diff options
Diffstat (limited to 'wqflask/base')
| -rwxr-xr-x | wqflask/base/GeneralObject.py | 68 | ||||
| -rw-r--r-- | wqflask/base/JinjaPage.py | 28 | ||||
| -rwxr-xr-x | wqflask/base/__init__.py | 0 | ||||
| -rwxr-xr-x | wqflask/base/admin.py | 86 | ||||
| -rwxr-xr-x | wqflask/base/cgiData.py | 66 | ||||
| -rwxr-xr-x | wqflask/base/cookieData.py | 49 | ||||
| -rwxr-xr-x | wqflask/base/data_set.py | 743 | ||||
| -rwxr-xr-x | wqflask/base/footer.py | 6 | ||||
| -rwxr-xr-x | wqflask/base/header.py | 6 | ||||
| -rwxr-xr-x | wqflask/base/indexBody.py | 290 | ||||
| -rwxr-xr-x | wqflask/base/myCookie.py | 51 | ||||
| -rwxr-xr-x | wqflask/base/sessionData.py | 50 | ||||
| -rw-r--r-- | wqflask/base/species.py | 117 | ||||
| -rwxr-xr-x | wqflask/base/template.py | 123 | ||||
| -rwxr-xr-x | wqflask/base/templatePage.py | 222 | ||||
| -rwxr-xr-x | wqflask/base/trait.py | 564 | ||||
| -rwxr-xr-x | wqflask/base/webqtlCaseData.py | 72 | ||||
| -rwxr-xr-x | wqflask/base/webqtlConfig.py | 73 | ||||
| -rwxr-xr-x | wqflask/base/webqtlConfigLocal.py | 20 | ||||
| -rwxr-xr-x | wqflask/base/webqtlFormData.py | 358 |
20 files changed, 2992 insertions, 0 deletions
diff --git a/wqflask/base/GeneralObject.py b/wqflask/base/GeneralObject.py new file mode 100755 index 00000000..53d1357b --- /dev/null +++ b/wqflask/base/GeneralObject.py @@ -0,0 +1,68 @@ +# 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 --- /dev/null +++ b/wqflask/base/__init__.py diff --git a/wqflask/base/admin.py b/wqflask/base/admin.py new file mode 100755 index 00000000..1ba75117 --- /dev/null +++ b/wqflask/base/admin.py @@ -0,0 +1,86 @@ +# 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..155b3ec3 --- /dev/null +++ b/wqflask/base/cgiData.py @@ -0,0 +1,66 @@ +# 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..eeb7c0cf --- /dev/null +++ b/wqflask/base/cookieData.py @@ -0,0 +1,49 @@ +# 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/data_set.py b/wqflask/base/data_set.py new file mode 100755 index 00000000..50ef8f57 --- /dev/null +++ b/wqflask/base/data_set.py @@ -0,0 +1,743 @@ +# 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 +# +#we +# +# This module is used by GeneNetwork project (www.genenetwork.org) + +from __future__ import absolute_import, print_function, division +import os + +from flask import Flask, g + +from htmlgen import HTMLgen2 as HT + +import reaper + +from base import webqtlConfig +from base import species +from dbFunction import webqtlDatabaseFunction +from utility import webqtlUtil + +from MySQLdb import escape_string as escape +from pprint import pformat as pf + +# Used by create_database to instantiate objects +DS_NAME_MAP = {} + +def create_dataset(dataset_name): + #cursor = db_conn.cursor() + print("dataset_name:", dataset_name) + + query = """ + SELECT DBType.Name + FROM DBList, DBType + WHERE DBList.Name = '%s' and + DBType.Id = DBList.DBTypeId + """ % (escape(dataset_name)) + print("query is: ", pf(query)) + dataset_type = g.db.execute(query).fetchone().Name + + #dataset_type = cursor.fetchone()[0] + print("[blubber] dataset_type:", pf(dataset_type)) + + dataset_ob = DS_NAME_MAP[dataset_type] + #dataset_class = getattr(data_set, dataset_ob) + print("dataset_ob:", dataset_ob) + print("DS_NAME_MAP:", pf(DS_NAME_MAP)) + + dataset_class = globals()[dataset_ob] + return dataset_class(dataset_name) + + +class DatasetGroup(object): + """ + Each group has multiple datasets; each species has multiple groups. + + For example, Mouse has multiple groups (BXD, BXA, etc), and each group + has multiple datasets associated with it. + + """ + def __init__(self, dataset): + """This sets self.group and self.group_id""" + self.name, self.id = g.db.execute(dataset.query_for_group).fetchone() + if self.name == 'BXD300': + self.name = "BXD" + + self.species = webqtlDatabaseFunction.retrieve_species(self.name) + + self.incparentsf1 = False + self.f1list = None + self.parlist = None + self.allsamples = None + + + #def read_genotype(self): + # self.read_genotype_file() + # + # if not self.genotype: # Didn'd succeed, so we try method 2 + # self.read_genotype_data() + + def read_genotype_file(self): + '''read genotype from .geno file instead of database''' + #if self.group == 'BXD300': + # self.group = 'BXD' + # + #assert self.group, "self.group needs to be set" + + #genotype_1 is Dataset Object without parents and f1 + #genotype_2 is Dataset Object with parents and f1 (not for intercross) + + genotype_1 = reaper.Dataset() + + # reaper barfs on unicode filenames, so here we ensure it's a string + full_filename = str(os.path.join(webqtlConfig.GENODIR, self.name + '.geno')) + genotype_1.read(full_filename) + + print("Got to after read") + + try: + # NL, 07/27/2010. ParInfo has been moved from webqtlForm.py to webqtlUtil.py; + f1, f12, maternal, paternal = webqtlUtil.ParInfo[self.name] + except KeyError: + f1 = f12 = maternal = paternal = None + + + if genotype_1.type == "group" and maternal and paternal: + genotype_2 = genotype_1.add(Mat=maternal, Pat=paternal) #, F1=_f1) + else: + genotype_2 = genotype_1 + + #determine default genotype object + if self.incparentsf1 and genotype_1.type != "intercross": + self.genotype = genotype_2 + else: + self.incparentsf1 = 0 + self.genotype = genotype_1 + + self.samplelist = list(self.genotype.prgy) + + if f1 and f12: + self.f1list = [f1, f12] + if maternal and paternal: + self.parlist = [maternal, paternal] + + +class DataSet(object): + """ + DataSet class defines a dataset in webqtl, can be either Microarray, + Published phenotype, genotype, or user input dataset(temp) + + """ + + def __init__(self, name): + + assert name, "Need a name" + self.name = name + self.id = None + self.type = None + + self.setup() + + self.check_confidentiality() + + self.retrieve_other_names() + + self.group = DatasetGroup(self) # sets self.group and self.group_id and gets genotype + self.species = species.TheSpecies(self) + + + + def get_desc(self): + """Gets overridden later, at least for Temp...used by trait's get_given_name""" + return None + + #@staticmethod + #def get_by_trait_id(trait_id): + # """Gets the dataset object given the trait id""" + # + # + # + # name = g.db.execute(""" SELECT + # + # """) + # + # return DataSet(name) + + # Delete this eventually + @property + def riset(): + Weve_Renamed_This_As_Group + + + #@property + #def group(self): + # if not self._group: + # self.get_group() + # + # return self._group + + + + def retrieve_other_names(self): + """ + If the data set name parameter is not found in the 'Name' field of the data set table, + check if it is actually the FullName or ShortName instead. + + This is not meant to retrieve the data set info if no name at all is passed. + + """ + + query_args = tuple(escape(x) for x in ( + (self.type + "Freeze"), + str(webqtlConfig.PUBLICTHRESH), + self.name, + self.name, + self.name)) + print("query_args are:", query_args) + + print(""" + SELECT Id, Name, FullName, ShortName + FROM %s + WHERE public > %s AND + (Name = '%s' OR FullName = '%s' OR ShortName = '%s') + """ % (query_args)) + + self.id, self.name, self.fullname, self.shortname = g.db.execute(""" + SELECT Id, Name, FullName, ShortName + FROM %s + WHERE public > %s AND + (Name = '%s' OR FullName = '%s' OR ShortName = '%s') + """ % (query_args)).fetchone() + + #self.cursor.execute(query) + #self.id, self.name, self.fullname, self.shortname = self.cursor.fetchone() + + + #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") + +class PhenotypeDataSet(DataSet): + DS_NAME_MAP['Publish'] = 