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

Jump to bottom

fixed alpha bug in tsne plot #6

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fixed alpha bug in tsne plot #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b888195
fixed alpha bug in tsne plot
nrosed Apr 10, 2024
20871eb
fix bug in future version of sklearn+anndata
nrosed Apr 10, 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
2 changes: 1 addition & 1 deletion buddi/plotting/validation_plotting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -654,7 +654,7 @@ def plot_tsne(plot_df, color_vec, ax, title="", alpha=0.1, legend_title="Y"):
hue=legend_title,
palette=sns.color_palette("hls", len(np.unique(color_vec))),
legend="full",
alpha=0.3, ax= ax
alpha=alpha, ax= ax
)

ax.set_title(title)
Expand Down
19 changes: 15 additions & 4 deletions buddi/preprocessing/sc_preprocess.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,9 @@ def get_cell_type_sum(in_adata, cell_df, num_samples): # pseudo
mult_by_zero = True

# now to the sampling
cell_sample = sk.utils.resample(cell_df, n_samples = num_samples, replace=True)
cell_sample = sk.utils.resample(range(cell_df.shape[0]), n_samples = num_samples, replace=True)
cell_sample = cell_df[cell_sample]


# add poisson noise
#dense_X = cell_sample.X.todense()
Expand Down Expand Up @@ -618,17 +620,26 @@ def read_all_kidney_pseudobulk_files(data_path, file_name, num_bulks_training=10

def write_cs_bp_files(cybersort_path, out_file_id, pbmc1_a_df, X_train, patient_idx=0): # pseudo
# write out the scRNA-seq signature matrix
sig_out_file = os.path.join(cybersort_path, f"{out_file_id}_{patient_idx}_cybersort_sig.tsv.gz")
sig_out_file = os.path.join(cybersort_path, f"{out_file_id}_{patient_idx}_cibersort_sig.tsv.gz")
sig_out_path = Path(sig_out_file)
pbmc1_a_df = pbmc1_a_df.transpose()

sig_df_vals = pbmc1_a_df.iloc[:,1:]
sig_df_celltype = pbmc1_a_df.scpred_CellType

# now we transpose
sig_sparse = sp.sparse.csr_matrix(sig_df_vals.values)
sig_sparse_t = sig_sparse.transpose()
sig_sparse = pd.DataFrame.sparse.from_spmatrix(sig_sparse_t)
sig_sparse.columns = sig_df_celltype
sig_sparse.index = pbmc1_a_df.columns[1:]

# cast from matrix to pd
pbmc1_a_df = pd.DataFrame(pbmc1_a_df)

pbmc1_a_df.to_csv(sig_out_path, sep='\t',header=False)

# write out the bulk RNA-seq mixture matrix
sig_out_file = os.path.join(cybersort_path, f"{out_file_id}_{patient_idx}_cybersort_mix.tsv.gz")
sig_out_file = os.path.join(cybersort_path, f"{out_file_id}_{patient_idx}_cibersort_mix.tsv.gz")
sig_out_path = Path(sig_out_file)

X_train.to_csv(sig_out_path, sep='\t',header=True)