From 44fe16997fba871feb16f0828d4b5e44d723bf7a Mon Sep 17 00:00:00 2001
From: Puxue Qiao <pqiao@svi.edu.au>
Date: Tue, 1 Oct 2019 19:08:25 +1000
Subject: [PATCH] add references and minor adjustments
---
course_files/book.bib | 134 +++++++++++++++++++++++++++++++++
course_files/clust-intro.Rmd | 32 +++++---
course_files/clustering.Rmd | 32 ++++----
course_files/latent-spaces.Rmd | 16 ++--
4 files changed, 179 insertions(+), 35 deletions(-)
diff --git a/course_files/book.bib b/course_files/book.bib
index 0af2137..5244f1a 100644
--- a/course_files/book.bib
+++ b/course_files/book.bib
@@ -1127,3 +1127,137 @@ doi = {10.18637/jss.v059.i10}
language = "en",
doi = "10.1101/574574"
}
+
+
+@article{xu2015identification,
+ title={Identification of cell types from single-cell transcriptomes using a novel clustering method},
+ author={Xu, Chen and Su, Zhengchang},
+ journal={Bioinformatics},
+ volume={31},
+ number={12},
+ pages={1974--1980},
+ year={2015},
+ publisher={Oxford University Press}
+}
+
+
+@article{newman2004finding,
+ title={Finding and evaluating community structure in networks},
+ author={Newman, Mark EJ and Girvan, Michelle},
+ journal={Physical review E},
+ volume={69},
+ number={2},
+ pages={026113},
+ year={2004},
+ publisher={APS}
+}
+
+@article{blondel2008fast,
+ title={Fast unfolding of communities in large networks},
+ author={Blondel, Vincent D and Guillaume, Jean-Loup and Lambiotte, Renaud and Lefebvre, Etienne},
+ journal={Journal of statistical mechanics: theory and experiment},
+ volume={2008},
+ number={10},
+ pages={P10008},
+ year={2008},
+ publisher={IOP Publishing}
+}
+
+@article{traag2019louvain,
+ title={From Louvain to Leiden: guaranteeing well-connected communities},
+ author={Traag, Vincent A and Waltman, Ludo and van Eck, Nees Jan},
+ journal={Scientific reports},
+ volume={9},
+ year={2019},
+ publisher={Nature Publishing Group}
+}
+
+@article{good2010performance,
+ title={Performance of modularity maximization in practical contexts},
+ author={Good, Benjamin H and De Montjoye, Yves-Alexandre and Clauset, Aaron},
+ journal={Physical Review E},
+ volume={81},
+ number={4},
+ pages={046106},
+ year={2010},
+ publisher={APS}
+}
+
+@article{freytag2018comparison,
+ title={Comparison of clustering tools in R for medium-sized 10x Genomics single-cell RNA-sequencing data},
+ author={Freytag, Saskia and Tian, Luyi and L{\"o}nnstedt, Ingrid and Ng, Milica and Bahlo, Melanie},
+ journal={F1000Research},
+ volume={7},
+ year={2018},
+ publisher={Faculty of 1000 Ltd}
+}
+
+@inproceedings{collins2002generalization,
+ title={A generalization of principal components analysis to the exponential family},
+ author={Collins, Michael and Dasgupta, Sanjoy and Schapire, Robert E},
+ booktitle={Advances in neural information processing systems},
+ pages={617--624},
+ year={2002}
+}
+
+@inproceedings{hinton2003stochastic,
+ title={Stochastic neighbor embedding},
+ author={Hinton, Geoffrey E and Roweis, Sam T},
+ booktitle={Advances in neural information processing systems},
+ pages={857--864},
+ year={2003}
+}
+
+@article{maaten2008visualizing,
+ title={Visualizing data using t-SNE},
+ author={Maaten, Laurens van der and Hinton, Geoffrey},
+ journal={Journal of machine learning research},
+ volume={9},
+ number={Nov},
+ pages={2579--2605},
+ year={2008}
+}
+
+@article{moon2017phate,
+ title={PHATE: a dimensionality reduction method for visualizing trajectory structures in high-dimensional biological data},
+ author={Moon, Kevin R and van Dijk, David and Wang, Zheng and Chen, William and Hirn, Matthew J and Coifman, Ronald R and Ivanova, Natalia B and Wolf, Guy and Krishnaswamy, Smita},