'PhenotypeDataSet' + + def setup(self): + # Fields in the database table + self.search_fields = ['Phenotype.Post_publication_description', + 'Phenotype.Pre_publication_description', + 'Phenotype.Pre_publication_abbreviation', + 'Phenotype.Post_publication_abbreviation', + 'Phenotype.Lab_code', + 'Publication.PubMed_ID', + 'Publication.Abstract', + 'Publication.Title', + 'Publication.Authors', + 'PublishXRef.Id'] + + # Figure out what display_fields is + self.display_fields = ['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'] + + # Fields displayed in the search results table header + self.header_fields = ['', + 'ID', + 'Description', + 'Authors', + 'Year', + 'Max LRS', + 'Max LRS Location'] + + self.type = 'Publish' + + self.query_for_group = ''' + SELECT + InbredSet.Name, InbredSet.Id + FROM + InbredSet, PublishFreeze + WHERE + PublishFreeze.InbredSetId = InbredSet.Id AND + PublishFreeze.Name = "%s" + ''' % escape(self.name) + + def check_confidentiality(self): + # (Urgently?) Need to write this + pass + + def get_trait_info(self, trait_list, species = ''): + for this_trait in trait_list: + if not this_trait.haveinfo: + this_trait.retrieveInfo(QTL=1) + + description = this_trait.post_publication_description + if this_trait.confidential: + continue # for now + if not webqtlUtil.hasAccessToConfidentialPhenotypeTrait(privilege=self.privilege, userName=self.userName, authorized_users=this_trait.authorized_users): + description = this_trait.pre_publication_description + this_trait.description_display = description + + if not this_trait.year.isdigit(): + this_trait.pubmed_text = "N/A" + + if this_trait.pubmed_id: + this_trait.pubmed_link = webqtlConfig.PUBMEDLINK_URL % this_trait.pubmed_id + + #LRS and its location + this_trait.LRS_score_repr = "N/A" + this_trait.LRS_score_value = 0 + this_trait.LRS_location_repr = "N/A" + this_trait.LRS_location_value = 1000000 + + if this_trait.lrs: + result = g.db.execute(""" + select Geno.Chr, Geno.Mb from Geno, Species + where Species.Name = %s and + Geno.Name = %s and + Geno.SpeciesId = Species.Id + """, (species, this_trait.locus)).fetchone() + #result = self.cursor.fetchone() + + if result: + if result[0] and result[1]: + LRS_Chr = result[0] + LRS_Mb = result[1] + + #XZ: LRS_location_value is used for sorting + try: + LRS_location_value = int(LRS_Chr)*1000 + float(LRS_Mb) + except: + if LRS_Chr.upper() == 'X': + LRS_location_value = 20*1000 + float(LRS_Mb) + else: + LRS_location_value = ord(str(LRS_chr).upper()[0])*1000 + float(LRS_Mb) + + this_trait.LRS_score_repr = LRS_score_repr = '%3.1f' % this_trait.lrs + this_trait.LRS_score_value = LRS_score_value = this_trait.lrs + this_trait.LRS_location_repr = LRS_location_repr = 'Chr %s: %.4f Mb' % (LRS_Chr, float(LRS_Mb)) + + def retrieve_sample_data(self, trait): + query = """ + SELECT + Strain.Name, PublishData.value, PublishSE.error, NStrain.count + 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 + """ % (trait.name, self.id) + results = g.db.execute(query).fetchall() + return results + + +class GenotypeDataSet(DataSet): + DS_NAME_MAP['Geno'] = 'GenotypeDataSet' + + def setup(self): + # Fields in the database table + self.search_fields = ['Name', + 'Chr'] + + # Find out what display_fields is + self.display_fields = ['name', + 'chr', + 'mb', + 'source2', + 'sequence'] + + # Fields displayed in the search results table header + self.header_fields = ['', + 'ID', + 'Location'] + + # Todo: Obsolete or rename this field + self.type = 'Geno' + + self.query_for_group = ''' + SELECT + InbredSet.Name, InbredSet.Id + FROM + InbredSet, GenoFreeze + WHERE + GenoFreeze.InbredSetId = InbredSet.Id AND + GenoFreeze.Name = "%s" + ''' % escape(self.name) + + def check_confidentiality(self): + return geno_mrna_confidentiality(self) + + def get_trait_info(self, trait_list, species=None): + for this_trait in trait_list: + if not this_trait.haveinfo: + this_trait.retrieveInfo() + + #XZ: trait_location_value is used for sorting + trait_location_repr = 'N/A' + trait_location_value = 1000000 + + if this_trait.chr and this_trait.mb: + try: + trait_location_value = int(this_trait.chr)*1000 + this_trait.mb + except: + if this_trait.chr.upper() == 'X': + trait_location_value = 20*1000 + this_trait.mb + else: + trait_location_value = ord(str(this_trait.chr).upper()[0])*1000 + this_trait.mb + + this_trait.location_repr = 'Chr%s: %.4f' % (this_trait.chr, float(this_trait.mb) ) + this_trait.location_value = trait_location_value + + def retrieve_sample_data(self, trait): + 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.retrieve_species_id(self.group.name), trait.name, self.name) + results = g.db.execute(query).fetchall() + return results + + +class MrnaAssayDataSet(DataSet): + ''' + An mRNA Assay is a quantitative assessment (assay) associated with an mRNA trait + + This used to be called ProbeSet, but that term only refers specifically to the Affymetrix + platform and is far too specific. + + ''' + DS_NAME_MAP['ProbeSet'] = 'MrnaAssayDataSet' + + def setup(self): + # Fields in the database table + self.search_fields = ['Name', + 'Description', + 'Probe_Target_Description', + 'Symbol', + 'Alias', + 'GenbankId', + 'UniGeneId', + 'RefSeq_TranscriptId'] + + # Find out what display_fields is + self.display_fields = ['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'] + + # Fields displayed in the search results table header + self.header_fields = ['', + 'ID', + 'Symbol', + 'Description', + 'Location', + 'Mean Expr', + 'Max LRS', + 'Max LRS Location'] + + # Todo: Obsolete or rename this field + self.type = 'ProbeSet' + + self.query_for_group = ''' + SELECT + InbredSet.Name, InbredSet.Id + FROM + InbredSet, ProbeSetFreeze, ProbeFreeze + WHERE + ProbeFreeze.InbredSetId = InbredSet.Id AND + ProbeFreeze.Id = ProbeSetFreeze.ProbeFreezeId AND + ProbeSetFreeze.Name = "%s" + ''' % escape(self.name) + + + def check_confidentiality(self): + return geno_mrna_confidentiality(self) + + def get_trait_info(self, trait_list=None, species=''): + + # Note: setting trait_list to [] is probably not a great idea. + if not trait_list: + trait_list = [] + + for this_trait in trait_list: + + if not this_trait.haveinfo: + this_trait.retrieveInfo(QTL=1) + + if this_trait.symbol: + pass + else: + this_trait.symbol = "N/A" + + #XZ, 12/08/2008: description + #XZ, 06/05/2009: Rob asked to add probe target description + description_string = str(this_trait.description).strip() + target_string = str(this_trait.probe_target_description).strip() + + description_display = '' + + if len(description_string) > 1 and description_string != 'None': + description_display = description_string + else: + description_display = this_trait.symbol + + if len(description_display) > 1 and description_display != 'N/A' and len(target_string) > 1 and target_string != 'None': + description_display = description_display + '; ' + target_string.strip() + + # Save it for the jinja2 template + this_trait.description_display = description_display + #print(" xxxxdd [%s]: %s" % (type(this_trait.description_display), description_display)) + + #XZ: trait_location_value is used for sorting + trait_location_repr = 'N/A' + trait_location_value = 1000000 + + if this_trait.chr and this_trait.mb: + try: + trait_location_value = int(this_trait.chr)*1000 + this_trait.mb + except: + if this_trait.chr.upper() == 'X': + trait_location_value = 20*1000 + this_trait.mb + else: + trait_location_value = ord(str(this_trait.chr).upper()[0])*1000 + this_trait.mb + + this_trait.location_repr = 'Chr %s: %.4f Mb' % (this_trait.chr, float(this_trait.mb) ) + this_trait.location_value = trait_location_value + #this_trait.trait_location_value = trait_location_value + + #XZ, 01/12/08: This SQL query is much faster. + query = ( +"""select ProbeSetXRef.mean from ProbeSetXRef, ProbeSet + where ProbeSetXRef.ProbeSetFreezeId = %s and + ProbeSet.Id = ProbeSetXRef.ProbeSetId and + ProbeSet.Name = '%s' + """ % (escape(str(this_trait.dataset.id)), + escape(this_trait.name))) + + print("query is:", pf(query)) + + result = g.db.execute(query).fetchone() + + if result: + if result[0]: + mean = result[0] + else: + mean=0 + else: + mean = 0 + + #XZ, 06/05/2009: It is neccessary to turn on nowrap + this_trait.mean = repr = "%2.3f" % mean + + #LRS and its location + this_trait.LRS_score_repr = 'N/A' + this_trait.LRS_score_value = 0 + this_trait.LRS_location_repr = 'N/A' + this_trait.LRS_location_value = 1000000 + + #Max LRS and its Locus location + if this_trait.lrs and this_trait.locus: + self.cursor.execute(""" + select Geno.Chr, Geno.Mb from Geno, Species + where Species.Name = '%s' and + Geno.Name = '%s' and + Geno.SpeciesId = Species.Id + """ % (species, this_trait.locus)) + result = self.cursor.fetchone() + + if result: + if result[0] and result[1]: + LRS_Chr = result[0] + LRS_Mb = result[1] + + #XZ: LRS_location_value is used for sorting + try: + LRS_location_value = int(LRS_Chr)*1000 + float(LRS_Mb) + except: + if LRS_Chr.upper() == 'X': + LRS_location_value = 20*1000 + float(LRS_Mb) + else: + LRS_location_value = ord(str(LRS_chr).upper()[0])*1000 + float(LRS_Mb) + + this_trait.LRS_score_repr = LRS_score_repr = '%3.1f' % this_trait.lrs + this_trait.LRS_score_value = LRS_score_value = this_trait.lrs + this_trait.LRS_location_repr = LRS_location_repr = 'Chr %s: %.4f Mb' % (LRS_Chr, float(LRS_Mb) ) + + def get_sequence(self): + 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 + """ % (escape(self.name), escape(self.dataset.name)) + results = g.db.execute(query).fetchone() + + return results[0] + + def retrieve_sample_data(self, trait): + 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 + """ % (escape(trait.name), escape(self.name)) + results = g.db.execute(query).fetchall() + return results + + +class TempDataSet(DataSet): + '''Temporary user-generated data set''' + + def setup(self): + self.search_fields = ['name', + 'description'] + + self.display_fields = ['name', + 'description'] + + self.header_fields = ['Name', + 'Description'] + + self.type = 'Temp' + + # Need to double check later how these are used + self.id = 1 + self.fullname = 'Temporary Storage' + self.shortname = 'Temp' + + + @staticmethod + def handle_pca(desc): + if 'PCA' in desc: + # Todo: Modernize below lines + desc = desc[desc.rindex(':')+1:].strip() + else: + desc = desc[:desc.index('entered')].strip() + return desc + + def get_desc(self): + g.db.execute('SELECT description FROM Temp WHERE Name=%s', self.name) + desc = g.db.fetchone()[0] + desc = self.handle_pca(desc) + return desc + + def get_group(self): + self.cursor.execute(""" + SELECT + InbredSet.Name, InbredSet.Id + FROM + InbredSet, Temp + WHERE + Temp.InbredSetId = InbredSet.Id AND + Temp.Name = "%s" + """, self.name) + self.group, self.group_id = self.cursor.fetchone() + #return self.group + + def retrieve_sample_data(self, trait): + 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 + """ % escape(trait.name) + + results = g.db.execute(query).fetchall() + + +def geno_mrna_confidentiality(ob): + dataset_table = ob.type + "Freeze" + print("dataset_table [%s]: %s" % (type(dataset_table), dataset_table)) + + query = '''SELECT Id, Name, FullName, confidentiality, + AuthorisedUsers FROM %s WHERE Name = %%s''' % (dataset_table) + + result = g.db.execute(query, ob.name) + + (dataset_id, + name, + full_name, + confidential, + authorized_users) = result.fetchall()[0] + + if confidential: + # Allow confidential data later + NoConfindetialDataForYouTodaySorry 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 -->', '%s') diff --git a/wqflask/base/header.py b/wqflask/base/header.py new file mode 100755 index 00000000..ec15e174 --- /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 -->', '%s') diff --git a/wqflask/base/indexBody.py b/wqflask/base/indexBody.py new file mode 100755 index 00000000..a5bc4c17 --- /dev/null +++ b/wqflask/base/indexBody.py @@ -0,0 +1,290 @@ +index_body_string = """ +<TD vAlign=top width="40%" align="left" height=10 bgColor=#eeeeee> + <p style="font-size:18px;font-family:verdana;color:black"><B> Select and Search</B> + <Form METHOD="POST" ACTION="/webqtl/main.py" ENCTYPE="multipart/form-data" NAME="SEARCHFORM"> + + <TABLE width="100%"> + + <!-- SPECIES SELECTION --> + <TR> + <TD align=right height="35" style="font-size:14px;font-family:verdana;color:black" width="16%"> + <B>Species:</B> + </TD> + + <TD width="3%"> + </TD> + + <TD NOWRAP width="85%" align="left"> + <DIV Id="menu0"> + <Select NAME="species" size=1 id="species" onchange="fillOptions('species');"> + </Select> + </DIV> + </TD> + </TR> + + <!-- GROUP SELECTION --> + + <TR> + + <TD align="right" height="35" style="font-size:14px;font-family:verdana;color:black"> + <B>Group:</B> + </TD> + + <TD width="3%"> + </TD> + + <TD NOWRAP width="85%" align="left"> + <DIV Id="menu1"> + + <Select NAME="cross" size=1 id="cross" onchange="fillOptions('cross');"> + </Select> + <input type="button" class="button" value=" Info " onCLick="javascript:crossinfo();"> + </DIV> + </TD> + </TR> + + + <!-- TYPE SELECTION --> + + <TR> + + <TD align=right height=35 style="font-size:14px;font-family:verdana;color:black"> + <B>Type:</B> + </TD> + + <TD width="3%"> + </TD> + <TD NOWRAP width="85%" align="left"> + <DIV Id="menu2"> + <Select NAME="tissue" size=1 id="tissue" onchange="fillOptions('tissue');"> + + </Select> + </DIV> + </TD> + </TR> + + + <!-- DATABASE SELECTION --> + <TR> + <TD align=right height=35 style="font-size:14px;font-family:verdana;color:black"> + <B>Database:</B> + </TD> + + <TD width="3%"> + </TD> + + <TD NOWRAP width="85%" align="left"> + <DIV Id="menu3"> + <Select NAME="database" size=1 id="database"> + </Select> + <input type="button" class="button" value=" Info " onCLick="javascript:databaseinfo();"> + </DIV> + + </TD> + </TR> + + <!-- USER HELP --> + <TR> + <TD align=right height=20 width="10%"> + </TD> + <TD width="3%"> + </TD> + + <TD align="left" width="85%"> + <P class="fs12"> Databases marked with <B>**</B> suffix are not public yet. + <BR> Access requires <A HREF="/account.html" target="_blank" class="fs14"><small>user login</small></A>.</P> + </TD> + </TR> + + +<!-- GET ANY SEARCH --> + <TR> + <TD align=right height=35 NOWRAP="on" style="font-size:14px;font-family:verdana;color:black" width="10%"> + <B>Get Any:</B> + </TD> + + <TD width="3%"> + </TD> + + <TD NOWRAP width="85%" align="left"> + + <input id="tfor" name="ORkeyword" style="width:420px; background-color:white; font-family:verdana; font-size:14px" type="text" maxlength="500"> + </TD> + </TR> + + + +<!-- GET ANY HELP --> + <TR> + <TD align=right height=20 width="10%"> + </TD> + <TD width="3%"> + + </TD> + <TD width="85%" align="left"> + <P class="fs12"> Enter terms, genes, ID numbers in the <B>Get Any</B> field. + <BR> Use <B>*</B> or <B>?</B> wildcards (Cyp*a?, synap*). + <BR> Use <B>Combined</B> for terms such as <I>tyrosine kinase</I>.</P> + + </TD> + </TR> + + + +<!