Mercurial > repos > yating-l > hubarchivecreator

comparison datatypes/Datatype.py @ 66:4ca7cbf2d9b8 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/goeckslab/hub-archive-creator commit 159730602ff500b59aefc7080fb49b726c88d655-dirty
author yating-l
date Tue, 26 Sep 2017 16:44:58 -0400
parents
children 2440ce10848b
comparison
equal deleted inserted replaced
65:5a4206366b41 66:4ca7cbf2d9b8
1 #!/usr/bin/python
2 # -*- coding: utf8 -*-
3
4 """
5 Super Class of the managed datatype
6 """
7
8 import os
9 import tempfile
10 import collections
11 import util
12 import logging
13 import abc
14 from abc import ABCMeta
15 from TrackDb import TrackDb
16 from datatypes.validators.DataValidation import DataValidation
17
18
19 class Datatype(object):
20 __metaclass__ = ABCMeta
21
22 twoBitFile = None
23 chromSizesFile = None
24 input_fasta_file = None
25 extra_files_path = None
26 tool_directory = None
27
28 mySpecieFolderPath = None
29 myTrackFolderPath = None
30
31
32 def __init__(self):
33 not_init_message = "The {0} is not initialized." \
34 "Did you use pre_init static method first?"
35 if Datatype.input_fasta_file is None:
36 raise TypeError(not_init_message.format('reference genome'))
37 if Datatype.extra_files_path is None:
38 raise TypeError(not_init_message.format('track Hub path'))
39 if Datatype.tool_directory is None:
40 raise TypeError(not_init_message.format('tool directory'))
41 self.inputFile = None
42 self.trackType = None
43 self.dataType = None
44 self.track = None
45 self.trackSettings = dict()
46 self.extraSettings = collections.OrderedDict()
47
48 @staticmethod
49 def pre_init(reference_genome, two_bit_path, chrom_sizes_file,
50 extra_files_path, tool_directory, specie_folder, tracks_folder):
51 Datatype.extra_files_path = extra_files_path
52 Datatype.tool_directory = tool_directory
53
54 # TODO: All this should be in TrackHub and not in Datatype
55 Datatype.mySpecieFolderPath = specie_folder
56 Datatype.myTrackFolderPath = tracks_folder
57
58 Datatype.input_fasta_file = reference_genome
59
60 # 2bit file creation from input fasta
61 Datatype.twoBitFile = two_bit_path
62 Datatype.chromSizesFile = chrom_sizes_file
63
64 def generateCustomTrack(self):
65 self.validateData()
66 self.initSettings()
67 #Create the track file
68 self.createTrack()
69 # Create the TrackDb Object
70 self.createTrackDb()
71 logging.debug("- %s %s created", self.dataType, self.trackName)
72
73
74 @abc.abstractmethod
75 def validateData(self):
76 """validate the input data with DataValidation"""
77
78 def initSettings(self, trackType = None):
79 #Initialize required fields: trackName, longLabel, shortLable
80 self.trackName = self.trackSettings["name"]
81 if self.trackSettings["long_label"]:
82 self.longLabel = self.trackSettings["long_label"]
83 else:
84 self.longLabel = self.trackName
85 if not "short_label" in self.trackSettings:
86 self.shortLabel = ""
87 else:
88 self.shortLabel = self.trackSettings["short_label"]
89 self.trackDataURL = os.path.join(self.myTrackFolderPath, self.trackName)
90 if trackType:
91 self.trackType = trackType
92
93 @abc.abstractmethod
94 def createTrack(self):
95 """Create the final track file"""
96
97 def createTrackDb(self):
98 self.track = TrackDb(self.trackName, self.longLabel, self.shortLabel, self.trackDataURL, self.trackType, self.extraSettings)
99
100
101
102
103
104
105
106 '''
107 def __init__(self):
108 not_init_message = "The {0} is not initialized." \
109 "Did you use pre_init static method first?"