+ journal={bioRxiv},
+ pages={120378},
+ year={2017},
+ publisher={Cold Spring Harbor Laboratory}
+}
+
+@article{buettner2017f,
+ title={f-scLVM: scalable and versatile factor analysis for single-cell RNA-seq},
+ author={Buettner, Florian and Pratanwanich, Naruemon and McCarthy, Davis J and Marioni, John C and Stegle, Oliver},
+ journal={Genome biology},
+ volume={18},
+ number={1},
+ pages={212},
+ year={2017},
+ publisher={BioMed Central}
+}
+
+@article{kingma2013auto,
+ title={Auto-encoding variational bayes},
+ author={Kingma, Diederik P and Welling, Max},
+ journal={arXiv preprint arXiv:1312.6114},
+ year={2013}
+}
+
+
+@article{mcinnes2018umap,
+ title={Umap: Uniform manifold approximation and projection for dimension reduction},
+ author={McInnes, Leland and Healy, John and Melville, James},
+ journal={arXiv preprint arXiv:1802.03426},
+ year={2018}
+}
+
+@article{townes2019feature,
+ title={Feature Selection and Dimension Reduction for Single Cell RNA-Seq based on a Multinomial Model},
+ author={Townes, F William and Hicks, Stephanie C and Aryee, Martin J and Irizarry, Rafael A},
+ journal={bioRxiv},
+ pages={574574},
+ year={2019},
+ publisher={Cold Spring Harbor Laboratory}
+}
\ No newline at end of file
diff --git a/course_files/clust-intro.Rmd b/course_files/clust-intro.Rmd
index 47b126b..f91ed43 100644
--- a/course_files/clust-intro.Rmd
+++ b/course_files/clust-intro.Rmd
@@ -108,7 +108,7 @@ to scRNA-seq data by building a graph where each vertice represents a cell
and (weight of) the edge measures similarity between two cells.
Actually, graph-based clustering is the most popular clustering algorithm in
scRNA-seq data analysis, and has been reported to have outperformed other
-clustering methods in many situations (ref).
+clustering methods in many situations [@freytag2018comparison].
##### Why do we want to represent the data as a graph?\
@@ -123,12 +123,12 @@ clustering methods in many situations (ref).
- __Step2__: Add weights, and obtain a shared nearest neighbour (__SNN__) graph
-<center>{width= 4%}</center>
+<center>{width=40%}</center>
There are two ways of adding weights: number and rank.\
- _number_: The number of shared nodes between $u$ and $v$, in this case, 3. \
-- _rank_: A measurement of the closeness to their common nearest neighbours. (ref) \
+- _rank_: A measurement of the closeness to their common nearest neighbours. (@xu2015identification) \
<font color="#bf812d">
@@ -145,28 +145,37 @@ $$ w(u, v) = K - s(u, v).$$
##### Quality function (Modularity)\
-Modularity is not the only quality function for graph-based clustering,
+Modularity [@newman2004finding] is not the only quality function for graph-based clustering,
but it is one of the first attempts to embed in a compact form many questions including
-<font color="red"> ... </font>.\
+the definition of quality function and null model etc.\
__The idea of modularity__: A random graph should not have a cluster structure. \
The more "quality" a partition has compared to a random graph, the "better" the partition is.\
Specifically, it is defined by:
the <font color="#bf812d"> quality </font> of a partition on the actual graph $-$ the quality of the same partition on a <font color="#bf812d"> random graph </font>
-
+
<font color="#bf812d"> quality </font>: Sum of the weights within clusters \
<font color="#bf812d"> random graph </font>: a copy of the original graph, with some of its properties, but without community structure. The random graph defined by modularity is: each node has the same degree as the original graph.
