def dictToHtml(dictionary,
byValueFirst=False,
addEcDescriptions=False,
headingDescriptionForHeading=None) -> str:
if addEcDescriptions is not False:
from FEV_KEGG.Graph.Elements import EcNumber
EcNumber.addEcDescriptions(addEcDescriptions)
sortedList = prettySortDict(dictionary, byValueFirst)
from yattag import Doc
doc, tag, _ = Doc().tagtext()
with tag('html'):
# remove underline from links
with tag('head'):
doc.asis(
'<style type="text/css">a {text-decoration:none;}</style>')
with tag('body'):
for heading, rows in sortedList:
with tag('p'):
with tag('table'):
doc.asis(heading.toHtml())
if headingDescriptionForHeading is not None:
headingDescription = headingDescriptionForHeading.get(
heading, None)
if headingDescription is not None:
with tag('table'):
with tag('tr'):
with tag('td'):
doc.asis('{')
for line in headingDescription:
with tag('tr'):
doc.asis(line.toHtml(short=True))
with tag('tr'):
with tag('td'):
doc.asis('}')
with tag('table'):
for row in rows:
with tag('tr'):
doc.asis(row.toHtml(short=True))
with tag('br'):
pass
return doc.getvalue()
def ecNumbers(self) -> Set[EcNumber]:
"""
GoldmanLUCA's EC numbers.
Generalised to the first three levels. The last level is always a wildcard.
Returns
-------
Set[EcNumber]
Set of the EC numbers predicted by Goldman et al. to belong to LUCA.
"""
lucaEcNumberStrings = [
'1.3.1.-', '2.4.1.-', '2.7.1.-', '2.7.7.-', '3.1.2.-', '3.1.4.-',
'3.2.1.-', '3.5.1.-', '4.1.2.-', '6.3.2.-'
]
lucaEcNumbers = set()
for string in lucaEcNumberStrings:
lucaEcNumbers.add(EcNumber(string))
return lucaEcNumbers
'4.2.1.20', '4.2.1.22', '4.2.1.24', '4.2.1.3', '4.2.1.35', '4.2.1.51',
'4.2.1.52', '4.2.1.55', '4.2.1.60', '4.2.1.75', '4.2.1.9', '4.2.3.1',
'4.3.1.17', '4.3.1.19', '4.3.2.1', '4.3.2.2', '4.6.1.12', '5.1.1.1',
'5.1.1.3', '5.1.1.7', '5.3.1.1', '5.3.1.16', '5.3.1.9', '5.4.2.1',
'5.4.2.10', '5.4.2.2', '5.4.2.7', '5.4.3.8', '5.4.99.18', '6.1.1.10',
'6.1.1.11', '6.1.1.17', '6.1.1.4', '6.1.1.5', '6.1.1.9', '6.2.1.1',
'6.2.1.5', '6.3.2.1', '6.3.2.10', '6.3.2.12', '6.3.2.13', '6.3.2.2',
'6.3.2.3', '6.3.2.4', '6.3.2.6', '6.3.2.8', '6.3.2.9', '6.3.3.1',
'6.3.3.3', '6.3.4.13', '6.3.4.14', '6.3.4.15', '6.3.4.18', '6.3.4.2',
'6.3.4.4', '6.3.4.5', '6.3.5.2', '6.3.5.3', '6.3.5.4', '6.3.5.5',
'6.4.1.2'
]
theirECnumbers = set()
for string in theirECnumberStrings:
theirECnumbers.add(EcNumber(string))
#- remove outdated EC numbers
outdatedEcNumberStrings = [
'1.1.1.158', '1.17.1.2', '1.17.4.2', '1.3.1.26', '1.3.3.1', '1.3.99.1',
'2.3.1.89', '2.4.2.11', '2.7.4.14', '3.5.1.47', '3.6.1.15', '3.6.1.19',
'4.2.1.52', '4.2.1.60', '5.4.2.1'
]
outdatedEcNumbers = set()
for string in outdatedEcNumberStrings:
outdatedEcNumbers.add(EcNumber(string))
theirECnumbers.difference_update(outdatedEcNumbers)
#- reduce set of EC numbers to first three levels
theirECnumbers = EcNumber.insertWildcards(theirECnumbers,
keepLevels=3,
def _SubstanceReactionGraph2SubstanceEcGraph(
self, speciesSubstanceReactionGraph: SubstanceReactionGraph
) -> SubstanceEcGraph:
"""
Converts NUKA's substance-reaction graph into a substance-EC graph. Uses pathway information embedded into the graph object.
