Skip to content

Commit

Permalink
pearson corr is simplified
Browse files Browse the repository at this point in the history
  • Loading branch information
@janursa
janursa committed Sep 23, 2024
1 parent 347b160 commit 59b4e9f
Show file tree
Hide file tree
Showing 10 changed files with 17 additions and 271 deletions.
221 changes: 12 additions & 209 deletions runs.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2332,24 +2332,26 @@
},
{
"cell_type": "code",
"execution_count": 30,
"execution_count": 31,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'reg_type': 'ridge', 'write_dir': 'resources/results/robustness_analysis', 'perturbation_data': 'resources/grn-benchmark/perturbation_data.h5ad', 'cell_type_specific': False, 'normalize': False, 'multiomics_rna': 'resources/grn-benchmark/multiomics_rna_d0_hvg.h5ad', 'tf_all': 'resources/prior/tf_all.csv', 'max_n_links': 50000, 'apply_tf': False, 'subsample': -2, 'verbose': 2, 'binarize': True, 'num_workers': 20, 'consensus': 'resources/prior/consensus-num-regulators.json', 'static_only': True, 'clip_scores': True, 'layer': 'scgen_pearson', 'prediction': 'resources/results/robustness_analysis/corr/corr_causal.csv', 'causal': False}\n",
"{'reg_type': 'ridge', 'write_dir': 'resources/results/robustness_analysis', 'perturbation_data': 'resources/grn-benchmark/perturbation_data.h5ad', 'cell_type_specific': False, 'normalize': False, 'multiomics_rna': 'resources/grn-benchmark/multiomics_rna_d0_hvg.h5ad', 'tf_all': 'resources/prior/tf_all.csv', 'max_n_links': 50000, 'apply_tf': False, 'subsample': -2, 'verbose': 2, 'binarize': True, 'num_workers': 20, 'consensus': 'resources/prior/consensus-num-regulators.json', 'static_only': True, 'clip_scores': True, 'layer': 'scgen_pearson', 'prediction': 'resources/results/robustness_analysis/corr/corr_causal.csv', 'causal': True}\n",
"Read data\n",
"Random subsetting\n",
"Causal subsetting\n",
" target source weight\n",
"0 AC107068.2 NFXL1 0.831974\n",
"1 FBN1 NR4A3 0.763036\n",
"2 BIRC3 NR4A3 0.751467\n",
"3 MFSD12 HMG20B 0.747598\n",
"4 STX17-AS1 NR4A3 0.744736\n",
"Traceback (most recent call last):\n",
" File \"/home/jnourisa/projs/ongoing/task_grn_inference/src/robustness_analysis/script_all.py\", line 126, in <module>\n",
" net = create_corr_net(par)\n",
" File \"/home/jnourisa/projs/ongoing/task_grn_inference/src/utils/util.py\", line 97, in create_corr_net\n",
" grn = corr_net(X, gene_names, par, tf_all, par['causal'])\n",
" File \"/home/jnourisa/projs/ongoing/task_grn_inference/src/utils/util.py\", line 49, in corr_net\n",
" net = net.sample(len(tf_all), axis=1, random_state=par['seed'])\n",
"KeyError: 'seed'\n"
" File \"/home/jnourisa/projs/ongoing/task_grn_inference/src/robustness_analysis/script_all.py\", line 128, in <module>\n",
" aa\n",
"NameError: name 'aa' is not defined\n"
]
}
],
Expand All @@ -2375,205 +2377,6 @@
"scores_causal = pd.read_csv(\"resources/results/robustness_analysis/corr/scores_causal.csv\", index_col=0)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>S1</th>\n",
" <th>S2</th>\n",
" <th>static-theta-0.0</th>\n",
" <th>static-theta-0.5</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.129438</td>\n",
" <td>0.146122</td>\n",
" <td>0.395947</td>\n",
" <td>0.531279</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" S1 S2 static-theta-0.0 static-theta-0.5\n",
"0 0.129438 0.146122 0.395947 0.531279"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"scores_causal"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>S1</th>\n",
" <th>S2</th>\n",
" <th>static-theta-0.0</th>\n",
" <th>static-theta-0.5</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.308404</td>\n",
" <td>0.530900</td>\n",
" <td>0.696251</td>\n",
" <td>0.543549</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.265614</td>\n",
" <td>0.475809</td>\n",
" <td>0.523504</td>\n",
" <td>0.541446</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.290910</td>\n",
" <td>0.491693</td>\n",
" <td>0.678848</td>\n",
" <td>0.545381</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.279864</td>\n",
" <td>0.488906</td>\n",
" <td>0.594799</td>\n",
" <td>0.533744</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.287134</td>\n",
" <td>0.505098</td>\n",
" <td>0.763991</td>\n",
" <td>0.550709</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.275764</td>\n",
" <td>0.503644</td>\n",
" <td>0.463909</td>\n",
" <td>0.535066</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.279247</td>\n",
" <td>0.498071</td>\n",
" <td>0.609557</td>\n",
" <td>0.534484</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.271350</td>\n",
" <td>0.468998</td>\n",
" <td>0.721520</td>\n",
" <td>0.538930</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.277122</td>\n",
" <td>0.484159</td>\n",
" <td>0.652754</td>\n",
" <td>0.537736</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.299330</td>\n",
" <td>0.537139</td>\n",
" <td>0.710375</td>\n",
" <td>0.540515</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>100 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" S1 S2 static-theta-0.0 static-theta-0.5\n",
"0 0.308404 0.530900 0.696251 0.543549\n",
"0 0.265614 0.475809 0.523504 0.541446\n",
"0 0.290910 0.491693 0.678848 0.545381\n",
"0 0.279864 0.488906 0.594799 0.533744\n",
"0 0.287134 0.505098 0.763991 0.550709\n",
".. ... ... ... ...\n",
"0 0.275764 0.503644 0.463909 0.535066\n",
"0 0.279247 0.498071 0.609557 0.534484\n",
"0 0.271350 0.468998 0.721520 0.538930\n",
"0 0.277122 0.484159 0.652754 0.537736\n",
"0 0.299330 0.537139 0.710375 0.540515\n",
"\n",
"[100 rows x 4 columns]"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"scores_corr"
]
},
{
"cell_type": "code",
"execution_count": 14,
Expand Down
5 changes: 0 additions & 5 deletions src/api/comp_method.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -52,11 +52,6 @@ functionality:
direction: input
default: false
description: normalize rna seq data before inference. currently, it's only applicable to baseline models
- name: --only_hvgs
type: boolean
direction: input
default: false
description: subset rna seq data to only 7000 hvgs to reduce dimensionality