-- COMBINED SEARCH --> + + <TR> + <TD align=right height=35 NOWRAP="on" STYLE="font-size:14px;font-family:verdana;color:black" width="10%"> + <B>Combined:</B> + </TD> + + <TD width="3%"> + </TD> + + <TD NOWRAP width="85%" align="left"> + <input id="tfand" NAME="ANDkeyword" STYLE="width:420px; background-color:white; font-family:verdana; font-size:14px" type="text" maxlength="500"> + <input name="matchwhole" type="hidden" value="ON"> + </TD> + </TR> + + + +<!-- SEARCH, MAKE DEFAULT, ADVANCED SEARCH --> + + <TR ALIGN="center"> + <TD width="3%"> + </TD> + <TD width="3%"> + </TD> + <TD ALIGN="left" HEIGHT="40" COLSPAN=3> + <INPUT id="btsearch" TYPE="Submit" CLASS="button" STYLE="font-size:12px" VALUE=" Search "> + <INPUT TYPE="button" CLASS="button" STYLE="font-size:12px" VALUE=" Make Default " onClick = "setDefault(this.form);"> + <INPUT TYPE="button" CLASS="button" STYLE="font-size:12px" VALUE=" Advanced Search " onClick="javascript:window.open('/index3.html', '_self');"> + + </TD> + </TR> + </TABLE> + <INPUT TYPE="hidden" NAME="FormID" VALUE="searchResult"> + <INPUT TYPE="hidden" NAME="RISet" VALUE="BXD"> + <SCRIPT SRC="/javascript/selectDatasetMenu.js"></SCRIPT> + </FORM> + </CENTER> + + + + + +<!-- QUICK HELP --> + +<P><LEFT> ______________________________________________________ + +<P STYLE="font-size:13px;font-family:verdana;color:black"><B> + +Quick HELP Examples and </B> +<A HREF="http://www.genenetwork.org/index4.html" target="_blank" class="fs14"><B> + User's Guide</B></A></P> + +</CENTER style="font-size:12px;font-family:verdana;color:black"> + You can also use advanced commands. Copy these simple examples +<BR> into the <B>Get Any</B> or <B>Combined</B> search fields: +<UL style="font-size:12px;font-family:verdana;color:black"> + +<LI><B><I>POSITION=(chr1 25 30)</I></B> finds genes, markers, or transcripts on chromosome 1 between 25 and 30 Mb. + +<LI><B><I>MEAN=(15 16) LRS=(23 46)</I></B> in the <B>Combined</B> field finds highly expressed genes (15 to 16 log2 units) AND with peak <A HREF="http://www.genenetwork.org/glossary.html#L" target="_blank" class="fs14"><small>LRS</small></A> linkage between 23 and 46. + + +<LI><B><I>RIF=mitochondrial</I></B> searches RNA databases for <A HREF="http://www.ncbi.nlm.nih.gov/projects/GeneRIF/GeneRIFhelp.html" target="_blank" class="fs14"><small>GeneRIF</small></A> links. + +<LI><B><I>WIKI=nicotine</I></B> searches <A HREF="http://www.genenetwork.org/webqtl/main.py?FormID=geneWiki" target="_blank" class="fs14"><small>GeneWiki</small></A> for genes that you or other users have annotated with the word <I>nicotine</I>. + +<LI><B><I>GO:0045202</I></B> searches for synapse-associated genes listed in the <A HREF="http://www.godatabase.org/cgi-bin/amigo/go.cgi" target="_blank" class="fs14"><small>Gene Ontology</small></A>. + + +<LI><B><I>GO:0045202 LRS=(9 99 Chr4 122 155) cisLRS=(9 999 10)</I> </B><BR> in <B>Combined</B> finds synapse-associated genes with <A HREF="http://www.genenetwork.org/glossary.html#E" target="_blank" class="fs14"><small>cis eQTL</small></A> on Chr 4 from 122 and 155 Mb with LRS scores between 9 and 999. + +<LI><B><I>RIF=diabetes LRS=(9 999 Chr2 100 105) transLRS=(9 999 10)</I> </B><BR> in <B>Combined</B> finds diabetes-associated transcripts with peak <A HREF="http://www.genenetwork.org/glossary.html#E" target="_blank" class="fs14"><small>trans eQTLs</small></A> on Chr 2 between 100 and 105 Mb with LRS scores between 9 and 999. + + +</UL> +</DIR> + </TD> +<!-- END OF FIND SELECTOR PULL-DOWN PANEL (LEFT SIDE) --> + +<!-- START OF TOP RIGHT PANEL --> + +<TD vAlign=top width="40%" bgColor=#FFFFFF> + <p style="font-size:15px;font-family:verdana;color:black"><B>Websites Affiliated with GeneNetwork</B></p> + <p style="font-size:12px;font-family:verdana;color:black"> + <ul> + <li><a href="http://ucscbrowser.genenetwork.org/" target="_blank">Genome Browser</a> at UTHSC</li> + <li><a href="http://galaxy.genenetwork.org/" target="_blank">Galaxy</a> at UTHSC</li> + <li>GeneNetwork at <a href="http://ec2.genenetwork.org/" target="_blank">Amazon Cloud (EC2)</a></li> + <li>GeneNetwork Source Codes at <a href="http://sourceforge.net/projects/genenetwork/" target="_blank">SourceForge</a></li> + </ul> + </p> + <P>____________________________ + + <p style="font-size:15px;font-family:verdana;color:black"><B>Getting Started</B> </p> + <OL style="font-size:12px;font-family:verdana;color:black"> + <LI>Select <B>Species</B> (or select All) + <LI>Select <B>Group</B> (a specific sample) + <LI>Select <B>Type</B> of data: + <UL> + <LI>Phenotype (traits) + <LI>Genotype (markers) + <LI>Expression (mRNAs) + </UL> + <LI>Select a <B>Database</B> + <LI>Enter search terms in the <B>Get Any</B> or <B>Combined</B> field: words, genes, ID numbers, probes, advanced search commands + <LI>Click on the <B>Search</B> button + <LI>Optional: Use the <B>Make Default</B> button to save your preferences + </OL> + + <P>____________________________ + +<p style="font-size:14px;font-family:verdana;color:black"><B>How to Use GeneNetwork</B> + + <BLOCKQUOTE> + <p style="font-size:12px;font-family:verdana;color:black">Take a 20-40 minute GeneNetwork <A HREF="http://www.genenetwork.org/tutorial/WebQTLTour/" target="_blank" class="fs14"><small>Tour</small></A> that includes screen shots and typical steps in the analysis.</P> + </BLOCKQUOTE> + <BLOCKQUOTE> + <p style="font-size:12px;font-family:verdana;color:black">For information about resources and methods, select the <img src="http://www.genenetwork.org/images/upload/Info.png" alt="INFO" border= 0 valign="middle"> buttons.</P> + + + +<p style="font-size:12px;font-family:verdana;color:black">Try the <A HREF="http://alexandria.uthsc.edu/" target="_blank" class="fs14"><small>Workstation</small></A> site to explore data and features that are being implemented.</P> + + +<p style="font-size:12px;font-family:verdana;color:black">Review the <A HREF="/conditionsofUse.html" target="_blank" class="fs14"><small>Conditions</small></A> and <A HREF="/statusandContact.html" target="_blank" class="fs14"><small>Contacts</small></A> pages for information on the status of data sets and advice on their use and citation.</P> + + + </BLOCKQUOTE> + + + + <p style="font-size:14px;font-family:verdana;color:black"><B>Mirror and Development Sites</B></P> + + <UL> + <LI><A HREF="http://www.genenetwork.org/" target="_blank" style="font-size:12px;font-family:verdana;color:blue">Main GN site at UTHSC</A> (main site) + <LI><A HREF="http://www.genenetwork.waimr.uwa.edu.au/" target="_blank" style="font-size:12px;font-family:verdana;color:blue">Australia at the UWA</A> + <LI><A HREF="http://gn.genetics.ucla.edu/" target="_blank" style="font-size:12px;font-family:verdana;color:blue">California at UCLA</A> + <LI><A HREF="http://genenetwork.helmholtz-hzi.de/" target="_blank" style="font-size:12px;font-family:verdana;color:blue">Germany at the HZI</A> + <LI><A HREF="https://genenetwork.hubrecht.eu/" target="_blank" style="font-size:12px;font-family:verdana;color:blue">Netherlands at the Hubrecht</A> (Development) + <LI><A HREF="http://xzhou3.memphis.edu/" target="_blank" style="font-size:12px;font-family:verdana;color:blue">Memphis at the U of M</A> + <LI><A HREF="http://webqtl.bic.nus.edu.sg/" target="_blank" style="font-size:12px;font-family:verdana;color:blue">Singapore at the NUS</A> + <LI><A HREF="http://genenetwork.epfl.ch/" target="_blank" style="font-size:12px;font-family:verdana;color:blue">Switzerland at the EPFL</A> + </UL> + + + <p style="font-size:14px;font-family:verdana;color:black"><B>History and Archive</B> + + <BLOCKQUOTE> + <p style="font-size:12px;font-family:verdana;color:black">GeneNetwork's <A HREF="http://artemis.uthsc.edu" target="_blank" class="fs14"><small>Time Machine</small></A> links to earlier versions that correspond to specific publication dates.