From 527bb0459cf488e5021696e326dc10d28ecdd74c Mon Sep 17 00:00:00 2001 From: Sam Ockman Date: Thu, 24 May 2012 02:18:20 -0400 Subject: Trying to get stuff working under new structure --- wqflask/base/GeneralObject.py | 71 +++++ wqflask/base/JinjaPage.py | 28 ++ wqflask/base/__init__.py | 0 wqflask/base/admin.py | 88 ++++++ wqflask/base/cgiData.py | 70 +++++ wqflask/base/cookieData.py | 52 ++++ wqflask/base/footer.py | 6 + wqflask/base/header.py | 6 + wqflask/base/indexBody.py | 290 +++++++++++++++++++ wqflask/base/myCookie.py | 55 ++++ wqflask/base/sessionData.py | 53 ++++ wqflask/base/template.py | 123 ++++++++ wqflask/base/templatePage.py | 222 +++++++++++++++ wqflask/base/webqtlCaseData.py | 54 ++++ wqflask/base/webqtlConfig.py | 73 +++++ wqflask/base/webqtlConfigLocal.py | 19 ++ wqflask/base/webqtlDataset.py | 160 +++++++++++ wqflask/base/webqtlFormData.py | 289 +++++++++++++++++++ wqflask/base/webqtlTrait.py | 581 ++++++++++++++++++++++++++++++++++++++ 19 files changed, 2240 insertions(+) create mode 100755 wqflask/base/GeneralObject.py create mode 100644 wqflask/base/JinjaPage.py create mode 100755 wqflask/base/__init__.py create mode 100755 wqflask/base/admin.py create mode 100755 wqflask/base/cgiData.py create mode 100755 wqflask/base/cookieData.py create mode 100755 wqflask/base/footer.py create mode 100755 wqflask/base/header.py create mode 100755 wqflask/base/indexBody.py create mode 100755 wqflask/base/myCookie.py create mode 100755 wqflask/base/sessionData.py create mode 100755 wqflask/base/template.py create mode 100755 wqflask/base/templatePage.py create mode 100755 wqflask/base/webqtlCaseData.py create mode 100755 wqflask/base/webqtlConfig.py create mode 100755 wqflask/base/webqtlConfigLocal.py create mode 100755 wqflask/base/webqtlDataset.py create mode 100755 wqflask/base/webqtlFormData.py create mode 100755 wqflask/base/webqtlTrait.py (limited to 'wqflask/base') diff --git a/wqflask/base/GeneralObject.py b/wqflask/base/GeneralObject.py new file mode 100755 index 00000000..311c9e22 --- /dev/null +++ b/wqflask/base/GeneralObject.py @@ -0,0 +1,71 @@ +# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. +# +# This program is free software: you can redistribute it and/or modify it +# under the terms of the GNU Affero General Public License +# as published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +# See the GNU Affero General Public License for more details. +# +# This program is available from Source Forge: at GeneNetwork Project +# (sourceforge.net/projects/genenetwork/). +# +# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) +# at rwilliams@uthsc.edu and xzhou15@uthsc.edu +# +# +# +# This module is used by GeneNetwork project (www.genenetwork.org) +# +# Created by GeneNetwork Core Team 2010/08/10 +# +# Last updated by GeneNetwork Core Team 2010/10/20 + +class GeneralObject: + """ + Base class to define an Object. + a = [Spam(1, 4), Spam(9, 3), Spam(4,6)] + a.sort(lambda x, y: cmp(x.eggs, y.eggs)) + """ + + def __init__(self, *args, **kw): + self.contents = list(args) + for name, value in kw.items(): + setattr(self, name, value) + + def __setitem__(self, key, value): + setattr(self, key, value) + + def __getitem__(self, key): + return getattr(self, key) + + def __getattr__(self, key): + if key in self.__dict__.keys(): + return self.__dict__[key] + else: + return eval("self.__dict__.%s" % key) + + def __len__(self): + return len(self.__dict__) - 1 + + def __str__(self): + s = '' + for key in self.__dict__.keys(): + if key != 'contents': + s += '%s = %s\n' % (key,self.__dict__[key]) + return s + + def __repr__(self): + s = '' + for key in self.__dict__.keys(): + s += '%s = %s\n' % (key,self.__dict__[key]) + return s + + def __cmp__(self,other): + return len(self.__dict__.keys()).__cmp__(len(other.__dict__.keys())) + + + diff --git a/wqflask/base/JinjaPage.py b/wqflask/base/JinjaPage.py new file mode 100644 index 00000000..07e485b1 --- /dev/null +++ b/wqflask/base/JinjaPage.py @@ -0,0 +1,28 @@ +import logging +logging.basicConfig(filename="/tmp/gn_log", level=logging.INFO) +_log = logging.getLogger("search") + +from pprint import pformat as pf + +import templatePage + +from utility import formatting + +import jinja2 +JinjaEnv = jinja2.Environment(loader=jinja2.FileSystemLoader('/gnshare/gn/web/webqtl/templates')) +JinjaEnv.globals['numify'] = formatting.numify + + +class JinjaPage(templatePage.templatePage): + """Class derived from our regular templatePage, but uses Jinja2 instead. + + When converting pages from Python generated templates, change the base class from templatePage + to JinjaPage + + """ + + + def write(self): + """We override the base template write so we can use Jinja2.""" + _log.info(pf(self.__dict__)) + return self.jtemplate.render(**self.__dict__) diff --git a/wqflask/base/__init__.py b/wqflask/base/__init__.py new file mode 100755 index 00000000..e69de29b diff --git a/wqflask/base/admin.py b/wqflask/base/admin.py new file mode 100755 index 00000000..a04df2da --- /dev/null +++ b/wqflask/base/admin.py @@ -0,0 +1,88 @@ +# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. +# +# This program is free software: you can redistribute it and/or modify it +# under the terms of the GNU Affero General Public License +# as published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +# See the GNU Affero General Public License for more details. +# +# This program is available from Source Forge: at GeneNetwork Project +# (sourceforge.net/projects/genenetwork/). +# +# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) +# at rwilliams@uthsc.edu and xzhou15@uthsc.edu +# +# +# +# This module is used by GeneNetwork project (www.genenetwork.org) +# +# Created by GeneNetwork Core Team 2010/08/10 +# +# Last updated by GeneNetwork Core Team 2010/10/20 + + + + + +#XZ, 04/02/2009: we should put this into database. + + +###LIST of databases used into gene name query + + +ADMIN_search_dbs = { + 'rat': {'PERITONEAL FAT': ['FT_2A_0605_Rz'], + 'KIDNEY': ['KI_2A_0405_Rz'], + 'ADRENAL GLAND': ['HXB_Adrenal_1208'], + 'HEART': ['HXB_Heart_1208'] + }, + 'mouse': {'CEREBELLUM': ['CB_M_0305_R'], + 'STRIATUM': ['SA_M2_0905_R', 'SA_M2_0405_RC', 'UTHSC_1107_RankInv', 'Striatum_Exon_0209'], + 'HIPPOCAMPUS': ['HC_M2_0606_R', 'UMUTAffyExon_0209_RMA'], + 'WHOLE BRAIN': ['BR_M2_1106_R', 'IBR_M_0106_R', 'BRF2_M_0805_R', 'UCLA_BHF2_BRAIN_0605'], + 'LIVER': ['LV_G_0106_B', 'UCLA_BHF2_LIVER_0605'], + 'EYE': ['Eye_M2_0908_R'], + 'HEMATOPOIETIC STEM CELLS': ['HC_U_0304_R'], + 'KIDNEY': ['MA_M2_0806_R'], + 'MAMMARY TUMORS': ['MA_M_0704_R', 'NCI_Agil_Mam_Tum_RMA_0409'], + 'PREFRONTAL CORTEX': ['VCUSal_1206_R'], + 'SPLEEN': ['IoP_SPL_RMA_0509'], + 'NUCLEUS ACCUMBENS': ['VCUSalo_1007_R'], + 'NEOCORTEX': ['HQFNeoc_0208_RankInv'], + 'ADIPOSE': ['UCLA_BHF2_ADIPOSE_0605'], + 'RETINA': ['Illum_Retina_BXD_RankInv0410'] + }, + 'human': { + 'LYMPHOBLAST B CELL': ['Human_1008', 'UT_CEPH_RankInv0909'], + 'WHOLE BRAIN': ['GSE5281_F_RMA0709', 'GSE15222_F_RI_0409'] + } + } + + +###LIST of tissue alias + +ADMIN_tissue_alias = {'CEREBELLUM': ['Cb'], + 'STRIATUM': ['Str'], + 'HIPPOCAMPUS': ['Hip'], + 'WHOLE BRAIN': ['Brn'], + 'LIVER': ['Liv'], + 'EYE': ['Eye'], + 'PERITONEAL FAT': ['Fat'], + 'HEMATOPOIETIC STEM CELLS': ['Hsc'], + 'KIDNEY': ['Kid'], + 'ADRENAL GLAND': ['Adr'], + 'HEART': ['Hea'], + 'MAMMARY TUMORS': ['Mam'], + 'PREFRONTAL CORTEX': ['Pfc'], + 'SPLEEN': ['Spl'], + 'NUCLEUS ACCUMBENS': ['Nac'], + 'NEOCORTEX': ['Ctx'], + 'ADIPOSE': ['Wfat'], + 'RETINA': ['Ret'] + } + + diff --git a/wqflask/base/cgiData.py b/wqflask/base/cgiData.py new file mode 100755 index 00000000..57416060 --- /dev/null +++ b/wqflask/base/cgiData.py @@ -0,0 +1,70 @@ +# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. +# +# This program is free software: you can redistribute it and/or modify it +# under the terms of the GNU Affero General Public License +# as published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +# See the GNU Affero General Public License for more details. +# +# This program is available from Source Forge: at GeneNetwork Project +# (sourceforge.net/projects/genenetwork/). +# +# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) +# at rwilliams@uthsc.edu and xzhou15@uthsc.edu +# +# +# +# This module is used by GeneNetwork project (www.genenetwork.org) +# +# Created by GeneNetwork Core Team 2010/08/10 +# +# Last updated by GeneNetwork Core Team 2010/10/20 + +######################################### +#convert Field storage object to Dict object +#in order to be able to saved into a session file +######################################### + +class cgiData(dict): + '''convert Field storage object to Dict object + Filed storage object cannot be properly dumped + ''' + + def __init__(self, field_storage=None): + + if not field_storage: + field_storage={} + + for key in field_storage.keys(): + temp = field_storage.getlist(key) + if len(temp) > 1: + temp = map(self.toValue, temp) + elif len(temp) == 1: + temp = self.toValue(temp[0]) + else: + temp = None + self[key]= temp + + def toValue(self, obj): + '''fieldstorge returns different type of objects, \ + need to convert to string or None''' + try: + return obj.value + except: + return "" + + def getvalue(self, k, default= None): + try: + return self[k] + except: + return default + + getfirst = getvalue + + + + diff --git a/wqflask/base/cookieData.py b/wqflask/base/cookieData.py new file mode 100755 index 00000000..4b7c9046 --- /dev/null +++ b/wqflask/base/cookieData.py @@ -0,0 +1,52 @@ +# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. +# +# This program is free software: you can redistribute it and/or modify it +# under the terms of the GNU Affero General Public License +# as published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +# See the GNU Affero General Public License for more details. +# +# This program is available from Source Forge: at GeneNetwork Project +# (sourceforge.net/projects/genenetwork/). +# +# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) +# at rwilliams@uthsc.edu and xzhou15@uthsc.edu +# +# +# +# This module is used by GeneNetwork project (www.genenetwork.org) +# +# Created by GeneNetwork Core Team 2010/08/10 +# +# Last updated by GeneNetwork Core Team 2010/10/20 + +######################################### +#convert mod_python object to Dict object +#in order to be able to be pickled +######################################### + +class cookieData(dict): + 'convert mod python Cookie object to Dict object' + + def __init__(self, cookies=None): + + if not cookies: + cookies={} + + for key in cookies.keys(): + self[key.lower()]= cookies[key].value + + def getvalue(self, k, default= None): + try: + return self[k.lower()] + except: + return default + + getfirst = getvalue + + + diff --git a/wqflask/base/footer.py b/wqflask/base/footer.py new file mode 100755 index 00000000..6f92fdf8 --- /dev/null +++ b/wqflask/base/footer.py @@ -0,0 +1,6 @@ +import webqtlConfig + +footer_html = open(webqtlConfig.HTMLPATH + 'footer.html', 'r').read() +footer = footer_html.replace('%"','%%"') + +footer_string = footer.replace('', '%s') diff --git a/wqflask/base/header.py b/wqflask/base/header.py new file mode 100755 index 00000000..b6136b51 --- /dev/null +++ b/wqflask/base/header.py @@ -0,0 +1,6 @@ +import webqtlConfig + +header_string = open(webqtlConfig.HTMLPATH + 'header.html', 'r').read() +header_string = header_string.replace("\\'", "'") +header_string = header_string.replace('%"','%%"') +header_string = header_string.replace('', '%s') \ No newline at end of file diff --git a/wqflask/base/indexBody.py b/wqflask/base/indexBody.py new file mode 100755 index 00000000..aa67dffa --- /dev/null +++ b/wqflask/base/indexBody.py @@ -0,0 +1,290 @@ +index_body_string = """ + +

