# Dimensionality reduction for visualisation

Reduction of high-dimensional datasets to 2D for visualization & interpretation

4 datasets · 23 methods · 3 control methods · 10 metrics

Task info Method info Metric info Dataset info Results

Dimensionality reduction is one of the key challenges in single-cell data representation. Routine single-cell RNA sequencing (scRNA-seq) experiments measure cells in roughly 20,000-30,000 dimensions (i.e., features - mostly gene transcripts but also other functional elements encoded in mRNA such as lncRNAs). Since its inception, scRNA-seq experiments have been growing in terms of the number of cells measured. Originally, cutting-edge SmartSeq experiments would yield a few hundred cells, at best. Now, it is not uncommon to see experiments that yield over 100,000 cells or even > 1 million cells.

Each *feature* in a dataset functions as a single dimension. While each of the ~30,000 dimensions measured in each cell contribute to an underlying data structure, the overall structure of the data is challenging to display in few dimensions due to data sparsity and the *“curse of dimensionality”* (distances in high dimensional data don’t distinguish data points well). Thus, we need to find a way to dimensionally reduce the data for visualization and interpretation.

## Summary

## Display settings

## Filter datasets

## Filter methods

## Filter metrics

## Results

Results table of the scores per method, dataset and metric (after scaling). Use the filters to make a custom subselection of methods and datasets. The “Overall mean” dataset is the mean value across all datasets.

## Dataset info

## Show

### Mouse hematopoietic stem cell differentiation

1.6k hematopoietic stem and progenitor cells from mouse bone marrow. Sequenced by Smart-seq2. 1920 cells x 43258 features with 3 cell type labels (Nestorowa et al. 2016).

### Mouse myeloid lineage differentiation

Myeloid lineage differentiation from mouse blood. Sequenced by SMARTseq in 2016 by Olsson et al. 660 cells x 112815 features with 4 cell type labels (Olsson et al. 2016).

### 5k Peripheral blood mononuclear cells

5k Peripheral Blood Mononuclear Cells (PBMCs) from a healthy donor. Sequenced on 10X v3 chemistry in July 2019 by 10X Genomics. 5247 cells x 20822 features with no cell type labels (10x Genomics 2019).

### Zebrafish

90k cells from zebrafish embryos throughout the first day of development, with and without a knockout of chordin, an important developmental gene. Dimensions: 26022 cells, 25258 genes. 24 cell types (avg. 1084±1156 cells per cell type) (Wagner et al. 2018).

## Method info

## Show

### densMAP (logCP10k)

densMAP is a modification of UMAP that adds an extra cost term in order to preserve information about the relative local density of the data. It is performed on the same inputs as UMAP (Narayan, Berger, and Cho 2021). Links: Docs.

### densMAP (logCP10k, 1kHVG)

densMAP is a modification of UMAP that adds an extra cost term in order to preserve information about the relative local density of the data. It is performed on the same inputs as UMAP (Narayan, Berger, and Cho 2021). Links: Docs.

### densMAP PCA (logCP10k)

densMAP is a modification of UMAP that adds an extra cost term in order to preserve information about the relative local density of the data. It is performed on the same inputs as UMAP (Narayan, Berger, and Cho 2021). Links: Docs.

### densMAP PCA (logCP10k, 1kHVG)

### Diffusion maps

Diffusion maps uses an affinity matrix to describe the similarity between data points, which is then transformed into a graph Laplacian. The eigenvalue-weighted eigenvectors of the graph Laplacian are then used to create the embedding. Diffusion maps is calculated on the logCPM expression matrix (Coifman and Lafon 2006). Links: Docs.

### NeuralEE (CPU) (Default)

NeuralEE is a neural network implementation of elastic embedding. It is a non-linear method that preserves pairwise distances between data points. NeuralEE uses a neural network to optimize an objective function that measures the difference between pairwise distances in the original high-dimensional space and the two-dimensional space. It is computed on both the recommended input from the package authors of 500 HVGs selected from a logged expression matrix (without sequencing depth scaling) and the default logCPM matrix with 1000 HVGs (Xiong et al. 2020). Links: Docs.

