Skip to content

Commit

Permalink
Merge branch 'add-brain-filter-protein-list'
Browse files Browse the repository at this point in the history
  • Loading branch information
@u8sand
u8sand committed Oct 20, 2023
2 parents 8572f20 + 828dc33 commit fa7448a
Show file tree
Hide file tree
Showing 2 changed files with 121 additions and 5 deletions.
117 changes: 114 additions & 3 deletions appyters/Tumor_Gene_Target_Screener/Tumor_Gene_Target_Screener.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -244,14 +244,52 @@
" section='primary',\n",
") %}\n",
"\n",
"{% set filter_brain = BoolField(\n",
" name='filter_brain',\n",
" label='Filter out brain related tissues from the background',\n",
" default=False,\n",
" section='primary',\n",
") %}\n",
"\n",
"\n",
"\n",
"{% set proteomics_vis_ = BoolField(\n",
" name='proteomics_vis',\n",
" label='Show protein expression profiles of gene candidates',\n",
" description='View protein expression levels in normal tissues, from Human Proteome Map and Human Protein Atlas proteomics data. Only human currently supported.',\n",
" default=True,\n",
" section='primary',\n",
") %}\n",
"{% set proteomics_vis = background_organism == '\"Mammalia/Homo_sapiens\"' and proteomics_vis_.raw_value %}"
"\n",
"{% set proteomics_vis = background_organism == '\"Mammalia/Homo_sapiens\"' and proteomics_vis_.raw_value %}\n",
"\n",
"{% set use_protein_list_ = TabField(\n",
" name='use_protein_list',\n",
" label='Prioritize list of highly expressed proteins',\n",
" description='Priortize a list of proteins highly expressed in the uploaded samples',\n",
" default='No',\n",
" section='primary',\n",
" choices={\n",
" 'Yes': [\n",
" FileField(\n",
" name='proteins_file',\n",
" label='Protein list',\n",
" description='A newline separated list of significantly highly expressed proteins in the uploaded samples',\n",
" default='proteins_example.txt',\n",
" required=True,\n",
" examples={\n",
" 'proteins_example.txt': 'https://appyters.maayanlab.cloud/storage/Tumor_Gene_Target_Screener/proteins_example.txt',\n",
" },\n",
" section='primary',\n",
" ),\n",
" ],\n",
" 'No': [\n",
" ]\n",
" }\n",
") %}\n",
"\n",
"\n",
"{% set use_protein_list = use_protein_list_.raw_value == 'Yes' %}"
]
},
{
Expand All @@ -273,6 +311,7 @@
"source": [
"%%appyter code_exec\n",
"import os\n",
"import re\n",
"import qnorm\n",
"import numpy as np\n",
"import pandas as pd\n",
Expand Down Expand Up @@ -364,6 +403,36 @@
"df_expr"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "214644e6",
"metadata": {},
"outputs": [],
"source": [
"%%appyter markdown\n",
"{% if use_protein_list %}\n",
"## Protein list\n",
"A list of proteins highly expressed in the uploaded samples was provided. These protiens will be prioritized in the final result of the analysis.\n",
"{% endif %}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9f2e6e2b",
"metadata": {},
"outputs": [],
"source": [
"%%appyter code_exec\n",
"{% if use_protein_list %}\n",
"protein_list_filename = {{ use_protein_list_.value[0] }}\n",
"with open(protein_list_filename, 'r') as fr:\n",
" lines = fr.readlines()\n",
" proteins = [x.strip() for x in lines]\n",
"{% endif %}"
]
},
{
"cell_type": "markdown",
"id": "ebcb9d0b",
Expand Down Expand Up @@ -394,6 +463,37 @@
"df_bg_expr"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7cbe4b90",
"metadata": {},
"outputs": [],
"source": [
"%%appyter markdown\n",
"{% if filter_brain.raw_value %}\n",
"## Include target genes that are only highly expressed in brain related cells and tissues\n",
