Skip to content
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

Add linear model results from concat plates #40

Merged
merged 3 commits into from
Mar 21, 2024
Merged

Add linear model results from concat plates #40

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
076f62d
add linear model results from concat plates
jenna-tomkinson Mar 18, 2024
46efbd7
update documentation
jenna-tomkinson Mar 18, 2024
d4d9362
update code and documentation
jenna-tomkinson Mar 21, 2024
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
Prev Previous commit
Next Next commit
update documentation
  • Loading branch information
@jenna-tomkinson
jenna-tomkinson committed Mar 18, 2024
commit 46efbd724fe7894382e8cdf550ed1e8e138dae3f
19 changes: 3 additions & 16 deletions 4.analyze_data/notebooks/linear_model/0.linear_model_concat_coeff.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,24 +6,11 @@
"source": [
"# Perform linear model per CellProfiler feature on concatenated normalized data from plates 5, 3 prime, and 3\n",
"\n",
"We will include 4 co-variates:\n",
"We will include 3 co-variates:\n",
"\n",
"1. Cell count per well contribution\n",
"2. Plate contribution -> need variability across plates for cell count per well \n",
"3. Genotype contribution (WT versus Null) -> could be imbalance \n",
"4. Interaction term between genotype and cell count -> remove first, Natalie think this might be too correlated\n",
"\n",
"Assumes Gaussian for LM -> need to check for that LM\n",
"\n",
"If co-variates are too highly correlated, then coefficients will \"explode\"\n",
"\n",
"Can Python show if there was convergence or not\n",
"\n",
"QC plot -> density and qq (do for one first for qq), and scatterplot with each of the covariantes \n",
"\n",
"Might need multiple test correction which uses p-value -> Bonferonni and Benjamini - Hockberg\n",
"\n",
"Under null hypothesis the p-values are evenly distributed but if there is a significant value of p-value that is low than reject null"
"2. Plate contribution\n",
"3. Genotype contribution (WT versus Null)"
]
},
{
Expand Down
19 changes: 3 additions & 16 deletions 4.analyze_data/notebooks/linear_model/scripts/0.linear_model_concat_coeff.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,24 +3,11 @@

# # Perform linear model per CellProfiler feature on concatenated normalized data from plates 5, 3 prime, and 3
#
# We will include 4 co-variates:
# We will include 3 co-variates:
#
# 1. Cell count per well contribution
# 2. Plate contribution -> need variability across plates for cell count per well
# 3. Genotype contribution (WT versus Null) -> could be imbalance
# 4. Interaction term between genotype and cell count -> remove first, Natalie think this might be too correlated
#
# Assumes Gaussian for LM -> need to check for that LM
#
# If co-variates are too highly correlated, then coefficients will "explode"
#
# Can Python show if there was convergence or not
#
# QC plot -> density and qq (do for one first for qq), and scatterplot with each of the covariantes
#
# Might need multiple test correction which uses p-value -> Bonferonni and Benjamini - Hockberg
#
# Under null hypothesis the p-values are evenly distributed but if there is a significant value of p-value that is low than reject null
# 2. Plate contribution
# 3. Genotype contribution (WT versus Null)

# In[1]:

Expand Down