Survival Analysis

Colorectal Cancer | Pyroptosis | Unique Genes per RCD Type | Log Fold Change

I. Preliminaries

Loading libraries

library("tidyverse")
library("tibble")
library("msigdbr")
library("ggplot2")
library("TCGAbiolinks")
library("RNAseqQC")
library("DESeq2")
library("ensembldb")
library("purrr")
library("magrittr")
library("vsn")
library("matrixStats")
library("dplyr")
library("grex")
library("survminer")
library("survival")

II. Downloading the TCGA gene expression data

Create a function for downloading TCGA gene expression data.

For more detailed documentation, refer to 2. Differential Gene Expression Analysis - TCGA.Rmd.

GDC_DIR = "../data/public/GDCdata"

query_and_filter_samples <- function(project) {
  query_tumor <- GDCquery(
    project = project,
    data.category = "Transcriptome Profiling",
    data.type = "Gene Expression Quantification",
    experimental.strategy = "RNA-Seq",
    workflow.type = "STAR - Counts",
    access = "open",
    sample.type = "Primary Tumor"
  )
  tumor <- getResults(query_tumor)

  query_normal <- GDCquery(
    project = project,
    data.category = "Transcriptome Profiling",
    data.type = "Gene Expression Quantification",
    experimental.strategy = "RNA-Seq",
    workflow.type = "STAR - Counts",
    access = "open",
    sample.type = "Solid Tissue Normal"
  )
  normal <- getResults(query_normal)

  submitter_ids <- inner_join(tumor, normal, by = "cases.submitter_id") %>%
    dplyr::select(cases.submitter_id)
  tumor <- tumor %>%
    dplyr::filter(cases.submitter_id %in% submitter_ids$cases.submitter_id)
  normal <- normal %>%
    dplyr::filter(cases.submitter_id %in% submitter_ids$cases.submitter_id)

  samples <- rbind(tumor, normal)
  unique(samples$sample_type)

  query_project <- GDCquery(
    project = project,
    data.category = "Transcriptome Profiling",
    data.type = "Gene Expression Quantification",
    experimental.strategy = "RNA-Seq",
    workflow.type = "STAR - Counts",
    access = "open",
    sample.type = c("Solid Tissue Normal", "Primary Tumor"),
    barcode = as.list(samples$sample.submitter_id)
  )

  # If this is your first time running this notebook (i.e., you have not yet downloaded the results of the query in the previous block),
  # uncomment the code block below

  # GDCdownload(
  #   query_coad,
  #   directory = GDC_DIR
  # )

  return(list(samples = samples, query_project = query_project))
}

Download the TCGA gene expression data for colorectal cancer (TCGA-COAD).

projects <- c("TCGA-COAD")

with_results_projects <- c()

samples <- list()
project_data <- list()

for (project in projects) {
  result <- tryCatch(
    {
      result <- query_and_filter_samples(project)
      samples[[project]] <- result$samples
      project_data[[project]] <- result$query_project

      with_results_projects <- c(with_results_projects, project)
    },
    error = function(e) {

    }
  )
}

Running the code block above should generate and populate a directory named GDCdata.

III. Data preprocessing

Construct the RNA-seq count matrix for each cancer type.

tcga_data <- list()
tcga_matrix <- list()

projects <- with_results_projects
for (project in projects) {
  tcga_data[[project]] <- GDCprepare(
    project_data[[project]], 
    directory = GDC_DIR,
    summarizedExperiment = TRUE
  )
}

for (project in projects) {
  count_matrix <- assay(tcga_data[[project]], "unstranded")

  # Remove duplicate entries
  count_matrix_df <- data.frame(count_matrix)
  count_matrix_df <- count_matrix_df[!duplicated(count_matrix_df), ]
  count_matrix <- data.matrix(count_matrix_df)
  rownames(count_matrix) <- cleanid(rownames(count_matrix))
  count_matrix <- count_matrix[!(duplicated(rownames(count_matrix)) | duplicated(rownames(count_matrix), fromLast = TRUE)), ]

  tcga_matrix[[project]] <- count_matrix
}

Format the samples table so that it can be fed as input to DESeq2.

