diff options
| -rw-r--r-- | wqflask/base/trait.py | 55 | ||||
| -rw-r--r-- | wqflask/wqflask/gsearch.py | 166 | ||||
| -rwxr-xr-x | wqflask/wqflask/templates/gsearch_gene.html | 60 | ||||
| -rw-r--r-- | wqflask/wqflask/update_search_results.py | 130 | ||||
| -rw-r--r-- | wqflask/wqflask/views.py | 13 |
5 files changed, 293 insertions, 131 deletions
diff --git a/wqflask/base/trait.py b/wqflask/base/trait.py index ce3a7608..0bc10b97 100644 --- a/wqflask/base/trait.py +++ b/wqflask/base/trait.py @@ -2,7 +2,7 @@ from __future__ import absolute_import, division, print_function import string import resource - +import codecs from htmlgen import HTMLgen2 as HT @@ -309,13 +309,50 @@ class GeneralTrait(object): holder = unicode(trait_info[i], "utf8", "ignore") setattr(self, field, holder) + description_string = unicode(str(self.description).strip(codecs.BOM_UTF8), 'utf-8') + target_string = unicode(str(self.probe_target_description).strip(codecs.BOM_UTF8), 'utf-8') + + if len(description_string) > 1 and description_string != 'None': + description_display = description_string + else: + description_display = self.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 + self.description_display = description_display + + #XZ: trait_location_value is used for sorting + trait_location_repr = 'N/A' + trait_location_value = 1000000 + + if self.chr and self.mb: + #Checks if the chromosome number can be cast to an int (i.e. isn't "X" or "Y") + #This is so we can convert the location to a number used for sorting + trait_location_value = convert_location_to_value(self.chr, self.mb) + #try: + # trait_location_value = int(self.chr)*1000 + self.mb + #except ValueError: + # if self.chr.upper() == 'X': + # trait_location_value = 20*1000 + self.mb + # else: + # trait_location_value = (ord(str(self.chr).upper()[0])*1000 + + # self.mb) + + #ZS: Put this in function currently called "convert_location_to_value" + self.location_repr = 'Chr%s: %.6f' % (self.chr, float(self.mb)) + self.location_value = trait_location_value + + if self.dataset.type == 'Publish': self.confidential = 0 if self.pre_publication_description and not self.pubmed_id: self.confidential = 1 - - description = self.post_publication_description + description = self.post_publication_description + #If the dataset is confidential and the user has access to confidential #phenotype traits, then display the pre-publication description instead #of the post-publication description @@ -662,7 +699,17 @@ class GeneralTrait(object): ZValue = ZValue*sqrt(self.overlap-3) self.p_value = 2.0*(1.0 - reaper.normp(abs(ZValue))) - +def convert_location_to_value(chromosome, mb): + try: + location_value = int(chromosome)*1000 + float(mb) + except ValueError: + if chromosome.upper() == 'X': + location_value = 20*1000 + float(mb) + else: + location_value = (ord(str(chromosome).upper()[0])*1000 + + float(mb)) + + return location_value @app.route("/trait/get_sample_data") def get_sample_data(): diff --git a/wqflask/wqflask/gsearch.py b/wqflask/wqflask/gsearch.py index 4cd3874c..4f9dc316 100644 --- a/wqflask/wqflask/gsearch.py +++ b/wqflask/wqflask/gsearch.py @@ -1,94 +1,94 @@ from __future__ import absolute_import, print_function, division from flask import Flask, g -from base.data_set import create_dataset -from base.trait import GeneralTrait -from dbFunction import webqtlDatabaseFunction +#from base.data_set import create_dataset +#from base.trait import GeneralTrait +#from dbFunction import webqtlDatabaseFunction -from utility.benchmark import Bench +#from utility.benchmark import Bench class GSearch(object): def __init__(self, kw): self.type = kw['type'] self.terms = kw['terms'] - if self.type == "gene": - sql = """ - SELECT - Species.