SpliceJAC benchmark on cell cycle

Notebook benchmarks GRN inference using SpliceJAC on cell cycling dataset

Library imports

import splicejac as sp

import pandas as pd

import anndata as ad

from rgv_tools import DATA_DIR
from rgv_tools.benchmarking import get_grn_auroc_cc

/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/anndata/utils.py:429: FutureWarning: Importing read_csv from `anndata` is deprecated. Import anndata.io.read_csv instead.
  warnings.warn(msg, FutureWarning)
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/anndata/utils.py:429: FutureWarning: Importing read_excel from `anndata` is deprecated. Import anndata.io.read_excel instead.
  warnings.warn(msg, FutureWarning)
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/anndata/utils.py:429: FutureWarning: Importing read_hdf from `anndata` is deprecated. Import anndata.io.read_hdf instead.
  warnings.warn(msg, FutureWarning)
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/anndata/utils.py:429: FutureWarning: Importing read_loom from `anndata` is deprecated. Import anndata.io.read_loom instead.
  warnings.warn(msg, FutureWarning)
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/anndata/utils.py:429: FutureWarning: Importing read_mtx from `anndata` is deprecated. Import anndata.io.read_mtx instead.
  warnings.warn(msg, FutureWarning)
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/anndata/utils.py:429: FutureWarning: Importing read_text from `anndata` is deprecated. Import anndata.io.read_text instead.
  warnings.warn(msg, FutureWarning)
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/anndata/utils.py:429: FutureWarning: Importing read_umi_tools from `anndata` is deprecated. Import anndata.io.read_umi_tools instead.
  warnings.warn(msg, FutureWarning)

Constants

DATASET = "cell_cycle"

SAVE_DATA = True
if SAVE_DATA:
    (DATA_DIR / DATASET / "results").mkdir(parents=True, exist_ok=True)

Data loading

adata = ad.io.read_h5ad(DATA_DIR / DATASET / "processed" / "adata_processed.h5ad")
adata

AnnData object with n_obs × n_vars = 1146 × 395
    obs: 'phase', 'fucci_time', 'initial_size_unspliced', 'initial_size_spliced', 'initial_size', 'n_counts'
    var: 'ensum_id', 'gene_count_corr', 'means', 'dispersions', 'dispersions_norm', 'highly_variable', 'velocity_gamma', 'velocity_qreg_ratio', 'velocity_r2', 'velocity_genes'
    uns: 'log1p', 'neighbors', 'pca', 'umap', 'velocity_params'
    obsm: 'X_pca', 'X_umap'
    varm: 'PCs', 'true_skeleton'
    layers: 'Ms', 'Mu', 'spliced', 'total', 'unspliced', 'velocity'
    obsp: 'connectivities', 'distances'

GRN pipeline

## We ignore the cell label information and assume all cells is the same label due to we use cellline dataset
adata.obs["clusters"] = "0"
n = len(adata.var_names)

sp.tl.estimate_jacobian(adata, n_top_genes=adata.shape[1], min_shared_counts=0)
grn_estimate = adata.uns["average_jac"]["0"][0][0:n, n:].copy()

grn_correlation = [get_grn_auroc_cc(ground_truth=adata.varm["true_skeleton"].toarray(), estimated=grn_estimate.T)]

WARNING: Did not normalize X as it looks processed already. To enforce normalization, set `enforce=True`.
WARNING: Did not normalize spliced as it looks processed already. To enforce normalization, set `enforce=True`.
WARNING: Did not normalize unspliced as it looks processed already. To enforce normalization, set `enforce=True`.
Extracted 395 highly variable genes.
WARNING: adata.X seems to be already log-transformed.
Logarithmized X.

/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/scvelo/preprocessing/utils.py:705: DeprecationWarning: `log1p` is deprecated since scVelo v0.3.0 and will be removed in a future version. Please use `log1p` from `scanpy.pp` instead.
  log1p(adata)

Running quick regression...
Running subset regression on the 0 cluster...

if SAVE_DATA:
    pd.DataFrame({"grn": grn_correlation}).to_parquet(
        path=DATA_DIR / DATASET / "results" / "splicejac_correlation.parquet"
    )