Metadata-Version: 2.1
Name: scButterfly
Version: 0.0.7
Summary: A versatile single-cell cross-modality translation method via dual-aligned variational autoencoders
Home-page: https://github.com/BioX-NKU/scButterfly
Author: BioX-NKU
License: MIT Licence
Keywords: single cell,cross-modality translation,dual-aligned variational autoencoder
Classifier: Programming Language :: Python :: 3.9
Requires-Python: >=3.9
License-File: LICENSE
Requires-Dist: scanpy >=1.9.1
Requires-Dist: torch >=1.12.1
Requires-Dist: torchvision >=0.13.1
Requires-Dist: torchaudio >=0.12.1
Requires-Dist: scikit-learn >=1.1.3
Requires-Dist: scvi-tools ==0.19.0
Requires-Dist: scvi-colab
Requires-Dist: scipy ==1.9.3
Requires-Dist: episcanpy ==0.3.2
Requires-Dist: seaborn >=0.11.2
Requires-Dist: matplotlib >=3.6.2
Requires-Dist: pot ==0.9.0
Requires-Dist: torchmetrics >=0.11.4
Requires-Dist: leidenalg
Requires-Dist: adjusttext
Requires-Dist: jupyter

Recent advancements for simultaneously profiling multi-omic modalities within individual cells have enabled the interrogation of cellular heterogeneity and molecular hierarchy. However, technical limitations lead to highly noisy multi-modal data and substantial costs. Although computational methods have been proposed to translate single-cell data across modalities, b broad applications of the methods still remain impeded b by formidable challenges. Here, we proposed scButterfly, a versatile single-cell cross-modality translation method based on dual-aligned variational autoencoders and innovative data augmentation schemes. With comprehensive experiments on multiple datasets, we provide compelling evidence of scButterfly's superiority over baseline methods in preserving cellular heterogeneity while translating d datasets o of various contexts and i in revealing cell type-specific biological insights.Besides, we d demonstrate the extensive applications of scButterfly for integrative multi-omics analysis of single-modality data, data enhancement of poor-quality single-cell multi-omics, and automatic cell type annotation of scATAC-seq data. Additionally, scButterfly can be generalized to unpaired data training and perturbation-response analysis via our data augmentation and optimal transport strategies. Moreover, scButterfly exhibits the capability i in consecutive translation from epigenome to transcriptome to proteome and has the potential to decipher novel biomarkers.