for (project in projects) {
  rownames(samples[[project]]) <- samples[[project]]$cases
  samples[[project]] <- samples[[project]] %>%
    dplyr::select(case = "cases.submitter_id", type = "sample_type")
  samples[[project]]$type <- str_replace(samples[[project]]$type, "Solid Tissue Normal", "normal")
  samples[[project]]$type <- str_replace(samples[[project]]$type, "Primary Tumor", "tumor")
}

DESeq2 requires the row names of samples should be identical to the column names of count_matrix.

for (project in projects) {
  colnames(tcga_matrix[[project]]) <- gsub(x = colnames(tcga_matrix[[project]]), pattern = "\\.", replacement = "-")
  tcga_matrix[[project]] <- tcga_matrix[[project]][, rownames(samples[[project]])]

  # Sanity check
  print(all(colnames(tcga_matrix[[project]]) == rownames(samples[[project]])))
}

IV. Differential gene expression analysis

For more detailed documentation on obtaining the gene set, refer to 7. Differential Gene Expression Analysis - TCGA - Pan-cancer - Unique Genes.Rmd.

RCDdb <- "../data/public/rcd-gene-list/unique-genes/necroptosis-ferroptosis-pyroptosis/"

Write utility functions for filtering the gene sets, performing differential gene expression analysis, plotting the results, and performing variance-stabilizing transformation.

filter_gene_set_and_perform_dgea <- function(genes) {
  tcga_rcd <- list()

  for (project in projects) {
    rownames(genes) <- genes$gene_id
    tcga_rcd[[project]] <- tcga_matrix[[project]][rownames(tcga_matrix[[project]]) %in% genes$gene_id, ]
    tcga_rcd[[project]] <- tcga_rcd[[project]][, rownames(samples[[project]])]
  }

  dds_rcd <- list()
  res_rcd <- list()

  for (project in projects) {
    print(project)
    print("=============")
    dds <- DESeqDataSetFromMatrix(
      countData = tcga_rcd[[project]],
      colData = samples[[project]],
      design = ~type
    )
    dds <- filter_genes(dds, min_count = 10)
    dds$type <- relevel(dds$type, ref = "normal")
    dds_rcd[[project]] <- DESeq(dds)
    res_rcd[[project]] <- results(dds_rcd[[project]])
  }

  deseq.bbl.data <- list()

  for (project in projects) {
    deseq.results <- res_rcd[[project]]
    deseq.bbl.data[[project]] <- data.frame(
      row.names = rownames(deseq.results),
      baseMean = deseq.results$baseMean,
      log2FoldChange = deseq.results$log2FoldChange,
      lfcSE = deseq.results$lfcSE,
      stat = deseq.results$stat,
      pvalue = deseq.results$pvalue,
      padj = deseq.results$padj,
      cancer_type = project,
      gene_symbol = genes[rownames(deseq.results), "gene"]
    )
  }

  deseq.bbl.data.combined <- bind_rows(deseq.bbl.data)
  deseq.bbl.data.combined <- dplyr::filter(deseq.bbl.data.combined, abs(log2FoldChange) >= 1.5 & padj < 0.05)

  return(deseq.bbl.data.combined)
}

plot_dgea <- function(deseq.bbl.data.combined) {
  sizes <- c("<10^-15" = 4, "10^-10" = 3, "10^-5" = 2, "0.05" = 1)

  deseq.bbl.data.combined <- deseq.bbl.data.combined %>%
    mutate(fdr_category = cut(padj,
      breaks = c(-Inf, 1e-15, 1e-10, 1e-5, 0.05),
      labels = c("<10^-15", "10^-10", "10^-5", "0.05"),
      right = FALSE
    ))

  top_genes <- deseq.bbl.data.combined %>%
    group_by(cancer_type) %>%
    mutate(rank = rank(-abs(log2FoldChange))) %>%
    dplyr::filter(rank <= 10) %>%
    ungroup()

  ggplot(top_genes, aes(y = cancer_type, x = gene_symbol, size = fdr_category, fill = log2FoldChange)) +
    geom_point(alpha = 0.5, shape = 21, color = "black") +
    scale_size_manual(values = sizes) +
    scale_fill_gradient2(low = "blue", mid = "white", high = "red", limits = c(min(deseq.bbl.data.combined$log2FoldChange), max(deseq.bbl.data.combined$log2FoldChange))) +
    theme_minimal() +
    theme(
      axis.text.x = element_text(size = 9, angle = 90, hjust = 1)
    ) +
    theme(legend.position = "bottom") +
    theme(legend.position = "bottom") +
    labs(size = "Adjusted p-value", fill = "log2 FC", y = "Cancer type", x = "Gene")
}

