Consensus label propagation with graph convolutional networks for single-cell RNA sequencing cell type annotation.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) data, annotated by cell type, is useful in a variety of downstream biological applications, such as profiling gene expression at the single-cell level. However, manually assigning these annotations with known marker genes is both time-consuming and subjective. RESULTS: We present a Graph Convolutional Network (GCN)-based approach to automate the annotation process. Our process builds upon existing labeling approaches, using state-of-the-art tools to find cells with highly confident label assignments through consensus and spreading these confident labels with a semi-supervised GCN. Using simulated data and two scRNA-seq datasets from different tissues, we show that our method improves accuracy over a simple consensus algorithm and the average of the underlying tools. We also compare our method to a nonparametric neighbor majority approach, showing comparable results. We then demonstrate that our GCN method allows for feature interpretation, identifying important genes for cell type classification. We present our completed pipeline, written in PyTorch, as an end-to-end tool for automating and interpreting the classification of scRNA-seq data. AVAILABILITY AND IMPLEMENTATION: Our code for conducting the experiments in this paper and using our model is available at https://github.com/lewinsohndp/scSHARP.

Graph metric learning quantifies morphological differences between two genotypes of shoot apical meristem cells in Arabidopsis.

We present a method for learning 'spectrally descriptive' edge weights for graphs. We generalize a previously known distance measure on graphs (graph diffusion distance [GDD]), thereby allowing it to be tuned to minimize an arbitrary loss function. Because all steps involved in calculating this modified GDD are differentiable, we demonstrate that it is possible for a small neural network model to learn edge weights which minimize loss. We apply this method to discriminate between graphs constructed from shoot apical meristem images of two genotypes of Arabidopsis thaliana specimens: wild-type and trm678 triple mutants with cell division phenotype. Training edge weights and kernel parameters with contrastive loss produce a learned distance metric with large margins between these graph categories. We demonstrate this by showing improved performance of a simple k -nearest-neighbour classifier on the learned distance matrix. We also demonstrate a further application of this method to biological image analysis. Once trained, we use our model to compute the distance between the biological graphs and a set of graphs output by a cell division simulator. Comparing simulated cell division graphs to biological ones allows us to identify simulation parameter regimes which characterize mutant versus wild-type Arabidopsis cells. We find that trm678 mutant cells are characterized by increased randomness of division planes and decreased ability to avoid previous vertices between cell walls.

An appraisal of whole-room indirect calorimeters and a metabolic cart for measuring resting and active metabolic rates.

Whole-room indirect calorimeters (WRICs) have traditionally been used for real-time resting metabolic rate (RMR) measurements, while metabolic rate (MR) during short-interval exercises has commonly been measured by metabolic carts (MCs). This study aims to investigate the feasibility of incorporating short-interval exercises into WRIC study protocols by comparing the performance of WRICs and an MC. We assessed the 40-min RMR of 15 subjects with 2-day repeats and the 10-15 min activity MR (AMR) of 14 subjects at three intensities, using a large WRIC, a small WRIC, and an MC. We evaluated the biases between the instruments and quantified sources of variation using variance component analysis. All three instruments showed good agreement for both RMR (maximum bias = 0.07 kcal/min) and AMR assessment (maximum bias = 0.53 kcal/min). Moreover, the majority of the variability was between-subject and between-intensity variation, whereas the types of instrument contributed only a small amount to total variation in RMR (2%) and AMR (0.2%) data. In Conclusion, the good reproducibility among the instruments indicates that they may be used interchangeably in well-designed studies. Overall, WRICs can serve as an accurate and versatile means of assessing MR, capable of integrating RMR and short-interval AMR assessments into a single protocol.