@@ -30,6 +30,6 @@ src/*.o

 src/*.dll

 src/*.so

 etc/*

-

 # Celda log files with default prefix

 Celda_chain.*log.txt

+inst/doc

@@ -314,13 +314,13 @@ DecontXoneBatch = function(counts, z=NULL, batch=NULL, max.iter=200, beta=1e-6,

     if ( !is.null(batch) ) {  logMessages("batch: ",  batch, logfile=logfile, append=TRUE, verbose=verbose)    }

     logMessages("----------------------------------------------------------------------", logfile=logfile, append=TRUE, verbose=verbose) 

-    run.params = list("beta"=beta, "delta.init"=delta.init, "iteration"=iter-1L, "seed"=seed)

+    run.params = list("beta.init"=beta, "delta.init"=delta.init, "iteration"=iter-1L, "seed"=seed)

-    res.list = list("logLikelihood" = ll, "est.rmat"=next.decon$est.rmat , "est.conp"= res.conp, "theta"=theta , "delta"=delta)

-    if( decon.method=="clustering" ) {

-        posterior.params = list( "est.GeneDist"=phi,  "est.ConDist"=eta  ) 

-        res.list = append( res.list , posterior.params ) 

-  }

+    res.list = list("logLikelihood" = ll, "est.nativeCounts"=next.decon$est.rmat , "est.conp"= res.conp, "theta"=theta , "delta"=delta)

+    #if( decon.method=="clustering" ) {

+    #    posterior.params = list( "est.GeneDist"=phi,  "est.ConDist"=eta  ) 

+    #    res.list = append( res.list , posterior.params ) 

+    #}

     return(list("run.params"=run.params, "res.list"=res.list, "method"=decon.method  ))

 }

new file mode 100644

@@ -0,0 +1,78 @@

+---

+title: "Estimate and remove cross-contamination from ambient RNA for scRNA-seq data with DecontX"

+author: "Shiyi Yang, Sean Corbett, Yusuke Koga, Zhe Wang, W. Evan Johnson, Masanao Yajima, Joshua D. Campbell"

+date: "`r Sys.Date()`"

+output: rmarkdown::html_vignette

+vignette: >

+  %\VignetteIndexEntry{Estimate and remove cross-contamination from ambient RNA for scRNA-seq data with DecontX}

+  %\VignetteEngine{knitr::rmarkdown}

+  %\VignetteEncoding{UTF-8}

+---

+

+```{r setup, include = FALSE}

+knitr::opts_chunk$set(

+  collapse = TRUE,

+  comment = "#>"

+)

+```

+

+# Introduction 

+DecontX is a Bayesian hierarchical model to estimate and remove cross-contamination from ambient RNA in single-cell RNA-seq count data generated from droplet-based sequencing devices.DecontX will take the count matrix with/without the cell labels and estimate the contamination level and deliver a decontaminted count matrix for downstream analysis. 

+

+In this vignette we will demonstrate how to use DecontX to estimate and remove contamination.  

+

+

+The package can be loaded using the `library` command.

+

+```{r, eval=TRUE, warning = FALSE, echo = FALSE, message = FALSE}

+library(celda)

+```

+To see the latest updates and releases or to post a bug, see our GitHub page at https://github.com/compbiomed/celda. To ask questions about running Celda, visit our Google group at https://groups.google.com/forum/#!forum/celda-list.

+

+

+# Generation of a cross-contaminated dataset 

+DecontX will take a matrix of counts (referred as observed counts) where each row is a feature, each column is a cell, and each entry in the matrix is the number of counts of each feature in each cell. To illustrate the utility of DecontX, we will apply it to a simulated dataset.

+

+In the function `simulateContaminatedMatrix`, the K parameter designates the number of cell clusters, the C parameter determines the number of cells, the G parameter determines the number of genes in the simulated dataset.

+

+```

+sim_counts = simulateContaminatedMatric( G = 300, C = 100, K = 3 ) 

+```

+

+The `nativeCounts` is the natively expressed counts matrix, and `observedCounts` is the observed counts matrix that contains both contaminated and natively expressed transctripts. The `N.by.C` is the total number of observed transcripts per cell. The counts matrix which only contains contamianted transcripts can be obtained by subtracting the observed counts matrix from the observed counts matrix. 

+

+```

+contamination = sim_counts$observedCounts - sim_counts$observedCounts 

+```

+

+The `z` variable contains the population label for each cell

+```

+table( sim_counts$z) 

+```

+

+The `phi` and `eta` variables contain the expression distributions and contamination distributions for each population, respectively. Each column corresponds to a population, each row represents a gene. The sum of the rows equal to 1. 

+```

+colSums( sim_counts$phi ) 

+colSums( sim_counts$eta )

+```

+

+

+# Decontamination using DecontX

+DecontX uses bayesian method to estimate and remove contamination via varitaional inference. 

+```{r, warning = FALSE, message = FALSE}

+decontx.model = DecontX( counts = sim_counts$observedCounts, z = sim_counts$z ) 

+```

+

+## Check convergance

+Use log-likelihood to check converagance 

+```{r, eval = TRUE, fig.width = 5, fig.height = 5}

+plot( decontx.model$res.list$loglikelihood ) 

+```

+## Evaluate model performance 

+`DecontX` estimates a contamination proportion for each cell. We compare the estimated contamination proportion with the real contamination proportion.

+```{r, eval = TRUE, fig.width = 5, fig.height = 5}

+plot( decontx.model$res.list$est.conp, colSums(contamination) / sim_counts$N.By.C,  col=sim_counts$z) 

+abline( 0, 1) 

+```

+

+