Select and Search +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ Species: + + + +
+ Group: + + + +
+ Type: + + + +
+ Database: + + + + +
+ + +

    Databases marked with ** suffix are not public yet. +
    Access requires user login.

+
+ Get Any: + + + + +
+ + + +

    Enter terms, genes, ID numbers in the Get Any field. +
    Use * or ? wildcards (Cyp*a?, synap*). +
    Use Combined for terms such as tyrosine kinase.

+ +
+ Combined: + + + + +
+ + +      +      + + +
+ + + +
+ + + + + + + + +

 ______________________________________________________ + +

  + +Quick HELP Examples and + + User's Guide

+ + +  You can also use advanced commands. Copy these simple examples +
  into the Get Any or Combined search fields: + + + + + + + + +

Websites Affiliated with GeneNetwork

+

+

+

+

____________________________ + +

Getting Started   

+
    +
  1. Select Species (or select All) +
  2. Select Group (a specific sample) +
  3. Select Type of data: + +
  4. Select a Database +
  5. Enter search terms in the Get Any or Combined field: words, genes, ID numbers, probes, advanced search commands +
  6. Click on the Search button +
  7. Optional: Use the Make Default button to save your preferences +
+ +

____________________________ + +

How to Use GeneNetwork + +

+

Take a 20-40 minute GeneNetwork Tour that includes screen shots and typical steps in the analysis.

+
+
+

For information about resources and methods, select the INFO buttons.

+ + + +

Try the Workstation site to explore data and features that are being implemented.

+ + +

Review the Conditions and Contacts pages for information on the status of data sets and advice on their use and citation.

+ + +
+ + + +

Mirror and Development Sites

+ + + + +

History and Archive + +

+

GeneNetwork's Time Machine links to earlier versions that correspond to specific publication dates.

