diff --git a/orthofinder.py b/orthofinder.py
index 859a7ea04b1588168639d61532c94fb51024ed33..45884e55ba207b700ba1d970acb1e6ff027b4b6b 100644
--- a/orthofinder.py
+++ b/orthofinder.py
@@ -25,6 +25,9 @@
# For any enquiries send an email to David Emms
# david_emms@hotmail.com
+nThreadsDefault = 16
+nAlgDefault = 1
+
import sys # Y
import subprocess # Y
import os # Y
@@ -47,10 +50,7 @@ import Queue # Y
import warnings # Y
import time # Y
-sys.path.append(os.path.split(os.path.abspath(__file__))[0] + "/scripts")
-import get_orthologues
-
-version = "0.6.1"
+version = "1.0.0"
fastaExtensions = {"fa", "faa", "fasta", "fas"}
picProtocol = 1
if sys.platform.startswith("linux"):
@@ -886,8 +886,6 @@ class WaterfallMethod:
OrthoFinder
-------------------------------------------------------------------------------
"""
-nThreadsDefault = 16
-nAlgDefault = 1
mclInflation = 1.5
def CanRunCommand(command, qAllowStderr = False):
@@ -1041,6 +1039,9 @@ def AssignIDsToSequences(fastaDirectory, outputDirectory):
return returnFilenames, originalFastaFilenames, idsFilename, speciesFilename, newSpeciesIDs, previousSpeciesIDs
if __name__ == "__main__":
+ sys.path.append(os.path.split(os.path.abspath(__file__))[0] + "/scripts")
+ import get_orthologues
+
print("\nOrthoFinder version %s Copyright (C) 2014 David Emms\n" % version)
print(""" This program comes with ABSOLUTELY NO WARRANTY.
This is free software, and you are welcome to redistribute it under certain conditions.
@@ -1380,3 +1381,4 @@ if __name__ == "__main__":
print(orthogroupsResultsFilesString)
print(orthologuesResultsFilesString.rstrip())
PrintCitation()
+ util.PrintTime("Done")
diff --git a/scripts/get_orthologues.py b/scripts/get_orthologues.py
index ab6a70dac4b081e17bf75e03562317e69bfd2937..f22758c59f832ac2bd83bb8f644856f6fb04da06 100755
--- a/scripts/get_orthologues.py
+++ b/scripts/get_orthologues.py
@@ -9,6 +9,7 @@ Created on Thu Jun 9 16:00:33 2016
import sys
import os
import ete2
+import subprocess
import numpy as np
from collections import Counter, defaultdict
import cPickle as pic
@@ -139,7 +140,7 @@ def lil_max(M):
# ASTRAL
def GetOGsToUse(ogSet):
- return range(50, min(10000, len(ogSet.ogs)))
+ return range(100, min(10000, len(ogSet.ogs)))
def CreateTaxaMapFile(ogSet, i_ogs_to_use, outputFN):
"""Get max number of sequences per species"""
@@ -180,8 +181,8 @@ def RunAstral(ogSet, treesPat, workingDir):
CreateTaxaMapFile(ogSet, i_ogs_to_use, tmFN)
treesFN = dir_astral + "TreesFile.txt"
ConcatenateTrees(i_ogs_to_use, treesPat, treesFN)
- speciesTreeFN = workingDir + "SpeciesTree.txt"
- print(" ".join(["java", "-Xmx6000M", "-jar", "/home/david/software/ASTRAL-multiind/Astral/astral.4.8.0.jar", "-a", tmFN, "-i", treesFN, "-o", speciesTreeFN]))
+ speciesTreeFN = workingDir + "SpeciesTree_astral.txt"
+ subprocess.call(" ".join(["java", "-Xmx6000M", "-jar", "~/software/ASTRAL-multiind/Astral/astral.4.8.0.jar", "-a", tmFN, "-i", treesFN, "-o", speciesTreeFN]), shell=True)
return speciesTreeFN
# ==============================================================================================================================
@@ -321,13 +322,14 @@ class DendroBLASTTrees(object):
values = " ".join(["%.6g" % (0. + M[i,j]) for j in range(n)]) # hack to avoid printing out "-0"
outfile.write(values + "\n")
treeFN = os.path.split(self.treesPatIDs)[0] + "/SpeciesTree_ids.txt"
- cmd = " ".join(["fastme", "-i", speciesMatrixFN, "-o", treeFN, "-s"])
+ cmd = " ".join(["fastme", "-i", speciesMatrixFN, "-o", treeFN, "-w", "O"] + (["-s"] if n < 1000 else []))
return cmd, treeFN
def PrepareGeneTreeCommand(self):
cmds = []
for iog in xrange(len(self.ogSet.ogs)):
- cmds.append([" ".join(["fastme", "-i", self.distPat % iog, "-o", self.treesPatIDs % iog, "-s"])])
+ nTaxa = len(self.ogSet.ogs[iog])
+ cmds.append([" ".join(["fastme", "-i", self.distPat % iog, "-o", self.treesPatIDs % iog, "-w", "O"] + (["-s"] if nTaxa < 1000 else []))])
return cmds
