Skip to content

CFDE gene partnership update #933

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
u8sand merged 5 commits into from
Sep 15, 2025
Merged

CFDE gene partnership update #933

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
cb7feb4
[CFDE-Gene-Partnership]: Support newer versions of some upstream libr…
u8sand Sep 15, 2025
ed57853
[CFDE-Gene-Partnership]: Upgrade to GTEx v2 API
u8sand Sep 15, 2025
5942003
[CFDE-Gene-Partnership]: Upgrade to GlyGen's new API
u8sand Sep 15, 2025
4877947
[CFDE-Gene-Partnership]: Support missing column in IMPC results
u8sand Sep 15, 2025
e7e9838
[CFDE-Gene-Partnership]: 0.3.0
u8sand Sep 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
94 changes: 50 additions & 44 deletions appyters/CFDE-Gene-Partnership/CFDE-Gene-Partnership.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,11 +103,15 @@
"console.setFormatter(formatter)\n",
"logger.addHandler(console)\n",
"\n",
"from itables_javascript import show\n",
"import itables.options as opt\n",
"opt.maxBytes = 0\n",
"opt.showIndex = False\n",
"\n",
"def show(df, *kargs, **kwargs):\n",
" from itables_javascript import show\n",
" try: return show(df, *kargs, **kwargs)\n",
" except: return display(df)\n",
"\n",
"class RenderJSON(object):\n",
" ''' https://gist.github.com/t27/48b3ac73a1479914f9fe9383e5d45325 '''\n",
" def __init__(self, json_data):\n",
Expand Down Expand Up @@ -364,17 +368,32 @@
"outputs": [],
"source": [
"@lru_cache()\n",
"def gtex_singleTissueEqtl(geneSymbol, datasetId='gtex_v8'):\n",
"def gtex_resolve_genecode_id(geneId):\n",
" res = requests.get(\n",
" 'https://gtexportal.org/api/v2/reference/gene',\n",
" params=dict(\n",
" format='json',\n",
" geneId=geneId,\n",
" pageSize=1,\n",
" )\n",
" )\n",
" if not res.ok: raise Exception(f\"The gene {geneId} could not be found in GTEx\")\n",
" return res.json()['data'][0]['gencodeId']\n",
"\n",
"@lru_cache()\n",
"def gtex_medianGeneExpression(geneSymbol, datasetId='gtex_v8'):\n",
" gencodeId = gtex_resolve_genecode_id(geneSymbol)\n",
" res = requests.get(\n",
" 'https://gtexportal.org/rest/v1/association/singleTissueEqtl',\n",
" 'https://gtexportal.org/api/v2/expression/medianGeneExpression',\n",
" params=dict(\n",
" format='json',\n",
" geneSymbol=geneSymbol,\n",
" gencodeId=gencodeId,\n",
" datasetId=datasetId,\n",
" )\n",
" )\n",
" results = res.json()['singleTissueEqtl']\n",
" if len(results) == 0: raise Exception(f\"No information for gene with identifier {geneSymbol} found in GTEx\")\n",
" if not res.ok: raise Exception(f\"Failed to resolve information about {geneSymbol} ({gencodeId}) from GTEx ({datasetId})\")\n",
" results = res.json()['data']\n",
" if len(results) == 0: raise Exception(f\"No information for gene {geneSymbol} ({gencodeId}) found in GTEx ({datasetId})\")\n",
" return pd.DataFrame(results)"
]
},
Expand All @@ -386,13 +405,8 @@
"outputs": [],
"source": [
"with ignore_exceptions(f\"Gene with identifier {gene_info['symbol']} currently not available in GTEx\"):\n",
" gtex_results = gtex_singleTissueEqtl(gene_info['symbol'])\n",
" columns = list(gtex_results.columns)\n",
" columns.insert(0, columns.pop(columns.index('nes')))\n",
" columns.insert(0, columns.pop(columns.index('pValue')))\n",
" columns.insert(0, columns.pop(columns.index('tissueSiteDetailId')))\n",
" gtex_results = gtex_results[columns]\n",
" show(gtex_results, order=[[gtex_results.columns.get_loc('pValue'), 'asc']])"
" gtex_results = gtex_medianGeneExpression(gene_info['symbol']).sort_values('median', ascending=False)\n",
" show(gtex_results, order=[[gtex_results.columns.get_loc('median'), 'desc']])"
]
},
{
Expand All @@ -403,20 +417,12 @@
"outputs": [],
"source": [
"with ignore_exceptions('Could not process GTEx output'):\n",
" gtex_combined_stouffer_statistic = gtex_results.groupby('tissueSiteDetailId')['pValue'] \\\n",
" .agg(partial(combine_pvalues, method='stouffer', select='statistic')) \\\n",
" .to_frame('combined_stouffer_statistic') \\\n",
" .reset_index() \\\n",
" .sort_values('combined_stouffer_statistic', ascending=False)\n",
