Dataset Information

DevCellPy: A machine learning-enabled pipeline for automated annotation of complex multilayered single-cell transcriptomic data

ABSTRACT: A major informatic challenge in single cell RNA-sequencing analysis is the precise annotation of datasets where cells exhibit complex multilayered identities or transitory states. Here, we present devCellPy a highly accurate and precise machine learning-enabled tool that enables automated prediction of cell types across complex annotation hierarchies. To demonstrate the power of devCellPy, we construct a murine cardiac developmental atlas from published datasets encompassing 104,199 cells from E6.5-E16.5 and train devCellPy to generate a cardiac prediction algorithm. Using this algorithm, we observe a high prediction accuracy (>90%) across multiple layers of annotation and across de novo murine developmental data. Furthermore, we conduct a cross-species prediction of cardiomyocyte subtypes from in vitro-derived human induced pluripotent stem cells and unexpectedly uncover a predominance of left ventricular (LV) identity that we confirmed by an LV-specific TBX5 lineage tracing system. Together, our results show devCellPy to be a powerful tool for automated cell prediction across complex cellular hierarchies, species, and experimental systems.

ORGANISM(S): Mus musculus Homo sapiens

PROVIDER: GSE184943 | GEO | 2022/08/14

REPOSITORIES: GEO

ACCESS DATA

Dataset's files

Source:

			Action	DRS
		Other

Items per page:

1 - 1 of 1

Similar Datasets

Project description:Background: Right ventricular (RV) and left ventricular (LV) myocardium differ in their response to pressure-overload hypertrophy (POH). In this report we use microarray and proteomic analyses to identify pathways modulated by LV-, and RV-POH in the immature heart. Methods: Newborn New Zealand White rabbits underwent banding of the descending thoracic aorta (LV-POH; n=6). RV-POH was achieved by banding the pulmonary artery (n=6). Sham–control animals (SC; n=6 each) were sham-manipulated. Following 4 (LV-POH) and 6 weeks (RV-POH) recovery, the hearts were removed and matched sample RNA and proteins were isolated for microarray and proteomic analysis. Results: There was no difference in body weight in RV-, LV-POH vs. SC but there was a significant increase vs. SC in RV (3.2±0.8g vs. 1.2±0.3g; P<0.01) and LV weight (7.08±0.6g vs. 4.02±0.2g; P<0.01). Fractional area change (RV-POH) and shortening fraction (LV-POH) decreased significantly (23±6 vs. 47±6 and 21±4 vs.44±2, respectively, P<0.01). Microarray analysis demonstrated that LV-POH enriched pathways for oxidative phosphorylation, mitochondria energy pathways, actin, ILK, hypoxia, calcium and protein kinase-A signalling. RV-POH enriched pathways for cardiac oxidative phosphorylation. Proteomic analysis revealed 19 proteins were uniquely expressed in LV-POH vs. SC. Functional annotation clustering analysis indicated significant enrichment for the mitochondrion, cellular macromolecular complex assembly and oxidative phosphorylation. RV-POH had 15 uniquely expressed proteins vs. SC. Functional annotation clustering analysis indicated significant enrichment in structural constituents of muscle, cardiac muscle tissue development and calcium handling. Conclusion: Our results identify unique transcript and protein expression profiles in LV, RV-POH and provide new insight into the biological basis of ventricular specific hypertrophy. 3 different conditions: PAB-RV vs. Sham-control RV, PAB-RV [test] vs. PAB-LV [control], AOB-LV vs. Sham-control LV.

Dataset Information

DevCellPy: A machine learning-enabled pipeline for automated annotation of complex multilayered single-cell transcriptomic data

Dataset's files

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets