/usr/lib/python2.7/dist-packages/cogent/parse/ncbi_taxonomy.py is in python-cogent 1.9-9.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 | #!/usr/bin/env python
"""Extracts data from NCBI nodes.dmp and names.dmp files.
"""
from cogent.core.tree import TreeNode
from string import strip
__author__ = "Jason Carnes"
__copyright__ = "Copyright 2007-2016, The Cogent Project"
__credits__ = ["Jason Carnes", "Rob Knight"]
__license__ = "GPL"
__version__ = "1.9"
__maintainer__ = "Jason Carnes"
__email__ = "jason.carnes@sbri.org"
__status__ = "Development"
class MissingParentError(Exception):
pass
#Note: numbers not guaranteed to be consistent if new taxa are invented...
RanksToNumbers = {
'forma':1,
'varietas':2,
'subspecies':3,
'species':4,
'species subgroup':5,
'species group':6,
'subgenus':7,
'genus':8,
'subtribe':9,
'tribe':10,
'subfamily':11,
'family':12,
'superfamily':13,
'parvorder':14,
'infraorder':15,
'suborder':16,
'order':17,
'superorder':18,
'infraclass':19,
'subclass':20,
'class':21,
'superclass':22,
'subphylum':23,
'phylum':24,
'superphylum':25,
'kingdom':26,
'superkingdom':27,
'no rank':28,
}
class NcbiTaxon(object):
"""Extracts taxon information: init from one line of NCBI's nodes.dmp.
Properties:
TaxonId ID of this node
ParentId ID of this node's parent
Rank Rank of this node: genus, species, etc.
EmblCode Locus name prefix; not unique
DivisionId From division.dmp
DivisionInherited 1 or 0; 1 if node inherits division from parent
TranslTable ID of this node's genetic code from gencode.dmp
GCInherit 1 or 0; 1 if node inherits genetic code from parent
TranslTableMt ID of this node's mitochondrial code from gencode.dmp
TranslTableMtInherited 1 or 0; 1 if node inherits mt code from parent
Hidden 1 or 0; 1 if hidden by default in GenBank's listing
HiddenSubtreeRoot 1 or 0; 1 if no sequences from this subtree exist
Comments free-text comments
RankId Arbitrary number corresponding to rank. See RanksToNumbers.
Name Name of this node: must get from external source. Thanks
so much, NCBI...
Expect a string: '' by default.
"""
Fields = ['TaxonId', 'ParentId', 'Rank', 'EmblCode',
'DivisionId', 'DivisionInherited', 'TranslTable',
'TranslTableInherited',
'TranslTableMt', 'TranslTableMtInherited', 'Hidden',
'HiddenSubtreeRoot', 'Comments']
def __init__(self, line):
"""Returns new NcbiTaxon from line containing taxonomy data."""
line_pieces = map(strip, line.split('|'))
for i in [0, 1, 5, 6, 7, 8, 9, 10, 11]:
line_pieces[i] = int(line_pieces[i])
#fix trailing delimiter
last = line_pieces[-1]
if last.endswith('|'):
line_pieces[-1] = last[:-1]
self.__dict__ = dict(zip(self.Fields, line_pieces))
self.Name = '' #will get name field from names.dmp; fillNames
self.RankId = RanksToNumbers.get(self.Rank, None)
def __str__(self):
"""Writes data out in format we got it."""
pieces = [str(getattr(self,f)) for f in self.Fields]
#remember to set the parent of the root to itself
if pieces[1] == 'None':
pieces[1] = pieces[0]
return '\t|\t'.join(pieces) + '\t|\n'
def __cmp__(self, other):
"""Compare by taxon rank."""
try:
return cmp(self.RankId, other.RankId)
except AttributeError:
return 1 #always sort ranked nodes above unranked
def NcbiTaxonParser(infile):
"""Returns a sequence of NcbiTaxon objects from sequence of lines."""
for line in infile:
if line.strip():
yield NcbiTaxon(line)
def NcbiTaxonLookup(taxa):
"""Returns dict of TaxonId -> NcbiTaxon object."""
result = {}
for t in taxa:
result[t.TaxonId] = t
return result
class NcbiName(object):
"""Extracts name information: init from one line of NCBI's names.dmp.