test_resources:
- type: python_script
Expand Down
2 changes: 1 addition & 1 deletion src/control_methods/pearson/script.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
sys.path.append(meta["resources_dir"])
from util import create_corr_net

par['causal'] = False
par['causal'] = True
net = create_corr_net(par)
print('Output GRN')
net.to_csv(par['prediction'])
26 changes: 0 additions & 26 deletions src/control_methods/pearson_causal/config.vsh.yaml
View file

This file was deleted.

21 changes: 0 additions & 21 deletions src/control_methods/pearson_causal/script.py
View file

This file was deleted.

5 changes: 0 additions & 5 deletions src/control_methods/pearson_causal/test.sh
View file

This file was deleted.

2 changes: 2 additions & 0 deletions src/metrics/regression_2/config.vsh.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,8 @@ functionality:
- type: python_script
path: script.py
- path: main.py
- path: /src/utils/util.py
dest: util.py
arguments:
- name: --consensus
type: file
Expand Down
4 changes: 2 additions & 2 deletions src/robustness_analysis/script_all.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,6 @@
def run_reg(par):
from metrics.regression_1.main import main
reg1 = main(par)
return reg1
from metrics.regression_2.main import main
reg2 = main(par)
score = pd.concat([reg1, reg2], axis=1)
Expand Down Expand Up @@ -98,6 +97,7 @@ def run_reg(par):
'static_only': True,
'clip_scores': True,
'layer': 'scgen_pearson',
'seed': 32
}

# # run for corr
Expand All @@ -124,7 +124,7 @@ def run_reg(par):
par['prediction'] = f"{par['write_dir']}/corr/corr_causal.csv"
par['causal'] = True
net = create_corr_net(par)

net.to_csv(par['prediction'])
score = run_reg(par)
print(score)
score.to_csv(f"{par['write_dir']}/corr/scores_causal.csv")
1 change: 0 additions & 1 deletion src/workflows/run_benchmark/config.vsh.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -109,7 +109,6 @@ functionality:
- name: grn_methods/scglue
# ---- baselines
- name: control_methods/pearson_corr
- name: control_methods/pearson_causal
- name: control_methods/negative_control
- name: control_methods/positive_control
# -- needs development
Expand Down
1 change: 0 additions & 1 deletion src/workflows/run_benchmark/main.nf
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ workflow run_wf {
scenic,

pearson_corr,
pearson_causal,
negative_control,
positive_control,

Expand Down

0 comments on commit 59b4e9f

Please sign in to comment.