`Name` AS species_name, - InbredSet.`Name` AS inbredset_name, - Tissue.`Name` AS tissue_name, - ProbeSetFreeze.Name AS probesetfreeze_name, - ProbeSet.Name AS probeset_name, - ProbeSet.Symbol AS probeset_symbol, - ProbeSet.`description` AS probeset_description, - ProbeSet.Chr AS chr, - ProbeSet.Mb AS mb, - ProbeSetXRef.Mean AS mean, - ProbeSetXRef.LRS AS lrs, - ProbeSetXRef.`Locus` AS locus, - ProbeSetXRef.`pValue` AS pvalue, - ProbeSetXRef.`additive` AS additive - FROM Species, InbredSet, ProbeSetXRef, ProbeSet, ProbeFreeze, ProbeSetFreeze, Tissue - WHERE InbredSet.`SpeciesId`=Species.`Id` - AND ProbeFreeze.InbredSetId=InbredSet.`Id` - AND ProbeFreeze.`TissueId`=Tissue.`Id` - AND ProbeSetFreeze.ProbeFreezeId=ProbeFreeze.Id - AND ( MATCH (ProbeSet.Name,ProbeSet.description,ProbeSet.symbol,alias,GenbankId, UniGeneId, Probe_Target_Description) AGAINST ('%s' IN BOOLEAN MODE) ) - AND ProbeSet.Id = ProbeSetXRef.ProbeSetId - AND ProbeSetXRef.ProbeSetFreezeId=ProbeSetFreeze.Id - AND ProbeSetFreeze.public > 0 - ORDER BY species_name, inbredset_name, tissue_name, probesetfreeze_name, probeset_name - LIMIT 6000 - """ % (self.terms) - with Bench("Running query"): - re = g.db.execute(sql).fetchall() - self.trait_list = [] - with Bench("Creating trait objects"): - for line in re: - dataset = create_dataset(line[3], "ProbeSet", get_samplelist=False) - trait_id = line[4] - #with Bench("Building trait object"): - this_trait = GeneralTrait(dataset=dataset, name=trait_id, get_qtl_info=True, get_sample_info=False) - self.trait_list.append(this_trait) + # if self.type == "gene": + # sql = """ + # SELECT + # Species.`Name` AS species_name, + # InbredSet.`Name` AS inbredset_name, + # Tissue.`Name` AS tissue_name, + # ProbeSetFreeze.Name AS probesetfreeze_name, + # ProbeSet.Name AS probeset_name, + # ProbeSet.Symbol AS probeset_symbol, + # ProbeSet.`description` AS probeset_description, + # ProbeSet.Chr AS chr, + # ProbeSet.Mb AS mb, + # ProbeSetXRef.Mean AS mean, + # ProbeSetXRef.LRS AS lrs, + # ProbeSetXRef.`Locus` AS locus, + # ProbeSetXRef.`pValue` AS pvalue, + # ProbeSetXRef.`additive` AS additive + # FROM Species, InbredSet, ProbeSetXRef, ProbeSet, ProbeFreeze, ProbeSetFreeze, Tissue + # WHERE InbredSet.`SpeciesId`=Species.`Id` + # AND ProbeFreeze.InbredSetId=InbredSet.`Id` + # AND ProbeFreeze.`TissueId`=Tissue.