v1.0

ba064f26 · Vladimir Reinharz · ba064f26 · ba064f26 · ba064f26 · ba064f26
Commit ba064f26 authored Oct 27, 2015 by Vladimir Reinharz
--- a/BioData/91347.nwk
+++ b/BioData/91347.nwk
--- a/BioData/ChosenSpecies.txt
+++ b/BioData/ChosenSpecies.txt
+AM942759.1: Proteus mirabilis strain HI4320, complete genome
+ABVP01000019.1: Proteus penneri ATCC 35198, P_penneri-1.1.1_Cont6.1, whole genome shotg   or   ABVP01000023.1: Proteus penneri ATCC 35198 P_penneri-1.1.1_Cont336, whole genome shotg
+
+ABJD02000102.1: Providencia stuartii ATCC 25827, P_stuartii-2.0.1_Cont1789, whole genom   or   ABJD02000101.1: Providencia stuartii ATCC 25827 P_stuartii-2.0.1_Cont1786, whole genom
+ABXV02000023.1: Providencia rustigianii DSM 4541, P_rustigianii-1.0.1_Cont1.9, whole ge   or   ABXV02000027.1: Providencia rustigianii DSM 4541 P_rustigianii-1.0.1_Cont2.12, whole g
+
+CP002154.1: Edwardsiella tarda FL6-60, complete genome
+CP001135.1: Edwardsiella tarda EIB202, complete genome
+
+CP002775.1: Serratia sp. AS13, complete genome
+CP002773.1: Serratia plymuthica AS9, complete genome
+
+CP000720.1: Yersinia pseudotuberculosis IP 31758, complete genome
+AM286415.1: Yersinia enterocolitica subsp. enterocolitica 8081, complete genome
+CP001608.1: Yersinia pestis biovar Medievalis str. Harbin 35, complete genome
+AL590842.1: Yersinia pestis CO92, complete genome
+CP000308.1: Yersinia pestis Antiqua, complete genome
+ACNR01000027.1: Yersinia pestis biovar Orientalis str. India 195, Chromosome_Sequence27
+AAOS02000021.1: Yersinia pestis biovar Orientalis str. IP275, gcontig_1106166534832, wh
+
+CP002038.1: Dickeya dadantii 3937, complete genome
+CP001790.1: Pectobacterium wasabiae WPP163, complete genome
+
+CP002124.1: Erwinia sp. Ejp617, complete genome
+CP003085.1: Pantoea ananatis PA13, complete genome
+
+FN543093.2: Cronobacter turicensis z3032, complete genome
+CP000783.1: Cronobacter sakazakii ATCC BAA-894, complete genome
+
+AP006725.1: Klebsiella pneumoniae subsp. pneumoniae NTUH-K2044, DNA complete genom
+CP000647.1: Klebsiella pneumoniae subsp. pneumoniae MGH 78578, complete genome
+CP000964.1: Klebsiella pneumoniae 342, complete genome
+CP001891.1: Klebsiella variicola At-22, complete genome
+
+CP001918.1: Enterobacter cloacae subsp. cloacae ATCC 13047, complete genome
+CP003026.1: Enterobacter asburiae LF7a, complete genome
+
+CP000822.1: Citrobacter koseri ATCC BAA-895, complete genome
+CACD01000298.1: Citrobacter freundii str. ballerup 7851/39, whole genome shotgun seque
+
+AETP01000030.1: Salmonella enterica subsp. enterica serovar Montevideo str. 2009085258,
+ABEJ01000018.1: Salmonella enterica subsp. enterica serovar Schwarzengrund str. SL480, 
+
+CAAZ01000080.1: Salmonella enterica subsp. enterica serovar Typhi str. E98-3139, conti
+FM200053.1: Salmonella enterica subsp. enterica serovar Paratyphi A str. AKU_12601,
+
+CP001113.1: Salmonella enterica subsp. enterica serovar Newport str. SL254, comple
+AE017220.1: Salmonella enterica subsp. enterica serovar Choleraesuis str. SC-B67, 
+
+ABEL01000007.1: Salmonella enterica subsp. enterica serovar Heidelberg str. SL486, gcon   or   ABEL01000016.1: Salmonella enterica subsp. enterica serovar Heidelberg str. SL486 gcon
+CP002614.1: Salmonella enterica subsp. enterica serovar Typhimurium str. UK-1, com
+
+CP001144.1: Salmonella enterica subsp. enterica serovar Dublin str. CT_02021853, c
+AM933172.1: Salmonella enterica subsp. enterica serovar Enteritidis str. P125109, c
+
+CU928145.2: Escherichia coli 55989, chromosome, complete genome
+FN649414.1: Escherichia coli ETEC H10407, complete genome
+CU651637.1: Escherichia coli LF82, chromosome, complete sequence
+CP000247.1: Escherichia coli 536, complete genome
+AE014075.1: Escherichia coli CFT073, complete genome
+CP002729.1: Escherichia coli UMNK88, complete genome
+AP009378.1: Escherichia coli SE15, DNA complete genome
+CP002167.1: Escherichia coli UM146, complete genome
+CP003034.1: Escherichia coli O7:K1 str. CE10, complete genome
+CP000243.1: Escherichia coli UTI89, complete genome
+BA000007.2: Escherichia coli O157:H7 str. Sakai, DNA complete genome
+AM946981.2: Escherichia coli BL21(DE3), complete genome
+CP001368.1: Escherichia coli O157:H7 str. TW14359, complete genome
+CP001671.1: Escherichia coli ABU 83972, complete genome
+CP002212.1: Escherichia coli str. 'clone D i14', complete genome
+AP009048.1: Escherichia coli str. K12 substr. W3110, DNA, complete genome
+CP001855.1: Escherichia coli O83:H1 str. NRG 857C, complete genome