</P> + + </BLOCKQUOTE> + + +</P> + </TD> +""" diff --git a/wqflask/base/myCookie.py b/wqflask/base/myCookie.py new file mode 100755 index 00000000..add7e6ea --- /dev/null +++ b/wqflask/base/myCookie.py @@ -0,0 +1,51 @@ +# 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..4b23060f --- /dev/null +++ b/wqflask/base/sessionData.py @@ -0,0 +1,50 @@ +# 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/species.py b/wqflask/base/species.py new file mode 100644 index 00000000..9d4cac4c --- /dev/null +++ b/wqflask/base/species.py @@ -0,0 +1,117 @@ +from __future__ import absolute_import, print_function, division + +import collections + +from flask import Flask, g + +#from MySQLdb import escape_string as escape + +from utility import Bunch + +from pprint import pformat as pf + +class TheSpecies(object): + def __init__(self, dataset): + self.dataset = dataset + print("self.dataset is:", pf(self.dataset.__dict__)) + self.chromosomes = Chromosomes(self.dataset) + self.genome_mb_length = self.chromosomes.get_genome_mb_length() + + + #@property + #def chromosomes(self): + # chromosomes = [("All", -1)] + # + # for counter, genotype in enumerate(self.dataset.group.genotype): + # if len(genotype) > 1: + # chromosomes.append((genotype.name, counter)) + # + # print("chromosomes is: ", pf(chromosomes)) + # + # return chromosomes + +class IndChromosome(object): + def __init__(self, length): + self.length = length + + @property + def mb_length(self): + """Chromosome length in megabases""" + return self.length / 1000000 + + def set_cm_length(self, genofile_chr): + self.cm_length = genofile_chr[-1].cM - genofile_chr[0].cM + + +class Chromosomes(object): + def __init__(self, dataset): + self.dataset = dataset + self.chromosomes = collections.OrderedDict() + + results = g.db.execute(""" + Select + Chr_Length.Name, Length from Chr_Length, InbredSet + where + Chr_Length.SpeciesId = InbredSet.SpeciesId AND + InbredSet.Name = %s + Order by OrderId + """, self.dataset.group.name).fetchall() + print("bike:", results) + + for item in results: + self.chromosomes[item.Name] = IndChromosome(item.Length) + + self.set_mb_graph_interval() + self.get_cm_length_list() + + + def set_mb_graph_interval(self): + """Empirical megabase interval""" + + #if self.chromosomes: + assert self.chromosomes, "Have to add some code back in apparently to set it to 1" + self.mb_graph_interval = self.get_genome_mb_length()/(len(self.chromosomes)*12) + #else: + #self.mb_graph_interval = 1 + + + def get_genome_mb_length(self): + """Gets the sum of each chromosome's length in megabases""" + + return sum([ind_chromosome.mb_length for ind_chromosome in self.chromosomes.values()]) + + + def get_genome_cm_length(self): + """Gets the sum of each chromosome's length in centimorgans""" + + return sum([ind_chromosome.cm_length for ind_chromosome in self.chromosomes.values()]) + + def get_cm_length_list(self): + """Chromosome length in centimorgans + + Calculates the length in centimorgans by subtracting the centimorgan position + of the last marker in a chromosome by the position of the first marker + + """ + + self.dataset.group.read_genotype_file() + + self.cm_length_list = [] + + for chromosome in self.dataset.group.genotype: + self.cm_length_list.append(chromosome[-1].cM - chromosome[0].cM) + + print("self.cm_length_list:", pf(self.cm_length_list)) + + assert len(self.cm_length_list) == len(self.chromosomes), "Uh-oh lengths should be equal!" + for counter, chromosome in enumerate(self.chromosomes.values()): + chromosome.cm_length = self.cm_length_list[counter] + #self.chromosomes[counter].cm_length = item + + for key, value in self.chromosomes.items(): + print("bread - %s: %s" % (key, pf(vars(value)))) + + +# Testing +#if __name__ == '__main__': +# foo = dict(bar=dict(length))
\ No newline at end of file diff --git a/wqflask/base/template.py b/wqflask/base/template.py new file mode 100755 index 00000000..aa8f90dc --- /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 = """ +<?XML VERSION="1.0" ENCODING="UTF-8"> +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"> +<HTML> +<HEAD> +<TITLE>%s</TITLE> + +<META http-equiv=Content-Type content="text/html; charset=iso-8859-1"> +<META NAME="keywords" CONTENT="genetics, bioinformatics, genome, phenome, gene expression, complex trait analysis, gene mapping, SNP, quantitative trait locus QTL, expression eQTL, WebQTL, Traitnet, Traitnetwork, personalized medicine"> +<META NAME="description" CONTENT ="GeneNetwork is a free scientific web resource used to study relationships between differences in genes, environmental factors, phenotypes, and disease risk." > +<META NAME="author" CONTENT ="GeneNetwork developers" > +<META NAME="geo.placename" CONTENT ="Memphis, TN" > +<META NAME="geo.region" CONTENT="US-TN"> +%s +<LINK REL="stylesheet" TYPE="text/css" HREF='/css/general.css'> +<LINK REL="stylesheet" TYPE="text/css" HREF='/css/menu.css'> +<link rel="stylesheet" media="all" type="text/css" href="/css/tabbed_pages.css" /> +<LINK REL="apple-touch-icon" href="/images/ipad_icon3.png" /> +<link type="text/css" href='/css/custom-theme/jquery-ui-1.8.12.custom.css' rel='Stylesheet' /> +<link type="text/css" href='/css/tab_style.css' rel='Stylesheet' /> + +<script type="text/javascript" src="/javascript/jquery-1.5.2.min.js"></script> +<SCRIPT SRC="/javascript/webqtl.js"></SCRIPT> +<SCRIPT SRC="/javascript/dhtml.js"></SCRIPT> +<SCRIPT SRC="/javascript/tablesorter.js"></SCRIPT> +<SCRIPT SRC="/javascript/jqueryFunction.js"></SCRIPT> +<script src="/javascript/tabbed_pages.js" type="text/javascript"></script> +<script src="/javascript/jquery-ui-1.8.12.custom.min.js" type="text/javascript"></script> +%s + +<script type="text/javascript"> + var _gaq = _gaq || []; + _gaq.push(['_setAccount', 'UA-3782271-1']); + _gaq.push(['_trackPageview']); + (function() { + var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; + ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; + var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); + })(); +</script> +</HEAD> +<BODY bottommargin="2" leftmargin="2" rightmargin="2" topmargin="2" text=#000000 bgColor=#ffffff %s> +%s +<TABLE cellSpacing=5 cellPadding=4 width="100%%" border=0> + <TBODY> + <!-- Start of header --> + <TR> + %s + </TR> + <!-- End of header --> + + <!-- Start of body --> + <TR> + <TD bgColor=#eeeeee class="solidBorder"> + <Table width= "100%%" cellSpacing=0 cellPadding=5> + <TR> + %s + </TR> + </TABLE> + </TD> + </TR> + <!-- End of body --> + + <!-- Start of footer --> + <TR> + <TD align=center bgColor=#ddddff class="solidBorder"> + <TABLE width="90%%">%s</table> + </td> + </TR> + <!-- End of footer --> +</TABLE> + +<!-- menu script itself. you should not modify this file --> +<script language="JavaScript" src="/javascript/menu_new.js"></script> +<!-- items structure. menu hierarchy and links are stored there --> +<script language="JavaScript" src="/javascript/menu_items.js"></script> +<!-- files with geometry and styles structures --> +<script language="JavaScript" src="/javascript/menu_tpl.js"></script> +<script language="JavaScript"> + <!