`Id` + # AND ProbeSetFreeze.ProbeFreezeId=ProbeFreeze.Id + # AND ( MATCH (ProbeSet.Name,ProbeSet.description,ProbeSet.symbol,alias,GenbankId, UniGeneId, Probe_Target_Description) AGAINST ('%s' IN BOOLEAN MODE) ) + # AND ProbeSet.Id = ProbeSetXRef.ProbeSetId + # AND ProbeSetXRef.ProbeSetFreezeId=ProbeSetFreeze.Id + # AND ProbeSetFreeze.public > 0 + # ORDER BY species_name, inbredset_name, tissue_name, probesetfreeze_name, probeset_name + # LIMIT 6000 + # """ % (self.terms) + # with Bench("Running query"): + # re = g.db.execute(sql).fetchall() + # self.trait_list = [] + # with Bench("Creating trait objects"): + # for line in re: + # dataset = create_dataset(line[3], "ProbeSet", get_samplelist=False) + # trait_id = line[4] + # with Bench("Building trait object"): + # this_trait = GeneralTrait(dataset=dataset, name=trait_id, get_qtl_info=True, get_sample_info=False) + # self.trait_list.append(this_trait) - elif self.type == "phenotype": - sql = """ - SELECT - Species.`Name`, - InbredSet.`Name`, - PublishFreeze.`Name`, - PublishXRef.`Id`, - Phenotype.`Post_publication_description`, - Publication.`Authors`, - Publication.`Year`, - PublishXRef.`LRS`, - PublishXRef.`Locus`, - PublishXRef.`additive` - FROM Species,InbredSet,PublishFreeze,PublishXRef,Phenotype,Publication - WHERE PublishXRef.`InbredSetId`=InbredSet.`Id` - AND PublishFreeze.`InbredSetId`=InbredSet.`Id` - AND InbredSet.`SpeciesId`=Species.`Id` - AND PublishXRef.`PhenotypeId`=Phenotype.`Id` - AND PublishXRef.`PublicationId`=Publication.`Id` - AND (Phenotype.Post_publication_description REGEXP "[[:<:]]%s[[:>:]]" - OR Phenotype.Pre_publication_description REGEXP "[[:<:]]%s[[:>:]]" - OR Phenotype.Pre_publication_abbreviation REGEXP "[[:<:]]%s[[:>:]]" - OR Phenotype.Post_publication_abbreviation REGEXP "[[:<:]]%s[[:>:]]" - OR Phenotype.Lab_code REGEXP "[[:<:]]%s[[:>:]]" - OR Publication.PubMed_ID REGEXP "[[:<:]]%s[[:>:]]" - OR Publication.Abstract REGEXP "[[:<:]]%s[[:>:]]" - OR Publication.Title REGEXP "[[:<:]]%s[[:>:]]" - OR Publication.Authors REGEXP "[[:<:]]%s[[:>:]]" - OR PublishXRef.Id REGEXP "[[:<:]]%s[[:>:]]") - ORDER BY Species.`Name`, InbredSet.`Name`, PublishXRef.`Id` - LIMIT 6000 - """ % (self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms) - re = g.db.execute(sql).fetchall() - self.trait_list = [] - with Bench("Creating trait objects"): - for line in re: - dataset = create_dataset(line[2], "Publish") - trait_id = line[3] - this_trait = GeneralTrait(dataset=dataset, name=trait_id, get_qtl_info=True, get_sample_info=False) - self.trait_list.append(this_trait) + # elif self.type == "phenotype": + # sql = """ + # SELECT + # Species.`Name`, + # InbredSet.`Name`, + # PublishFreeze.`Name`, + # PublishXRef.`Id`, + # Phenotype.`Post_publication_description`, + # Publication.`Authors`, + # Publication.`Year`, + # PublishXRef.`LRS`, + # PublishXRef.`Locus`, + # PublishXRef.`additive` + # FROM Species,InbredSet,PublishFreeze,PublishXRef,Phenotype,Publication + # WHERE PublishXRef.`InbredSetId`=InbredSet.`Id` + # AND PublishFreeze.`InbredSetId`=InbredSet.`Id` + # AND InbredSet.`SpeciesId`=Species.`Id` + # AND PublishXRef.`PhenotypeId`=Phenotype.`Id` + # AND PublishXRef.`PublicationId`=Publication.`Id` + # AND (Phenotype.Post_publication_description REGEXP "[[:<:]]%s[[:>:]]" + # OR Phenotype.Pre_publication_description REGEXP "[[:<:]]%s[[:>:]]" + # OR Phenotype.Pre_publication_abbreviation REGEXP "[[:<:]]%s[[:>:]]" + # OR Phenotype.Post_publication_abbreviation REGEXP "[[:<:]]%s[[:>:]]" + # OR Phenotype.Lab_code REGEXP "[[:<:]]%s[[:>:]]" + # OR Publication.PubMed_ID REGEXP "[[:<:]]%s[[:>:]]" + # OR Publication.Abstract REGEXP "[[:<:]]%s[[:>:]]" + # OR Publication.Title REGEXP "[[:<:]]%s[[:>:]]" + # OR Publication.Authors REGEXP "[[:<:]]%s[[:>:]]" + # OR PublishXRef.Id REGEXP "[[:<:]]%s[[:>:]]") + # ORDER BY Species.