+AE005174.2: Escherichia coli O157:H7 EDL933, complete genome
+AP010960.1: Escherichia coli O111:H- str. 11128, DNA, complete genome
+CP001969.1: Escherichia coli IHE3034, complete genome
+CP001396.1: Escherichia coli BW2952, complete genome
+CP001164.1: Escherichia coli O157:H7 str. EC4115, complete genome
+CP002797.2: Escherichia coli NA114, complete genome
+CP000800.1: Escherichia coli E24377A, complete genome
+CP000802.1: Escherichia coli HS, complete genome
+CU928163.2: Escherichia coli UMN026, chromosome, complete genome
+CU928164.2: Escherichia coli IAI39, chromosome, complete genome
+CP002185.1: Escherichia coli W, complete genome
+CP001509.3: Escherichia coli BL21(DE3), complete genome
+CP000819.1: Escherichia coli B str. REL606, complete genome
+FN554766.1: Escherichia coli 042, complete genome
+CP000970.1: Escherichia coli SMS-3-5, complete genome
+AP009240.1: Escherichia coli SE11, DNA complete genome
+CP001846.1: Escherichia coli O55:H7 str. CB9615, complete genome
+CP002516.1: Escherichia coli KO11, complete genome
+CP000468.1: Escherichia coli APEC O1, complete genome
+CP000946.1: Escherichia coli ATCC 8739, complete genome
+U00096.2: Escherichia coli str. K-12 substr. MG1655, complete genome
+CP002211.1: Escherichia coli str. 'clone D i2', complete genome
+CU928161.2: Escherichia coli S88, chromosome, complete genome
+CP000948.1: Escherichia coli str. K12 substr. DH10B, complete genome
+AP010953.1: Escherichia coli O26:H11 str. 11368, DNA, complete genome
+AP010958.1: Escherichia coli O103:H2 str. 12009, DNA, complete genome
+CU928162.2: Escherichia coli ED1a, chromosome, complete genome
+CU928160.2: Escherichia coli IAI1, chromosome, complete genome
+CP001637.1: Escherichia coli DH1, complete genome
+
+AE005674.2: Shigella flexneri 2a str. 301, complete genome
+CP000266.1: Shigella flexneri 5 str. 8401, complete genome
+CP001383.1: Shigella flexneri 2002017, complete genome
+CP000036.1: Shigella boydii Sb227, complete genome
+CP001063.1: Shigella boydii CDC 3083-94, complete genome
+CP000038.1: Shigella sonnei Ss046, complete genome
\ No newline at end of file
--- a/BioData/RF00083_RF00128_merged.fasta
+++ b/BioData/RF00083_RF00128_merged.fasta
--- a/BioData/RF00083_full.txt
+++ b/BioData/RF00083_full.txt
--- a/BioData/RF00128_full.txt
+++ b/BioData/RF00128_full.txt
--- a/BioData/getNewickTree.py
+++ b/BioData/getNewickTree.py
+import sys
+from Bio import Phylo
+from io import StringIO
+
+
+
+if __name__ == '__main__':
+
+    if len(sys.argv) < 3:
+        print("USAGE : python getNewickTree newickTree listOfSpeciesToKeep")
+        sys.exit()
+
+    newickFile = open(sys.argv[1], 'r')
+    for line in newickFile:
+        theTree = line  #there should be only one line
+    
+    phyloTree = Phylo.read(StringIO(theTree), "newick")
+
+    listToKeep = []
+    listNodesToDel = []
+
+    listToKeepFile = open(sys.argv[2], 'r')
+    dictNameToID = {}
+    for line in listToKeepFile:
+
+        if line == "\n":
+            #print("empty line")
+            continue
+        
+        colonSplit = line.split(": ")
+
+        name = colonSplit[1].split(",")[0]
+        name.strip()
+        name = name.replace(" ", "_")
+        print("The name: " + name)
+        dictNameToID[name] = colonSplit[0]
+        
+        listToKeep.append(name)
+
+    #listToKeep = ["Escherichia_coli_TA124", "Escherichia_coli_DEC2B"]
+
+    print("List to keep size = " + str(len(listToKeep)))
+    
+    for element in phyloTree.find_elements():
+        if element.name is not None and element.name not in listToKeep:
+            #print("Adding node to listNodesToDel")
+            listNodesToDel.append(element.name)
+
+    
+    for node in listNodesToDel:
+        #print("Deleting node: " + node)
+        try:
+            phyloTree.prune(target=node)
+        except:
+            print("Could not delete node: " + node)
+            
+
+    print("Tree after pruning:")
+    print(str(phyloTree))
+
+    outputNewick = open("theTree.out", 'w')
+    Phylo.write(phyloTree, outputNewick, format="newick")
+
+    outputNewick.write("\n\nMapping:\n")
+
+    for key, value in dictNameToID.items():
+        
+        outputNewick.write(key + ":" + value + "\n")
--- a/BioData/getNewickTree.py~
+++ b/BioData/getNewickTree.py~
+import sys
+from urllib.request import urlopen
+from urllib.error import HTTPError, URLError
+
+def name(id):
+    if '.' in id:
+        id = id[:id.find('.')]