+ +
+ + +

+ +""" diff --git a/wqflask/base/myCookie.py b/wqflask/base/myCookie.py new file mode 100755 index 00000000..db5320df --- /dev/null +++ b/wqflask/base/myCookie.py @@ -0,0 +1,55 @@ +# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. +# +# This program is free software: you can redistribute it and/or modify it +# under the terms of the GNU Affero General Public License +# as published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +# See the GNU Affero General Public License for more details. +# +# This program is available from Source Forge: at GeneNetwork Project +# (sourceforge.net/projects/genenetwork/). +# +# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) +# at rwilliams@uthsc.edu and xzhou15@uthsc.edu +# +# +# +# This module is used by GeneNetwork project (www.genenetwork.org) +# +# Created by GeneNetwork Core Team 2010/08/10 +# +# Last updated by GeneNetwork Core Team 2010/10/20 + +######################################### +## python cookie and mod python cookie are +## not compatible +######################################### + +class myCookie(dict): + 'define my own cookie' + + def __init__(self, name="", value="", expire = None, path="/"): + self['name']= name + self['value']= value + self['expire']= expire + self['path']= path + + def __getattr__(self, key): + if key in self.keys(): + return self[key] + else: + return None + + def __nonzero__ (self): + if self['name']: + return 1 + else: + return 0 + + + + diff --git a/wqflask/base/sessionData.py b/wqflask/base/sessionData.py new file mode 100755 index 00000000..01555f87 --- /dev/null +++ b/wqflask/base/sessionData.py @@ -0,0 +1,53 @@ +# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. +# +# This program is free software: you can redistribute it and/or modify it +# under the terms of the GNU Affero General Public License +# as published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +# See the GNU Affero General Public License for more details. +# +# This program is available from Source Forge: at GeneNetwork Project +# (sourceforge.net/projects/genenetwork/). +# +# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) +# at rwilliams@uthsc.edu and xzhou15@uthsc.edu +# +# +# +# This module is used by GeneNetwork project (www.genenetwork.org) +# +# Created by GeneNetwork Core Team 2010/08/10 +# +# Last updated by GeneNetwork Core Team 2010/10/20 + +######################################### +#convert mod_python object to Dict object +#in order to be able to be pickled +######################################### + +class sessionData(dict): + 'convert mod python Session object to Dict object' + + def __init__(self, mod_python_session=None): + + if not mod_python_session: + mod_python_session = {} + + for key in mod_python_session.keys(): + self[key]= mod_python_session[key] + + + def getvalue(self, k, default= None): + try: + return self[k] + except: + return default + + getfirst = getvalue + + + diff --git a/wqflask/base/template.py b/wqflask/base/template.py new file mode 100755 index 00000000..85bd86df --- /dev/null +++ b/wqflask/base/template.py @@ -0,0 +1,123 @@ +# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. +# +# This program is free software: you can redistribute it and/or modify it +# under the terms of the GNU Affero General Public License +# as published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +# See the GNU Affero General Public License for more details. +# +# This program is available from Source Forge: at GeneNetwork Project +# (sourceforge.net/projects/genenetwork/). +# +# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) +# at rwilliams@uthsc.edu and xzhou15@uthsc.edu +# +# +# +# This module is used by GeneNetwork project (www.genenetwork.org) +# +# Created by GeneNetwork Core Team 2010/08/10 +# +# Last updated by GeneNetwork Core Team 2010/10/20 + +template = """ + + + + +%s + + + + + + + +%s + + + + + + + + + + + + + + +%s + + + + +%s + + + + + %s + + + + + + + + + + + + + + +
+ + + %s + +
+
+ %s
+
+ + + + + + + + + + +""" diff --git a/wqflask/base/templatePage.py b/wqflask/base/templatePage.py new file mode 100755 index 00000000..4dece24a --- /dev/null +++ b/wqflask/base/templatePage.py @@ -0,0 +1,222 @@ +# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. +# +# This program is free software: you can redistribute it and/or modify it +# under the terms of the GNU Affero General Public License +# as published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +# See the GNU Affero General Public License for more details. +# +# This program is available from Source Forge: at GeneNetwork Project +# (sourceforge.net/projects/genenetwork/). +# +# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) +# at rwilliams@uthsc.edu and xzhou15@uthsc.edu +# +# +# +# This module is used by GeneNetwork project (www.genenetwork.org) +# +# Created by GeneNetwork Core Team 2010/08/10 +# +# Last updated by GeneNetwork Core Team 2010/10/20 + +#templatePage.py +# +#--Genenetwork generates a lot of pages; this file is the generic version of them, defining routines they all use. +# +#Classes: +#templatePage +# +#Functions (of templatePage): +#__init__(...) -- class constructor, allows a more specific template to be used in addition to templatePage +#__str__(self) -- returns the object's elements as a tuple +#__del__(self) -- closes the current connection to MySQL, if there is one +#write -- explained below +#writefile -- explained below +#openMysql(self) -- opens a MySQL connection and stores the resulting cursor in the object's cursor variable +#updMysql(self) -- same as openMysql +#error -- explained below +#session -- explained below + + +import socket +import time +import shutil +import MySQLdb +import os + +from htmlgen import HTMLgen2 as HT + +import template +import webqtlConfig +import header +import footer +from utility import webqtlUtil + + + +class templatePage: + + contents = ['title','basehref','js1','js2', 'layer', 'header', 'body', 'footer'] + + # you can pass in another template here if you want + def __init__(self, fd=None, template=template.template): + + # initiate dictionary + self.starttime = time.time() + self.dict = {} + self.template = template + + for item in self.contents: + self.dict[item] = "" + + self.dict['basehref'] = "" #webqtlConfig.BASEHREF + self.cursor = None + + self.cookie = [] #XZ: list to hold cookies (myCookie object) being changed + self.content_type = 'text/html' + self.content_disposition = '' + self.redirection = '' + self.debug = '' + self.attachment = '' + + #XZ: Holding data (new data or existing data being changed) that should be saved to session. The data must be picklable!!! + self.session_data_changed = {} + + self.userName = 'Guest' + self.privilege = 'guest' + if fd.input_session_data.has_key('user'): + self.userName = fd.input_session_data['user'] + if fd.input_session_data.has_key('privilege'): + self.privilege = fd.input_session_data['privilege'] + + def __str__(self): + + #XZ: default setting + thisUserName = self.userName + thisPrivilege = self.privilege + #XZ: user may just go through login or logoff page + if self.session_data_changed.has_key('user'): + thisUserName = self.session_data_changed['user'] + if self.session_data_changed.has_key('privilege'): + thisPrivilege = self.session_data_changed['privilege'] + + if thisUserName == 'Guest': + userInfo = 'Welcome! Login' + else: + userInfo = 'Hi, %s! Logout' % thisUserName + + reload(header) + self.dict['header'] = header.header_string % userInfo + + serverInfo = "It took %2.3f second(s) for %s to generate this page" % (time.time()-self.starttime, socket.getfqdn()) + reload(footer) + self.dict['footer'] = footer.footer_string % serverInfo + + slist = [] + for item in self.contents: + slist.append(self.dict[item]) + return self.template % tuple(slist) + + + def __del__(self): + if self.cursor: + self.cursor.close() + + def write(self): + 'return string representation of this object' + + if self.cursor: + self.cursor.close() + + return str(self) + + def writeFile(self, filename): + 'save string representation of this object into a