### NeuralEE (CPU) (logCP10k, 1kHVG)

NeuralEE is a neural network implementation of elastic embedding. It is a non-linear method that preserves pairwise distances between data points. NeuralEE uses a neural network to optimize an objective function that measures the difference between pairwise distances in the original high-dimensional space and the two-dimensional space. It is computed on both the recommended input from the package authors of 500 HVGs selected from a logged expression matrix (without sequencing depth scaling) and the default logCPM matrix with 1000 HVGs (Xiong et al. 2020). Links: Docs.

### PCA (logCP10k)

PCA or “Principal Component Analysis” is a linear method that finds orthogonal directions in the data that capture the most variance. The first two principal components are chosen as the two-dimensional embedding. We select only the first two principal components as the two-dimensional embedding. PCA is calculated on the logCPM expression matrix with and without selecting 1000 HVGs (Pearson 1901). Links: Docs.

### PCA (logCP10k, 1kHVG)

PCA or “Principal Component Analysis” is a linear method that finds orthogonal directions in the data that capture the most variance. The first two principal components are chosen as the two-dimensional embedding. We select only the first two principal components as the two-dimensional embedding. PCA is calculated on the logCPM expression matrix with and without selecting 1000 HVGs (Pearson 1901). Links: Docs.

### PHATE (default)

PHATE or “Potential of Heat - diffusion for Affinity - based Transition Embedding” uses the potential of heat diffusion to preserve trajectories in a dataset via a diffusion process. It is an affinity - based method that creates an embedding by finding the dominant eigenvalues of a Markov transition matrix. We evaluate several variants including using the recommended square - root transformed CPM matrix as input, this input with the gamma parameter set to zero and the normal logCPM transformed matrix with and without HVG selection (Moon et al. 2019). Links: Docs.

### PHATE (logCP10k, 1kHVG)

PHATE or “Potential of Heat - diffusion for Affinity - based Transition Embedding” uses the potential of heat diffusion to preserve trajectories in a dataset via a diffusion process. It is an affinity - based method that creates an embedding by finding the dominant eigenvalues of a Markov transition matrix. We evaluate several variants including using the recommended square - root transformed CPM matrix as input, this input with the gamma parameter set to zero and the normal logCPM transformed matrix with and without HVG selection (Moon et al. 2019). Links: Docs.

### PHATE (logCP10k)

PHATE or “Potential of Heat - diffusion for Affinity - based Transition Embedding” uses the potential of heat diffusion to preserve trajectories in a dataset via a diffusion process. It is an affinity - based method that creates an embedding by finding the dominant eigenvalues of a Markov transition matrix. We evaluate several variants including using the recommended square - root transformed CPM matrix as input, this input with the gamma parameter set to zero and the normal logCPM transformed matrix with and without HVG selection (Moon et al. 2019). Links: Docs.

### PHATE (gamma=0)

### PyMDE Preserve Distances (logCP10k)

PyMDE is a Python implementation of minimum-distortion embedding. It is a non-linear method that preserves distances between cells or neighborhoods in the high-dimensional space. It is computed with options to preserve distances between cells or neighbourhoods and with the logCPM matrix with and without HVG selection as input (Agrawal, Ali, and Boyd 2021). Links: Docs.

### PyMDE Preserve Distances (logCP10k, 1kHVG)

PyMDE is a Python implementation of minimum-distortion embedding. It is a non-linear method that preserves distances between cells or neighborhoods in the high-dimensional space. It is computed with options to preserve distances between cells or neighbourhoods and with the logCPM matrix with and without HVG selection as input (Agrawal, Ali, and Boyd 2021). Links: Docs.