+    url = 'http://www.ncbi.nlm.nih.gov/nuccore/%s' % id
+    try:
+        f = urlopen(url)
+    except HTTPError as e:
+        print("HTTP Error:", e.code)
+        print("PDB url %s: download failed" % url)
+        sys.exit(1)
+    except URLError as e:
+        print("URL Error:", e.reason)
+        print("PDB url %s: download failed" %  url)
+        sys.exit(1)
+    for x in f:
+        x = x.decode().strip()
+        if '<title>' in x:
+            return x[x.find('>')+1:-len(r' - Nucleotide - NCBI<\title>')]
+
+if __name__ == '__main__':
+    print(name('AFGV00000000'))
--- a/BioData/listOfSpecies_intersect.txt
+++ b/BioData/listOfSpecies_intersect.txt
--- a/BioData/ncby_name.py
+++ b/BioData/ncby_name.py
+import sys
+from urllib.request import urlopen
+from urllib.error import HTTPError, URLError
+
+def name(id):
+    if '.' in id:
+        id = id[:id.find('.')]
+    url = 'http://www.ncbi.nlm.nih.gov/nuccore/%s' % id
+    try:
+        f = urlopen(url)
+    except HTTPError as e:
+        print("HTTP Error:", e.code)
+        print("PDB url %s: download failed" % url)
+        sys.exit(1)
+    except URLError as e:
+        print("URL Error:", e.reason)
+        print("PDB url %s: download failed" %  url)
+        sys.exit(1)
+    for x in f:
+        x = x.decode().strip()
+        if '<title>' in x:
+            return x[x.find('>')+1:-len(r' - Nucleotide - NCBI<\title>')]
+
+if __name__ == '__main__':
+    print(name('AFGV00000000'))
--- a/BioData/readAlignments_findIntersec.py
+++ b/BioData/readAlignments_findIntersec.py
+import sys
+from urllib.request import urlopen
+from urllib.error import HTTPError, URLError
+
+def name(id):
+    if '.' in id:
+        id = id[:id.find('.')]
+    url = 'http://www.ncbi.nlm.nih.gov/nuccore/%s' % id
+    try:
+        f = urlopen(url)
+    except HTTPError as e:
+        return "HTTP Error:" + str(e.code) + "--> failed to find name for id: " + id
+        #print("PDB url %s: download failed" % url)
+        #sys.exit(1)
+    except URLError as e:
+        return "URL Error:" + e.reason + "--> failed  to find name for id: " + id
+        #print("PDB url %s: download failed" %  url)
+        #sys.exit(1)
+    for x in f:
+        x = x.decode().strip()
+        if '<title>' in x:
+            return x[x.find('>')+1:-len(r' - Nucleotide - NCBI<\title>')]
+
+
+#Reads an RFAM alignment and puts it in a dictionary {"name": alignment. Returns the dictionary.}
+def readAlignment(filename):
+
+    rfamFile = open(filename, 'r')
+
+    nameToAlignDict = {}
+
+    for line in rfamFile:
+
+        tabsplit = line.split("\t")
+        #print("Name = " + tabsplit[0] + " and align = " + tabsplit[1])
+        speciesID = tabsplit[0].split("/")[0]  #eliminating the positions
+        nameToAlignDict[speciesID] = tabsplit[1]
+
+    return nameToAlignDict
+
+#Finds and returns a list of keys that are present in both dicts.
+def intersectDictKeys(dict1, dict2):
+
+    listNamesIntersected = []
+
+    for key in dict1:
+        if key in dict2:
+            listNamesIntersected.append(key)
+
+    return listNamesIntersected
+
+if __name__ == '__main__':
+    #print(name('AFGV00000000'))
+
+    if len(sys.argv) < 3:
+        print("USAGE: python rfamAlignFile1 rfamALignFile2")
+        sys.exit()
+
+    dictFam1 = readAlignment(sys.argv[1])
+    dictFam2 = readAlignment(sys.argv[2])
+
+    intersectionOfNames = intersectDictKeys(dictFam1, dictFam2)
+    print(str(len(intersectionOfNames)))
+
+    for speciesID in intersectionOfNames:
+        print(speciesID + ": " + name(speciesID))
+    
--- a/BioData/readAlignments_findIntersec.py~
+++ b/BioData/readAlignments_findIntersec.py~
+import sys
+from urllib.request import urlopen
+from urllib.error import HTTPError, URLError
+
+def name(id):
+    if '.' in id:
+        id = id[:id.find('.')]
+    url = 'http://www.ncbi.nlm.nih.gov/nuccore/%s' % id
+    try:
+        f = urlopen(url)
+    except HTTPError as e:
+        print("HTTP Error:", e.code)
+        print("PDB url %s: download failed" % url)
+        sys.exit(1)
+    except URLError as e:
+        print("URL Error:", e.reason)
+        print("PDB url %s: download failed" %  url)
+        sys.exit(1)
+    for x in f:
+        x = x.decode().strip()
+        if '<title>' in x:
+            return x[x.find('>')+1:-len(r' - Nucleotide - NCBI<\title>')]
+
+if __name__ == '__main__':
+    print(name('AFGV00000000'))
--- a/BioData/theTree.newick
+++ b/BioData/theTree.newick
+.((((((((......(((((...().)))))....)))))).)).((((((..((((.....((....))...))))...((.....)).)))).))...
+.((((((((......((((((..()))))))....)))))).)).((((((.(((((....(((....)))..))))).(((.....))))))).))...