--// + // Note where menu initialization block is located in HTML document. + // Don't try to position menu locating menu initialization block in + // some table cell or other HTML element. Always put it before </body> + // each menu gets two parameters (see demo files) + // 1. items structure + // 2. geometry structure + new menu (MENU_ITEMS, MENU_POS); + // make sure files containing definitions for these variables are linked to the document + // if you got some javascript error like "MENU_POS is not defined", then you've made syntax + // error in menu_tpl.js file or that file isn't linked properly. + + // also take a look at stylesheets loaded in header in order to set styles + //--> +</script> +</BODY> +</HTML> +""" diff --git a/wqflask/base/templatePage.py b/wqflask/base/templatePage.py new file mode 100755 index 00000000..a94d5153 --- /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' + + # Commenting this out for flask - we'll have to reimplement later - Sam + #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! <a href=/account.html><U>Login</U></a>' + else: + userInfo = 'Hi, %s! <a href=/webqtl/main.py?FormID=userLogoff><U>Logout</U></a>' % 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.db_conn = MySQLdb.Connect(db=webqtlConfig.DB_NAME,host=webqtlConfig.MYSQL_SERVER, \ + user=webqtlConfig.DB_USER,passwd=webqtlConfig.DB_PASSWD) + self.cursor = self.db_conn.cursor() + return True + except Exception: + 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 False + + def updMysql(self): + try: + self.db_conn = MySQLdb.Connect(db=webqtlConfig.DB_UPDNAME,host=webqtlConfig.MYSQL_UPDSERVER, \ + user=webqtlConfig.DB_UPDUSER,passwd=webqtlConfig.DB_UPDPASSWD) + self.cursor = self.db_conn.cursor() + return True + except Exception: + 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 False + + 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/trait.py b/wqflask/base/trait.py new file mode 100755 index 00000000..241bf2ab --- /dev/null +++ b/wqflask/base/trait.py @@ -0,0 +1,564 @@ +from __future__ import absolute_import, division, print_function + +import string + +from htmlgen import HTMLgen2 as HT + +from base import webqtlConfig +from base.webqtlCaseData import webqtlCaseData +from base.data_set import create_dataset +from dbFunction import webqtlDatabaseFunction +from utility import webqtlUtil + +from MySQLdb import escape_string as escape +from pprint import pformat as pf + +from flask import Flask, g + +class GeneralTrait: + """ + Trait class defines a trait in webqtl, can be either Microarray, + Published phenotype, genotype, or user input trait + + """ + + def __init__(self, **kw): + print("in GeneralTrait") + self.dataset = kw.get('dataset') # database name + self.name = kw.get('name') # Trait ID, ProbeSet ID, Published ID, etc. + self.cellid = kw.get('cellid') + self.identification = kw.get('identification', 'un-named trait') + self.haveinfo = kw.get('haveinfo', False) + self.sequence = kw.get('sequence') # Blat sequence, available for ProbeSet + self.data = kw.get('data', {}) + + if kw.get('fullname'): + name2 = value.split("::") + if len(name2) == 2: + self.dataset, self.name = name2 + # self.cellid is set to None above + elif len(name2) == 3: + self.dataset, self.name, self.cellid = name2 + + self.dataset = create_dataset(self.dataset) + + # Todo: These two lines are necessary most of the time, but perhaps not all of the time + # So we could add a simple if statement to short-circuit this if necessary + self.retrieve_info() + self.retrieve_sample_data() + + + def get_name(self): + stringy = "" + if self.dataset and self.name: + stringy = "%s::%s" % (self.dataset, self.name) + if self.cellid: + stringy += "::" + self.cellid + else: + stringy = self.description + return stringy + + + def get_given_name(self): + """ + 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 + + """ + stringy = self.name + if self.dataset and self.name: + desc = self.dataset.get_desc() + if desc: + #desc = self.handle_pca(desc) + stringy = desc + return stringy + + + + def display_name(self): + stringy = "" + if self.dataset and self.name: + desc = self.dataset.get_desc() + #desc = self.handle_pca(desc) + if desc: + #desc = self.handle_pca(desc) + #stringy = desc + #if desc.__contains__('PCA'): + # desc = desc[desc.rindex(':')+1:].strip() + #else: + # desc = desc[:desc.index('entered')].strip() + #desc = self.handle_pca(desc) + stringy = "%s::%s" % (self.dataset, desc) + else: + stringy = "%s::%s" % (self.dataset, self.name) + if self.cellid: + stringy += "::" + self.cellid + else: + stringy = self.description + + return stringy + + + #def __str__(self): + # #return "%s %s" % (self.getName(), self.group) + # return self.getName() + #__str__ = getName + #__repr__ = __str__ + + def export_data(self, samplelist, the_type="val"): + """ + export data according to samplelist + mostly used in calculating correlation + + """ + result = [] + for sample in samplelist: + if self.data.has_key(sample): + if the_type=='val': + result.append(self.data[sample].val) + elif the_type=='var': + result.append(self.data[sample].var) + elif the_type=='N': + result.append(self.data[sample].N) + else: + raise KeyError, `the_type`+' the_type is incorrect.' + else: + result.append(None) + return result + + def export_informative(self, incVar=0): + """ + export informative sample + mostly used in qtl regression + + """ + samples = [] + vals = [] + the_vars = [] + for sample, value in self.data.items(): + if value.val != None: + if not incVar or value.var != None: + samples.append(sample) + vals.append(value.val) + the_vars.append(value.var) + return samples, vals, the_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.dataset.type == 'ProbeSet': + # self.cursor.execute(''' + # 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.dataset.name) + # #self.cursor.execute(query) + # results = self.fetchone() + # + # return results[0] + + + + def retrieve_sample_data(self, samplelist=None): + if samplelist == None: + samplelist = [] + + #assert self.dataset + + #if 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.dataset.name) + # + #else: + results = self.dataset.retrieve_sample_data(self) + + # Todo: is this necessary? If not remove + self.data.clear() + + if results: + for item in results: + #name, value, variance, num_cases = item + if not samplelist or (samplelist and name in samplelist): + name = item[0] + self.data[name] = webqtlCaseData(*item) #name, value, variance, num_cases) + + #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 retrieve_info(self, QTL=False): + assert self.dataset, "Dataset doesn't exist" + if self.dataset.type == 'Publish': + 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.dataset.id) + traitInfo = g.db.execute(query).fetchone() + #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.dataset.type == 'ProbeSet': + display_fields_string = ', ProbeSet.'