"By removing brain related tissues and cell types from the normal backgrounds, we can identify genes that are \n",
"highly expressed only in the brain and in non-brain solid tumors, while lowly expressed in all other non-brain \n",
"normal tissues and cell types. The idea behind this filter is that the blood brain barrier (BBB) can server as a \n",
"protective layer from therapeutic agents aimed at targeting genes that are highly expressed in tumors.\n",
"{% endif %}"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "15eb496b",
"metadata": {},
"outputs": [],
"source": [
"%%appyter code_eval\n",
"{% if filter_brain.raw_value %}\n",
"brainvar = \"brain|cerebral|hippocampus|amygdala|neocortex|prefrontal|thalamus|cerebellum|pons|hypothalamic|hypothalamus|caudate|intracranial|cortical|dlpfc|cerebellar|basal ganglia\"\n",
"df_bg_expr = df_bg_expr[df_bg_expr.columns.drop(list(df_bg_expr.filter(regex=re.compile(brainvar, re.IGNORECASE))))]\n",
"{% endif %}"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand Down Expand Up @@ -736,6 +836,7 @@
"dge['is_deg'] = dge['adj.P.Val'] < 0.05\n",
"dge['is_significant'] = prod > prod.mean() + 3 * prod.std()\n",
"dge['score'] = dge['is_deg'].astype(int) + dge['is_significant'].astype(int)\n",
"\n",
"#\n",
"fig = go.Figure()\n",
"fig.add_trace(go.Scattergl(\n",
Expand Down Expand Up @@ -847,7 +948,11 @@
"outputs": [],
"source": [
"%%appyter code_exec\n",
"dge_final = dge[dge.score >= 1].sort_values(['score', '-log(adj.P.Val)'], ascending=False).iloc[:16]\n",
"{% if use_protein_list %}\n",
"dge['in_protein_list'] = np.in1d(dge['gene_symbol'], proteins)\n",
"dge['score'] = dge['score'] + dge['in_protein_list'].astype(int)\n",
"{% endif %}\n",
"dge_final = dge[dge.score >= 1].sort_values(['score', 't'], ascending=False).iloc[:16]\n",
"pd.set_option('display.max_colwidth', None)\n",
"dge_final['Link'] = dge_final['gene_symbol'].map(lambda g: f\"<a href=\\\"https://cfde-gene-pages.cloud/gene/{g}\\\">{g}</a>\")\n",
"{% if membrane_screener %}\n",
Expand All @@ -859,6 +964,9 @@
" 'is_deg',\n",
" 'is_significant',\n",
" 'is_membrane',\n",
"{% if use_protein_list %}\n",
" 'in_protein_list',\n",
"{% endif %}\n",
" 'score',\n",
" 'Link',\n",
"]].to_html(notebook=True, escape=False)))\n",
Expand All @@ -870,6 +978,9 @@
" 'adj.P.Val',\n",
" 'is_deg',\n",
" 'is_significant',\n",
"{% if use_protein_list %}\n",
" 'in_protein_list',\n",
"{% endif %}\n",
" 'score',\n",
" 'Link',\n",
"]].to_html(notebook=True, escape=False)))\n",
Expand Down Expand Up @@ -1122,7 +1233,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.15"
"version": "3.9.17"
},
"vscode": {
"interpreter": {
Expand Down
9 changes: 7 additions & 2 deletions appyters/Tumor_Gene_Target_Screener/appyter.json
View file
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": "Tumor_Gene_Target_Screener",
"title": "Tumor Gene Target Screener",
"version": "0.3.9",
"version": "0.4.0",
"description": "An appyter for gene target screening of tumors",
"authors": [
{
Expand All @@ -16,7 +16,12 @@
{
"name": "Reid H. Fleishman",
"email": "reidfleishman5@gmail.com"
},
{
"name": "Giacomo B. Marino",
"email": "giacomobmarino@gmail.com"
}

],
"image": "thumbnail.png",
"url": "https://github.com/maayanLab/appyter-catalog",
Expand All @@ -25,7 +30,7 @@
"Differential Expression Analysis"
],
"license": "CC-BY-NC-SA-4.0",
"public": false,
"public": true,
"appyter": {
"file": "Tumor_Gene_Target_Screener.ipynb",
"profile": "biojupies",
Expand Down

0 comments on commit fa7448a

Please sign in to comment.