Parameters
----------
speciesSubstanceReactionGraph : SubstanceReactionGraph
NUKA's substance-reaction graph.
Returns
-------
SubstanceEcGraph
NUKA's substance-EC graph.
Warnings
--------
This function is special to NUKA and **MUST NOT** be used anywhere else!
"""
# shallow-copy old graph to new graph
graph = SubstanceEcGraph(
speciesSubstanceReactionGraph.underlyingRawGraph)
graph.name = 'Substance-EC NUKA'
# create dict of replacements: reaction -> {EC numbers}
replacementDict = dict()
# for each embedded pathway, get list of 'enzyme' entries
for pathway in speciesSubstanceReactionGraph.pathwaySet:
ecEntryList = [
e for e in pathway.entries.values() if e.type == 'enzyme'
]
# for each EC number, get reactions in which it is involved
for ecEntry in ecEntryList:
reactionIDList = ecEntry.reaction.split()
if len(
reactionIDList
) > 0: # filter EC numbers not associated with any reaction
ecNumberList = ecEntry.name.split()
# replace each reaction with its associated EC number
for reactionID in reactionIDList:
reactionName = reactionID.split(':', 1)[1]
reaction = ReactionID(reactionName)
# save associated EC numbers in a set
ecNumberSet = set()
for ecNumberString in ecNumberList:
ecNumber = EcNumber(
ecNumberString.replace('ec:', ''))
ecNumberSet.add(ecNumber)
# update the replacement dict for the current reaction, adding the newly created EC number set
replacementSet = replacementDict.get(reaction, None)
if replacementSet == None or replacementSet.__class__ != set:
replacementSet = set()
replacementSet.update(ecNumberSet)
replacementDict[reaction] = replacementSet
# get list of all reaction edges. Copy edge list to prevent changes in-place, which would NOT work
edgeList = list(graph.getEdges())
# replace reaction edges with EC number edges, using replacement dict
for edge in edgeList:
substrate, product, reaction = edge
# delete old edge
graph.removeEdge(substrate, product, reaction, False)
# add new edges, according to replacement dict
replacementSet = replacementDict[reaction]
for ecNumber in replacementSet:
graph.addEC(substrate, product, ecNumber, False)
if init_verbosity > 0:
print('calculated ' + graph.name)
return graph
CoreLUCA.CladeType.archaeaBacteria
]:
#- get collective metabolism of clade
coreLuca = CoreLUCA(clade)
output.append(coreLuca.nameAbbreviation)
#- REPEAT for varying majority percentages
for percentage in range(100, 0, -10):
#- calculate core metabolism
ourECnumbers = coreLuca.substanceEcGraph(percentage).getECs()
#- reduce EC numbers to first three levels
ourECnumbers = EcNumber.insertWildcards(ourECnumbers,
keepLevels=3,
allowHigherWildcards=False,
returnSet=True)
onlyInTheirs = goldmanLucaEcNumbers.difference(ourECnumbers)
inBoth = goldmanLucaEcNumbers.intersection(ourECnumbers)
onlyInOurs = ourECnumbers.difference(goldmanLucaEcNumbers)
output.append(
str(percentage) + '%:\t' + str(len(onlyInTheirs)) + '\t' +
str(len(inBoth)) + '\t' + str(len(onlyInOurs)))
output.append("\n")
for line in output:
print(line)
theirECnumberStrings = [
'1.1.1.158', '1.1.1.193', '1.1.1.25', '1.5.1.3', '1.6.4.5', '1.7.99.5',
'2.2.1.2', '2.3.1.129', '2.3.1.39', '2.4.1.182', '2.4.1.21',
'2.5.1.15', '2.5.1.19', '2.5.1.7', '2.5.1.9', '2.6.1.16', '2.7.1.107',
'2.7.1.130', '2.7.1.23', '2.7.1.24', '2.7.1.26', '2.7.1.33', '2.7.2.3',
'2.7.4.6', '2.7.4.8', '2.7.4.9', '2.7.6.3', '2.7.7.18', '2.7.7.2',
'2.7.7.23', '2.7.7.27', '2.7.7.3', '2.7.7.38', '2.7.7.41', '2.7.8.5',
'2.7.8.8', '3.1.3.45', '3.5.4.16', '3.5.4.25', '3.5.4.26', '3.6.1.1',
'3.6.1.34', '3.6.1.45', '4.1.1.36', '4.1.1.65', '4.1.2.13', '4.1.2.16',
'4.1.2.25', '4.2.1.10', '4.2.1.11', '4.6.1.3', '4.6.1.4', '5.1.1.3',
'5.3.1.1', '5.3.1.13', '6.3.2.12', '6.3.2.13', '6.3.2.15', '6.3.2.4',
'6.3.2.5', '6.3.2.8', '6.3.2.9'
]
theirECnumbers = set()
for string in theirECnumberStrings:
theirECnumbers.add(EcNumber(string))
#- get group of organisms 'Escherichia coli'
eco = Organism.Organism('eco')
#- calculate EC numbers occuring in eco's core metabolism
ourECnumbersWithWildcard = eco.substanceEcGraph(
noMultifunctional=True).getECs()
ourECnumbers = EcNumber.removeWildcards(ourECnumbersWithWildcard)
#- overlap Almaas' set with ours and print amount of EC numbers inside the intersection and falling off either side
onlyInTheirs = theirECnumbers.difference(ourECnumbers)
inBoth = theirECnumbers.intersection(ourECnumbers)
onlyInOurs = ourECnumbers.difference(theirECnumbers)
output.append(
cladePair = CladePair(archaea_clade, gammaproteobacteria_clade)
#- export coloured graph to file, containing all three sets of differing ECs, using the default majority percentage of 80
cladePair_graph = cladePair.unifiedMetabolism(colour=True)
Export.forCytoscape(cladePair_graph,
'experiments/40/archaea_vs_gammaproteobacteria',
inCacheFolder=True)
#- REPEAT for varying majority-percentages:
for percentage in [100, 90, 80, 70, 60, 50, 40, 30, 20, 10, 1]:
#- overlap sets and print amount of EC numbers inside the intersection and falling off either side
only_archaea = cladePair.lostMetabolism(percentage).getECs()
both = cladePair.conservedMetabolism(percentage).getECs()
only_gammaproteobacteria = cladePair.addedMetabolism(
percentage).getECs()
#- remove wildcard EC numbers
only_archaea = EcNumber.removeWildcards(only_archaea)
both = EcNumber.removeWildcards(both)
only_gammaproteobacteria = EcNumber.removeWildcards(
only_gammaproteobacteria)
output.append(
str(percentage) + '%:\t' + str(len(only_archaea)) + '\t' +
str(len(both)) + '\t' + str(len(only_gammaproteobacteria)))
for line in output:
print(line)
'2.4.2.1', '2.4.2.1', '2.4.2.1', '2.4.2.1', '2.4.2.2', '2.4.2.1',
'2.7.1.21', '2.1.1.45', '1.7.3.3', '2.7.1.48', '2.7.1.48', '2.7.1.48',
'1.1.1.204', '2.4.2.22', '6.3.4.13', '6.3.3.1', '6.3.5.3', '6.3.4.2',
'2.7.4.3', '2.4.2.7', '4.3.2.2', '4.3.2.2', '6.3.4.4', '2.1.2.3',
'2.1.3.2', '6.3.4.2', '1.3.3.1', '3.5.2.3', '2.1.2.2', '2.7.4.8',
'2.4.2.14', '6.3.5.2', '3.5.4.10', '1.1.1.205', '2.7.4.6', '2.4.2.10',
'2.4.2.9', '2.7.4.3', '3.5.3.4', '3.5.4.1', '2.7.4.6', '4.1.1.23',
'2.7.4.4', '1.1.1.204', '1.2.1.8', '1.1.99.1', '3.5.2.6', '2.1.2.9',
'1.11.1.9', '6.1.1.10', '3.5.1.11', '1.15.1.1', '6.1.1.17', '1.11.1.6',
'3.6.1.15', '4.2.1.1', '2.7.7.4', '1.8.1.2', '3.1.3.1', '3.6.1.1',
'3.1.3.1', '3.6.1.2'
]
theirECnumbers = set()
for string in theirECnumberStrings:
theirECnumbers.add(EcNumber(string))
#- remove outdated EC numbers
outdatedEcNumberStrings = [
'1.1.1.118', '1.1.1.158', '1.1.1.2', '1.1.1.204', '1.1.1.21',
'1.1.1.40', '1.1.1.57', '1.1.1.60', '1.1.99.1', '1.1.99.21',
'1.1.99.5', '1.10.2.2', '1.13.11.24', '1.15.1.1', '1.2.1.19',
'1.2.1.2', '1.2.1.21', '1.2.1.22', '1.2.1.25', '1.2.1.51', '1.3.1.26',
'1.3.3.1', '1.3.3.3', '1.3.99.1', '1.3.99.2', '1.3.99.3', '1.4.3.3',
'1.5.1.12', '1.5.1.29', '1.5.1.30', '1.5.3.1', '1.6.5.3', '1.7.99.4',
'1.7.99.5', '1.9.3.1', '2.1.1.13', '2.3.1.41', '2.3.1.79', '2.4.2.11',
'2.4.2.4', '2.5.1.22', '2.5.1.33', '2.6.1.2', '2.6.1.5', '2.6.1.58',
'2.6.1.62', '2.7.1.20', '2.7.1.31', '2.7.1.34', '2.7.1.41', '2.7.1.47',
'2.7.4.11', '2.7.4.14', '2.7.4.4', '2.7.7.1', '2.7.7.10', '2.7.7.58',
'3.1.2.4', '3.1.3.18', '3.1.3.27', '3.1.4.14', '3.2.1.108', '3.2.1.21',
'3.2.1.48', '3.2.2.16', '3.5.1.11', '3.5.1.19', '3.5.1.28', '3.5.1.31',
bacteriaClade = getBacteriaClade()
#- build Archaea clade
archaeaClade = getArchaeaClade()
#- REPEAT for varying majority-percentages:
for percentage in [100, 90, 80, 70, 60, 50, 40, 30, 20, 10, 1]:
#- overlap core metabolisms and print amount of EC numbers inside the intersection and falling off either side
bacteriaECs = bacteriaClade.coreMetabolism(percentage).getECs()
archaeaECs = archaeaClade.coreMetabolism(percentage).getECs()
bothECs = bacteriaECs.intersection(archaeaECs)
onlyBacteriaECs = bacteriaECs.difference(archaeaECs)
onlyArchaeaECs = archaeaECs.difference(bacteriaECs)
#- remove wildcard EC numbers
onlyBacteriaECs = EcNumber.removeWildcards(onlyBacteriaECs)
bothECs = EcNumber.removeWildcards(bothECs)
onlyArchaeaECs = EcNumber.removeWildcards(onlyArchaeaECs)
output.append(
str(percentage) + '%:\t' + str(len(onlyBacteriaECs)) + '\t' +
str(len(bothECs)) + '\t' + str(len(onlyArchaeaECs)))
for line in output:
print(line)
#- build clade pair
cladePair = CladePair(bacteriaClade, archaeaClade)
#- export unified metabolism, coloured by only Archaea/both/only Bacteria
unifiedEcGraph = cladePair.unifiedMetabolism(colour=True)
Export.forCytoscape(unifiedEcGraph,