neuralee 0.1.2

Scalable Visualization of Massive Single-Cell DataUsing Neural Networks

This is an applicable version for NeuralEE.

1. The datasets loading and preprocessing module is modified from scVI.

2. Define NeuralEE class and some auxiliary function, mainly for cuda computation, except like entropic affinity calculation which is quite faster computed on cpu.

3. General elastic embedding algorithm on cuda is given based on matlab code from Max Vladymyrov.

4. Add some demos of notebook helping to reproduce.

Usage

1. Install Python 3.7.

2. Install PyTorch. If you have an NVIDIA GPU, be sure to install a version of PyTorch that supports it. NeuralEE runs much faster with a discrete GPU.

3. Install NeuralEE through pip or from GitHub:

pip install neuralee

git clone git://github.com/HiBearME/NeuralEE.git
cd NeuralEE
python setup.py install --user

4. How to use NeuralEE.

from neuralee.dataset import CortexDataset
from neuralee.embedding import NeuralEE

import torch
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# preprocess dataset
cortex_dataset = CortexDataset(save_path='../data/')
cortex_dataset.log_shift()
cortex_dataset.subsample_genes(558)
cortex_dataset.standardscale()

cortex_dataset.affinity()
NEE = NeuralEE(cortex_dataset, device=device)

results = NEE.EE()  # Elastic embedding results.
results_Neural = NEE.fine_tune()  # NeuralEE results.

# with 'mini-batch' trick
cortex_dataset.affinity_split(N_small=0.25)
NEE = NeuralEE(cortex_dataset, device=device)
results_Neural_with4batches = NEE.fine_tune()

5. Reproduction. Reference from notebook files.

Examples

1. HEMATO

2. BRAIN LARGE