file' + if self.cursor: + self.cursor.close() + + try: + 'it could take a long time to generate the file, save to .tmp first' + fp = open(os.path.join(webqtlConfig.TMPDIR, filename+'.tmp'), 'wb') + fp.write(str(self)) + fp.close() + path_tmp = os.path.join(webqtlConfig.TMPDIR, filename+'.tmp') + path_html = os.path.join(webqtlConfig.TMPDIR, filename) + shutil.move(path_tmp,path_html) + except: + pass + + def openMysql(self): + try: + self.con = MySQLdb.Connect(db=webqtlConfig.DB_NAME,host=webqtlConfig.MYSQL_SERVER, \ + user=webqtlConfig.DB_USER,passwd=webqtlConfig.DB_PASSWD) + self.cursor = self.con.cursor() + return 1 + except: + heading = "Connect MySQL Server" + detail = ["Can't connect to MySQL server on '"+ webqtlConfig.MYSQL_SERVER+"':100061. \ + The server may be down at this time"] + self.error(heading=heading,detail=detail,error="Error 2003") + return 0 + + def updMysql(self): + try: + self.con = MySQLdb.Connect(db=webqtlConfig.DB_UPDNAME,host=webqtlConfig.MYSQL_UPDSERVER, \ + user=webqtlConfig.DB_UPDUSER,passwd=webqtlConfig.DB_UPDPASSWD) + self.cursor = self.con.cursor() + return 1 + except: + heading = "Connect MySQL Server" + detail = ["update: Can't connect to MySQL server on '"+ webqtlConfig.MYSQL_UPDSERVER+"':100061. \ + The server may be down at this time "] + self.error(heading=heading,detail=detail,error="Error 2003") + return 0 + + def error(self,heading="",intro=[],detail=[],title="Error",error="Error"): + 'generating a WebQTL style error page' + Heading = HT.Paragraph(heading) + Heading.__setattr__("class","title") + + Intro = HT.Blockquote() + if intro: + for item in intro: + Intro.append(item) + else: + Intro.append(HT.Strong('Sorry!'),' Error occurred while processing\ + your request.', HT.P(),'The nature of the error generated is as\ + follows:') + + Detail = HT.Blockquote() + Detail.append(HT.Span("%s : " % error,Class="fwb cr")) + if detail: + Detail2 = HT.Blockquote() + for item in detail: + Detail2.append(item) + Detail.append(HT.Italic(Detail2)) + + #Detail.__setattr__("class","subtitle") + TD_LR = HT.TD(height=200,width="100%",bgColor='#eeeeee',valign="top") + TD_LR.append(Heading,Intro,Detail) + self.dict['body'] = str(TD_LR) + self.dict['title'] = title + + def session(self,mytitle="",myHeading=""): + 'generate a auto-refreshing temporary html file(waiting page)' + self.filename = webqtlUtil.generate_session() + self.dict['title'] = mytitle + self.dict['basehref'] = webqtlConfig.REFRESHSTR % (webqtlConfig.CGIDIR, self.filename) + "" #webqtlConfig.BASEHREF + + TD_LR = HT.TD(align="center", valign="middle", height=200,width="100%", bgColor='#eeeeee') + Heading = HT.Paragraph(myHeading, Class="fwb fs16 cr") + # NL, 07/27/2010. variable 'PROGRESSBAR' has been moved from templatePage.py to webqtlUtil.py; + TD_LR.append(Heading, HT.BR(), webqtlUtil.PROGRESSBAR) + self.dict['body'] = TD_LR + self.writeFile(self.filename + '.html') + return self.filename + + diff --git a/wqflask/base/webqtlCaseData.py b/wqflask/base/webqtlCaseData.py new file mode 100755 index 00000000..4df32ca4 --- /dev/null +++ b/wqflask/base/webqtlCaseData.py @@ -0,0 +1,54 @@ +# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. +# +# This program is free software: you can redistribute it and/or modify it +# under the terms of the GNU Affero General Public License +# as published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +# See the GNU Affero General Public License for more details. +# +# This program is available from Source Forge: at GeneNetwork Project +# (sourceforge.net/projects/genenetwork/). +# +# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) +# at rwilliams@uthsc.edu and xzhou15@uthsc.edu +# +# +# +# This module is used by GeneNetwork project (www.genenetwork.org) +# +# Created by GeneNetwork Core Team 2010/08/10 +# +# Last updated by GeneNetwork Core Team 2010/10/20 + +class webqtlCaseData: + """ + one case data in one trait + """ + + val = None #Trait Value + var = None #Trait Variance + N = None #Number of individuals + + def __init__(self, val=val, var=var, N=N): + self.val = val + self.var = var + self.N = N + + def __str__(self): + str = "" + if self.val != None: + str += "value=%2.3f" % self.val + if self.var != None: + str += " variance=%2.3f" % self.var + if self.N != None: + str += " ndata=%d" % self.N + return str + + __repr__ = __str__ + + + diff --git a/wqflask/base/webqtlConfig.py b/wqflask/base/webqtlConfig.py new file mode 100755 index 00000000..755595e0 --- /dev/null +++ b/wqflask/base/webqtlConfig.py @@ -0,0 +1,73 @@ +from webqtlConfigLocal import * +#########################################' +# Environment Variables - public +######################################### + +#Debug Level +#1 for debug, mod python will reload import each time +DEBUG = 1 + +#USER privilege +USERDICT = {'guest':1,'user':2, 'admin':3, 'root':4} + +#minimum number of informative strains +KMININFORMATIVE = 5 + +#maximum number of traits for interval mapping +MULTIPLEMAPPINGLIMIT = 11 + +#maximum number of traits for correlation +MAXCORR = 100 + +#Daily download limit from one IP +DAILYMAXIMUM = 1000 + +#maximum LRS value +MAXLRS = 460.0 + +#temporary data life span +MAXLIFE = 86400 + +#MINIMUM Database public value +PUBLICTHRESH = 0 + +#NBCI address +NCBI_LOCUSID = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=gene&cmd=Retrieve&dopt=Graphics&list_uids=%s" +UCSC_REFSEQ = "http://genome.cse.ucsc.edu/cgi-bin/hgGene?db=%s&hgg_gene=%s&hgg_chrom=chr%s&hgg_start=%s&hgg_end=%s" +GENBANK_ID = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=Nucleotide&cmd=search&doptcmdl=DocSum&term=%s" +OMIM_ID = "http://www.ncbi.nlm.nih.gov/omim/%s" +UNIGEN_ID = "http://www.ncbi.nlm.nih.gov/UniGene/clust.cgi?ORG=%s&CID=%s" +HOMOLOGENE_ID = "http://www.ncbi.nlm.nih.gov/sites/entrez?Db=homologene&Cmd=DetailsSearch&Term=%s" +PUBMEDLINK_URL = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=%s&dopt=Abstract" +UCSC_POS = "http://genome.ucsc.edu/cgi-bin/hgTracks?clade=mammal&org=%s&db=%s&position=chr%s:%s-%s&pix=800&Submit=submit" +UCSC_BLAT = 'http://genome.ucsc.edu/cgi-bin/hgBlat?org=%s&db=%s&type=0&sort=0&output=0&userSeq=%s' +UTHSC_BLAT = 'http://ucscbrowser.genenetwork.org/cgi-bin/hgBlat?org=%s&db=%s&type=0&sort=0&output=0&userSeq=%s' +UCSC_GENOME = "http://genome.ucsc.edu/cgi-bin/hgTracks?db=%s&position=chr%s:%d-%d&hgt.customText=http://web2qtl.utmem.edu:88/snp/chr%s" +ENSEMBLE_BLAT = 'http://www.ensembl.org/Mus_musculus/featureview?type=AffyProbe&id=%s' +DBSNP = 'http://www.ncbi.nlm.nih.gov/SNP/snp_ref.cgi?type=rs&rs=%s' +UCSC_RUDI_TRACK_URL = " http://genome.cse.ucsc.edu/cgi-bin/hgTracks?org=%s&db=%s&hgt.customText=http://gbic.biol.rug.nl/~ralberts/tracks/%s/%s" +GENOMEBROWSER_URL="http://ucscbrowser.genenetwork.org/cgi-bin/hgTracks?clade=mammal&org=Mouse&db=mm9&position=%s&hgt.suggest=&pix=800&Submit=submit" +ENSEMBLETRANSCRIPT_URL="http://useast.ensembl.org/Mus_musculus/Lucene/Details?species=Mus_musculus;idx=Transcript;end=1;q=%s" + +SECUREDIR = GNROOT + 'secure/' +COMMON_LIB = GNROOT + 'support/admin' +HTMLPATH = GNROOT + 'web/' +IMGDIR = HTMLPATH +'image/' +IMAGESPATH = HTMLPATH + 'images/' +UPLOADPATH = IMAGESPATH + 'upload/' +TMPDIR = '/tmp/' +GENODIR = HTMLPATH + 'genotypes/' +GENO_ARCHIVE_DIR = GENODIR + 'archive/' +TEXTDIR = HTMLPATH + 'ProbeSetFreeze_DataMatrix/' +CMDLINEDIR = HTMLPATH + 'webqtl/cmdLine/' +ChangableHtmlPath = GNROOT + 'web/' + +SITENAME = 'GN' +PORTADDR = "http://132.192.47.32" +BASEHREF = '' +INFOPAGEHREF = '/dbdoc/%s.html' +GLOSSARYFILE = "/glossary.html" +CGIDIR = '/webqtl/' #XZ: The variable name 'CGIDIR' should be changed to 'PYTHONDIR' +SCRIPTFILE = 'main.py' +REFRESHSTR = '' +REFRESHDIR = '%s' + SCRIPTFILE +'?sid=%s' diff --git a/wqflask/base/webqtlConfigLocal.py b/wqflask/base/webqtlConfigLocal.py new file mode 100755 index 00000000..35da73c2 --- /dev/null +++ b/wqflask/base/webqtlConfigLocal.py @@ -0,0 +1,19 @@ +#########################################' +# Environment Variables - private +######################################### + +MYSQL_SERVER = 'localhost' +DB_NAME = 'db_webqtl' +DB_USER = 'webqtlupd' +DB_PASSWD = 