.join(self.dataset.display_fields) + display_fields_string = 'ProbeSet.' + display_fields_string + 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' + """ % (escape(display_fields_string), + escape(self.dataset.name), + escape(self.name)) + traitInfo = g.db.execute(query).fetchone() + print("traitInfo is: ", pf(traitInfo)) + #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.dataset.type == 'Geno': + display_fields_string = string.join(self.dataset.display_fields,',Geno.') + display_fields_string = 'Geno.' + display_fields_string + 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' + """ % (escape(display_fields_string), + escape(self.dataset.name), + escape(self.name)) + traitInfo = g.db.execute(query).fetchone() + print("traitInfo is: ", pf(traitInfo)) + else: #Temp type + query = """SELECT %s FROM %s WHERE Name = %s + """ % (string.join(self.dataset.display_fields,','), + self.dataset.type, self.name) + traitInfo = g.db.execute(query).fetchone() + + + #self.cursor.execute(query) + #traitInfo = self.cursor.fetchone() + if traitInfo: + self.haveinfo = True + + #XZ: assign SQL query result to trait attributes. + for i, field in enumerate(self.dataset.display_fields): + setattr(self, field, traitInfo[i]) + + if self.dataset.type == 'Publish': + self.confidential = 0 + if self.pre_publication_description and not self.pubmed_id: + self.confidential = 1 + + self.homologeneid = None + if self.dataset.type == 'ProbeSet' and self.dataset.group 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 + """ % (escape(str(self.geneid)), escape(self.dataset.group.name)) + result = g.db.execute(query).fetchone() + else: + result = None + + if result: + self.homologeneid = result[0] + + if QTL: + if self.dataset.type == 'ProbeSet' and not self.cellid: + traitQTL = g.db.execute(""" + 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.dataset.id)).fetchone() + #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.dataset.type == 'Publish': + traitQTL = g.db.execute(""" + SELECT + PublishXRef.Locus, PublishXRef.LRS + FROM + PublishXRef, PublishFreeze + WHERE + PublishXRef.Id = %s AND + PublishXRef.InbredSetId = PublishFreeze.InbredSetId AND + PublishFreeze.Id =%s + """, (self.name, self.dataset.id)).fetchone() + #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.dataset.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.dataset.name, self.name), Class = "fs14") + else: + setDescription2 = HT.Href(url="javascript:showDatabase2('%s','%s','')" % + (self.dataset.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.dataset.type == 'Temp': + setDescription = HT.Href(text="%s" % (self.description),url="javascript:showDatabase2\ + ('%s','%s','')" % (self.dataset.name,self.name), Class = "fs14") + setDescription = HT.Span(setDescription) + + elif self.dataset.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.dataset.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.dataset.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.dataset.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.dataset.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.dataset.name,self.name), \ + Class = "fs14") + else: + setDescription = HT.Href(text="ProbeSet/%s" % self.name, url=\ + "javascript:showDatabase2('%s','%s','')" % (self.dataset.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.dataset.type != 'Temp' and dispFromDatabase: + setDescription.append( ' --- FROM : ') + setDescription.append(self.dataset.genHTML(Class='cori')) + return setDescription + + @property + def description_fmt(self): + '''Return a text formated description''' + if self.description: + formatted = self.description + if self.probe_target_description: + formatted += "; " + self.probe_target_description + else: + formatted = "Not available" + return formatted.capitalize() + + @property + def alias_fmt(self): + '''Return a text formatted alias''' + if self.alias: + alias = string.replace(self.alias, ";", " ") + alias = string.join(string.split(alias), ", ") + return alias + + + @property + def location_fmt(self): + '''Return a text formatted location + + While we're at it we set self.location in case we need it later (do we?) + + ''' + + if self.chr and self.mb: + self.location = 'Chr %s @ %s Mb' % (self.chr,self.mb) + elif self.chr: + self.location = 'Chr %s @ Unknown position' % (self.chr) + else: + self.location = 'Not available' + + fmt = self.location + ##XZ: deal with direction + if self.strand_probe == '+': + fmt += (' on the plus strand ') + elif self.strand_probe == '-': + fmt += (' on the minus strand ') + + return fmt + + + def get_database(self): + """ + Returns the database, and the url referring to the database if it exists + + We're going to to return two values here, and we don't want to have to call this twice from + the template. So it's not a property called from the template, but instead is called from the view + + """ + if self.cellid: + self.cursor.execute(""" + select ProbeFreeze.Name from ProbeFreeze, ProbeSetFreeze + where + ProbeFreeze.Id = ProbeSetFreeze.ProbeFreezeId AND + ProbeSetFreeze.Id = %d""" % thisTrait.dataset.id) + probeDBName = self.cursor.fetchone()[0] + return dict(name = probeDBName, + url = None) + else: + return dict(name = self.dataset.fullname, + url = webqtlConfig.INFOPAGEHREF % self.dataset.name) + + def calculate_correlation(self, values, method): + """Calculate the correlation value and p value according to the method specified""" + + #ZS: This takes the list of values of the trait our selected trait is being correlated against and removes the values of the samples our trait has no value for + #There's probably a better way of dealing with this, but I'll have to ask Christian + updated_raw_values = [] + updated_values = [] + for i in range(len(values)): + if values[i] != "None": + updated_raw_values.append(self.raw_values[i]) + updated_values.append(values[i]) + + self.raw_values = updated_raw_values + values = updated_values + + if method == METHOD_SAMPLE_PEARSON or method == METHOD_LIT or method == METHOD_TISSUE_PEARSON: + corr, nOverlap = webqtlUtil.calCorrelation(self.raw_values, values, len(values)) + else: + corr, nOverlap = webqtlUtil.calCorrelationRank(self.raw_values, values, len(values)) + + self.correlation = corr + self.overlap = nOverlap + + if self.overlap < 3: + self.p_value = 1.0 + else: + #ZS - This is probably the wrong way to deal with this. Correlation values of 1.0 definitely exist (the trait correlated against itself), so zero division needs to br prevented. + if abs(self.correlation) >= 1.0: + self.p_value = 0.0 + else: + ZValue = 0.5*log((1.0+self.correlation)/(1.0-self.correlation)) + ZValue = ZValue*sqrt(self.overlap-3) + self.p_value = 2.0*(1.0 - reaper.normp(abs(ZValue))) diff --git a/wqflask/base/webqtlCaseData.py b/wqflask/base/webqtlCaseData.py new file mode 100755 index 00000000..42763aed --- /dev/null +++ b/wqflask/base/webqtlCaseData.py @@ -0,0 +1,72 @@ +# 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 + +print("Mr. Mojo Risin 2") + +class webqtlCaseData(object): + """one case data in one trait""" + + def __init__(self, name, value=None, variance=None, num_cases=None): + self.name = name + self.value = value # Trait Value + self.variance = variance # Trait Variance + self.num_cases = num_cases # Number of individuals/cases + self.extra_attributes = None + self.this_id = None # Set a sane default (can't be just "id" cause that's a reserved word) + self.outlier = None # Not set to True/False until later + + def __repr__(self): + str = "<webqtlCaseData> " + if self.value != None: + str += "value=%2.3f" % self.value + if self.variance != None: + str += " variance=%2.3f" % self.variance + if self.num_cases != None: + str += " ndata=%d" % self.num_cases + return str + + @property + def class_outlier(self): + """Template helper""" + if self.outlier: + return "outlier" + else: + return "" + + @property + def display_value(self): + if self.value: + return "%2.3f" % self.value + else: + return "x" + + @property + def display_variance(self): + if self.variance: + return "%2.3f" % self.variance + else: + return "x" + 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 = '<base href="http://132.192.47.32/">' +INFOPAGEHREF = '/dbdoc/%s.html' +GLOSSARYFILE = "/glossary.html" +CGIDIR = '/webqtl/' #XZ: The variable name 'CGIDIR' should be changed to 'PYTHONDIR' +SCRIPTFILE = 'main.py' +REFRESHSTR = '<meta