+#
+(((((((((UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUAGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00006,(UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00008,GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00012)91.00:0.00003)98.00:0.00089,UGCUCAUUUCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUUCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00130)98.00:0.00050,GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUAGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00119)96.00:0.00016,UGCUCAUUCUAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUCUAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00140)70.00:0.00002,(UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00102,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00116)12.00:0.00066)97.00:0.00077,(((GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00074,GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00028)19.00:0.00085,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00129)97.00:0.00319,((((GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00002,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUUGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00005)63.00:0.00091,(UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00097,(GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00099,GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00113)27.00:0.00004)27.00:0.00013)23.00:0.00002,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUAGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00131)96.00:0.00062,((UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00141,GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00189)94.00:0.00155,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCCAC-GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUUGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00234)91.00:0.00043)97.00:0.00059)98.00:0.00004)96.00:0.00104,(UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUUGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00177,GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUUGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00166)95.00:0.00093)97.00:0.00000,((((GGCUCAUUCGCCGACUUAUGUCAGCACAUAAAAUUGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00206,((GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00071,GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00004)93.00:0.00190,GGCUCAUUCGCCGACUUAUGUCAGCACAUAAAAUUGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-GGCUCAUUCGCCGACUUAUGUCAGCACAUAAAAUUGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00172)20.00:0.00000)44.00:0.00005,(((UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00030,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00036)90.00:0.00006,(UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUUGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00001,(GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00022,GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUUGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00012)76.00:0.00007)95.00:0.00014)97.00:0.00129,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00226)60.00:0.00009)64.00:0.00062,(UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00086,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUUGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00105)51.00:0.00171)63.00:0.00212,(GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCUAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCCUU:0.00221,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGACGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACACAACGUUGAGUGAAGCACCACU-GGCUCAUUCACCGACUUAUGUCAGCACAUAAAAUUGAAUGACGCAGGGCCUGCGUCCACUUUGAUCUAUCAUCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00210)100.00:0.00075)100.00:0.00039)97.00:0.00381,(((UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACAGAGAUCCAUCAAUGGACAUAACGUUGAGUGAAGCACCUUU-GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUUUGAAUUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU:0.02365,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACAGAGAUCCAUCAAUGGACAUAACGUUGAGUGAAGCACCUUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACAGAGAUCCAUCACCGGACAUAACGUUGAGUGAAGCACCUUU:0.03183)85.00:0.00668,(((((GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUCGAAUGACGCAGGGCCUGCGUCCAACUUGAAUUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU-GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUUUGAAUUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00290,GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUCGAAUGACGCAGGGCCUGCGUCCAACUUGAAUUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU-GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUUUGAAUUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00108)95.00:0.00047,(GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUCGAAUGACGCAGGGCCUGCGUCCAACUUGAACUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU-GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUUUGAACUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00099,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCACUGGACACAACGUUGAGUGAAGCACCUUU-GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUUUGAACUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00124)1.00:0.00000)0.00:0.00020,(GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUCGAAUGACGCAGGGCCUGCGUCCAACUUGAAUUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU-GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUUUGAAUUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00251,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCACUGGACACAACGUUGAGUGAAGCACCUUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCUUU:0.00279)15.00:0.00027)45.00:0.00044,(UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCACUGGACACAACGUUGAGUGAAGCACCUUA-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCUUU:0.00582,GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUCGAAUGACGCAGGGCCUGCGUCCAACUUGAAUUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCUUU:0.00238)96.00:0.00040)97.00:0.00025,(GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUCGAAUGACGCAGGGCCUGCGUCCAACUUGAAUUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU-GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUUUGAAUUAUCACCGGGCGAAACGUCGAGUUAGGCACCCUU:0.00341,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCACUGGACACAACGUUGAGUGAAGCACCUUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACACAACGUUGAGUGAAGCACCUUU:0.00125)62.00:0.00072)100.00:0.03213)85.00:0.00208,((((GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUCGAAUGACGCAGGGCCUGCGUCCAACUUGAUCUUUCACCGGGCGACACGUUGAGUAAGGCACCCUG-GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUGUGAAUUUUCACCGGGCGACACGUUGAGUAAGGCACCCUG:0.00874,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACCAGAAUGACGCCGGGCUUACGUCCACAGAGAUCCAUCAAUGGACAUAACGUUGAGUGAAGCACCAUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACCAGAAUGACGCCGGGCUUACGUCCACAGAGAUCCAUCACCGGACAUAACGUUGAGUGAAGCACCAUU:0.01083)57.00:0.09021,(((UGCUCAUUCAACUGGUUAUGAUUGCUCAUAACAUUGAAUGAUGCGGGGCCUACGUCCACAGCGAACUAUCAUCGGGCGACACGUUGAGUGAGGCACCCUA-UGCUCAUUCAACUGGUUAUGAUGCGUCAUAACAUUGAAUGAUGCGGGGCCUACGUCCCCAGCGAACUAUCAUCGGGCGACACGUUGAGUGAGGCACCCUA:0.09613,UGCUCAUUCAACUGGUUAUGAUGGCUCAUAACGCCGAAUGAUGCAGGGCCUACGUCCAUUUUGAACUAUCAUCGGGCGACACGUUGAGUGAGGCACCCUA-UGCUCAUUCAACUGGUUAUGAUGUGUCAUAACGCCGAAUGAUGCAGGGCCUACGUCCGCUUUGAACUAUCAUCGGGCGACACGUUGAGUGAGGCACCCUA:0.11281)96.00:0.05374,((((UGCUCAUUCCACUCAUUAUGAUAGCUCAUAAACCAGAAUGAUGCCGGGCCUAUGUCCAAUAAGAAACAUCAAUGGACGAAACGUUGAGUGAGGCACCUCC-UGCUCAUUCCACUCAUUAUGAUAGCUCAUAAACCAGAAUGAUGCCGGGCCUAUGUCCAUAUAGAAACAUCAAUGGACGAAACGUUGAGUGAGGCACCCCG:0.08231,UGCUCAUCCCACUUAUUAUGACAGCUCAUAAACCAGGAUGACGCCGGGCCUAUGUCCAAUUAGAAUCAUCAACGGGCGAAACGUUGAGUGAGGCACCUCC-UGCUCAUCCCACUUAUUAUGACAGCUCAUAAACCAGGAUGACGCCGGGCCUAUGUCCAUUUUGAAACAUCAACGGGCGAAACGUUGAGUGAGGCACCCCG:0.18368)2.00:0.04626,UGCUCAUUCCACUCCUUAUGACAGCUCAUAAACCAGAAUGAUGCCGGGCCUACGUCCAGUUCGAAACAUCACAGGACGAAACGUUGAGUGAGGCACCUCC-UGCUCAUUCCACUCCUUAUGACAGCUCAUAAACCAGAAUGAUGCCGGGCCUACGUCCCGUUCGAAACAUCACAGGACGAAACGUUGAGUGAGGCACCCCG:0.14659)87.00:0.16591,(UGCUCAUUCGCCCCCUUAUGUUUGCUCAUAAAUCGGAAUGAUGCUGGGCCUACGUCCGAAUUGCUCCAGCAACGGACACGUCGUUGAGUGAGGCACCUCA-UGCUCAUUCGCCCCCUUAUGUUUGCUCAUAAAUCGGAAUGAUGCUGGGCCUACGUCCAAUCUGCUCCAGCAACGGACACGUCGUUGAGUGAGGCACCUCA:0.01271,UGCUCAUUCGCCCCCUUAUGUUUGCUCAUAAAUCGGAAUGAUGCUGGGCCUACGUCCGAAUUGCUCCAGCAACGGACACGUCGUUGAGUGAGGCACCUCA-UGCUCAUUCGCCCCCUUAUGUUUGCUCAUAAAUCGGAAUGAUGCUGGGCCUACGUCCAAUCUGCUCCAGCAACGGACACGUCGUUGAGUGAGGCACCUCA:0.01633)26.00:0.19555)45.00:0.00000,(((UGCUCAUUCACCUUUUUAUGAUAGCUCAUAAGCCCGAAUGAUGCUGGGCCUACGUCCAUAACGAUUUAUCAUCGGACGACACGUUGAGUGAGGCACCCUA-UGCUCAUCCCACUUAUUAUGACAGCUCAUAAACCAGGAUGACGCGAGGCCUAUGUCCUGUACGAUUCAUCACCGGGCAUAACGUUGAGUGAGGCACUUAU:0.00000,((UGCUCAUCCCACUUAUUAUGACAGCUCAUAAACCAGGAUGACGCGAGGCCUAUGUCCAGUACGAUUCAUCACCGGGCAUAACGUUGAGUGAGGCACUUAU-UGCUCAUCCCACUUAUUAUGACAGCUCAUAAACCAGGAUGACGCGAGGCCUAUGUCCUGUACGAUUCAUCACCGGGCAUAACGUUGAGUGAGGCACUUAU:0.02902,UGCUCAUCCCACUUAUUAUGACAGCUCAUAAACCAGGAUGACGCGAGGCCUAUGUCCAGUACGAUUCAUCACCGGGCAUAACGUUGAGUGAGGCACUUAU-UGCUCAUCCCACUUAUUAUGACAGCUCAUAAACCAGGAUGACGCGAGGCCUAUGUCCUGUACGAUUCAUCACCGGGCAUAACGUUGAGUGAGGCACUUAU:0.01020)47.00:0.00000,((UGCUCAUCCCACUUAUUAUGACAGCUCAUAAACCAGGAUGACGCGAGGCCUAUGUCCAGUACGAUUCAUCACCGGGCAUAACGUUGAGUGAGGCACUUAU-UGCUCAUCCCACUUAUUAUGACAGCUCAUAAACCAGGAUGACGCGAGGCCUAUGUCCUGUACGAUUCAUCACCGGGCAUAACGUUGAGUGAGGCACUUAU:0.00011,UGCUCAUUCACCUUUUUAUGAUAGCUCAUAAGCCCGAAUGAUGCUGGGCCUACGUCCAUAACGAUUUAUCAUCGGACGACACGUUGAGUGAGGCACCCUA-UGCUCAUUCACCUUUUUAUGAUAGCUCAUAAGCCCGAAUGAUGCUGGGCCUACGUCCCCUACGAUUUAUCAUCGGACGACACGUUGAGUGAGGCACCCUA:0.00000)30.00:0.00000,UGCUCAUUCACCUUUUUAUGAUAGCUCAUAAGCCCGAAUGAUGCUGGGCCUACGUCCAUAACGAUUUAUCAUCGGACGACACGUUGAGUGAGGCACCCUA-UGCUCAUUCACCUUUUUAUGAUAGCUCAUAAGCCCGAAUGAUGCUGGGCCUACGUCCCCUACGAUUUAUCAUCGGACGACACGUUGAGUGAGGCACCCUA:0.00618)51.00:0.00482)80.00:0.00252)96.00:0.02880,UGCUCAUUCACCUCUUUAUGAUAGCUCAUAAGCCCGAAUGAUGCUGGGCCUACGUCCACAACGAUUUAUCAUCGGACGACACGUUGAGUGAGGCGCCCUA-UGCUCAUCCCACUUAUUAUGAUAGCUCAUAAACCAGGAUGACGCGGGGCCUAUGUCCUGUACGAUUCAUCACCGGGCAUAACGUUGAGUGAGGCACCCAU:0.03414)96.00:0.07287,(UGCUCAUUCCACCUCUUAUGUUCGCUCAUAAACCUGAAUGAUGCGGGGCCUAUGUCCACAGCGAACCAUCACCGGGCAUAACGUUGAGUGAGGCACCCCC-UGCUCAUUCAACUUUUUAUGAUGGCUCAUAAGCCCGAAUGAUGCUGGGCCUACGUCCACCACGAACUAUCAUCGGGCGACACGUGGAGUGAGGCACCCUG:0.01254,UGCUCAUUCCACCUCUUAUGUUCGCUCAUAAACCUGAAUGAUGCGGGGCCUAUGUCCACAGCGAACCAUCACCGGGCAUAACGUUGAGUGAGGCACCCCC-UGCUCAUUCCACCUCUUAUGUUCGCUCAUAAACCUGAAUGAUGCGGGGCCUAUGUCCCCAGCGAACCAUCACCGGGCAUAACGUUGAGUGAGGCACCCCC:0.03652)29.00:0.07913)52.00:0.02192)94.00:0.01375)97.00:0.04726,(GGCUCAUUCACCCGGUUAUGACAGCCCAUAACAUCGAAUGACGCCGGGCCUGCGUCCACCCCGAAUUAUCAUCGGACGCCACGUUGAGUCAGGUACCCUA-GGCUCAUUCACCCGGUUAUGACAGCCCAUAACAUUGAAUGACGCCGGGCCUGCGUCCCCCCCGAAUUAUCAUCGGACGCCACGUUGAGUCAGGUACCCUA:0.12892,UGCUCAUUCAUCUGUUUAUGAUUGCUCAUAAAAUCGAAUGACGCCGGGCCUGCGUCCACCACGAAUUAUCAUCGGACGCAACGUUGAGUUAGGCUCCCCA-UGCUCAUUCAUCUGUUUAUGAUUGCUCAUAAAAUCGAAUGACGCCGGGCCUGCGUCCCCCACGAAUUAUCAUCGGACGCAACGUUGAGUUAGGCUCCCCA:0.11159)99.00:0.04734)98.00:0.06592)97.00:0.02944,((GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUCGAAUGACGCAGGGCCUGCGUCCAACUUGAACUAUCAUCGGGCGAAACGUCGAGUAAGGCACCCUC-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACAUUACGUUGAGUGAAGCACCAUU:0.00648,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACAUUACGUUGAGUGAAGCACCAUU-UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCACCGGACAUUACGUUGAGUGAAGCACCAUU:0.00165)71.00:0.00487,(GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUCGAAUGACGCAGGGCCUGCGUCCAACUUGAACUAUCAUCGGGCGAAACGUCGAGUAAGGCACCCUC-GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUCUGAACUAUCAUCGGGCGAAACGUCGAGUAAGGCACCCUC:0.00156,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUCGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGACAUUACGUUGAGUGAAGCACCAUU-GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUCUGAACUAUCAUCGGGCGAAACGUCGAGUAAGGCACCCUC:0.00086)98.00:0.00522)99.00:0.05774)98.00:0.00205,(GGCUCAUUCACCCUCUUAUGUCAGCACAUAAACUCGAAUGACGCAGGGCCUGCGUCCAACUUGAAAUAUCACAGGGCGUAACGUCGAGUUAGGCACCCUC-GGCUCAUUCACCCUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUAUGAAAUAUCACAGGGCGUAACGUCGAGUUAGGCACCCUC:0.01964,UGCUCAUUCCAUCUCUUAUGUUCGCUCAUAAACUAGAAUGAUGCCGGGCUUACGUCCACUGAGAUCCAUCAAUGGGCAUAACGUUGAGUGAAGCACCAUA-GGCUCAUUCACCUUCUUAUGUCAGCACAUAAACUUGAAUGACGCAGGGCCUGCGUCCACUAUGAAUUAUCACAGGGCGAAACGUCGAGUUAGGCACCCUC:0.01620)98.00:0.03634)98.00:0.02469)84.00:0.03348)100.00:0.00000;
\ No newline at end of file
--- a/BioData/theTree_algo4.out
+++ b/BioData/theTree_algo4.out
--- a/README
+++ b/README
+The algorithms are implemented in:
+
+    Src/fitchAndCompany.py
+
+Given a newick tree, simply run: python fitchAndCompany <alg> tree.newick
+where <alg> can be: 1=Fitch  2=Sankoff  3=one structure  4=two structures
+
+Different tools in Src/
+    frnakenstein_generator.py       -Generates by-stable sequences for pair of structures using frnakenstein tool
+    incubator.py                    -Given a seed, target structures a tree, a mutation rate and a transition matrix,
+                                     populates a tree evolving from the seed
+    data_generator.py               -Executes incubator.py
+    run_fitchAndCompany.py          -Executes fitchAndCompany.py
+    make_rfam_tree.py               -Generates the tree to input to fitchAndCompany given BioData/
+    analysis.py                     -Generates the graphs given the output of fitchAndCompany.py
--- a/Src/.DS_Store
+++ b/Src/.DS_Store
--- a/Src/analysis.py
+++ b/Src/analysis.py
+import os
+import sys
+import re
+import cPickle
+from math import log, fsum
+
+from numpy import std, average
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+import matplotlib.patches as mpatches
+
+
+MUT = ['0.01', '0.05', '0.1']
+
+
+DATA = os.path.join('..', 'Data_sank_results')
+re_tot = re.compile(r'Total: (\d+) errors / (\d+) nucleotides \((\d+\.\d+) % error\)') #For the best
+re_tot_uns = r'Total for unstructured positions: (\d+) errors / (\d+) nucleotides \((\d+.\d+) % error\)'
+re_tot_str = r'Total for structured positions: (\d+) errors / (\d+) nucleotides \((\d+.\d+) % error\)'
+re_avg = r'Average \(over (\d+) optimal sequences\): (\d+.\d+) aver. errors per optimal sequence of length = (\d+.\d+) nucleotides \((\d+.\d+) % error\)'
+re_Uns = r'Average for unstructured positions: (\d+.\d+) aver. errors per optimal sequence, considering (\d+.\d+) nucleotides per seq. \((\d+.\d+) % error\)'
+re_Struct = r'Average for structured positions: (\d+.\d+) aver. errors per optimal sequence, considering (\d+.\d+) nucleotides per seq. \((\d+.\d+) % error\)'
+re_tot_err = r'Total: (\d+) errors' #Best root 4 next lines
+re_opt = r'Average \(over (\d+) optimal sequences\): (\d+.\d+) aver. errors per optimal sequence of length = 100.0 nucleotides \((\d+.\d+) % error\)' #All optimales
+re_opt_uns = r'Average for unstructured positions: (\d+.\d+) aver. errors per optimal sequence, considering (\d+.\d+) nucleotides per seq. \((\d+.\d+) % error\)'
+re_opt_str = r'Average for structured positions: (\d+.\d+) aver. errors per optimal sequence, considering (\d+.\d+) nucleotides per seq. \((\d+.\d+) % error\)'
+
+
+#Average pair de structures 
+#Taux d'erreurs Y / mutation X
+#% Total, Uns, Struct
+
+def parser(lines):
+    data = {x:[] for x in ('tot', 'tot_uns', 'tot_str', 'avg', 'Uns', 'Struct', 'tot_err', 'opt', 'opt_uns', 'opt_str')}
+    algos = zip(('tot', 'tot_uns', 'tot_str', 'avg', 'Uns', 'Struct', 'tot_err', 'opt', 'opt_uns', 'opt_str'),
+                (re_tot, re_tot_uns, re_tot_str, re_avg, re_Uns, re_Struct, re_tot_err, re_opt, re_opt_uns, re_opt_str))
+
+    z = 0
+    for x in lines:
+        if "-For the root only:" in x:
+            z += 1
+        if z == 3:break
+        for name, alg in algos:
+            g = re.match(alg, x)
+            if g:
+                data[name].append(g.groups())
+                continue
+    return data
+
+def root_parser(lines):
+    found = False
+    z = 0
+    for x in lines:
+        if "-For the root only:" in x:
+            z += 1
+        if z == 3:
+            found = True
+        if found:
+            g = re.match(re_opt, x)
+            if g:
+                tot = g.groups()[0]
+    return tot
+
+def graph_by_alg(data):
+    def plot_honor(data, color):
+        tot = []
+        tot_err = []
+        str = []
+        str_err = []
+        uns = []
+        uns_err = []
+        ind_data = data.set_index('mut')
+
+        all_plot = [('total', tot, tot_err), 
+                    ('structured', str, str_err), 
+                    ('unstructured', uns, uns_err)]
+
+        for mut in MUT:
+            try:
+                tot.append(ind_data.loc[mut, 'tot'])
+                #print tot[-1]
+                tot_err.append(ind_data.loc[mut, 'tot_err'])
+                str.append(ind_data.loc[mut, 'str'])
+                str_err.append(ind_data.loc[mut, 'str_err'])
+                uns.append(ind_data.loc[mut, 'uns'])
+                uns_err.append(ind_data.loc[mut, 'uns_err'])
+            except KeyError:
+                print mut
+
+        cols = {'total':'k', 'structured':'red', 'unstructured':'blue'}
+        for n, p, e in all_plot:
+            if len(p) != 3:
+                continue
+            plt.errorbar([0.01, 0.05, 0.1], p, yerr=e, label=n, color=cols[n])
+        plt.xlabel([0.01, 0.05, 0.1])
+        plt.legend()
+                
+
+    g = {}
+    for name in data:
+        _, s1, s2, rep, mut, alg, _ = name.split('_')
+        g.setdefault((s1, s2, alg, mut), {})
+        g[s1,s2, alg, mut].setdefault('tot', []).append(
+            float(data[name]['tot'][-1][-1]))
+        g[s1,s2, alg, mut].setdefault('Uns', []).append(
+            float(data[name]['Uns'][-1][-1]))
+        g[s1,s2, alg, mut].setdefault('Struct', []).append(
+            float(data[name]['Struct'][-1][-1]))
+
+    d = {'ss':[], 'alg':[], 'tot':[], 
+         'tot_err':[],  'uns':[], 'uns_err':[],
+         'str':[], 'str_err':[],
+         'mut':[]}
+    for s1,s2,alg, mut in g:
+        d['mut'].append(mut)
+        d['ss'].append(s1+s2)
+        d['alg'].append(alg)
+        d['tot'].append(average(g[s1,s2,alg,mut]['tot']))
+        d['tot_err'].append(std(g[s1,s2,alg,mut]['tot']))
