Modifications to allow spectrofloparser to work despite rearranging h…

…tml across versions. Hopefully also across Cytek instruments rather than just 5L.
StepUpCytometry · Dec 17, 2024 · 189961b · 189961b
1 parent b0aa344
commit 189961b
Show file tree

Hide file tree

Showing 2 changed files with 164 additions and 0 deletions.
diff --git a/SpectroFloParser/README.md b/SpectroFloParser/README.md
@@ -0,0 +1,5 @@
+Contained within this folder is the SpectroFloParser.qmd file. A rendered html version can be found on Quarto-Pub at the [following link](https://stepupcytometry.quarto.pub/spectrofloparser/). You will need to provide your own SpectroFlo.EXPT file from your local instrument.
+
+Run the code-blocks to locally create the functions that you will need to retrieve the signatures contained within the SpectroFlo .EXPT file. Then process your experiment file to retrieve the data. 
+
+I have added a ggplot2/plotly example as an example for visualization. Note that the "fluorophore signature" generated by the gate placements for this particular experiment vary quite wildly from what they should be. Gentle reminder proper unmixing controls and gate setting are needed for good results :D
diff --git a/SpectroFloParser/SpectroFloParser.qmd b/SpectroFloParser/SpectroFloParser.qmd
@@ -0,0 +1,159 @@
+---
+title: "Single-color control signature parsing via SpectroFlo .Expt file"
+date: "12/17/2024"
+layout: full
+format:
+  html: default
+toc: true
+toc-location: right
+embed-resources: TRUE
+---
+
+# Load Required Libraries
+
+```{r}
+#| message: false
+#| warning: false
+library(dplyr)
+library(purrr)
+library(xml2)
+```
+
+# Locate Experiment
+
+Manually
+
+```{r}
+#| eval: false
+experiment <- file.choose()
+```
+
+or by file.path
+```{r}
+experiment <- file.path("UnmixedExperiment.Expt")
+```
+
+# Create Functions
+
+Create the required functions locally by running the following code
+```{r}
+  SpectroFloSignatureParser <- function(x, ColumnNames="detector"){
+    Parsed <- read_xml(x)
+    Landing <- xml_children(Parsed)
+    Info <- Landing[xml_name(Landing) == "Info"][[1]]
+    Info_child <- xml_children(Info)
+    ExperimentDesc <- Info_child[xml_name(Info_child) == "ExperimentDesc"][[1]]
+    Experiment_child <- xml_children(ExperimentDesc)
+    RefSetUp <- Experiment_child[xml_name(Experiment_child) == "_RefSetupResult"][[1]]
+    RefSetUp_child <- xml_children(RefSetUp)
+    SpillOverColumn <- RefSetUp_child[xml_name(RefSetUp_child) == "SpilloverColumnList"][[1]]
+    Spill_child <- xml_children(SpillOverColumn) # Number Children
+    Data <- map(.x=Spill_child, .f=NormalizedParser) %>% bind_rows()
+    
+    if (ColumnNames=="detector"){
+    Data <- ColumnNaming(x=Data)
+    }
+    
+    return(Data)
+  }
+
+  NormalizedParser <- function(x){
+  Parameters <- xml_children(x)
+  RefControl <- Parameters[xml_name(Parameters) == "_RefControlDesc"]
+  RefControl_child <- xml_children(RefControl)
+  FluorophoreFloat <- RefControl_child[xml_name(RefControl_child) == "Fluorochrome"]
+  Fluorophore <- xml_text(FluorophoreFloat)
+  Fluorophore <- data.frame(Fluorophore)
+  
+  Param_child <- Parameters[xml_name(Parameters) == "_SpilloverVectorArea"]
+  FloatingValues <- xml_find_all(Param_child, ".//d7p1:float", ns = xml_ns(Param_child))
+  ValueVector <- as.numeric(xml2::xml_text(FloatingValues))
+  Data <- data.frame(t(ValueVector))
+  Data <- cbind(Fluorophore, Data)
+  return(Data)
+  }
+  
+  ColumnNaming <- function(x){
+    TotalDetectors <- ncol(x)-1
+    
+    The5L <- c("Fluorophore", "UV1", "UV2", "UV3", "UV4", "UV5", "UV6", "UV7", "UV8",
+               "UV9", "UV10", "UV11", "UV12", "UV13", "UV14", "UV15", "UV16",