'zhou&yan@ut' + +MYSQL_UPDSERVER = 'localhost' +DB_UPDNAME = 'db_webqtl' +DB_UPDUSER = 'webqtlupd' +DB_UPDPASSWD = 'zhou&yan@ut' + +GNROOT = '/gnshare/gn/' +PythonPath = '/usr/bin/python' +PIDDLE_FONT_PATH = '/usr/lib/python2.4/site-packages/piddle/truetypefonts/' + +TEXTUI=1 # XZ: This is to protect GN production server. If set to 0, no text UI is allowed. diff --git a/wqflask/base/webqtlDataset.py b/wqflask/base/webqtlDataset.py new file mode 100755 index 00000000..da1b8601 --- /dev/null +++ b/wqflask/base/webqtlDataset.py @@ -0,0 +1,160 @@ +# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. +# +# This program is free software: you can redistribute it and/or modify it +# under the terms of the GNU Affero General Public License +# as published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +# See the GNU Affero General Public License for more details. +# +# This program is available from Source Forge: at GeneNetwork Project +# (sourceforge.net/projects/genenetwork/). +# +# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) +# at rwilliams@uthsc.edu and xzhou15@uthsc.edu +# +# +# +# This module is used by GeneNetwork project (www.genenetwork.org) +# +# Created by GeneNetwork Core Team 2010/08/10 +# +# Last updated by GeneNetwork Core Team 2010/10/20 + +from htmlgen import HTMLgen2 as HT + +import webqtlConfig + + + +class webqtlDataset: + """ + Database class defines a database in webqtl, can be either Microarray, + Published phenotype, genotype, or user input database(temp) + """ + + def __init__(self, dbName, cursor=None): + + assert dbName + self.id = 0 + self.name = '' + self.type = '' + self.riset = '' + self.cursor = cursor + + #temporary storage + if dbName.find('Temp') >= 0: + self.searchfield = ['name','description'] + self.disfield = ['name','description'] + self.type = 'Temp' + self.id = 1 + self.fullname = 'Temporary Storage' + self.shortname = 'Temp' + elif dbName.find('Publish') >= 0: + self.searchfield = ['name','post_publication_description','abstract','title','authors'] + self.disfield = ['name','pubmed_id', + 'pre_publication_description', 'post_publication_description', 'original_description', + 'pre_publication_abbreviation', 'post_publication_abbreviation', + 'lab_code', 'submitter', 'owner', 'authorized_users', + 'authors','title','abstract', 'journal','volume','pages','month', + 'year','sequence', 'units', 'comments'] + self.type = 'Publish' + elif dbName.find('Geno') >= 0: + self.searchfield = ['name','chr'] + self.disfield = ['name','chr','mb', 'source2', 'sequence'] + self.type = 'Geno' + else: #ProbeSet + self.searchfield = ['name','description','probe_target_description', + 'symbol','alias','genbankid','unigeneid','omim', + 'refseq_transcriptid','probe_set_specificity', 'probe_set_blat_score'] + self.disfield = ['name','symbol','description','probe_target_description', + 'chr','mb','alias','geneid','genbankid', 'unigeneid', 'omim', + 'refseq_transcriptid','blatseq','targetseq','chipid', 'comments', + 'strand_probe','strand_gene','probe_set_target_region', + 'probe_set_specificity', 'probe_set_blat_score','probe_set_blat_mb_start', + 'probe_set_blat_mb_end', 'probe_set_strand', + 'probe_set_note_by_rw', 'flag'] + self.type = 'ProbeSet' + self.name = dbName + if self.cursor and self.id == 0: + self.retrieveName() + + def __str__(self): + return self.name + + __repr__ = __str__ + + + def getRISet(self): + assert self.cursor + if self.type == 'Publish': + query = ''' + SELECT + InbredSet.Name, InbredSet.Id + FROM + InbredSet, PublishFreeze + WHERE + PublishFreeze.InbredSetId = InbredSet.Id AND + PublishFreeze.Name = "%s" + ''' % self.name + elif self.type == 'Geno': + query = ''' + SELECT + InbredSet.Name, InbredSet.Id + FROM + InbredSet, GenoFreeze + WHERE + GenoFreeze.InbredSetId = InbredSet.Id AND + GenoFreeze.Name = "%s" + ''' % self.name + elif self.type == 'ProbeSet': + query = ''' + SELECT + InbredSet.Name, InbredSet.Id + FROM + InbredSet, ProbeSetFreeze, ProbeFreeze + WHERE + ProbeFreeze.InbredSetId = InbredSet.Id AND + ProbeFreeze.Id = ProbeSetFreeze.ProbeFreezeId AND + ProbeSetFreeze.Name = "%s" + ''' % self.name + else: + return "" + self.cursor.execute(query) + RISet, RIID = self.cursor.fetchone() + if RISet == 'BXD300': + RISet = "BXD" + self.riset = RISet + self.risetid = RIID + return RISet + + + def retrieveName(self): + assert self.id == 0 and self.cursor + query = ''' + SELECT + Id, Name, FullName, ShortName + FROM + %sFreeze + WHERE + public > %d AND + (Name = "%s" OR FullName = "%s" OR ShortName = "%s") + '''% (self.type, webqtlConfig.PUBLICTHRESH, self.name, self.name, self.name) + try: + self.cursor.execute(query) + self.id,self.name,self.fullname,self.shortname=self.cursor.fetchone() + except: + raise KeyError, `self.name`+' doesn\'t exist.' + + + def genHTML(self, Class='c0dd'): + return HT.Href(text = HT.Span('%s Database' % self.fullname, Class= "fwb " + Class), + url= webqtlConfig.INFOPAGEHREF % self.name,target="_blank") + + + + + diff --git a/wqflask/base/webqtlFormData.py b/wqflask/base/webqtlFormData.py new file mode 100755 index 00000000..84e41cae --- /dev/null +++ b/wqflask/base/webqtlFormData.py @@ -0,0 +1,289 @@ +# Copyright (C) University of Tennessee Health Science Center, Memphis, TN. +# +# This program is free software: you can redistribute it and/or modify it +# under the terms of the GNU Affero General Public License +# as published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. +# See the GNU Affero General Public License for more details. +# +# This program is available from Source Forge: at GeneNetwork Project +# (sourceforge.net/projects/genenetwork/). +# +# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) +# at rwilliams@uthsc.edu and xzhou15@uthsc.edu +# +# +# +# This module is used by GeneNetwork project (www.genenetwork.org) +# +# Created by GeneNetwork Core Team 2010/08/10 +# +# Last updated by GeneNetwork Core Team 2010/10/20 + +from mod_python import Cookie +import string +import os + +import reaper + +import webqtlConfig +import cookieData +import sessionData +from cgiData import cgiData +from webqtlCaseData import webqtlCaseData +from utility import webqtlUtil + + + +class webqtlFormData: + 'Represents data from a WebQTL form page, needed to generate the next page' + attrs = ('formID','RISet','genotype','strainlist','allstrainlist', + 'suggestive','significance','submitID','identification', 'enablevariance', + 'nperm','nboot','email','incparentsf1','genotype_1','genotype_2','traitInfo') + + #XZ: Attention! All attribute values must be picklable! + + def __init__(self, req = None, mod_python_session=None, FieldStorage_formdata=None): + + for item in self.attrs: + setattr(self,item, None) + + try: + self.remote_ip = req.connection.remote_ip + except: + self.remote_ip = '1.2.3.4' + + if req and req.headers_in.has_key('referer'): + self.refURL = req.headers_in['referer'] + else: + self.refURL = None + + + self.cookies = cookieData.cookieData(Cookie.get_cookies(req)) #XZ: dictionary type. To hold values transfered from mod_python Cookie. + + #XZ: dictionary type. To hold values transfered from mod_python Session object. We assume that it is always picklable. + self.input_session_data = sessionData.sessionData( mod_python_session ) + + #XZ: FieldStorage_formdata may contain item that can't be pickled. Must convert to picklable data. + self.formdata = cgiData( FieldStorage_formdata ) + + #get Form ID + self.formID = self.formdata.getfirst('FormID') + + #get rest of the attributes + if self.formID: + for item in self.attrs: + value = self.formdata.getfirst(item) + if value != None: + setattr(self,item,string.strip(value)) + + self.ppolar = "" + self.mpolar = "" + if self.RISet: + try: + # NL, 07/27/2010. ParInfo has been moved from webqtlForm.py to webqtlUtil.py; + f1, f12, self.mpolar, self.ppolar = webqtlUtil.ParInfo[self.RISet] + except: + f1 = f12 = self.mpolar = self.ppolar = None + + try: + self.nperm = int(self.nperm) + self.nboot = int(self.nboot) + except: + self.nperm = 2000 #XZ: Rob asked to change the default value to 2000 + self.nboot = 2000 #XZ: Rob asked