def RenameTreeTaxa(self, treeFN, newTreeFilename, idsMap, qFixNegatives=False):
@@ -355,7 +357,9 @@ class DendroBLASTTrees(object):
seqDict = self.ogSet.Spec_SeqDict()
for iog in xrange(len(self.ogSet.ogs)):
self.RenameTreeTaxa(self.treesPatIDs % iog, self.treesPat % iog, seqDict, qFixNegatives=True)
- self.RenameTreeTaxa(spTreeFN_ids, self.workingDir + "SpeciesTree_unrooted.txt", self.ogSet.SpeciesDict(), qFixNegatives=True)
+ self.RenameTreeTaxa(spTreeFN_ids, self.workingDir + "SpeciesTree_unrooted.txt", self.ogSet.SpeciesDict(), qFixNegatives=True)
+ #spTreeFN_ids = RunAstral(self.ogSet, self.treesPatIDs, self.workingDir)
+ #self.RenameTreeTaxa(spTreeFN_ids, self.workingDir + "SpeciesTree_astral_unrooted.txt", self.ogSet.SpeciesDict(), qFixNegatives=True)
return len(ogs), D, spPairs, spTreeFN_ids
# ==============================================================================================================================
@@ -434,7 +438,7 @@ def RunDlcpar(treesPat, ogSet, nOGs, speciesTreeFN, workingDir):
if not os.path.exists(dlcparResultsDir): os.mkdir(dlcparResultsDir)
filenames = [rootedTreeDir + os.path.split(treesPat % i)[1] for i in xrange(nOGs)]
- dlcCommands = ['dlcpar_search -s %s -S %s -D 1 -C 0.5 %s -O %s' % (speciesTreeFN, geneMapFN, fn, dlcparResultsDir + os.path.splitext(os.path.split(fn)[1])[0]) for fn in filenames]
+ dlcCommands = ['dlcpar_search -s %s -S %s -D 1 -C 0.125 %s -O %s' % (speciesTreeFN, geneMapFN, fn, dlcparResultsDir + os.path.splitext(os.path.split(fn)[1])[0]) for fn in filenames]
# print(dlcCommands[0])
# use this to run in parallel
tfo.RunParallelCommandSets(nThreads, [[c] for c in dlcCommands], qHideStdout = True)
@@ -535,7 +539,6 @@ def GetOrthologues(orthofinderWorkingDir, orthofinderResultsDir, clustersFilenam
print("Best outgroup for species tree:")
for r in roots: print(" " + (", ".join([spDict[s] for s in r])) )
-# speciesTreeFN = RunAstral(ogSet, db.treesPat, resultsDir)
qMultiple = len(roots) > 1
if qMultiple: print("\nAnalysing each of the potential species tree roots.")
resultsSpeciesTrees = []
diff --git a/scripts/root_from_duplications.py b/scripts/root_from_duplications.py
index bcb71cef9edaad57566a74ce851ad4648357d508..da905e8d635e7e2676d30fc1a51dc0e6de02b146 100644
--- a/scripts/root_from_duplications.py
+++ b/scripts/root_from_duplications.py
@@ -426,8 +426,8 @@ def PlotTree(speciesTree, treesDir, supported_clusters, qSimplePrint=True):
tree_for_figure.render(treesDir + "Duplications.pdf")
def GetRoot(speciesTreeFN, treesDir, GeneToSpeciesMap, nProcessors, treeFmt=None):
- if treeFmt != None: spTreeFormat = treeFmt
- speciesTree = ete2.Tree(speciesTreeFN, format=spTreeFormat)
+ if treeFmt == None: treeFmt = spTreeFormat
+ speciesTree = ete2.Tree(speciesTreeFN, format=treeFmt)
species, dict_clades, clade_names = AnalyseSpeciesTree(speciesTree)
pool = mp.Pool(nProcessors, maxtasksperchild=1)
list_of_lists = pool.map(SupportedHierachies_wrapper2, [(fn, GeneToSpeciesMap, species, dict_clades, clade_names) for fn in glob.glob(treesDir + "/*")])
@@ -490,7 +490,7 @@ if __name__ == "__main__":
print(r)
if args.verbose: PlotTree(speciesTree, args.input_tree, clusters)
else:
- root, clusters, _ = GetRoot(args.Species_tree, args.input_tree, GeneToSpecies, nProcs, treeFmt = 1)
+ root, clusters, _, nSupport = GetRoot(args.Species_tree, args.input_tree, GeneToSpecies, nProcs, treeFmt = 1)
for r in root: print(r)
speciesTree = ete2.Tree(args.Species_tree, format=1)
if args.verbose: PlotTree(speciesTree, args.input_tree, clusters, qSimplePrint=False)
diff --git a/trees_for_orthogroups.py b/trees_for_orthogroups.py
index 9e85022bb2288542ecee8d2483614658804d39c1..7dbd61de3da03f1e85c80ab1cd3b34a2202a6cd4 100755
--- a/trees_for_orthogroups.py
+++ b/trees_for_orthogroups.py
@@ -40,7 +40,7 @@ import glob
import orthofinder
-version = "0.6.1"
+version = "1.0.0"
def RunCommandSet(commandSet, qHideStdout):
# orthofinder.util.PrintTime("Runing command: %s" % commandSet[-1])