expressed in NO3',\
                 'ylaC': 'no signal, diff expressed',\
                 'csgD': 'two significant anaerobic peaks, diff expressed',\
                 'ycgZ': 'two significant anaerobic peaks, diff expressed',\
                 'ydcI': 'very weak, insignicant signal, diff expressed',\
                 'maeB': 'very weak, insignicant signal, diff expressed',\
                 'hcaR': 'peak and diff exp for NO3 but no measurement anaerobically',\
                 'trxC': 'peak and diff exp for NO3 but no measurement anaerobically',\
                 'ycgZ-ymgA-ariR-ymgC': 'two significant anaerobic peaks, diff expressed',\
                 'kefGB-yheV': 'two significant anaerobic peaks, diff expressed',\
                 'dctA': 'two significant anaerobic peaks, diff expressed',\
                 'nepI': 'peak and diff exp for NO3 but no measurement anaerobically',\
                 'yifK': 'very weak, insignificant signal',\
                 'ybcW': 'two significant anaerobic peaks, prophage related, diff expressed',\
                 'appY': 'peak and diff exp for NO3 but no measurement anaerobically',\
                 'hyaABCDEF': 'very weak, insignicant signal, diff expressed',\
                 'slp-dctR': 'two significant anaerobic peaks, diff expressed just above cutoff',\
                 'adiC': 'peak and diff exp for NO3 but no measurement anaerobically',\
                 'fnrS': 'no signal, sRNA'
                 }
                 
                 

In [51]:

direct_reg

Out[51]:

<class 'pandas.core.frame.DataFrame'>
Index: 85 entries, pdhR-aceEF-lpdA to fnrS
Data columns (total 6 columns):
Function                       85  non-null values
Fold_change                    85  non-null values
occupancy_change_σ70_-O2_O2    85  non-null values
ArcA_TSS_distance              82  non-null values
Previous_ArcA-P_Binding        16  non-null values
Previous_effect                39  non-null values
dtypes: object(6)

In [48]:

mapping_errors = {
                       'pdhR-aceEF-lpdA': 'aceEF-lpdA is repressed but not pdhR',\
                       'cstA': 'peak calling error, now FP',\
                       'feaR': 'peak calling error, now FP',\
                       'yehDCBA': 'peak calling error, now FP',\
                       'rsd': 'peak is called for thiABCDEF',\
                       'appY':' peak calling error, now FP'
                       
                       
                       }

In [ ]: