def __init__(self):
self.config = Utils.loadConfig()
self.task = self.config.get('eval', 'task')
self.gold = self.config.get('eval', 'goldID.path')
self.result = self.config.get('eval', 'result.path')
self.threshold = float(self.config.get('eval', 'threshold'))
self.sparkContext = SparkContext(conf=Utils.getSparkConf('filter'))
self.Similarity = Similarity.Similarity(self.config)
self.Filter = Filter.Filter(self.config,
sparkContext=self.sparkContext)
self.Merger = Merger.Merger(self.config)
self.goldIDs = Utils.readFileLines(self.gold)[1:]
self.resultFiles = Utils.listFilesExt(self.result, 'IDs.test')
# total nb of gold genes
self.nbGoldGenes = len(self.goldIDs)
# total nb of gold clusters
self.foldedGold = Utils.foldClusterData(self.goldIDs, 'gold', 0)
self.goldGenes = [
gene for genes in self.foldedGold.values() for gene in genes
]
self.nbGoldClusters = len(self.foldedGold)
self.outputheader = 'goldClusterID\tgoldGeneID\tpredictedClusterLabel\tpredictedClusterID\n'
self.scoreheader = 'goldClusterID\tpredictedClusterID\tclusterScore\n'
def __init__(self):
self.config = Utils.loadConfig()
self.path = self.config.get('prediction', 'source.path')
self.path = Utils.normalizePath(self.path)
self.trainPath = self.path + 'train/'
self.testPath = self.path + 'test/'
self.outputPath = self.path + 'metricsQLearner/models/'
self.geneMapPath = self.config.get('eval', 'filter.map')
self.geneMap = {}
self.extractor = Extractor.Extractor(self.config, self.outputPath)
self.rewardType = 'occ'
self.rewardPath = self.outputPath + self.rewardType + 'PerDomains.feat' # pfam domain list
self.rewardList, self.rewardIDs, self.rewardLabels = '', '', ''
self.actions = ['keep', 'skip']
self.task = 'train'
self.rewardTable, self.QTable = [], []
self.episodes = int(self.config.get('prediction', 'episodes'))
# hyperparams
self.alpha = float(self.config.get('prediction',
'alpha')) # learning rate
self.gamma = float(self.config.get('prediction',
'gamma')) # discount factor
self.epsilon = float(self.config.get('prediction',
'epsilon')) # exploration
self.penaltyThreshold = float(
self.config.get(
'prediction',
'penalty.threshold')) # negative rewards mean penalty
self.keepskipThreshold = float(
self.config.get('prediction', 'keepskip.threshold')
) # keep reward ratio wrt skip reward for domain to be kept
self.useSimilarityWeight = False
self.useCompWeights = False
self.useNeighborWeight = self.config.getboolean(
'prediction', 'neighbor.weight')
self.useDryIslands = self.config.getboolean('prediction',
'dry.islands')
self.useAvAction = self.config.getboolean('prediction',
'average.action')
self.weightsPath = self.config.get('eval', 'weights')
self.weights = Utils.readFileLines(
self.weightsPath
) if self.useCompWeights or self.useNeighborWeight else ''
self.params = self.rewardType + '_keepgt' + str(
self.keepskipThreshold) + 'skip' + '_ep' + str(
self.episodes) + '_alpha' + str(self.alpha) + '_gamma' + str(
self.gamma) + '_eps' + str(self.epsilon)
self.params += '_neighbor' if self.useCompWeights else ''
self.QTablePath = self.outputPath + 'Qtable_' + self.params + '.npy'
self.rewardTablePath = self.outputPath + 'Rewards_' + self.params + '.npy'
self.IDmapPath = self.outputPath + 'RewardIDsmap_' + self.params + '.map'
def __init__(self, blastTask):
self.config = Utils.loadConfig()
self.sourceType = self.config.get('dataPipeline', 'source.type')
self.blastTask = blastTask
self.blastdb = self.config.get('blaster', 'blastdb.path')
self.blastdb = Utils.normalizePath(self.blastdb)
self.blastdbName = self.config.get('blaster', 'blastdb.name')
if(not self.blastdbName.endswith('fasta')):
self.blastdbName += '.fasta'
self.goTerms = True if 'goterm' in blastTask.lower() else False
self.mappingFile = self.blastdb + self.blastdbName.replace('.fasta','.tab')
self.mapping = ''
if(self.goTerms):
self.mapping = self.loadMapping()
def __init__(self):
self.config = Utils.loadConfig()
self.corpus_path = self.config.get('corpusPrep', 'corpus.home')
self.source_path = self.config.get('corpusPrep', 'source.path')
self.result_path = self.config.get('corpusPrep', 'result.path')
self.task = self.config.get('corpusPrep', 'task')
self.ext = self.config.get('corpusPrep', 'source.ext')
self.seqType = self.config.get('corpusPrep', 'source.type')
self.posPath = self.config.get('corpusPrep', 'pos.path')
self.negPath = self.config.get('corpusPrep', 'neg.path')
self.validPerc = self.config.get('corpusPrep', 'valid.perc')
self.posPerc = self.config.getint('corpusPrep', 'pos.perc')
self.targetIds = self.config.get('corpusPrep', 'pos.ids')
self.filterIds = self.config.get('corpusPrep', 'pos.filters')
self.length = self.config.getint('corpusPrep', 'cluster.length')
self.windowOverlap = self.config.getint('corpusPrep', 'window.overlap')
self.clusterLen = self.config.getint('corpusPrep', 'cluster.length')
def __init__(self):
# read application configuration props
self.config = Utils.loadConfig()
self.path = self.config.get('prediction', 'source.path')
self.path = Utils.normalizePath(self.path)
self.trainPath = self.path + 'train/'
self.validPath = self.path + 'validation/'
self.gridCVPath = self.path + 'train_validation/'
self.testPath = self.path + 'test/'
self.outputPath = self.path + 'metrics/cv_gridsearchparams/'
self.task = self.config.get('prediction', 'task')
self.posPerc = int(self.config.get('prediction', 'pos.perc'))
self.classif = self.config.get('prediction', 'classifier')
os.makedirs(os.path.dirname(self.outputPath), exist_ok=True)
self.extractor = Extractor.Extractor(self.config, self.outputPath)
self.loader = Loader.Loader(self.config, self.outputPath)
self.dimHandler = DimensionHandler.DimensionHandler(
self.config, self.outputPath)
self.outFile = ''
self.useEmbeddings = self.config.getboolean('prediction',
'use.embeddings')
self.cv = self.config.getboolean('prediction', 'use.crossvalid')
if ('cross' in self.task):
self.cv = True
if (not 'none' in self.dimHandler.name.lower()):
self.outFile = self.dimHandler.getOutFile(self.classif)
self.outFile = self.outFile + '_embeddings' if self.useEmbeddings else self.outFile
else:
self.outFile = self.outputPath + self.classif + '_' + self.extractor.featType
if ('kmers' in self.extractor.featType):
kmerfeats = 'kmers' + str(
self.extractor.size) + '_minOcc' + str(
self.extractor.minOcc)
self.outFile = self.outFile.replace('kmers', kmerfeats)
#self.outFile += str(self.extractor.size) + '_minOcc' + str(self.extractor.minOcc)
if ('cross' in self.task or 'grid' in self.task or self.cv):
self.extractor.featFile = self.extractor.featFile.replace(
'.feat', '.complete.feat'
) if 'grid' in self.task else self.extractor.featFile
if ('cross' in self.task or self.cv):
self.outFile += '_cv05'
self.modelFile = self.outFile + '.model.pkl'
self.classifier = self.setUpClassifier()
def __init__(self, source_type=None, source_path=None, result_path=None):
self.config = Utils.loadConfig()
self.task = self.config.get('dataPipeline', 'task')
self.source_path = self.config.get(
'dataPipeline',
'source.path') if source_path is None else source_path
self.source_type = self.config.get(
'dataPipeline',
'source.type') if source_type is None else source_type
self.result_path = self.config.get(
'dataPipeline',
'result.path') if result_path is None else result_path
self.result_path = Utils.normalizePath(self.result_path)
# create if it doesnt exist
os.makedirs(os.path.dirname(self.result_path), exist_ok=True)
# recover the species name for using in temp files
self.species = Utils.getSpecies(self.source_path)
# temp dir + file used by sub-pipelines
self.path = os.path.dirname(os.path.realpath(__file__))
self.path += '/temp/'
os.makedirs(os.path.dirname(self.path), exist_ok=True)
def genBankToFasta():
config = Utils.loadConfig()
source = config.get('parsers', 'source.path')
if not str(source).endswith('/'):
output = source + '_fasta/'
source += '/'
else:
source[len(source) - 1] = ''
output = source + '_fasta/'
source += '/'
os.makedirs(os.path.dirname(output), exist_ok=True)
list = genBankToAminoacid(source)
content = ''
for item in list:
content += item + '\n'
Utils.writeFile(output + 'fungi_complete' + '.fasta', content)
def __init__(self):
self.config = Utils.loadConfig()