RegVelo-based analysis on murine NCC cell

RegVelo-based analysis on murine NCC cell#

We run RegVelo on each scale dataset.

import numpy as np
import torch

import scanpy as sc
import scvi
from regvelo import REGVELOVI

from rgv_tools import DATA_DIR
from rgv_tools.benchmarking import set_output

General settings#

scvi.settings.seed = 0

[rank: 0] Seed set to 0

Constants#

DATASET = "mouse_neural_crest"

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

Function definations#

def min_max_scaling(data):
    """Compute min and max values for each feature."""
    min_vals = np.min(data, axis=0)
    max_vals = np.max(data, axis=0)

    # Perform min-max scaling
    scaled_data = (data - min_vals) / (max_vals - min_vals)

    return scaled_data

Velocity pipeline#

for i in range(1, 5):
    adata = sc.read_h5ad(DATA_DIR / DATASET / "processed" / f"adata_stage{i}_processed_velo_all_regulons.h5ad")

    # Prepare skeleton
    scvi.settings.seed = 0
    W = adata.uns["skeleton"].copy()
    W = torch.tensor(np.array(W)).int()

    # Prepare TF
    TF = adata.var_names[adata.var["TF"]]

    # Prepare model
    REGVELOVI.setup_anndata(adata, spliced_layer="Ms", unspliced_layer="Mu")
    vae = REGVELOVI(adata, W=W.T, regulators=TF)

    vae.train()
    set_output(adata, vae, n_samples=30, batch_size=adata.n_obs)

    if SAVE_DATA:
        adata.write_h5ad(DATA_DIR / DATASET / "processed" / f"adata_run_stage_{i}_regvelo_all_regulons.h5ad")
        vae.save(DATA_DIR / DATASET / "processed" / f"rgv_run_stage_{i}_all_regulons")

[rank: 0] Seed set to 0
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/lightning/fabric/plugins/environments/slurm.py:204: The `srun` command is available on your system but is not used. HINT: If your intention is to run Lightning on SLURM, prepend your python command with `srun` like so: srun python /home/icb/weixu.wang/miniconda3/envs/regvelo_test/li ...
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/lightning/fabric/plugins/environments/slurm.py:204: The `srun` command is available on your system but is not used. HINT: If your intention is to run Lightning on SLURM, prepend your python command with `srun` like so: srun python /home/icb/weixu.wang/miniconda3/envs/regvelo_test/li ...
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
HPU available: False, using: 0 HPUs
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/lightning/fabric/plugins/environments/slurm.py:204: The `srun` command is available on your system but is not used. HINT: If your intention is to run Lightning on SLURM, prepend your python command with `srun` like so: srun python /home/icb/weixu.wang/miniconda3/envs/regvelo_test/li ...
You are using a CUDA device ('NVIDIA A100 80GB PCIe') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:424: The 'train_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=5` in the `DataLoader` to improve performance.
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/lightning/pytorch/loops/fit_loop.py:298: The number of training batches (1) is smaller than the logging interval Trainer(log_every_n_steps=10). Set a lower value for log_every_n_steps if you want to see logs for the training epoch.
/home/icb/weixu.wang/miniconda3/envs/regvelo_test/lib/python3.10/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:424: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=5` in the `DataLoader` to improve performance.

IOPub message rate exceeded.
The Jupyter server will temporarily stop sending output
to the client in order to avoid crashing it.
To change this limit, set the config variable
`--ServerApp.iopub_msg_rate_limit`.

Current values:
ServerApp.iopub_msg_rate_limit=1000.0 (msgs/sec)
ServerApp.rate_limit_window=3.0 (secs)
Contents