+        d['str'].append(average(g[s1,s2,alg,mut]['Struct']))
+        d['str_err'].append(std(g[s1,s2,alg,mut]['Struct']))
+        d['uns'].append(average(g[s1,s2,alg,mut]['Uns']))
+        d['uns_err'].append(std(g[s1,s2,alg,mut]['Uns']))
+    data = pd.DataFrame(d)
+
+    sns.set(font_scale=1.5)
+    g = sns.FacetGrid(data, col="ss", row='alg', row_order=['1', '2', '3', '4'],
+                     col_order = ['01', '02', '12'])
+    g.map_dataframe(plot_honor).set_axis_labels("Mutation rate", "Percentage Error").add_legend().set(xticks=[0.01, 0.05, 0.1])
+
+    plt.tight_layout()
+    plt.savefig('test.pdf')
+    plt.close()
+    #plt.show()
+
+
+def _graph_by_Region(data):
+    def plot_honor(data, color):
+        d_algs_val = {str(x):[] for x in range(1,5)}
+        d_algs_err = {str(x):[] for x in range(1,5)}
+        d_muts = {str(x):[] for x in range(1,5)}
+        ind_data = data.set_index('alg')
+
+        for x in range(1, 5):
+            x = str(x)
+            m = ind_data.loc[x, 'mut']
+            m = {z:i for i,z in enumerate(m)}
+            vals = ind_data.loc[x, 'vals']
+            errs = ind_data.loc[x, 'errs']
+            for mut in MUT:
+                if mut in m:
+                    d_algs_val[x].append(vals[m[mut]])
+                    d_algs_err[x].append(errs[m[mut]])
+                    d_muts[x].append(mut)
+
+        cols = dict(zip('1234', 'kbgr'))
+        for x in range(1, 5):
+            x = str(x)
+            print d_algs_val[x]
+            eb = plt.errorbar(d_muts[x], d_algs_val[x], yerr=d_algs_err[x], label=x, color=cols[x], alpha=0.5 if x != '1' else 1, linewidth=3.0)
+            eb[-1][0].set_linestyle('--')
+            eb[-1][0].set_linewidth(1)
+        #plt.xlabel([0.01, 0.05, 0.1])
+        plt.legend()
+                
+
+    g = {}
+    for name in data:
+        _, s1, s2, rep, mut, alg, _ = name.split('_')
+        g.setdefault((s1, s2, alg, mut), {})
+        g[s1,s2, alg, mut].setdefault('tot', []).append(
+            float(data[name]['tot'][-1][-1]))
+        g[s1,s2, alg, mut].setdefault('Uns', []).append(
+            float(data[name]['Uns'][-1][-1]))
+        g[s1,s2, alg, mut].setdefault('Struct', []).append(
+            float(data[name]['Struct'][-1][-1]))
+
+    d = {'ss':[], 'alg':[], 'errs':[],
+         'mut':[], 'Region':[], 'vals':[]}
+    for s1,s2,alg, mut in g:
+        for x in ('tot', 'Struct', 'Uns'):
+            d['mut'].append(mut)
+            d['ss'].append(s1+s2)
+            d['alg'].append(alg)
+            d['Region'].append(x)
+            d['vals'].append(average(g[s1,s2,alg,mut][x]))
+            d['errs'].append(std(g[s1,s2,alg,mut][x]))
+    data = pd.DataFrame(d)
+
+    sns.set(font_scale=1.5)
+    g = sns.FacetGrid(data, col="ss", row='Region', row_order=['tot', 'Struct', 'Uns'],
+                     col_order = ['01', '02', '12'])
+    g.map_dataframe(plot_honor).set_axis_labels("Mutation rate", "Percentage Error").add_legend().set(xticks=[0.01, 0.05, 0.1], yticks=[0,2,4,6,8])
+    plt.tight_layout()
+    plt.savefig('error.pdf')
+    plt.close()
+
+    #plt.show()
+
+def graph_by_Region(data):
+    def plot_honor(data, color):
+        d_algs_val = {str(x):[] for x in range(1,5)}
+        d_algs_err = {str(x):[] for x in range(1,5)}
+        d_muts = {str(x):[] for x in range(1,5)}
+        ind_data = data.set_index('alg')
+
+        for x in range(1, 5):
+            x = str(x)
+            m = ind_data.loc[x, 'mut']
+            m = {z:i for i,z in enumerate(m)}
+            vals = ind_data.loc[x, 'vals']
+            errs = ind_data.loc[x, 'errs']
+            for mut in MUT:
+                if mut in m:
+                    d_algs_val[x].append(vals[m[mut]])
+                    d_algs_err[x].append(errs[m[mut]])
+                    d_muts[x].append(mut)
+
+        cols = dict(zip('1234', 'kbgr'))
+        for x in range(1, 5):
+            x = str(x)
+            print d_algs_val[x]
+            eb = plt.errorbar(d_muts[x], d_algs_val[x], yerr=d_algs_err[x], label=x, color=cols[x], alpha=0.5 if x != '1' else 1, linewidth=3.0)
+            eb[-1][0].set_linestyle('--')
+            eb[-1][0].set_linewidth(1)
+        #plt.xlabel([0.01, 0.05, 0.1])
+        plt.legend()
+                
+
+    g = {}
+    for name in data:
+        _, s1, s2, rep, mut, alg, _ = name.split('_')
+        g.setdefault((s1, s2, alg, mut), {})
+        g[s1,s2, alg, mut].setdefault('tot', []).append(
+            float(data[name]['tot'][-1][-1]))
+        g[s1,s2, alg, mut].setdefault('Uns', []).append(