to change the default value to 2000 + + if self.allstrainlist: + self.allstrainlist = map(string.strip, string.split(self.allstrainlist)) + #self.readGenotype() + #self.readData() + + if self.RISet == 'BXD300': + self.RISet = 'BXD' + else: + pass + + def __str__(self): + rstr = '' + for item in self.attrs: + if item != 'genotype': + rstr += '%s:%s\n' % (item,str(getattr(self,item))) + return rstr + + + def readGenotype(self): + 'read genotype from .geno file' + if self.RISet == 'BXD300': + self.RISet = 'BXD' + else: + pass + assert self.RISet + #genotype_1 is Dataset Object without parents and f1 + #genotype_2 is Dataset Object with parents and f1 (not for intercross) + self.genotype_1 = reaper.Dataset() + self.genotype_1.read(os.path.join(webqtlConfig.GENODIR, self.RISet + '.geno')) + try: + # NL, 07/27/2010. ParInfo has been moved from webqtlForm.py to webqtlUtil.py; + _f1, _f12, _mat, _pat = webqtlUtil.ParInfo[self.RISet] + except: + _f1 = _f12 = _mat = _pat = None + + self.genotype_2 =self.genotype_1 + if self.genotype_1.type == "riset" and _mat and _pat: + self.genotype_2 = self.genotype_1.add(Mat=_mat, Pat=_pat) #, F1=_f1) + + #determine default genotype object + if self.incparentsf1 and self.genotype_1.type != "intercross": + self.genotype = self.genotype_2 + else: + self.incparentsf1 = 0 + self.genotype = self.genotype_1 + self.strainlist = list(self.genotype.prgy) + self.f1list = self.parlist = [] + if _f1 and _f12: + self.f1list = [_f1, _f12] + if _mat and _pat: + self.parlist = [_mat, _pat] + + def readData(self, strainlst=[], incf1=[]): + 'read user input data or from trait data and analysis form' + + if not self.genotype: + self.readGenotype() + if not strainlst: + if incf1: + strainlst = self.f1list + self.strainlist + else: + strainlst = self.strainlist + + + traitfiledata = self.formdata.getfirst('traitfile') + traitpastedata = self.formdata.getfirst('traitpaste') + variancefiledata = self.formdata.getfirst('variancefile') + variancepastedata = self.formdata.getfirst('variancepaste') + Nfiledata = self.formdata.getfirst('Nfile') + + + if traitfiledata: + tt = string.split(traitfiledata) + vals = map(webqtlUtil.StringAsFloat, tt) + elif traitpastedata: + tt = string.split(traitpastedata) + vals = map(webqtlUtil.StringAsFloat, tt) + else: + vals = map(self.FormDataAsFloat, strainlst) + + if len(vals) < len(strainlst): + vals += [None]*(len(strainlst) - len(vals)) + elif len(vals) > len(strainlst): + vals = vals[:len(strainlst)] + else: + pass + + + if variancefiledata: + tt = string.split(variancefiledata) + vars = map(webqtlUtil.StringAsFloat, tt) + elif variancepastedata: + tt = string.split(variancepastedata) + vars = map(webqtlUtil.StringAsFloat, tt) + else: + vars = map(self.FormVarianceAsFloat, strainlst) + + if len(vars) < len(strainlst): + vars += [None]*(len(strainlst) - len(vars)) + elif len(vars) > len(strainlst): + vars = vars[:len(strainlst)] + else: + pass + + if Nfiledata: + tt = string.split(Nfiledata) + nstrains = map(webqtlUtil.IntAsFloat, tt) + if len(nstrains) < len(strainlst): + nstrains += [None]*(len(strainlst) - len(nstrains)) + else: + nstrains = map(self.FormNAsFloat, strainlst) + + ##vals, vars, nstrains is obsolete + self.allTraitData = {} + for i, _strain in enumerate(strainlst): + if vals[i] != None: + self.allTraitData[_strain] = webqtlCaseData(vals[i], vars[i], nstrains[i]) + + + + def informativeStrains(self, strainlst=[], incVars = 0): + '''if readData was called, use this to output the informative strains + (strain with values)''' + if not strainlst: + strainlst = self.strainlist + strains = [] + vals = [] + vars = [] + for _strain in strainlst: + if self.allTraitData.has_key(_strain): + _val, _var = self.allTraitData[_strain].val, self.allTraitData[_strain].var + if _val != None: + if incVars: + if _var != None: + strains.append(_strain) + vals.append(_val) + vars.append(_var) + else: + strains.append(_strain) + vals.append(_val) + vars.append(None) + return strains, vals, vars, len(strains) + + + + def FormDataAsFloat(self, key): + try: + return float(self.formdata.getfirst(key)) + except: + return None + + + def FormVarianceAsFloat(self, key): + try: + return float(self.formdata.getfirst('V' + key)) + except: + return None + + def FormNAsFloat(self, key): + try: + return int(self.formdata.getfirst('N' + key)) + except: + return None + + def Sample(self): + 'Create some dummy data for testing' + self.RISet = 'BXD' + self.incparentsf1 = 'on' + #self.display = 9.2 + #self.significance = 16.1 + self.readGenotype() + self.identification = 'BXD : Coat color example by Lu Lu, et al' + #self.readGenotype() + #self.genotype.ReadMM('AXBXAforQTL') + #self.strainlist = map((lambda x, y='': '%s%s' % (y,x)), self.genotype.prgy) + #self.strainlist.sort() + self.allTraitData = {'BXD29': webqtlCaseData(3), 'BXD28': webqtlCaseData(2), + 'BXD25': webqtlCaseData(2), 'BXD24': webqtlCaseData(2), 'BXD27': webqtlCaseData(2), + 'BXD21': webqtlCaseData(1), 'BXD20': webqtlCaseData(4), 'BXD23': webqtlCaseData(4), + 'BXD22': webqtlCaseData(3), 'BXD14': webqtlCaseData(4), 'BXD15': webqtlCaseData(2), + 'BXD16': webqtlCaseData(3), 'BXD11': webqtlCaseData(4), 'BXD12': webqtlCaseData(3), + 'BXD13': webqtlCaseData(2), 'BXD18': webqtlCaseData(3), 'BXD19': webqtlCaseData(3), + 'BXD38': webqtlCaseData(3), 'BXD39': webqtlCaseData(3), 'BXD36': webqtlCaseData(2), + 'BXD34': webqtlCaseData(4), 'BXD35': webqtlCaseData(4), 'BXD32': webqtlCaseData(4), + 'BXD33': webqtlCaseData(3), 'BXD30': webqtlCaseData(1), 'BXD31': webqtlCaseData(4), + 'DBA/2J': webqtlCaseData(1), 'BXD8': webqtlCaseData(3), 'BXD9': webqtlCaseData(1), + 'BXD6': webqtlCaseData(3), 'BXD5': webqtlCaseData(3), 'BXD2': webqtlCaseData(4), + 'BXD1': webqtlCaseData(1), 'C57BL/6J': webqtlCaseData(4), 'B6D2F1': webqtlCaseData(4), + 'BXD42': webqtlCaseData(4), 'BXD40': webqtlCaseData(3)} + diff --git a/wqflask/base/webqtlTrait.py b/wqflask/base/webqtlTrait.py new file mode 100755 index 00000000..f5051e45 --- /dev/null +++ b/wqflask/base/webqtlTrait.py @@ -0,0 +1,581 @@ +import string + +from htmlgen import HTMLgen2 as HT + +import webqtlConfig +from webqtlCaseData import webqtlCaseData +from webqtlDataset import webqtlDataset +from dbFunction import webqtlDatabaseFunction +from utility import webqtlUtil + + +class webqtlTrait: + """ + Trait class defines a trait in webqtl, can be either Microarray, + Published phenotype, genotype, or user input trait + """ + + def __init__(self, cursor = None, **kw): + self.cursor = cursor + self.db = None # database object + self.name = '' # Trait ID, ProbeSet ID, Published ID, etc. + self.cellid = '' + self.identification = 'un-named trait' + self.riset = '' + self.haveinfo = 0 + self.sequence = '' # Blat sequence, available for ProbeSet + self.data = {} + for name, value in kw.items(): + if self.__dict__.has_key(name): + setattr(self, name, value) + elif name == 'fullname': + name2 = value.split("::") + if len(name2) == 2: + self.db, self.name = name2 + elif len(name2) == 3: + self.db, self.name, self.cellid = name2 + else: + raise KeyError, `value` + ' parameter format error.' + else: + raise KeyError, `name`+' not a valid parameter for this class.' + + if self.db and type(self.db) == type("1"): + assert self.cursor + self.db = webqtlDataset(self.db, self.cursor) + + #if self.db == None, not from a database + if self.db: + if self.db.type == "Temp": + self.cursor.execute(''' + SELECT + InbredSet.Name + FROM + InbredSet, Temp + WHERE + Temp.InbredSetId = InbredSet.Id AND + Temp.Name = "%s" + ''' % self.name) + self.riset = self.cursor.fetchone()[0] + else: + self.riset = self.db.getRISet() + + # + # In ProbeSet, there are maybe several annotations match one sequence + # so we need use sequence(BlatSeq) as the identification, when we update + # one annotation, we update the others who match the sequence also. + # + # Hongqiang Li, 3/3/2008 + # + + #XZ, 05/08/2009: This block is not neccessary. We can add 'BlatSeq' into disfield. + # The variable self.sequence should be changed to self.BlatSeq + # It also should be changed in other places where it are used. + + if