perform_vsd <- function(genes) {
  tcga_rcd <- list()

  for (project in projects) {
    rownames(genes) <- genes$gene_id
    tcga_rcd[[project]] <- tcga_matrix[[project]][rownames(tcga_matrix[[project]]) %in% genes$gene_id, ]
    tcga_rcd[[project]] <- tcga_rcd[[project]][, rownames(samples[[project]])]
  }

  vsd_rcd <- list()

  for (project in projects) {
    print(project)
    print("=============")
    dds <- DESeqDataSetFromMatrix(
      countData = tcga_rcd[[project]],
      colData = samples[[project]],
      design = ~type
    )
    dds <- filter_genes(dds, min_count = 10)

    # Perform variance stabilization
    dds <- estimateSizeFactors(dds)
    nsub <- sum(rowMeans(counts(dds, normalized = TRUE)) > 10)
    vsd <- vst(dds, nsub = nsub)
    vsd_rcd[[project]] <- assay(vsd)
  }

  return(vsd_rcd)
}

Pyroptosis

Fetch the gene set of interest.

genes <- read.csv(paste0(RCDdb, "Pyroptosis.csv"))
print(genes)

genes$gene_id <- cleanid(genes$gene_id)
genes <- distinct(genes, gene_id, .keep_all = TRUE)
genes <- subset(genes, gene_id != "")
genes

Filter the genes to include only those in the gene set of interest, and then perform differential gene expression analysis.

deseq.bbl.data.combined <- filter_gene_set_and_perform_dgea(genes)

[1] "TCGA-COAD"
[1] "============="

Warning: some variables in design formula are characters, converting to factorsestimating size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
-- replacing outliers and refitting for 3 genes
-- DESeq argument 'minReplicatesForReplace' = 7 
-- original counts are preserved in counts(dds)
estimating dispersions
fitting model and testing

deseq.bbl.data.combined

Plot the results.

plot_dgea(deseq.bbl.data.combined)

Perform variance-stabilizing transformation for further downstream analysis (i.e., for survival analysis).

vsd <- perform_vsd(genes)

[1] "TCGA-COAD"
[1] "============="

V. Downloading the clinical data

Download clinical data from TCGA, and perform some preprocessing: - The deceased column should be FALSE if the patient is alive and TRUE otherwise - The overall_survival column should reflect the follow-up time if the patient is alive and the days to death otherwise

download_clinical_data <- function(project) {
  clinical_data <- GDCquery_clinic(project)
  clinical_data$deceased <- ifelse(clinical_data$vital_status == "Alive", FALSE, TRUE)
  clinical_data$overall_survival <- ifelse(clinical_data$vital_status == "Alive",
    clinical_data$days_to_last_follow_up,
    clinical_data$days_to_death
  )

  return(clinical_data)
}

tcga_clinical <- list()
for (project in projects) {
  tcga_clinical[[project]] <- download_clinical_data(project)
}

VI. Performing survival analysis

Write utility functions for performing survival analysis.

construct_gene_df <- function(gene_of_interest, project) {
  normal_df <- tcga_matrix[[project]] %>%
    as.data.frame() %>%
    rownames_to_column(var = "gene_id") %>%
    gather(key = "case_id", value = "counts", -gene_id) %>%
    left_join(., genes, by = "gene_id") %>%
    dplyr::filter(gene == gene_of_interest) %>%
    dplyr::filter(case_id %in% rownames(samples[[project]] %>% dplyr::filter(type == "normal")))
  normal_df$case_id <- paste0(sapply(strsplit(as.character(normal_df$case_id), "-"), `[`, 1), '-',
                            sapply(strsplit(as.character(normal_df$case_id), "-"), `[`, 2), '-', 
                            sapply(strsplit(as.character(normal_df$case_id), "-"), `[`, 3))
  