Properties:
TaxonId TaxonId of this node
Name Text representation of the name, e.g. Homo sapiens
UniqueName The unique variant of this name if Name not unique
NameClass Kind of name, e.g. scientific name, synonym, etc.
"""
Fields = ['TaxonId', 'Name', 'UniqueName', 'NameClass']
def __init__(self, line):
"""Returns new NcbiName from line containing name data."""
line_pieces = map(strip, line.split('|'))
line_pieces[0] = int(line_pieces[0]) #convert taxon_id
self.__dict__ = dict(zip(self.Fields, line_pieces))
def __str__(self):
"""Writes data out in similar format as the one we got it from."""
return '\t|\t'.join([str(getattr(self, f)) for f in self.Fields]) \
+ '|\n'
def NcbiNameParser(infile):
"""Returns sequence of NcbiName objects from sequence of lines."""
for line in infile:
if line.strip():
yield NcbiName(line)
def NcbiNameLookup(names):
"""Returns dict mapping taxon id -> NCBI scientific name."""
result = {}
for name in names:
if name.NameClass == 'scientific name':
result[name.TaxonId] = name
return result
class NcbiTaxonomy(object):
"""Holds root node of a taxonomy tree, plus lookup by id or name."""
def __init__(self, taxa, names, strict=False):
"""Creates new taxonomy, using data in Taxa and Names.
taxa should be the product of NcbiTaxonLookup.
names should be the product of NcbiNameLookup.
strict, if True, raises an error on finding taxa whose parents don't
exist. Otherwise, will put them in self.Deadbeats keyed by parent ID.
Note: because taxa is a dict, nodes will be added in arbitrary order.
"""
names_to_nodes = {}
ids_to_nodes = {}
for t_id, t in taxa.iteritems():
name_rec = names.get(t_id, None)
if name_rec:
name = name_rec.Name
else:
name = 'Unknown'
t.Name = name
node = NcbiTaxonNode(t)
names_to_nodes[name] = node
ids_to_nodes[t_id] = node
self.ByName = names_to_nodes
self.ById = ids_to_nodes
deadbeats = {}
#build the tree by connecting each node to its parent
for t_id, t in ids_to_nodes.iteritems():
if t.ParentId == t.TaxonId:
t.Parent = None
else:
try:
ids_to_nodes[t.ParentId].append(t)
except KeyError: #found a child whose parent doesn't exist
if strict:
raise MissingParentError, \
"Node %s has parent %s, which isn't in taxa." % \
(t_id, t.ParentId)
else:
deadbeats[t.ParentId] = t
self.Deadbeats = deadbeats
self.Root = t.root()
def __getitem__(self, item):
"""If item is int, returns taxon by id: otherwise, searches by name.
Returns the relevant NcbiTaxonNode.
Will raise KeyError if not present.
"""
try:
return self.ById[int(item)]
except ValueError:
return self.ByName[item]
class NcbiTaxonNode(TreeNode):
"""Provides some additional methods specific to Ncbi taxa."""
def __init__(self, Data):
"""Returns a new NcbiTaxonNode object; requires NcbiTaxon to initialize."""
self.Data = Data
self._parent = None
self.Children = []
def getRankedDescendants(self, rank):
"""Returns all descendants of self with specified rank as flat list."""
curr = self.Rank
if curr == rank:
result = [self]
else:
result = []
for i in self:
result.extend(i.getRankedDescendants(rank))
return result
def _get_parent_id(self):
return self.Data.ParentId
ParentId = property(_get_parent_id)
def _get_taxon_id(self):
return self.Data.TaxonId
TaxonId = property(_get_taxon_id)
def _get_rank(self):
return self.Data.Rank
Rank = property(_get_rank)
def _get_name(self):
return self.Data.Name
Name = property(_get_name)
def NcbiTaxonomyFromFiles(nodes_file, names_file, strict=False):
"""Returns new NcbiTaxonomy fron nodes and names files."""
taxa = NcbiTaxonLookup(NcbiTaxonParser(nodes_file))
names = NcbiNameLookup(NcbiNameParser(names_file))
return NcbiTaxonomy(taxa, names, strict)
|