From b0ccb12682fed83bf72d22ff42f1f442a8e6176e Mon Sep 17 00:00:00 2001 From: BonfaceKilz Date: Mon, 19 Apr 2021 14:43:16 +0300 Subject: Remove stale comments --- wqflask/base/data_set.py | 11 ---- wqflask/utility/helper_functions.py | 4 -- wqflask/wqflask/show_trait/show_trait.py | 72 +++++++++++++++----------- wqflask/wqflask/templates/index_page_orig.html | 10 ---- wqflask/wqflask/templates/submit_trait.html | 12 ----- wqflask/wqflask/views.py | 23 ++------ 6 files changed, 46 insertions(+), 86 deletions(-) diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py index 178234fe..cc5a428c 100644 --- a/wqflask/base/data_set.py +++ b/wqflask/base/data_set.py @@ -262,8 +262,6 @@ class Markers(object): elif isinstance(p_values, dict): filtered_markers = [] for marker in self.markers: - #logger.debug("marker[name]", marker['name']) - #logger.debug("p_values:", p_values) if marker['name'] in p_values: #logger.debug("marker {} IS in p_values".format(i)) marker['p_value'] = p_values[marker['name']] @@ -276,10 +274,6 @@ class Markers(object): marker['lrs_value'] = - \ math.log10(marker['p_value']) * 4.61 filtered_markers.append(marker) - # else: - #logger.debug("marker {} NOT in p_values".format(i)) - # self.markers.remove(marker) - #del self.markers[i] self.markers = filtered_markers @@ -306,7 +300,6 @@ class HumanMarkers(Markers): marker['Mb'] = float(splat[3]) / 1000000 self.markers.append(marker) - #logger.debug("markers is: ", pf(self.markers)) def add_pvalues(self, p_values): super(HumanMarkers, self).add_pvalues(p_values) @@ -520,7 +513,6 @@ def datasets(group_name, this_group=None): break if tissue_already_exists: - #logger.debug("dataset_menu:", dataset_menu[i]['datasets']) dataset_menu[i]['datasets'].append((dataset, dataset_short)) else: dataset_menu.append(dict(tissue=tissue_name, @@ -735,9 +727,6 @@ class PhenotypeDataSet(DataSet): DS_NAME_MAP['Publish'] = 'PhenotypeDataSet' def setup(self): - - #logger.debug("IS A PHENOTYPEDATASET") - # Fields in the database table self.search_fields = ['Phenotype.Post_publication_description', 'Phenotype.Pre_publication_description', diff --git a/wqflask/utility/helper_functions.py b/wqflask/utility/helper_functions.py index 7eb7f013..15d5b3ab 100644 --- a/wqflask/utility/helper_functions.py +++ b/wqflask/utility/helper_functions.py @@ -10,7 +10,6 @@ import logging logger = logging.getLogger(__name__ ) def get_species_dataset_trait(self, start_vars): - #assert type(read_genotype) == type(bool()), "Expecting boolean value for read_genotype" if "temp_trait" in list(start_vars.keys()): if start_vars['temp_trait'] == "True": self.dataset = data_set.create_dataset(dataset_name = "Temp", dataset_type = "Temp", group_name = start_vars['group']) @@ -27,9 +26,6 @@ def get_species_dataset_trait(self, start_vars): get_qtl_info=True) logger.debug("After creating trait") - #if read_genotype: - #self.dataset.group.read_genotype_file() - #self.genotype = self.dataset.group.genotype def get_trait_db_obs(self, trait_db_list): if isinstance(trait_db_list, str): diff --git a/wqflask/wqflask/show_trait/show_trait.py b/wqflask/wqflask/show_trait/show_trait.py index 6892f02b..ed55d473 100644 --- a/wqflask/wqflask/show_trait/show_trait.py +++ b/wqflask/wqflask/show_trait/show_trait.py @@ -138,17 +138,12 @@ class ShowTrait(object): self.ncbi_summary = get_ncbi_summary(self.this_trait) - #Get nearest marker for composite mapping + # Get nearest marker for composite mapping if not self.temp_trait: if check_if_attr_exists(self.this_trait, 'locus_chr') and self.dataset.type != "Geno" and self.dataset.type != "Publish": self.nearest_marker = get_nearest_marker(self.this_trait, self.dataset) - #self.nearest_marker1 = get_nearest_marker(self.this_trait, self.dataset)[0] - #self.nearest_marker2 = get_nearest_marker(self.this_trait, self.dataset)[1] else: self.nearest_marker = "" - #self.nearest_marker1 = "" - #self.nearest_marker2 = "" - self.make_sample_lists() @@ -168,16 +163,19 @@ class ShowTrait(object): categorical_var_list = [] if not self.temp_trait: - categorical_var_list = get_categorical_variables(self.this_trait, self.sample_groups[0]) #ZS: Only using first samplelist, since I think mapping only uses those samples + # ZS: Only using first samplelist, since I think mapping only uses those samples + categorical_var_list = get_categorical_variables(self.this_trait, self.sample_groups[0]) - #ZS: Get list of chromosomes to select for mapping + # ZS: Get list of chromosomes to select for mapping self.chr_list = [["All", -1]] for i, this_chr in enumerate(self.dataset.species.chromosomes.chromosomes): self.chr_list.append([self.dataset.species.chromosomes.chromosomes[this_chr].name, i]) self.genofiles = self.dataset.group.get_genofiles() - if "QTLReaper" or "R/qtl" in dataset.group.mapping_names: #ZS: No need to grab scales from .geno file unless it's using a mapping method that reads .geno files + # ZS: No need to grab scales from .geno file unless it's using + # a mapping method that reads .geno files + if "QTLReaper" or "R/qtl" in dataset.group.mapping_names: if self.genofiles: self.scales_in_geno = get_genotype_scales(self.genofiles) else: @@ -187,10 +185,15 @@ class ShowTrait(object): self.has_num_cases = has_num_cases(self.this_trait) - #ZS: Needed to know whether to display bar chart + get max sample name length in order to set table column width + # ZS: Needed to know whether to display bar chart + get max + # sample name length in order to set table column width self.num_values = 0 - self.binary = "true" #ZS: So it knows whether to display the Binary R/qtl mapping method, which doesn't work unless all values are 0 or 1 - self.negative_vals_exist = "false" #ZS: Since we don't want to show log2 transform option for situations where it doesn't make sense + # ZS: So it knows whether to display the Binary R/qtl mapping + # method, which doesn't work unless all values are 0 or 1 + self.binary = "true" + # ZS: Since we don't want to show log2 transform option for + # situations where it doesn't make sense + self.negative_vals_exist = "false" max_samplename_width = 1 for group in self.sample_groups: for sample in group.sample_list: @@ -203,7 +206,8 @@ class ShowTrait(object): if sample.value < 0: self.negative_vals_exist = "true" - #ZS: Check whether any attributes have few enough distinct values to show the "Block samples by group" option + # ZS: Check whether any attributes have few enough distinct + # values to show the "Block samples by group" option self.categorical_attr_exists = "false" for attribute in self.sample_groups[0].attributes: if len(self.sample_groups[0].attributes[attribute].distinct_values) <= 10: @@ -258,7 +262,6 @@ class ShowTrait(object): if not self.temp_trait: if hasattr(self.this_trait, 'locus_chr') and self.this_trait.locus_chr != "" and self.dataset.type != "Geno" and self.dataset.type != "Publish": hddn['control_marker'] = self.nearest_marker - #hddn['control_marker'] = self.nearest_marker1+","+self.nearest_marker2 hddn['do_control'] = False hddn['maf'] = 0.05 hddn['mapping_scale'] = "physic" @@ -268,7 +271,8 @@ class ShowTrait(object): if len(self.scales_in_geno) < 2: hddn['mapping_scale'] = self.scales_in_geno[list(self.scales_in_geno.keys())[0]][0][0] - # We'll need access to this_trait and hddn in the Jinja2 Template, so we put it inside self + # We'll need access to this_trait and hddn in the Jinja2 + # Template, so we put it inside self self.hddn = hddn js_data = dict(trait_id = self.trait_id, @@ -294,7 +298,8 @@ class ShowTrait(object): self.js_data = js_data def get_external_links(self): - #ZS: There's some weirdness here because some fields don't exist while others are empty strings + # ZS: There's some weirdness here because some fields don't + # exist while others are empty strings self.pubmed_link = webqtlConfig.PUBMEDLINK_URL % self.this_trait.pubmed_id if check_if_attr_exists(self.this_trait, 'pubmed_id') else None self.ncbi_gene_link = webqtlConfig.NCBI_LOCUSID % self.this_trait.geneid if check_if_attr_exists(self.this_trait, 'geneid') else None self.omim_link = webqtlConfig.OMIM_ID % self.this_trait.omim if check_if_attr_exists(self.this_trait, 'omim') else None @@ -320,7 +325,6 @@ class ShowTrait(object): self.panther_link = webqtlConfig.PANTHER_URL % self.this_trait.symbol self.ebi_gwas_link = webqtlConfig.EBIGWAS_URL % self.this_trait.symbol self.protein_atlas_link = webqtlConfig.PROTEIN_ATLAS_URL % self.this_trait.symbol - #self.open_targets_link = webqtlConfig.OPEN_TARGETS_URL % self.this_trait.symbol if self.dataset.group.species == "mouse" or self.dataset.group.species == "human": self.rgd_link = webqtlConfig.RGD_URL % (self.this_trait.symbol, self.dataset.group.species.capitalize()) @@ -429,7 +433,9 @@ class ShowTrait(object): all_samples_ordered.append(sample) other_sample_names.append(sample) - #ZS: CFW is here because the .geno file doesn't properly contain its full list of samples. This should probably be fixed. + # ZS: CFW is here because the .geno file doesn't properly + # contain its full list of samples. This should probably + # be fixed. if self.dataset.group.species == "human" or (set(primary_sample_names) == set(parent_f1_samples)) or self.dataset.group.name == "CFW": primary_sample_names += other_sample_names other_sample_names = [] @@ -445,7 +451,8 @@ class ShowTrait(object): sample_group_type='primary', header=primary_header) - #if other_sample_names and self.dataset.group.species != "human" and self.dataset.group.name != "CFW": + # if other_sample_names and self.dataset.group.species != + # "human" and self.dataset.group.name != "CFW": if len(other_sample_names) > 0: other_sample_names.sort() #Sort other samples if parent_f1_samples: @@ -539,7 +546,8 @@ def get_z_scores(sample_groups): def get_nearest_marker(this_trait, this_db): this_chr = this_trait.locus_chr this_mb = this_trait.locus_mb - #One option is to take flanking markers, another is to take the two (or one) closest + # One option is to take flanking markers, another is to take the + # two (or one) closest query = """SELECT Geno.Name FROM Geno, GenoXRef, GenoFreeze WHERE Geno.Chr = '{}' AND @@ -552,7 +560,6 @@ def get_nearest_marker(this_trait, this_db): if result == []: return "" - #return "", "" else: return result[0][0] @@ -617,7 +624,8 @@ def check_if_attr_exists(the_trait, id_type): def get_ncbi_summary(this_trait): if check_if_attr_exists(this_trait, 'geneid'): - #ZS: Need to switch this try/except to something that checks the output later + # ZS: Need to switch this try/except to something that checks + # the output later try: response = requests.get("http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=gene&id=%s&retmode=json" % this_trait.geneid) summary = json.loads(response.content)['result'][this_trait.geneid]['summary'] @@ -661,8 +669,8 @@ def get_genotype_scales(genofiles): def get_scales_from_genofile(file_location): geno_path = locate_ignore_error(file_location, 'genotype') - - if not geno_path: #ZS: This is just to allow the code to run when + # ZS: This is just to allow the code to run when + if not geno_path: return [["physic", "Mb"]] cm_and_mb_cols_exist = True cm_column = None @@ -670,7 +678,9 @@ def get_scales_from_genofile(file_location): with open(geno_path, "r") as geno_fh: for i, line in enumerate(geno_fh): if line[0] == "#" or line[0] == "@": - if "@scale" in line: #ZS: If the scale is made explicit in the metadata, use that + # ZS: If the scale is made explicit in the metadata, + # use that + if "@scale" in line: scale = line.split(":")[1].strip() if scale == "morgan": return [["morgan", "cM"]] @@ -690,12 +700,16 @@ def get_scales_from_genofile(file_location): mb_column = 3 break - #ZS: This attempts to check whether the cM and Mb columns are 'real', since some .geno files have one column be a copy of the other column, or have one column that is all 0s + # ZS: This attempts to check whether the cM and Mb columns are + # 'real', since some .geno files have one column be a copy of + # the other column, or have one column that is all 0s cm_all_zero = True mb_all_zero = True cm_mb_all_equal = True for i, line in enumerate(geno_fh): - if first_marker_line <= i < first_marker_line + 10: #ZS: I'm assuming there won't be more than 10 markers where the position is listed as 0 + # ZS: I'm assuming there won't be more than 10 markers + # where the position is listed as 0 + if first_marker_line <= i < first_marker_line + 10: if cm_column: cm_val = line.split("\t")[cm_column].strip() if cm_val != "0": @@ -711,8 +725,8 @@ def get_scales_from_genofile(file_location): if i > first_marker_line + 10: break - - #ZS: This assumes that both won't be all zero, since if that's the case mapping shouldn't be an option to begin with + # ZS: This assumes that both won't be all zero, since if that's + # the case mapping shouldn't be an option to begin with if mb_all_zero: return [["morgan", "cM"]] elif cm_mb_all_equal: diff --git a/wqflask/wqflask/templates/index_page_orig.html b/wqflask/wqflask/templates/index_page_orig.html index 7f82b35c..87cf1b45 100755 --- a/wqflask/wqflask/templates/index_page_orig.html +++ b/wqflask/wqflask/templates/index_page_orig.html @@ -7,16 +7,6 @@ {% endblock %} {% block content %} - - -
Paste or Type Multiple Values: You can enter data by pasting a series of numbers representing trait values into this area. diff --git a/wqflask/wqflask/views.py b/wqflask/wqflask/views.py index 2c0ba586..c4b510d4 100644 --- a/wqflask/wqflask/views.py +++ b/wqflask/wqflask/views.py @@ -156,12 +156,6 @@ def index_page(): import_collections = params['import_collections'] if import_collections == "true": g.user_session.import_traits_to_user(params['anon_id']) - #if USE_GN_SERVER: - # # The menu is generated using GN_SERVER - # return render_template("index_page.html", gn_server_url = GN_SERVER_URL, version=GN_VERSION) - #else: - - # Old style static menu (OBSOLETE) return render_template("index_page_orig.html", version=GN_VERSION) @@ -343,14 +337,10 @@ def intro(): @app.route("/tutorials") def tutorials(): - #doc = Docs("links", request.args) - #return render_template("docs.html", **doc.__dict__) return render_template("tutorials.html") @app.route("/credits") def credits(): - #doc = Docs("links", request.args) - #return render_template("docs.html", **doc.__dict__) return render_template("credits.html") @app.route("/update_text", methods=('POST',)) @@ -368,12 +358,9 @@ def submit_trait_form(): @app.route("/create_temp_trait", methods=('POST',)) def create_temp_trait(): logger.info(request.url) - - #template_vars = submit_trait.SubmitTrait(request.form) - doc = Docs("links") return render_template("links.html", **doc.__dict__) - #return render_template("show_trait.html", **template_vars.__dict__) + @app.route('/export_trait_excel', methods=('POST',)) def export_trait_excel(): @@ -487,21 +474,17 @@ def export_perm_data(): mimetype='text/csv', headers={"Content-Disposition":"attachment;filename=" + file_name + ".csv"}) + @app.route("/show_temp_trait", methods=('POST',)) def show_temp_trait_page(): logger.info(request.url) template_vars = show_trait.ShowTrait(request.form) - #logger.info("js_data before dump:", template_vars.js_data) template_vars.js_data = json.dumps(template_vars.js_data, default=json_default_handler, indent=" ") - # Sorting the keys messes up the ordered dictionary, so don't do that - #sort_keys=True) - - #logger.info("js_data after dump:", template_vars.js_data) - #logger.info("show_trait template_vars:", pf(template_vars.