- $$ Q \propto \sum_{i, j} A_{i, j} \delta(i, j) - \sum_{i, j} \dfrac{k_i k_j}{2m} \delta(i, j)$$
-<font color="red"> [notations] </font>
+ $$ Q \propto \sum_{i, j} A_{i, j} \delta(i, j) - \sum_{i, j} \dfrac{k_i k_j}{2m} \delta(i, j)$$
+
+- $A_{i, j}$: weight between node $i$ and $j$;
+
+- $\delta(i, j)$: indicator of whether $i$ and $j$ are in the same cluster;
+
+- $k_i$: the degree of node $i$ (the sum of weights of all edges connected to $i$);
+
+- $m$: the total weight in the all graph.
+
+
__Higher modularity implies better partition__:
<center>{width=80%}</center>
-__Limits of modularity__: \
+__Limits of modularity__: [@good2010performance]\
1. Resolution limit. \
Short version: Modularity maximization forces small communities into larger ones. \
Longer version: For two clusters $A$ and $B$, if $k_A k_B < 2m$ then modularity increases by merging A and B into a single cluster, even if A and B are distinct clusters.\
@@ -182,12 +191,13 @@ __Limits of modularity__: \
Modularity-based clustering methods implemented in single cell analysis are mostly greedy algorithms,
that are very fast, although not the most accurate approaches.
- __Louvain__:
+ __Louvain__: [@blondel2008fast]
<center>{width=80%}</center>
- __Leiden__: Improved Louvain, hybrid of greedy algorithm and sampling technique \
+ __Leiden__:[@traag2019louvain] \
+ Improved Louvain, hybrid of greedy algorithm and sampling technique \
##### __Advantages__: \
-Fast \
diff --git a/course_files/clustering.Rmd b/course_files/clustering.Rmd
index 48d434c..89cc2a7 100644
--- a/course_files/clustering.Rmd
+++ b/course_files/clustering.Rmd
@@ -59,14 +59,14 @@ Perform Louvain clustering:
```{r clustering}
cl <- igraph::cluster_louvain(deng15)$membership
colData(deng)$cl <- factor(cl)
-mclust::adjustedRandIndex(colData(deng)$cell_type1, colData(deng)$cl)
+mclust::adjustedRandIndex(colData(deng)$cell_type2, colData(deng)$cl)
```
Reaches very high similarity with the labels provided in the original paper.
However, it tend to merge small clusters into larger ones.
```{r}
-table(deng$cell_type1, cl)
+table(deng$cell_type2, cl)
```
@@ -94,19 +94,15 @@ table(muraro$cell_type1, cl)
Let's run `SC3` clustering on the Deng data. The advantage of the `SC3` is that it can directly ingest a `SingleCellExperiment` object.
