DPT benchmark on cell cycle data

Notebook benchmarks latent time inference using DPT on cell cycle data.

Library imports

import numpy as np
import pandas as pd

import anndata as ad
import scanpy as sc

from rgv_tools import DATA_DIR
from rgv_tools.benchmarking import get_time_correlation

/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'

Pseuodtime inference

adata.uns["iroot"] = np.flatnonzero(adata.obs["fucci_time"] == 0)[0]

sc.pp.neighbors(adata)
sc.tl.diffmap(adata)
sc.tl.dpt(adata)

time_correlation = [
    get_time_correlation(ground_truth=adata.obs["fucci_time"], estimated=adata.obs["dpt_pseudotime"].values)
]

Data saving

if SAVE_DATA:
    pd.DataFrame({"time": time_correlation}).to_parquet(path=DATA_DIR / DATASET / "results" / "dpt_correlation.parquet")