`Name`, InbredSet.`Name`, PublishXRef.`Id` + # LIMIT 6000 + # """ % (self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms) + # re = g.db.execute(sql).fetchall() + # self.trait_list = [] + # with Bench("Creating trait objects"): + # for line in re: + # dataset = create_dataset(line[2], "Publish") + # trait_id = line[3] + # this_trait = GeneralTrait(dataset=dataset, name=trait_id, get_qtl_info=True, get_sample_info=False) + # self.trait_list.append(this_trait) diff --git a/wqflask/wqflask/templates/gsearch_gene.html b/wqflask/wqflask/templates/gsearch_gene.html index 7cc9a1bd..2ff75052 100755 --- a/wqflask/wqflask/templates/gsearch_gene.html +++ b/wqflask/wqflask/templates/gsearch_gene.html @@ -13,6 +13,7 @@ <div class="container"> + <p>You searched for {{ terms }}.</p> <p>To study a record, click on its ID below.<br />Check records below and click Add button to add to selection.</p> <div> @@ -27,44 +28,6 @@ <br /> <br /> <table width="2000px" class="table table-hover table-striped" id="trait_table"> - <thead> - <tr> - <th style="width: 30px;"></th> - <th>Index</th> - <th>Species</th> - <th>Group</th> - <th>Tissue</th> - <th>Dataset</th> - <th>Record</th> - <th>Symbol</th> - <th>Description</th> - <th>Location</th> - <th>Mean</th> - <th style="text-align: right;">Max <br>LRS<a href="http://genenetwork.org//glossary.html#L" target="_blank"><sup style="color:#f00"> ?</sup></a></th> - <th>Max LRS Location</th> - <th style="text-align: right;">Additive<br>Effect<a href="http://genenetwork.org//glossary.html#A" target="_blank"><sup style="color:#f00"> ?</sup></a></th> - </tr> - </thead> - <tbody> - {% for this_trait in trait_list %} - <TR id="trait:{{ this_trait.name }}:{{ this_trait.dataset.name }}"> - <TD><INPUT TYPE="checkbox" NAME="searchResult" class="checkbox trait_checkbox" style="transform: scale(1.5);" VALUE="{{ data_hmac('{}:{}'.format(this_trait.name, this_trait.dataset.name)) }}"></TD> - <TD>{{ loop.index }}</TD> - <TD>{{ this_trait.dataset.group.species }}</TD> - <TD>{{ this_trait.dataset.group.name }}</TD> - <TD>{{ this_trait.dataset.tissue }}</TD> - <TD>{{ this_trait.dataset.fullname }}</TD> - <TD><a href="{{ url_for('show_trait_page', trait_id = this_trait.name, dataset = this_trait.dataset.name)}}">{{ this_trait.name }}</a></TD> - <TD>{{ this_trait.symbol }}</TD> - <TD>{{ this_trait.description_display }}</TD> - <TD>{{ this_trait.location_repr }}</TD> - <TD align="right">{{ '%0.3f' % this_trait.mean|float }}</TD> - <TD align="right">{{ '%0.3f' % this_trait.LRS_score_repr|float }}</TD> - <TD>{{ this_trait.LRS_location_repr }}</TD> - <TD align="right">{{ '%0.3f' % this_trait.additive|float }}</TD> - </TR> - {% endfor %} - </tbody> </table> </div> </div> @@ -156,6 +119,17 @@ console.time("Creating table"); $('#trait_table').DataTable( { + "processing": true, + "serverSide": true, + "paging": false, + "ajax": { + "url": "/gsearch_updating?terms={{ terms }}&type={{ type }}&draw=100", + "dataType": "json", + "contentType": "application/json; charset=utf-8", + "complete": function(response) { + console.log("Response:" + JSON.stringify(response)); + } + }, "columns": [ { "type": "natural" }, { "type": "natural" }, @@ -184,15 +158,15 @@ } } ], - "sDom": "RZBtir", - "autoWidth": false, - "bLengthChange": true, + "sDom": "RZBfrtiS", + "scrollY": 800, "bDeferRender": true, - "scrollCollapse": false, + "scroller": { + "loadingIndicator": true + }, "colResize": { "tableWidthFixed": false, }, - "paging": false } ); console.timeEnd("Creating table"); diff --git a/wqflask/wqflask/update_search_results.py b/wqflask/wqflask/update_search_results.py new file mode 100644 index 00000000..976fc1cd --- /dev/null +++ b/wqflask/wqflask/update_search_results.py @@ -0,0 +1,130 @@ +from __future__ import absolute_import, print_function, division + +import json + +from flask import Flask, g +from base.data_set import create_dataset +from base.trait import GeneralTrait +from dbFunction import webqtlDatabaseFunction + +from utility.benchmark import Bench + +class GSearch(object): + + def __init__(self, kw): + self.type = kw['type'] + self.terms = kw['terms'] + self.draw = int(kw['draw']) + #self.row_range = kw['row_range'] + if self.type == "gene": + sql = """ + SELECT + Species.`Name` AS species_name, + InbredSet.`Name` AS inbredset_name, + Tissue.`Name` AS tissue_name, + ProbeSetFreeze.Name AS probesetfreeze_name, + ProbeSet.Name AS probeset_name, + ProbeSet.Symbol AS probeset_symbol, + ProbeSet.`description` AS probeset_description, + ProbeSet.Chr AS chr, + ProbeSet.Mb AS mb, + ProbeSetXRef.Mean AS mean, + ProbeSetXRef.LRS AS lrs, + ProbeSetXRef.`Locus` AS locus, + ProbeSetXRef.`pValue` AS pvalue, + ProbeSetXRef.`additive` AS additive + FROM Species, InbredSet, ProbeSetXRef, ProbeSet, ProbeFreeze, ProbeSetFreeze, Tissue + WHERE InbredSet.`SpeciesId`=Species.`Id` + AND ProbeFreeze.InbredSetId=InbredSet.`Id` + AND ProbeFreeze.`TissueId`=Tissue.`Id` + AND ProbeSetFreeze.ProbeFreezeId=ProbeFreeze.Id + AND ( MATCH (ProbeSet.Name,ProbeSet.description,ProbeSet.symbol,alias,GenbankId, UniGeneId, Probe_Target_Description) AGAINST ('%s' IN BOOLEAN MODE) ) + AND ProbeSet.Id = ProbeSetXRef.ProbeSetId + AND ProbeSetXRef.ProbeSetFreezeId=ProbeSetFreeze.Id + AND ProbeSetFreeze.public > 0 + ORDER BY species_name, inbredset_name, tissue_name, probesetfreeze_name, probeset_name + LIMIT %s + """ % (self.terms, self.draw) + with Bench("Running query"): + re = g.db.execute(sql).fetchall() + self.trait_list = [] + with Bench("Creating trait objects"): + for line in re: + dataset = create_dataset(line[3], "ProbeSet", get_samplelist=False) + trait_id = line[4] + #with Bench("Building trait object"): + this_trait = GeneralTrait(dataset=dataset, name=trait_id, get_qtl_info=True, get_sample_info=False) + self.trait_list.append(this_trait) + + elif self.type == "phenotype": + sql = """ + SELECT + Species.`Name`, + InbredSet.`Name`, + PublishFreeze.`Name`, + PublishXRef.`Id`, + Phenotype.`Post_publication_description`, + Publication.`Authors`, + Publication.`Year`, + PublishXRef.`LRS`, + PublishXRef.`Locus`, + PublishXRef.`additive` + FROM Species,InbredSet,PublishFreeze,PublishXRef,Phenotype,Publication + WHERE PublishXRef.`InbredSetId`=InbredSet.`Id` + AND PublishFreeze.`InbredSetId`=InbredSet.`Id` + AND InbredSet.