sccross.models¶

scCross is a dDeep Learning-Based Model for integration, cross-dataset cross-modality generation and matched muti-omics simulation of single-cell multi-omics data. Our model can also maintain in-silico perturbations in cross-modality generation and can use in-silico perturbations to find key genes. Part of the sccross’ code is adapted from MIT licensed projects GLUE and SCDIFF2. Thanks for these projects:

Author: Zhi-Jie Cao Project: GLUE Ref: Cao Z J, Gao G. Multi-omics single-cell data integration and regulatory inference with graph-linked embedding[J]. Nature Biotechnology, 2022, 40(10): 1458-1466.

Author: Jun Ding Project: SCDIFF2 Ref: Ding, J., Aronow, B. J., Kaminski, N., Kitzmiller, J., Whitsett, J. A., & Bar-Joseph, Z. (2018). Reconstructing differentiation networks and their regulation from time series single-cell expression data. Genome research, 28(3), 383-395.

Functions

fit_SCCROSS

rtype

SCCROSSModel

load_model

Load model from file

Submodules

sccross.models.data

Data handling utilities

sccross.models.layers

sccross.models.sccross

sccross.models.utils

Probability distributions