  tumor_df <- tcga_matrix[[project]] %>%
      as.data.frame() %>%
      rownames_to_column(var = "gene_id") %>%
      gather(key = "case_id", value = "counts", -gene_id) %>%
      left_join(., genes, by = "gene_id") %>%
      dplyr::filter(gene == gene_of_interest) %>%
      dplyr::filter(case_id %in% rownames(samples[[project]] %>% dplyr::filter(type == "tumor")))
  tumor_df$case_id <- paste0(sapply(strsplit(as.character(tumor_df$case_id), "-"), `[`, 1), '-',
                            sapply(strsplit(as.character(tumor_df$case_id), "-"), `[`, 2), '-', 
                            sapply(strsplit(as.character(tumor_df$case_id), "-"), `[`, 3))
  
  gene_df <- inner_join(normal_df, tumor_df, by = c("gene_id", "case_id", "deathtype", "gene", "description", "gene_biotype", "pmid", "comment"))
  gene_df$log_fold = log2(gene_df$counts.y / gene_df$counts.x)
  
  gene_df$strata <- ifelse(abs(gene_df$log_fold) >= 1.5, "HIGH", "LOW")
  gene_df <- merge(gene_df, tcga_clinical[[project]], by.x = "case_id", by.y = "submitter_id")
  
  return(gene_df)
}

compute_surival_fit <- function(gene_df) {
  return (survfit(Surv(overall_survival, deceased) ~ strata, data = gene_df))
}

compute_cox <- function(gene_df) {
  return (coxph(Surv(overall_survival, deceased) ~ strata, data=gene_df))
}

plot_survival <- function(fit) {
  return(ggsurvplot(fit,
    data = gene_df,
    pval = T,
    risk.table = T,
    risk.table.height = 0.3
  ))
}

compute_survival_diff <- function(gene_df) {
  return(survdiff(Surv(overall_survival, deceased) ~ strata, data = gene_df))
}

Perform survival analysis by testing for the difference in the Kaplan-Meier curves using the G-rho family of Harrington and Fleming tests: https://rdrr.io/cran/survival/man/survdiff.html

Our genes of interest are GSDMD (the primary executor of pyroptosis) and the differentially expressed genes..

significant_projects <- c()
significant_genes <- c()

ctr <- 1
for (project in projects) {
  for (gene in c("GSDMD", genes$gene)) {
    cat(project, gene, "\n\n")
    error <- tryCatch (
      {
        gene_df <- construct_gene_df(gene, project)
      },
      error = function(e) {
        cat("\n\n============================\n\n")
        e
      }
    )
    
    if(inherits(error, "error")) next

    if (nrow(gene_df) > 0) {
      fit <- compute_surival_fit(gene_df)
      tryCatch (
        {
          survival <- compute_survival_diff(gene_df)
          cox <- compute_cox(gene_df)
          print(ctr)
          ctr <- ctr + 1
          print(survival)
          cat("\n")
          print(cox)
          print(plot_survival(fit))
          if (pchisq(survival$chisq, length(survival$n)-1, lower.tail = FALSE) < 0.05) {
            significant_projects <- c(significant_projects, project)
            significant_genes <- c(significant_genes, gene)
          }
        },
        error = function(e) {
        }
      )
      
    }
    
    cat("\n\n============================\n\n")
  }
}

TCGA-COAD GSDMD 

[1] 1
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     2.77   0.01966    0.0277
strata=LOW  9        9     9.23   0.00589    0.0277

 Chisq= 0  on 1 degrees of freedom, p= 0.9 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.1159    0.8906   0.6967 -0.166 0.868

Likelihood ratio test=0.03  on 1 df, p=0.8689
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD CHMP7 

[1] 2
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     3.08  0.001892   0.00279
strata=LOW  9        9     8.92  0.000652   0.00279

 Chisq= 0  on 1 degrees of freedom, p= 1 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)     z     p
strataLOW 0.03677   1.03746  0.69665 0.053 0.958

Likelihood ratio test=0  on 1 df, p=0.9578
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD GSDMC 

[1] 3
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 8        8     7.56    0.0257    0.0852
strata=LOW  4        4     4.44    0.0438    0.0852

 Chisq= 0.1  on 1 degrees of freedom, p= 0.8 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.2005    0.8183   0.6881 -0.291 0.771

Likelihood ratio test=0.09  on 1 df, p=0.7676
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD ELANE 

[1] 4
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 11       11    10.98  0.000036   0.00045
strata=LOW   1        1     1.02  0.000387   0.00045

 Chisq= 0  on 1 degrees of freedom, p= 1 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

              coef exp(coef) se(coef)      z     p
strataLOW -0.02281   0.97744  1.07582 -0.021 0.983