### PyMDE Preserve Neighbors (logCP10k)

PyMDE is a Python implementation of minimum-distortion embedding. It is a non-linear method that preserves distances between cells or neighborhoods in the high-dimensional space. It is computed with options to preserve distances between cells or neighbourhoods and with the logCPM matrix with and without HVG selection as input (Agrawal, Ali, and Boyd 2021). Links: Docs.

### PyMDE Preserve Neighbors (logCP10k, 1kHVG)

### t-SNE (logCP10k)

t-SNE or t-distributed Stochastic Neighbor Embedding converts similarities between data points to joint probabilities and tries to minimize the Kullback-Leibler divergence between the joint probabilities of the low-dimensional embedding and the high-dimensional data. We use the implementation in the scanpy package with the result of PCA on the logCPM expression matrix (with and without HVG selection) (van der Maaten and Hinton 2008). Links: Docs.

### t-SNE (logCP10k, 1kHVG)

t-SNE or t-distributed Stochastic Neighbor Embedding converts similarities between data points to joint probabilities and tries to minimize the Kullback-Leibler divergence between the joint probabilities of the low-dimensional embedding and the high-dimensional data. We use the implementation in the scanpy package with the result of PCA on the logCPM expression matrix (with and without HVG selection) (van der Maaten and Hinton 2008). Links: Docs.

### UMAP (logCP10k)

UMAP or Uniform Manifold Approximation and Projection is an algorithm for dimension reduction based on manifold learning techniques and ideas from topological data analysis. We perform UMAP on the logCPM expression matrix before and after HVG selection and with and without PCA as a pre-processing step (McInnes, Healy, and Melville 2018). Links: Docs.

### UMAP (logCP10k, 1kHVG)

UMAP or Uniform Manifold Approximation and Projection is an algorithm for dimension reduction based on manifold learning techniques and ideas from topological data analysis. We perform UMAP on the logCPM expression matrix before and after HVG selection and with and without PCA as a pre-processing step (McInnes, Healy, and Melville 2018). Links: Docs.

### UMAP PCA (logCP10k)

UMAP or Uniform Manifold Approximation and Projection is an algorithm for dimension reduction based on manifold learning techniques and ideas from topological data analysis. We perform UMAP on the logCPM expression matrix before and after HVG selection and with and without PCA as a pre-processing step (McInnes, Healy, and Melville 2018). Links: Docs.

### UMAP PCA (logCP10k, 1kHVG)

## Control method info

## Show

### Random Features

Randomly generated two-dimensional coordinates from a normal distribution

### Spectral Features

Use 1000-dimensional diffusions maps as an embedding

### True Features

Use of the original feature inputs as the ‘embedding’

## Metric info

## Show

### continuity

Continuity measures error of hard extrusions based on nearest neighbor coranking (Zhang, Shang, and Zhang 2021).

### Density preservation

Similarity between local densities in the high-dimensional data and the reduced data (Narayan, Berger, and Cho 2021).

### Distance correlation

Spearman correlation between all pairwise Euclidean distances in the original and dimension-reduced data (Schober, Boer, and Schwarte 2018).

### Distance correlation (spectral)

Spearman correlation between all pairwise diffusion distances in the original and dimension-reduced data (Coifman and Lafon 2006).

### local continuity meta criterion

The local continuity meta criterion is the co-KNN size with baseline removal which favors locality (Zhang, Shang, and Zhang 2021).

### global property

The global property metric is a summary of the global co-KNN (Zhang, Shang, and Zhang 2021).

### local property

The local property metric is a summary of the local co-KNN (Zhang, Shang, and Zhang 2021).

### co-KNN size

co-KNN size counts how many points are in both k-nearest neighbors before and after the dimensionality reduction (Zhang, Shang, and Zhang 2021).

### co-KNN AUC

co-KNN AUC is area under the co-KNN curve (Zhang, Shang, and Zhang 2021).