http-equiv="refresh" content="5;url=%s' + SCRIPTFILE +'?sid=%s">' +REFRESHDIR = '%s' + SCRIPTFILE +'?sid=%s' diff --git a/wqflask/base/webqtlConfigLocal.py b/wqflask/base/webqtlConfigLocal.py new file mode 100755 index 00000000..84686234 --- /dev/null +++ b/wqflask/base/webqtlConfigLocal.py @@ -0,0 +1,20 @@ +#########################################' +# Environment Variables - private +######################################### + +MYSQL_SERVER = 'localhost' +DB_NAME = 'db_webqtl_zas1024' +DB_USER = 'webqtl' +DB_PASSWD = 'webqtl' + +MYSQL_UPDSERVER = 'localhost' +DB_UPDNAME = 'db_webqtl_zas1024' +DB_UPDUSER = 'webqtl' +DB_UPDPASSWD = 'webqtl' + +GNROOT = '/home/zas1024/gn/' +ROOT_URL = 'http://alexandria.uthsc.edu:91/' +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/webqtlFormData.py b/wqflask/base/webqtlFormData.py new file mode 100755 index 00000000..a3537c87 --- /dev/null +++ b/wqflask/base/webqtlFormData.py @@ -0,0 +1,358 @@ +# 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 + +from __future__ import print_function +from pprint import pformat as pf + +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(object): + 'Represents data from a WebQTL form page, needed to generate the next page' + + attrs = ('formID','group','genotype','samplelist','allsamplelist', 'display_variance' + '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, + start_vars = None, + req = None, + mod_python_session=None, + FieldStorage_formdata=None): + # Todo: rework this whole thing + print("in webqtlFormData start_vars are:", pf(start_vars)) + for item in webqtlFormData.attrs: + self.__dict__[item] = None + + #ZS: This is only used in DataEditingPage.py (as far as I know) + self.varianceDispName = None + + for item in start_vars: + self.__dict__[item] = start_vars[item] + print(" Now self.dict is:", pf(self.__dict__)) + + #Todo: This can't be good below...rework + 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 + + # For now let's just comment all this out - Sam + + #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 = None + self.mpolar = None + + print("[yellow] self.group is:", self.group) + if self.group: + #try: + # # NL, 07/27/2010. ParInfo has been moved from webqtlForm.py to webqtlUtil.py; + _f1, _f12, self.mpolar, self.ppolar = webqtlUtil.ParInfo[self.group] + #except: + # f1 = f12 = self.mpolar = self.ppolar = None + + + def set_number(stringy): + return int(stringy) if stringy else 2000 # Rob asked to change the default value to 2000 + + self.nperm = set_number(self.nperm) + self.nboot = set_number(self.nboot) + + + #if self.allsamplelist: + # self.allsamplelist = map(string.strip, string.split(self.allsamplelist)) + print("self.allsamplelist is:", self.allsamplelist) + if self.allsamplelist: + self.allsamplelist = self.allsamplelist.split() + print("now self.allsamplelist is:", self.allsamplelist) + #self.readGenotype() + #self.readData() + + if self.group == 'BXD300': + self.group = 'BXD' + + + def __getitem__(self, key): + print("in __getitem__") + return self.__dict__[key] + + def get(self, key, default=None): + if key in self.__dict__: + return self.__dict__[key] + else: + return default + + 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.group == 'BXD300': + self.group = 'BXD' + + assert self.group, "self.group needs to be set" + + #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() + + full_filename = os.path.join(webqtlConfig.GENODIR, self.group + '.geno') + + # reaper barfs on unicode filenames, so here we ensure it's a string + full_filename = str(full_filename) + self.genotype_1.read(full_filename) + + print("Got to after read") + + try: + # NL, 07/27/2010. ParInfo has been moved from webqtlForm.py to webqtlUtil.py; + _f1, _f12, _mat, _pat = webqtlUtil.ParInfo[self.group] + except KeyError: + _f1 = _f12 = _mat = _pat = None + + self.genotype_2 = self.genotype_1 + if self.genotype_1.type == "group" 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.samplelist = 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, samplelist, incf1=None): + '''read user input data or from trait data and analysis form''' + + if incf1 == None: + incf1 = [] + + if not self.genotype: + self.readGenotype() + if not samplelist: + if incf1: + samplelist = self.f1list + self.samplelist + else: + samplelist = self.samplelist + + #print("before traitfiledata self.traitfile is:", pf(self.traitfile)) + + traitfiledata = getattr(self, "traitfile", None) + traitpastedata = getattr(self, "traitpaste", None) + variancefiledata = getattr(self, "variancefile", None) + variancepastedata = getattr(self, "variancepaste", None) + Nfiledata = getattr(self, "Nfile", None) + + #### Todo: Rewrite below when we get to someone submitting their own trait ##### + + def to_float(item): + try: + return float(item) + except ValueError: + return None + + print("bottle samplelist is:", samplelist) + if traitfiledata: + tt = traitfiledata.split() + values = map(webqtlUtil.StringAsFloat, tt) + elif traitpastedata: + tt = traitpastedata.split() + values = map(webqtlUtil.StringAsFloat, tt) + else: + print("mapping formdataasfloat") + #values = map(self.FormDataAsFloat, samplelist) + values = [to_float(getattr(self, key)) for key in samplelist] + print("rocket values is:", values) + + + if len(values) < len(samplelist): + values += [None] * (len(samplelist) - len(values)) + elif len(values) > len(samplelist): + values = values[:len(samplelist)] + print("now values is:", values) + + + if variancefiledata: + tt = variancefiledata.split() + variances = map(webqtlUtil.StringAsFloat, tt) + elif variancepastedata: + tt = variancepastedata.split() + variances = map(webqtlUtil.StringAsFloat, tt) + else: + variances = map(self.FormVarianceAsFloat, samplelist) + + if len(variances) < len(samplelist): + variances += [None]*(len(samplelist) - len(variances)) + elif len(variances) > len(samplelist): + variances = variances[:len(samplelist)] + + if Nfiledata: + tt = string.split(Nfiledata) + nsamples = map(webqtlUtil.IntAsFloat, tt) + if len(nsamples) < len(samplelist): + nsamples += [None]*(len(samplelist) - len(nsamples)) + else: + nsamples = map(self.FormNAsFloat, samplelist) + + ##values, variances, nsamples is obsolete + self.allTraitData = {} + for i, _sample in enumerate(samplelist): + if values[i] != None: + self.allTraitData[_sample] = webqtlCaseData( + _sample, values[i], variances[i], nsamples[i]) + print("allTraitData is:", pf(self.allTraitData)) + + + + def informativeStrains(self, samplelist=None, include_variances = None): + '''if readData was called, use this to output informative samples (sample with values)''' + + if not samplelist: + samplelist = self.samplelist + + samples = [] + values = [] + variances = [] + + #print("self.allTraitData is:", pf(self.allTraitData)) + + for sample in samplelist: + if sample in self.allTraitData: + _val, _var = self.allTraitData[sample].value, self.allTraitData[sample].variance + if _val != None: + if include_variances: + if _var != None: + samples.append(sample) + values.append(_val) + variances.append(_var) + else: + samples.append(sample) + values.append(_val) + variances.append(None) + + return samples, values, variances, len(samples) + + + + #def FormDataAsFloat(self, key): + # + # #try: + # # return float(self.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.group = '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.samplelist = map((lambda x, y='': '%s%s' % (y,x)), self.genotype.prgy) + #self.samplelist.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)} |