110 if Datatype.input_fasta_file is None:
111 raise TypeError(not_init_message.format('reference genome'))
112 if Datatype.extra_files_path is None:
113 raise TypeError(not_init_message.format('track Hub path'))
114 if Datatype.tool_directory is None:
115 raise TypeError(not_init_message.format('tool directory'))
116 self.track = None
117 self.extra_settings = collections.OrderedDict()
118
119
120 @staticmethod
121 def pre_init(reference_genome, two_bit_path, chrom_sizes_file,
122 extra_files_path, tool_directory, specie_folder, tracks_folder):
123 Datatype.extra_files_path = extra_files_path
124 Datatype.tool_directory = tool_directory
125
126 # TODO: All this should be in TrackHub and not in Datatype
127 Datatype.mySpecieFolderPath = specie_folder
128 Datatype.myTrackFolderPath = tracks_folder
129
130 Datatype.input_fasta_file = reference_genome
131
132 # 2bit file creation from input fasta
133 Datatype.twoBitFile = two_bit_path
134 Datatype.chromSizesFile = chrom_sizes_file
135
136 @staticmethod
137 def get_largest_scaffold_name(self):
138 # We can get the biggest scaffold here, with chromSizesFile
139 with open(Datatype.chromSizesFile.name, 'r') as chrom_sizes:
140 # TODO: Check if exists
141 return chrom_sizes.readline().split()[0]
142
143
144 def createTrack(self, trackName, longLabel, shortLabel, trackDataURL, trackType, extra_settings=None):
145 self.track = TrackDb(trackName, longLabel, shortLabel, trackDataURL, trackType, extra_settings)
146
147 def initRequiredSettings(self, trackSettings, trackDataURL = None, trackType = None):
148
149 #Initialize required fields: trackName, longLabel, shortLable
150
151 self.trackSettings = trackSettings
152 self.trackName = self.trackSettings["name"]
153 #self.priority = self.trackSettings["order_index"]
154 #self.track_color = self.trackSettings["track_color"]
155 # TODO: Think about how to avoid repetition of the group_name everywhere
156 #self.group_name = self.trackSettings["group_name"]
157 #self.database = self.trackSettings["database"]
158 if self.trackSettings["long_label"]:
159 self.longLabel = self.trackSettings["long_label"]
160 else:
161 self.longLabel = self.trackName
162 if not "short_label" in self.trackSettings:
163 self.shortLabel = ""
164 else:
165 self.shortLabel = self.trackSettings["short_label"]
166 self.trackDataURL = trackDataURL
167 self.trackType = trackType
168
169 def setExtLink(self, database, inputFile, seqType=None, useIframe=True, iframeHeight=None, iframeWidth=None):
170 if "NCBI" in database:
171 if not seqType:
172 self.seqType = int(self.getSeqType(inputFile))
173 else:
174 self.seqType = seqType
175 if self.seqType < 0:
176 print self.seqType
177 raise Exception("Sequence Type is not set for bigPsl. Stopping the application")
178 if self.seqType == 2:
179 self.extra_settings["url"] = "https://www.ncbi.nlm.nih.gov/protein/$$"
180 elif self.seqType == 1:
181 self.extra_settings["url"] = "https://www.ncbi.nlm.nih.gov/nuccore/$$"
182 else:
183 raise Exception("Sequence Type {0} is not valid for bigPsl. Stopping the application".format(self.seqType))
184 elif "UniProt" in database:
185 self.extra_settings["url"] = "http://www.uniprot.org/uniprot/$$"
186 elif "FlyBase" in database:
187 self.extra_settings["url"] = "http://flybase.org/reports/$$"
188 else:
189 self.extra_settings["url"] = "https://www.ncbi.nlm.nih.gov/gquery/?term=$$"
190 self.extra_settings["urlLabel"] = database + " Details:"
191 if useIframe:
192 self.extra_settings["iframeUrl"] = self.extra_settings["url"]
193 if not iframeHeight:
194 iframeHeight = "600"
195 if not iframeWidth:
196 iframeWidth = "800"
197 self.extra_settings["iframeOptions"] = "height= %s width= %s" % (iframeHeight, iframeWidth)
198
199 def getSeqType(self, inputFile):
200 with open(inputFile, "r") as bigpsl:
201 sampleSeq = bigpsl.readline().split()
202 if len(sampleSeq) == 25:
203 return sampleSeq[-1]
204 else:
205 return "-1"
206 '''