__dict__)) return render_template("show_trait.html", **template_vars.__dict__) + @app.route("/show_trait") def show_trait_page(): logger.info(request.url) -- cgit v1.2.3 From 4534daa6fb07c23b90e024560ca64091fc330eed Mon Sep 17 00:00:00 2001 From: BonfaceKilz Date: Mon, 19 Apr 2021 17:46:38 +0300 Subject: Move looped sql query into one statement in "get_species_groups" It's in-efficient to have a sql query executed in a loop. As data grows, the query becomes slower. It's better to let sql handle such queries. --- wqflask/utility/helper_functions.py | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) diff --git a/wqflask/utility/helper_functions.py b/wqflask/utility/helper_functions.py index 15d5b3ab..4ba92ed5 100644 --- a/wqflask/utility/helper_functions.py +++ b/wqflask/utility/helper_functions.py @@ -47,19 +47,18 @@ def get_trait_db_obs(self, trait_db_list): if trait_ob: self.trait_list.append((trait_ob, dataset_ob)) -def get_species_groups(): - - species_query = "SELECT SpeciesId, MenuName FROM Species" - species_ids_and_names = g.db.execute(species_query).fetchall() - - species_and_groups = [] - for species_id, species_name in species_ids_and_names: - this_species_groups = {} - this_species_groups['species'] = species_name - groups_query = "SELECT InbredSetName FROM InbredSet WHERE SpeciesId = %s" % (species_id) - groups = [group[0] for group in g.db.execute(groups_query).fetchall()] - this_species_groups['groups'] = groups - species_and_groups.append(this_species_groups) - - return species_and_groups +def get_species_groups(): + """Group each species into a group""" + _menu = {} + for species, group_name in g.db.execute( + "SELECT s.MenuName, i.InbredSetName FROM InbredSet i " + "INNER JOIN Species s ON s.SpeciesId = i.SpeciesId " + "ORDER BY i.SpeciesId ASC, i.Name ASC").fetchall(): + if _menu.get(species): + _menu = _menu[species].append(group_name) + else: + _menu[species] = [group_name] + return [{"species": key, + "groups": value} for key, value in + list(_menu.items())] -- cgit v1.2.3 From d2e2046a3ce1af0ca97ea1b6d9ccb3a4c9aecf7c Mon Sep 17 00:00:00 2001 From: BonfaceKilz Date: Fri, 23 Apr 2021 17:21:12 +0300 Subject: Add full link to genetic data collected as part of WebQTL project --- wqflask/wqflask/templates/submit_trait.html | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/wqflask/wqflask/templates/submit_trait.html b/wqflask/wqflask/templates/submit_trait.html index 334a608d..2cc18240 100644 --- a/wqflask/wqflask/templates/submit_trait.html +++ b/wqflask/wqflask/templates/submit_trait.html @@ -14,7 +14,7 @@
The trait values that you enter are statistically compared with verified genotypes collected at a set of microsatellite markers in each RI set. The markers are drawn from a set of over 750, but for each set redundant markers have been removed, preferentially retaining those that are most informative.
-These error-checked RI mapping data match theoretical expectations for RI strain sets. The cumulative adjusted length of the RI maps are approximately 1400 cM, a value that matches those of both MIT maps and Chromosome Committee Report maps. See our full description of the genetic data collected as part of the WebQTL project.
+These error-checked RI mapping data match theoretical expectations for RI strain sets. The cumulative adjusted length of the RI maps are approximately 1400 cM, a value that matches those of both MIT maps and Chromosome Committee Report maps. See our full description of the genetic data collected as part of the WebQTL project.