### trustworthiness

a measurement of similarity between the rank of each point’s nearest neighbors in the high-dimensional data and the reduced data (Venna and Kaski 2001).

## Quality control results

## Show

Category | Name | Value | Condition | Severity |
---|---|---|---|---|

Raw results | Dataset 'zebrafish_labs' %missing | 0.60 | pct_missing <= .1 | ✗✗✗ |

Raw results | Metric 'continuity' %missing | 0.25 | pct_missing <= .1 | ✗✗ |

Raw results | Metric 'lcmc' %missing | 0.25 | pct_missing <= .1 | ✗✗ |

Raw results | Metric 'qglobal' %missing | 0.25 | pct_missing <= .1 | ✗✗ |

Raw results | Metric 'qlocal' %missing | 0.25 | pct_missing <= .1 | ✗✗ |

Raw results | Metric 'qnn' %missing | 0.25 | pct_missing <= .1 | ✗✗ |

Raw results | Metric 'qnn_auc' %missing | 0.25 | pct_missing <= .1 | ✗✗ |

Raw results | Method 'densmap_logCP10k' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'densmap_logCP10k_1kHVG' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'densmap_pca_logCP10k' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'densmap_pca_logCP10k_1kHVG' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'diffusion_map' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'neuralee_default' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'neuralee_logCP10k_1kHVG' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'pca_logCP10k' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'pca_logCP10k_1kHVG' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'phate_default' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'phate_logCP10k' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'phate_logCP10k_1kHVG' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'phate_sqrt' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'pymde_distances_log_cp10k' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'pymde_distances_log_cp10k_hvg' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'pymde_neighbors_log_cp10k' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'pymde_neighbors_log_cp10k_hvg' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'random_features' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'spectral_features' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'true_features' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'tsne_logCP10k' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'tsne_logCP10k_1kHVG' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'umap_logCP10k' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'umap_logCP10k_1kHVG' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'umap_pca_logCP10k' %missing | 0.15 | pct_missing <= .1 | ✗ |

Raw results | Method 'umap_pca_logCP10k_1kHVG' %missing | 0.15 | pct_missing <= .1 | ✗ |

## Normalisation visualisation

## Show

`Warning: Removed 1 row containing missing values (`geom_path()`).`

`Warning: Removed 156 rows containing missing values (`geom_point()`).`

## References

*Foundations and Trends in Machine Learning*14 (3): 211–378. https://doi.org/10.1561/2200000090.

*Applied and Computational Harmonic Analysis*21 (1): 5–30. https://doi.org/10.1016/j.acha.2006.04.006.

*arXiv*. https://doi.org/10.48550/arxiv.1802.03426.

*Nature Biotechnology*37 (12): 1482–92. https://doi.org/10.1038/s41587-019-0336-3.

*Nature Biotechnology*39 (6): 765–74. https://doi.org/10.1038/s41587-020-00801-7.

*Blood*128 (8): e20–31. https://doi.org/10.1182/blood-2016-05-716480.

*Nature*537 (7622): 698–702. https://doi.org/10.1038/nature19348.

*The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science*2 (11): 559–72. https://doi.org/10.1080/14786440109462720.

*Anesthesia & Analgesia*126 (5): 1763–68. https://doi.org/10.1213/ane.0000000000002864.

*Journal of Machine Learning Research*9 (86): 2579–2605. http://jmlr.org/papers/v9/vandermaaten08a.html.

*Artificial Neural Networks ICANN 2001*, 485–91. Springer Berlin Heidelberg. https://doi.org/{10.1007/3-540-44668-0\_68}.

*Science*360 (6392): 981–87. https://doi.org/10.1126/science.aar4362.

*Frontiers in Genetics*11. https://doi.org/10.3389/fgene.2020.00786.

*Heliyon*7 (2): e06199. https://doi.org/10.1016/j.heliyon.2021.e06199.