`SpeciesId`=Species.`Id` + AND PublishXRef.`PhenotypeId`=Phenotype.`Id` + AND PublishXRef.`PublicationId`=Publication.`Id` + AND (Phenotype.Post_publication_description REGEXP "[[:<:]]%s[[:>:]]" + OR Phenotype.Pre_publication_description REGEXP "[[:<:]]%s[[:>:]]" + OR Phenotype.Pre_publication_abbreviation REGEXP "[[:<:]]%s[[:>:]]" + OR Phenotype.Post_publication_abbreviation REGEXP "[[:<:]]%s[[:>:]]" + OR Phenotype.Lab_code REGEXP "[[:<:]]%s[[:>:]]" + OR Publication.PubMed_ID REGEXP "[[:<:]]%s[[:>:]]" + OR Publication.Abstract REGEXP "[[:<:]]%s[[:>:]]" + OR Publication.Title REGEXP "[[:<:]]%s[[:>:]]" + OR Publication.Authors REGEXP "[[:<:]]%s[[:>:]]" + OR PublishXRef.Id REGEXP "[[:<:]]%s[[:>:]]") + ORDER BY Species.`Name`, InbredSet.`Name`, PublishXRef.`Id` + LIMIT 6000 + """ % (self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms, self.terms) + re = g.db.execute(sql).fetchall() + self.trait_list = [] + with Bench("Creating trait objects"): + for line in re: + dataset = create_dataset(line[2], "Publish") + trait_id = line[3] + this_trait = GeneralTrait(dataset=dataset, name=trait_id, get_qtl_info=True, get_sample_info=False) + self.trait_list.append(this_trait) + + self.results = self.convert_to_json() + + def convert_to_json(self): + json_dict = {} + json_dict['draw'] = self.draw, + json_dict['recordsTotal'] = len(self.trait_list), + json_dict['data'] = [] + + for i, trait in enumerate(self.trait_list): + trait_row = ["<INPUT TYPE=\"checkbox\" NAME=\"searchResult\" class=\"checkbox trait_checkbox\" style=\"transform: scale(1.5);\" VALUE=\"{}:{}\">".format(trait.name, trait.dataset.name), + i+1, + trait.dataset.group.species, + trait.dataset.group.name, + trait.dataset.tissue, + trait.dataset.fullname, + trait.name, + trait.symbol, + trait.description_display, + trait.location_repr, + trait.mean, + trait.LRS_score_repr, + trait.LRS_location_repr, + trait.additive] + json_dict['data'].append(trait_row) + + json_results = json.dumps(json_dict) + return json_results + + + + diff --git a/wqflask/wqflask/views.py b/wqflask/wqflask/views.py index 3bf64a18..aa145969 100644 --- a/wqflask/wqflask/views.py +++ b/wqflask/wqflask/views.py @@ -34,6 +34,7 @@ from flask import (render_template, request, make_response, Response, from wqflask import search_results from wqflask import gsearch +from wqflask import update_search_results from wqflask import docs from wqflask import news from base.data_set import DataSet # Used by YAML in marker_regression @@ -163,9 +164,19 @@ def gsearchact(): result = gsearch.GSearch(request.args).__dict__ type = request.args['type'] if type == "gene": - return render_template("gsearch_gene.html", **result) + return render_template("gsearch_gene_updating.html", **result) elif type == "phenotype": return render_template("gsearch_pheno.html", **result) + +@app.route("/gsearch_updating", methods=('GET',)) +def gsearch_updating(): + result = update_search_results.GSearch(request.args).__dict__ + return result['results'] + # type = request.args['type'] + # if type == "gene": + # return render_template("gsearch_gene_updating.html", **result) + # elif type == "phenotype": + # return render_template("gsearch_pheno.html", **result) @app.route("/docedit") def docedit(): |