" gtex_combined_stouffer_statistic['group'] = gtex_combined_stouffer_statistic['tissueSiteDetailId'].apply(lambda name: name.split('_', maxsplit=1)[0])\n",
"\n",
" fig = px.bar(\n",
" gtex_combined_stouffer_statistic,\n",
" y='combined_stouffer_statistic',\n",
" gtex_results,\n",
" y='median',\n",
" x='tissueSiteDetailId',\n",
" color='group',\n",
" orientation='v',\n",
" title=f\"Tissues with significant expression of {gene_info['symbol']} in GTEx\",\n",
" title=f\"Tissues with median expression of {gene_info['symbol']} in GTEx\",\n",
" height=1000,\n",
" )\n",
" fig.show()"
Expand Down Expand Up @@ -449,7 +455,7 @@
"metadata": {},
"outputs": [],
"source": [
"import matplotlib.cm as cm\n",
"import matplotlib; cm = matplotlib.colormaps\n",
"import matplotlib.colors as colors\n",
"from bokeh.io import output_notebook\n",
"from bokeh.plotting import figure, show as bokeh_show\n",
Expand Down Expand Up @@ -506,8 +512,8 @@
" ]\n",
" # generate plot and relevant plot labels\n",
" plot = figure(\n",
" plot_width=700,\n",
" plot_height=500,\n",
" width=700,\n",
" height=500,\n",
" tooltips=tools\n",
" )\n",
" \n",
Expand Down Expand Up @@ -684,7 +690,7 @@
"source": [
"with ignore_exceptions(f\"No information for gene with identifier {gene_info['symbol']} found in IPMC\"):\n",
" impc_results = impc_phenotype(gene_info['symbol'].capitalize())\n",
" show(impc_results[[\n",
" show(impc_results.loc[:, impc_results.columns.isin([\n",
" 'marker_accession_id',\n",
" 'mp_term_id',\n",
" 'mp_term_name',\n",
Expand All @@ -693,7 +699,7 @@
" 'phenotyping_center',\n",
" 'percentage_change',\n",
" 'statistical_method',\n",
" ]])"
" ])])"
]
},
{
Expand Down Expand Up @@ -751,20 +757,20 @@
"outputs": [],
"source": [
"@lru_cache()\n",
"def glygen_geneNameSearch(recommended_gene_name, organism_taxon_id=9606):\n",
" res = requests.get(\n",
" 'https://api.glygen.org/directsearch/gene/',\n",
" params=dict(\n",
" query=json.dumps(dict(\n",
" recommended_gene_name=recommended_gene_name,\n",
" organism=dict(\n",
" id=organism_taxon_id\n",
" ),\n",
" )),\n",
" ),\n",
" verify=False, # not sure why on my system I get SSL errors\n",
" )\n",
" return res.json()"
"def glygen_protein_search(gene_name):\n",
" search_results = requests.post('https://api.glygen.org/protein/search/', json={'gene_name': gene_name}, verify=False).json()\n",
" return requests.post('https://api.glygen.org/protein/list/', json={'id': search_results['list_id']}, verify=False).json()\n",
"\n",
"@lru_cache()\n",
"def glygen_protein_detail(uniprot_canonical_ac):\n",
" return requests.post(f'https://api.glygen.org/protein/detail/{uniprot_canonical_ac}/', json={}, verify=False).json()\n",
"\n",
"@lru_cache()\n",
"def glygen_geneNameSearch(recommended_gene_name):\n",
" protein_list_results = glygen_protein_search(recommended_gene_name)\n",
" protein_uniprot_canonical_ac = protein_list_results['results'][0]['uniprot_canonical_ac']\n",
" protein_details = requests.post(f'https://api.glygen.org/protein/detail/{protein_uniprot_canonical_ac}/', json={}, verify=False).json()\n",
" return protein_details"
]
},
{
Expand All @@ -777,7 +783,7 @@
"with ignore_exceptions(f\"No information for gene with identifier {gene_info['symbol']} found in GlyGen\"):\n",
" glygen_geneInfo = glygen_geneNameSearch(gene_info['symbol'])\n",
" display(RenderJSON(glygen_geneInfo))\n",
" d = pd.DataFrame(glygen_geneInfo['results'][0]['glycosylation'])\n",
" d = pd.DataFrame(glygen_geneInfo['glycosylation'])\n",
" d['evidence'] = d['evidence'].apply(\n",
" lambda evidence: ' '.join(f\"<a href='{e['url']}'>{e['url']}></a>\" for e in evidence if 'url' in e)\n",
" )\n",
Expand Down
2 changes: 1 addition & 1 deletion appyters/CFDE-Gene-Partnership/appyter.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
"$schema": "https://raw.githubusercontent.com/MaayanLab/appyter-catalog/main/schema/appyter-validator.json",
"name": "CFDE-Gene-Partnership",
"title": "CFDE Gene Partnership",
"version": "0.2.9",
"version": "0.3.0",
"description": "This Appyter uses FAIR APIs from different DCCs to Resolve gene-centric information from CF DCCs.",
"image": "cfde-gene-partnership.png",
"public": true,
Expand Down