-Now let's image we do not know the number of clusters _k_ (cell types). `SC3` can estimate a number of clusters for you:
-```{r, eval= F}
+`SC3` can estimate a number of clusters:
+```{r}
deng <- sc3_estimate_k(deng)
metadata(deng)$sc3$k_estimation
```
-Interestingly, the number of cell types predicted by `SC3` is smaller than in the original data annotation. However, early, mid and late stages of different cell types together, we will have exactly 6 cell types. We store the merged cell types in `cell_type1` column of the `colData` slot:
-```{r, eval= F}
-plotPCA(deng, colour_by = "cell_type1")
-```
-Now we are ready to run `SC3` (we also ask it to calculate biological properties of the clusters):
-```{r, eval= F}
+Next we run `SC3` (we also ask it to calculate biological properties of the clusters):
+```{r}
deng <- sc3(deng, ks = 10, biology = TRUE, n_cores = 1)
```
@@ -118,27 +114,27 @@ sc3_plot_consensus(deng, k = 10, show_pdata = "cell_type2")
```
Silhouette plot:
-```{r, fig.height=9, eval= F}
+```{r, fig.height=9}
sc3_plot_silhouette(deng, k = 10)
```
Heatmap of the expression matrix:
-```{r, fig.height=6, eval= F}
+```{r, fig.height=6}
sc3_plot_expression(deng, k = 10, show_pdata = "cell_type2")
```
Identified marker genes:
-```{r, fig.height=11, eval= F}
+```{r, fig.height=11}
sc3_plot_markers(deng, k = 10, show_pdata = "cell_type2")
```
PCA plot with highlighted `SC3` clusters:
-```{r, eval= F}
+```{r}
plotPCA(deng, colour_by = "sc3_10_clusters")
```
Compare the results of `SC3` clustering with the original publication cell type labels:
-```{r, eval= F}
+```{r}
adjustedRandIndex(colData(deng)$cell_type2, colData(deng)$sc3_10_clusters)
```
@@ -176,7 +172,9 @@ __Note__ Due to direct calculation of distances `SC3` becomes very slow when the
<center> {width=80%} </center>
- __Step4. Fine tuning__\
We stop here and assign each cell with label that score the highest, actually, if we set the argument ```fine.tune = FALSE```, that is exactly what the package function ```SingleR``` does.
- But there is one more question, what if the second highest score is very close to the highest?
+ But there is one more question, what if the second highest score is very close to the highest? say, 1, 1, 1, 9.5, 10.
+ `SingleR` set a threshold to define how close is "very close", the default is 0.05.
+ For (only) the cells that falls into this category, it goes back to Step2.
#### Example
@@ -314,4 +312,4 @@ plot(
sessionInfo()
```
-Among the 2126 cells in the data, only 89 are annotated as different labels as the
+
diff --git a/course_files/latent-spaces.Rmd b/course_files/latent-spaces.Rmd
index ec109be..922221b 100644
--- a/course_files/latent-spaces.Rmd
+++ b/course_files/latent-spaces.Rmd
@@ -107,7 +107,9 @@ plotPCA(deng, colour_by = "cell_type2") +
non-linear dependencies. For instance, PCA would not be able to “unroll†the
following structure.\ <center> {width=30%} </center>
-#### GLM-PCA
+#### [GLM-PCA](https://rdrr.io/cran/glmpca/)
+[@collins2002generalization]
+[@townes2019feature]
GLM-PCA is a generalized version of the traditional PCA.
@@ -217,8 +219,7 @@ ggplot(pd, aes(x=dim1, y=dim2, shape=clust, colour=batch)) +
### tSNE: t-Distributed Stochastic Neighbor Embedding
-t-SNE is an advanced version of the original SNE algorithm. <font color="red">
-[ref] </font>
+t-SNE [@maaten2008visualizing] is an advanced version of the original SNE algorithm. [@hinton2003stochastic]
#### Motivation
@@ -321,7 +322,7 @@ Therefore can merely be used for visualization.\
### Manifold methods
-#### UMAP: Uniform Manifold Approximation and Projection
+#### UMAP: Uniform Manifold Approximation and Projection [@mcinnes2018umap]
##### __Advantages of UMAP over t-SNE:__
@@ -368,7 +369,7 @@ plotUMAP(muraro, colour_by="cell_type1")
-#### PHATE
+#### PHATE [@moon2017phate]
##### Sketch of algorithm
@@ -450,7 +451,7 @@ The __factor loadings__ or weights indicate how much each latent factor is affec
### [Slalom](https://bioconductor.org/packages/release/bioc/html/slalom.html): Interpretable latent spaces
-Highlight of Slalom:
+Highlight of Slalom: [@buettner2017f]
- It incorporates prior information to help the model estimation;
@@ -524,7 +525,8 @@ The `plotTerms` function shows the relevance of all terms in the model, enabling
plotTerms(model_deng)
```
-## Autoencoders
+## Autoencoders
+[@kingma2013auto]
<center>{width=80%}</center>
--
GitLab