Skip to content

Add multiple enrichment methods #49

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
ajlee21 merged 1 commit into from
Dec 18, 2020
Merged

Add multiple enrichment methods #49

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
154 changes: 154 additions & 0 deletions human_general_analysis/Try_other_enrichment_methods.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,154 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Name\n",
"\n",
"This notebook plugs in other gene set enrichment methods to demonstrate that our method, SOPHIE, can be inserted into different pipelines and work with other methods"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using TensorFlow backend.\n",
"/home/alexandra/anaconda3/envs/generic_expression/lib/python3.7/site-packages/matplotlib/__init__.py:886: MatplotlibDeprecationWarning: \n",
"examples.directory is deprecated; in the future, examples will be found relative to the 'datapath' directory.\n",
" \"found relative to the 'datapath' directory.\".format(key))\n"
]
}
],
"source": [
"%load_ext autoreload\n",
"%load_ext rpy2.ipython\n",
"%autoreload 2\n",
"\n",
"import os\n",
"import sys\n",
"import pandas as pd\n",
"import numpy as np\n",
"import pickle\n",
"\n",
"from rpy2.robjects import pandas2ri\n",
"pandas2ri.activate()\n",
"\n",
"from ponyo import utils\n",
"from generic_expression_patterns_modules import calc, process\n",
"\n",
"np.random.seed(123)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# Read in config variables\n",
"base_dir = os.path.abspath(os.path.join(os.getcwd(), \"../\"))\n",
"\n",
"config_filename = os.path.abspath(\n",
" os.path.join(base_dir, \"configs\", \"config_human_general.tsv\")\n",
")\n",
"\n",
"params = utils.read_config(config_filename)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# Load params\n",
"local_dir = params[\"local_dir\"]\n",
"project_id = params['project_id']\n",
"hallmark_DB_filename = params[\"pathway_DB_filename\"]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"# Load DE stats directory\n",
"DE_stats_dir = os.path.join(local_dir, \"DE_stats\")\n",
"\n",
"# Template experiment DE stats\n",
"template_DE_stats_filename = os.path.join(\n",
" DE_stats_dir,\n",
" f\"DE_stats_template_data_{project_id}_real.txt\"\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Enrichment methods\n",
"* [ROAST](https://pubmed.ncbi.nlm.nih.gov/20610611/) is available in limma\n",
"* [CAMERA](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3458527/) is available in limma\n",
"* [GSVA](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3618321/) its own bioconductor package\n",
"* [ORA]() is available in PathwayStudios or David\n",
"\n",
"TO DO: Write about each method"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"# Define function\n",
"# ORA works on list of DE\n",
"# Apply voom on gene expression >> ROAST, CAMERA, GVSA\n",
"\n",
"# Process data using voom\n",
"\n",
"\n",
"# Run method on template experiments\n",
"# Run method on simulated experiments\n",
"# Output table sort by ranking"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"# Get summary rank of pathways"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python [conda env:generic_expression] *",
"language": "python",
"name": "conda-env-generic_expression-py"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.8"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
92 changes: 92 additions & 0 deletions human_general_analysis/nbconverted/Try_other_enrichment_methods.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,92 @@
#!/usr/bin/env python
# coding: utf-8

# ## Name
#
# This notebook plugs in other gene set enrichment methods to demonstrate that our method, SOPHIE, can be inserted into different pipelines and work with other methods

# In[1]:


get_ipython().run_line_magic('load_ext', 'autoreload')
get_ipython().run_line_magic('load_ext', 'rpy2.ipython')
get_ipython().run_line_magic('autoreload', '2')

import os
import sys
import pandas as pd
import numpy as np
import pickle

from rpy2.robjects import pandas2ri
pandas2ri.activate()

from ponyo import utils
Copy link
Contributor

@danich1 danich1 Dec 18, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What tensorflow version are you using? If it is less than 2.x.x, your ponyo code might become outdated. (Example Here Really tiny issue in the overall scheme, but I wanted to just let you know.

Copy link
Contributor Author

@ajlee21 ajlee21 Dec 18, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for looking out. I remember having some conflicts with other dependencies that arose when i previously tried to upgrade tensorflow. But it has been a while since I looked at this so I'll make an issue in my ponyo repo, which is using v<2.x.x for tensorflow

from generic_expression_patterns_modules import calc, process

np.random.seed(123)


# In[2]:


# Read in config variables
base_dir = os.path.abspath(os.path.join(os.getcwd(), "../"))
Copy link
Contributor

@danich1 danich1 Dec 18, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Might want to try and use pathlib. I know broken record, but it definitely makes os path generation a lot easier to deal with.

Copy link
Contributor Author

@ajlee21 ajlee21 Dec 18, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not a broken record. I definitely agree with using paths instead of the way I currently have my config. The legacy reason for having the config this way is 1) to be consistent with how ponyo is, which this repo uses and 2) it seemed more user friendly at the time to have a tab-delimited file and have that passed into the notebook as opposed to "importing a python file. I also wasn't aware, at the time when I created the config, that I could define both variables and paths in the same file. But rest assured that my other newer repo uses paths:)


config_filename = os.path.abspath(
os.path.join(base_dir, "configs", "config_human_general.tsv")
)

params = utils.read_config(config_filename)


# In[3]:


# Load params
local_dir = params["local_dir"]
project_id = params['project_id']
hallmark_DB_filename = params["pathway_DB_filename"]


# In[4]:


# Load DE stats directory
DE_stats_dir = os.path.join(local_dir, "DE_stats")

# Template experiment DE stats
template_DE_stats_filename = os.path.join(
DE_stats_dir,
f"DE_stats_template_data_{project_id}_real.txt"
)


# ## Enrichment methods
# * [ROAST](https://pubmed.ncbi.nlm.nih.gov/20610611/) is available in limma
# * [CAMERA](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3458527/) is available in limma
# * [GSVA](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3618321/) its own bioconductor package
# * [ORA]() is available in PathwayStudios or David
#
# TO DO: Write about each method

# In[5]:


# Define function
# ORA works on list of DE
# Apply voom on gene expression >> ROAST, CAMERA, GVSA

# Process data using voom


# Run method on template experiments
# Run method on simulated experiments
# Output table sort by ranking


# In[6]:


# Get summary rank of pathways