+               "V1", "V2", "V3", "V4", "V5", "V6", "V7", "V8",
+               "V9", "V10", "V11","V12", "V13", "V14", "V15", "V16",
+               "B1", "B2", "B3", "B4", "B5", "B6", "B7", "B8",
+               "B9", "B10", "B11", "B12", "B13", "B14",
+               "YG1", "YG2", "YG3", "YG4", "YG5", "YG6", "YG7", "YG8", "YG9", "YG10",
+               "R1", "R2", "R3", "R4", "R5", "R6", "R7", "R8")
+    The4LUV <- c("Fluorophore", "UV1", "UV2", "UV3", "UV4", "UV5", "UV6", "UV7", "UV8",
+               "UV9", "UV10", "UV11", "UV12", "UV13", "UV14", "UV15", "UV16",
+               "V1", "V2", "V3", "V4", "V5", "V6", "V7", "V8",
+               "V9", "V10", "V11","V12", "V13", "V14", "V15", "V16",
+               "B1", "B2", "B3", "B4", "B5", "B6", "B7", "B8",
+               "B9", "B10", "B11", "B12", "B13", "B14",
+               "R1", "R2", "R3", "R4", "R5", "R6", "R7", "R8")
+    The4LYG <- c("Fluorophore", "V1", "V2", "V3", "V4", "V5", "V6", "V7", "V8",
+               "V9", "V10", "V11","V12", "V13", "V14", "V15", "V16",
+               "B1", "B2", "B3", "B4", "B5", "B6", "B7", "B8",
+               "B9", "B10", "B11", "B12", "B13", "B14",
+               "YG1", "YG2", "YG3", "YG4", "YG5", "YG6", "YG7", "YG8", "YG9", "YG10",
+               "R1", "R2", "R3", "R4", "R5", "R6", "R7", "R8")
+    The3L <- c("Fluorophore", "V1", "V2", "V3", "V4", "V5", "V6", "V7", "V8",
+               "V9", "V10", "V11","V12", "V13", "V14", "V15", "V16",
+               "B1", "B2", "B3", "B4", "B5", "B6", "B7", "B8",
+               "B9", "B10", "B11", "B12", "B13", "B14",
+               "R1", "R2", "R3", "R4", "R5", "R6", "R7", "R8")
+    The2LVB <- c("Fluorophore", "V1", "V2", "V3", "V4", "V5", "V6", "V7", "V8",
+               "V9", "V10", "V11","V12", "V13", "V14", "V15", "V16",
+               "B1", "B2", "B3", "B4", "B5", "B6", "B7", "B8",
+               "B9", "B10", "B11", "B12", "B13", "B14")
+    The2LBR <- c("Fluorophore", "B1", "B2", "B3", "B4", "B5", "B6", "B7", "B8",
+               "B9", "B10", "B11", "B12", "B13", "B14",
+               "R1", "R2", "R3", "R4", "R5", "R6", "R7", "R8")
+    The1L <- c("Fluorophore", "B1", "B2", "B3", "B4", "B5", "B6", "B7", "B8",
+               "B9", "B10", "B11", "B12", "B13", "B14")
+    
+    if (TotalDetectors == 64){colnames(x) <- The5L
+    } else if (TotalDetectors == 54){colnames(x) <- The4LUV
+    } else if (TotalDetectors == 48){colnames(x) <- The4LYG
+    } else if (TotalDetectors == 38){colnames(x) <- The3L
+    } else if (TotalDetectors == 30){colnames(x) <- The2LVB
+    } else if (TotalDetectors == 22){colnames(x) <- The2LBR
+    } else if (TotalDetectors == 14){colnames(x) <- The1L
+    } else {message("Number of Columns didn't match known Instrument")
+    }
+    
+    return(x)
+  }
+```
+
+# Data Extraction
+
+Process the .Expt to a data.frame
+```{r}
+Data <- SpectroFloSignatureParser(experiment)
+```
+
+
+# Plotting
+And proceed to plot
+```{r}
+#| warning: false
+#| message: false
+library(tidyr)
+library(ggplot2)
+library(plotly)
+```
+
+```{r}
+#BV711 <- Data %>% filter(Fluorophore %in% "BV711")
+Tidyed <- Data %>% pivot_longer(cols = where(is.numeric), names_to = "Detector", values_to = "Value")
+
+DetectorOrder <- Tidyed %>% pull(Detector) %>% unique()
+Tidyed$Detector <- factor(Tidyed$Detector, levels=DetectorOrder)
+
+plot <- ggplot(Tidyed, aes(x = Detector, y = Value, color = Fluorophore, group = Fluorophore)) +
+  geom_line() + labs(x = "Detector", y = "Normalized MFI", color = "Fluorophore") +
+  theme_bw() + theme(axis.text.x = element_text(size=5, angle = 70, hjust = 1))
+
+plotly::ggplotly(plot)
+```