self.db: + if self.db.type == 'ProbeSet': + query = ''' + SELECT + ProbeSet.BlatSeq + FROM + ProbeSet, ProbeSetFreeze, ProbeSetXRef + WHERE + ProbeSet.Id=ProbeSetXRef.ProbeSetId and + ProbeSetFreeze.Id = ProbeSetXRef.ProbeSetFreezeId and + ProbeSet.Name = "%s" and + ProbeSetFreeze.Name = "%s" + ''' % (self.name, self.db.name) + self.cursor.execute(query) + self.sequence = self.cursor.fetchone()[0] + + + def getName(self): + str = "" + if self.db and self.name: + str = "%s::%s" % (self.db, self.name) + if self.cellid: + str += "::" + self.cellid + else: + str = self.description + return str + + # + # when user enter a trait or GN generate a trait, user want show the name + # not the name that generated by GN randomly, the two follow function are + # used to give the real name and the database. displayName() will show the + # database also, getGivenName() just show the name. + # For other trait, displayName() as same as getName(), getGivenName() as + # same as self.name + # + # Hongqiang 11/29/07 + # + def getGivenName(self): + str = self.name + if self.db and self.name: + if self.db.type=='Temp': + self.cursor.execute('SELECT description FROM Temp WHERE Name=%s',self.name) + desc = self.cursor.fetchone()[0] + if desc.__contains__('PCA'): + desc = desc[desc.rindex(':')+1:].strip() + else: + desc = desc[:desc.index('entered')].strip() + str = desc + return str + + def displayName(self): + str = "" + if self.db and self.name: + if self.db.type=='Temp': + desc = self.description + if desc.__contains__('PCA'): + desc = desc[desc.rindex(':')+1:].strip() + else: + desc = desc[:desc.index('entered')].strip() + str = "%s::%s" % (self.db, desc) + else: + str = "%s::%s" % (self.db, self.name) + if self.cellid: + str += "::" + self.cellid + else: + str = self.description + + return str + + + #def __str__(self): + # #return "%s %s" % (self.getName(), self.riset) + # return self.getName() + __str__ = getName + __repr__ = __str__ + + def exportData(self, strainlist, type="val"): + """ + export data according to strainlist + mostly used in calculating correlation + """ + result = [] + for strain in strainlist: + if self.data.has_key(strain): + if type=='val': + result.append(self.data[strain].val) + elif type=='var': + result.append(self.data[strain].var) + elif type=='N': + result.append(self.data[strain].N) + else: + raise KeyError, `type`+' type is incorrect.' + else: + result.append(None) + return result + + def exportInformative(self, incVar=0): + """ + export informative strain + mostly used in qtl regression + """ + strains = [] + vals = [] + vars = [] + for strain, value in self.data.items(): + if value.val != None: + if not incVar or value.var != None: + strains.append(strain) + vals.append(value.val) + vars.append(value.var) + return strains, vals, vars + + + # + # In ProbeSet, there are maybe several annotations match one sequence + # so we need use sequence(BlatSeq) as the identification, when we update + # one annotation, we update the others who match the sequence also. + # + # Hongqiang Li, 3/3/2008 + # + def getSequence(self): + assert self.cursor + if self.db.type == 'ProbeSet': + query = ''' + SELECT + ProbeSet.BlatSeq + FROM + ProbeSet, ProbeSetFreeze, ProbeSetXRef + WHERE + ProbeSet.Id=ProbeSetXRef.ProbeSetId and + ProbeSetFreeze.Id = ProbeSetXRef.ProbSetFreezeId and + ProbeSet.Name = %s + ProbeSetFreeze.Name = %s + ''' , (self.name, self.db.name) + self.cursor.execute(query) + results = self.fetchone() + + return results[0] + + + + def retrieveData(self, strainlist=[]): + assert self.db and self.cursor + + if self.db.type == 'Temp': + query = ''' + SELECT + Strain.Name, TempData.value, TempData.SE, TempData.NStrain, TempData.Id + FROM + TempData, Temp, Strain + WHERE + TempData.StrainId = Strain.Id AND + TempData.Id = Temp.DataId AND + Temp.name = '%s' + Order BY + Strain.Name + ''' % self.name + #XZ, 03/02/2009: Xiaodong changed Data to PublishData, SE to PublishSE + elif self.db.type == 'Publish': + query = ''' + SELECT + Strain.Name, PublishData.value, PublishSE.error, NStrain.count, PublishData.Id + FROM + (PublishData, Strain, PublishXRef, PublishFreeze) + left join PublishSE on + (PublishSE.DataId = PublishData.Id AND PublishSE.StrainId = PublishData.StrainId) + left join NStrain on + (NStrain.DataId = PublishData.Id AND + NStrain.StrainId = PublishData.StrainId) + WHERE + PublishXRef.InbredSetId = PublishFreeze.InbredSetId AND + PublishData.Id = PublishXRef.DataId AND PublishXRef.Id = %s AND + PublishFreeze.Id = %d AND PublishData.StrainId = Strain.Id + Order BY + Strain.Name + ''' % (self.name, self.db.id) + + #XZ, 03/02/2009: Xiaodong changed Data to ProbeData, SE to ProbeSE + elif self.cellid: + #Probe Data + query = ''' + SELECT + Strain.Name, ProbeData.value, ProbeSE.error, ProbeData.Id + FROM + (ProbeData, ProbeFreeze, ProbeSetFreeze, ProbeXRef, + Strain, Probe, ProbeSet) + left join ProbeSE on + (ProbeSE.DataId = ProbeData.Id AND ProbeSE.StrainId = ProbeData.StrainId) + WHERE + Probe.Name = '%s' AND ProbeSet.Name = '%s' AND + Probe.ProbeSetId = ProbeSet.Id AND + ProbeXRef.ProbeId = Probe.Id AND + ProbeXRef.ProbeFreezeId = ProbeFreeze.Id AND + ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id AND + ProbeSetFreeze.Name = '%s' AND + ProbeXRef.DataId = ProbeData.Id AND + ProbeData.StrainId = Strain.Id + Order BY + Strain.Name + ''' % (self.cellid, self.name, self.db.name) + #XZ, 03/02/2009: Xiaodong added this block for ProbeSetData and ProbeSetSE + elif self.db.type == 'ProbeSet': + #ProbeSet Data + query = ''' + SELECT + Strain.Name, ProbeSetData.value, ProbeSetSE.error, ProbeSetData.Id + FROM + (ProbeSetData, ProbeSetFreeze, Strain, ProbeSet, ProbeSetXRef) + left join ProbeSetSE on + (ProbeSetSE.DataId = ProbeSetData.Id AND ProbeSetSE.StrainId = ProbeSetData.StrainId) + WHERE + ProbeSet.Name = '%s' AND ProbeSetXRef.ProbeSetId = ProbeSet.Id AND + ProbeSetXRef.ProbeSetFreezeId = ProbeSetFreeze.Id AND + ProbeSetFreeze.Name = '%s' AND + ProbeSetXRef.DataId = ProbeSetData.Id AND + ProbeSetData.StrainId = Strain.Id + Order BY + Strain.Name + ''' % (self.name, self.db.name) + #XZ, 03/02/2009: Xiaodong changeded Data to GenoData, SE to GenoSE + else: + #Geno Data + #XZ: The SpeciesId is not necessary, but it's nice to keep it to speed up database search. + query = ''' + SELECT + Strain.Name, GenoData.value, GenoSE.error, GenoData.Id + FROM + (GenoData, GenoFreeze, Strain, Geno, GenoXRef) + left join GenoSE on + (GenoSE.DataId = GenoData.Id AND GenoSE.StrainId = GenoData.StrainId) + WHERE + Geno.SpeciesId = %s AND Geno.Name = '%s' AND GenoXRef.GenoId = Geno.Id AND + GenoXRef.GenoFreezeId = GenoFreeze.Id AND + GenoFreeze.Name = '%s' AND + GenoXRef.DataId = GenoData.Id AND + GenoData.StrainId = Strain.Id + Order BY + Strain.Name + ''' % (webqtlDatabaseFunction.retrieveSpeciesId(self.cursor, self.db.riset), self.name, self.db.name) + + + self.cursor.execute(query) + results = self.cursor.fetchall() + self.data.clear() + if results: + self.mysqlid = results[0][-1] + if strainlist: + for item in results: + if item[0] in strainlist: + val = item[1] + if val != None: + var = item[2] + ndata = None + if self.db.type in ('Publish', 'Temp'): + ndata = item[3] + self.data[item[0]] = webqtlCaseData(val, var, ndata) + #end for + else: + for item in results: + val = item[1] + if val != None: + var = item[2] + ndata = None + if self.db.type in ('Publish', 'Temp'): + ndata = item[3] + self.data[item[0]] = webqtlCaseData(val, var, ndata) + #end for + #end if + else: + pass + + def keys(self): + return self.__dict__.keys() + + def has_key(self, key): + return self.__dict__.has_key(key) + + def items(self): + return self.__dict__.items() + + def retrieveInfo(self, QTL = None): + assert self.db and self.cursor + if self.db.type == 'Publish': + #self.db.DisField = ['Name','PubMed_ID','Phenotype','Abbreviation','Authors','Title',\ + # 'Abstract', 'Journal','Volume','Pages','Month','Year','Sequence',\ + # 'Units', 'comments'] + query = ''' + SELECT + PublishXRef.Id, Publication.PubMed_ID, + Phenotype.Pre_publication_description, Phenotype.Post_publication_description, Phenotype.Original_description, + Phenotype.Pre_publication_abbreviation, Phenotype.Post_publication_abbreviation, + Phenotype.Lab_code, Phenotype.Submitter, Phenotype.Owner, Phenotype.Authorized_Users, + Publication.Authors, Publication.Title, Publication.Abstract, + Publication.Journal, Publication.Volume, Publication.Pages, + Publication.Month, Publication.Year, PublishXRef.Sequence, + Phenotype.Units, PublishXRef.comments + FROM + PublishXRef, Publication, Phenotype, PublishFreeze + WHERE + PublishXRef.Id = %s AND + Phenotype.Id = PublishXRef.PhenotypeId AND + Publication.Id = PublishXRef.PublicationId AND + PublishXRef.InbredSetId = PublishFreeze.InbredSetId AND + PublishFreeze.Id =%s + ''' % (self.name, self.db.id) + #XZ, 05/08/2009: Xiaodong add this block to use ProbeSet.Id to find the probeset instead of just using ProbeSet.Name + #XZ, 05/08/2009: to avoid the problem of same probeset name from different platforms. + elif self.db.type == 'ProbeSet': + disfieldString = string.join(self.db.disfield,',ProbeSet.') + disfieldString = 'ProbeSet.' + disfieldString + query = """ + SELECT %s + FROM ProbeSet, ProbeSetFreeze, ProbeSetXRef + WHERE + ProbeSetXRef.ProbeSetFreezeId = ProbeSetFreeze.Id AND + ProbeSetXRef.ProbeSetId = ProbeSet.Id AND + ProbeSetFreeze.Name = '%s' AND + ProbeSet.Name = '%s' + """ % (disfieldString, self.db.name, self.name) + #XZ, 05/08/2009: We also should use Geno.Id to find marker instead of just using Geno.Name + # to avoid the problem of same marker name from different species. + elif self.db.type == 'Geno': + disfieldString = string.join(self.db.disfield,',Geno.') + disfieldString = 'Geno.' + disfieldString + query = """ + SELECT %s + FROM Geno, GenoFreeze, GenoXRef + WHERE + GenoXRef.GenoFreezeId = GenoFreeze.Id AND + GenoXRef.GenoId = Geno.Id AND + GenoFreeze.Name = '%s' AND + Geno.Name = '%s' + """ % (disfieldString, self.db.name, self.name) + else: #Temp type + query = 'SELECT %s FROM %s WHERE Name = "%s"' % \ + (string.join(self.db.disfield,','), self.db.type, self.name) + + + self.cursor.execute(query) + traitInfo = self.cursor.fetchone() + if traitInfo: + self.haveinfo = 1 + + #XZ: assign SQL query result to trait attributes. + for i, field in enumerate(self.db.disfield): + setattr(self, field, traitInfo[i]) + + if self.db.type == 'Publish': + self.confidential = 0 + if self.pre_publication_description and not self.pubmed_id: + self.confidential = 1 + + self.homologeneid = None + if self.db.type == 'ProbeSet' and self.riset and self.geneid: + #XZ, 05/26/2010: From time to time, this query get error message because some geneid values in database are not number. + #XZ: So I have to test if geneid is number before execute the query. + #XZ: The geneid values in database should be cleaned up. + try: + junk = float(self.geneid) + geneidIsNumber = 1 + except: + geneidIsNumber = 0 + + if geneidIsNumber: + query = """ + SELECT + HomologeneId + FROM + Homologene, Species, InbredSet + WHERE + Homologene.GeneId =%s AND + InbredSet.Name = '%s' AND + InbredSet.SpeciesId = Species.Id AND + Species.TaxonomyId = Homologene.TaxonomyId + """ % (self.geneid, self.riset) + self.cursor.execute(query) + result = self.cursor.fetchone() + else: + result = None + + if result: + self.homologeneid = result[0] + + if QTL: + if self.db.type == 'ProbeSet' and not self.cellid: + query = ''' + SELECT + ProbeSetXRef.Locus, ProbeSetXRef.LRS, ProbeSetXRef.pValue, ProbeSetXRef.mean + FROM + ProbeSetXRef, ProbeSet + WHERE + ProbeSetXRef.ProbeSetId = ProbeSet.Id AND + ProbeSet.Name = "%s" AND + ProbeSetXRef.ProbeSetFreezeId =%s + ''' % (self.name, self.db.id) + self.cursor.execute(query) + traitQTL = self.cursor.fetchone() + if traitQTL: + self.locus, self.lrs, self.pvalue, self.mean = traitQTL + else: + self.locus = self.lrs = self.pvalue = self.mean = "" + if self.db.type == 'Publish': + query = ''' + SELECT + PublishXRef.Locus, PublishXRef.LRS + FROM + PublishXRef, PublishFreeze + WHERE + PublishXRef.Id = %s AND + PublishXRef.InbredSetId = PublishFreeze.InbredSetId AND + PublishFreeze.Id =%s + ''' % (self.name, self.db.id) + self.cursor.execute(query) + traitQTL = self.cursor.fetchone() + if traitQTL: + self.locus, self.lrs = traitQTL + else: + self.locus = self.lrs = "" + else: + raise KeyError, `self.name`+' information is not found in the database.' + + def genHTML(self, formName = "", dispFromDatabase=0, privilege="guest", userName="Guest", authorized_users=""): + if not self.haveinfo: + self.retrieveInfo() + + if self.db.type == 'Publish': + PubMedLink = "" + if self.pubmed_id: + PubMedLink = HT.Href(text="PubMed %d : " % self.pubmed_id, + target = "_blank", url = webqtlConfig.PUBMEDLINK_URL % self.pubmed_id) + else: + PubMedLink = HT.Span("Unpublished : ", Class="fs15") + + if formName: + setDescription2 = HT.Href(url="javascript:showDatabase3('%s','%s','%s','')" % + (formName, self.db.name, self.name), Class = "fs14") + else: + setDescription2 = HT.Href(url="javascript:showDatabase2('%s','%s','')" % + (self.db.name,self.name), Class = "fs14") + + if self.confidential and not webqtlUtil.hasAccessToConfidentialPhenotypeTrait(privilege=privilege, userName=userName, authorized_users=authorized_users): + setDescription2.append('RecordID/%s - %s' % (self.name, self.pre_publication_description)) + else: + setDescription2.append('RecordID/%s - %s' % (self.name, self.post_publication_description)) + + #XZ 03/26/2011: Xiaodong comment out the following two lins as Rob asked. Need to check with Rob why in PublishXRef table, there are few row whose Sequence > 1. + #if self.sequence > 1: + # setDescription2.append(' btach %d' % self.sequence) + if self.authors: + a1 = string.split(self.authors,',')[0] + while a1[0] == '"' or a1[0] == "'" : + a1 = a1[1:] + setDescription2.append(' by ') + setDescription2.append(HT.Italic('%s, and colleagues' % a1)) + setDescription = HT.Span(PubMedLink, setDescription2) + + elif self.db.type == 'Temp': + setDescription = HT.Href(text="%s" % (self.description),url="javascript:showDatabase2\ + ('%s','%s','')" % (self.db.name,self.name), Class = "fs14") + setDescription = HT.Span(setDescription) + + elif self.db.type == 'Geno': # Genome DB only available for single search + if formName: + setDescription = HT.Href(text="Locus %s [Chr %s @ %s Mb]" % (self.name,self.chr,\ + '%2.3f' % self.mb),url="javascript:showDatabase3('%s','%s','%s','')" % \ + (formName, self.db.name, self.name), Class = "fs14") + else: + setDescription = HT.Href(text="Locus %s [Chr %s @ %s Mb]" % (self.name,self.chr,\ + '%2.3f' % self.mb),url="javascript:showDatabase2('%s','%s','')" % \ + (self.db.name,self.name), Class = "fs14") + + setDescription = HT.Span(setDescription) + + else: + if self.cellid: + if formName: + setDescription = HT.Href(text="ProbeSet/%s/%s" % (self.name, self.cellid),url=\ + "javascript:showDatabase3('%s','%s','%s','%s')" % (formName, self.db.name,self.name,self.cellid), \ + Class = "fs14") + else: + setDescription = HT.Href(text="ProbeSet/%s/%s" % (self.name,self.cellid),url=\ + "javascript:showDatabase2('%s','%s','%s')" % (self.db.name,self.name,self.cellid), \ + Class = "fs14") + else: + if formName: + setDescription = HT.Href(text="ProbeSet/%s" % self.name, url=\ + "javascript:showDatabase3('%s','%s','%s','')" % (formName, self.db.name,self.name), \ + Class = "fs14") + else: + setDescription = HT.Href(text="ProbeSet/%s" % self.name, url=\ + "javascript:showDatabase2('%s','%s','')" % (self.db.name,self.name), \ + Class = "fs14") + if self.symbol and self.chr and self.mb: + setDescription.append(' [') + setDescription.append(HT.Italic('%s' % self.symbol,Class="cdg fwb")) + setDescription.append(' on Chr %s @ %s Mb]' % (self.chr,self.mb)) + if self.description: + setDescription.append(': %s' % self.description) + if self.probe_target_description: + setDescription.append('; %s' % self.probe_target_description) + setDescription = HT.Span(setDescription) + + if self.db.type != 'Temp' and dispFromDatabase: + setDescription.append( ' --- FROM : ') + setDescription.append(self.db.genHTML(Class='cori')) + return setDescription + + -- cgit v1.2.3