Likelihood ratio test=0  on 1 df, p=0.983
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD IRF1 

[1] 5
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 6        6     6.54    0.0441     0.107
strata=LOW  6        6     5.46    0.0528     0.107

 Chisq= 0.1  on 1 degrees of freedom, p= 0.7 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

            coef exp(coef) se(coef)     z     p
strataLOW 0.1993    1.2206   0.6110 0.326 0.744

Likelihood ratio test=0.11  on 1 df, p=0.7437
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD CYCS 

[1] 6
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 6        6     5.88   0.00260   0.00668
strata=LOW  6        6     6.12   0.00249   0.00668

 Chisq= 0  on 1 degrees of freedom, p= 0.9 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

              coef exp(coef) se(coef)      z     p
strataLOW -0.05431   0.94714  0.66451 -0.082 0.935

Likelihood ratio test=0.01  on 1 df, p=0.9348
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD GSDMA 

[1] 7
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 7        7     6.78   0.00735    0.0207
strata=LOW  5        5     5.22   0.00954    0.0207

 Chisq= 0  on 1 degrees of freedom, p= 0.9 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.0928    0.9114   0.6446 -0.144 0.886

Likelihood ratio test=0.02  on 1 df, p=0.8855
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD CASP4 

[1] 8
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     6.11     0.728      1.94
strata=LOW  8        8     5.89     0.756      1.94

 Chisq= 1.9  on 1 degrees of freedom, p= 0.2 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

            coef exp(coef) se(coef)     z     p
strataLOW 1.0791    2.9421   0.8078 1.336 0.182

Likelihood ratio test=2.13  on 1 df, p=0.1449
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD BAK1 

[1] 9
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     4.35    0.0276      0.05
strata=LOW  8        8     7.65    0.0157      0.05

 Chisq= 0  on 1 degrees of freedom, p= 0.8 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

            coef exp(coef) se(coef)     z     p
strataLOW 0.1459    1.1571   0.6533 0.223 0.823

Likelihood ratio test=0.05  on 1 df, p=0.8225
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD NOD1 

[1] 10
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     1.95     0.569     0.759
strata=LOW  9        9    10.05     0.110     0.759

 Chisq= 0.8  on 1 degrees of freedom, p= 0.4 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.6303    0.5324   0.7350 -0.858 0.391

Likelihood ratio test=0.69  on 1 df, p=0.4063
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD NLRP7 

[1] 11
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 11       11   11.615    0.0325      1.09
strata=LOW   1        1    0.385    0.9804      1.09

 Chisq= 1.1  on 1 degrees of freedom, p= 0.3 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

           coef exp(coef) se(coef)     z     p
strataLOW 1.142     3.134    1.156 0.988 0.323

Likelihood ratio test=0.79  on 1 df, p=0.374
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD CASP3 

[1] 12
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     1.98     0.521     0.741
strata=LOW  9        9    10.02     0.103     0.741

 Chisq= 0.7  on 1 degrees of freedom, p= 0.4 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.6540    0.5200   0.7729 -0.846 0.397

Likelihood ratio test=0.68  on 1 df, p=0.4079
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD GSDMB 

[1] 13
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 6        6     5.77   0.00891    0.0191
strata=LOW  6        6     6.23   0.00826    0.0191

 Chisq= 0  on 1 degrees of freedom, p= 0.9 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

              coef exp(coef) se(coef)      z    p
strataLOW -0.08464   0.91884  0.61184 -0.138 0.89

Likelihood ratio test=0.02  on 1 df, p=0.8899
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD GZMB 

[1] 14
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 6        6     7.39     0.260     0.809
strata=LOW  6        6     4.61     0.417     0.809

 Chisq= 0.8  on 1 degrees of freedom, p= 0.4 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

            coef exp(coef) se(coef)     z     p
strataLOW 0.5866    1.7978   0.6605 0.888 0.375

Likelihood ratio test=0.81  on 1 df, p=0.3685
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD GSDME 

[1] 15
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     3.61    0.0427     0.065
strata=LOW  8        8     8.39    0.0183     0.065

 Chisq= 0.1  on 1 degrees of freedom, p= 0.8 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.1617    0.8507   0.6347 -0.255 0.799

Likelihood ratio test=0.06  on 1 df, p=0.8004
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD CHMP3 

[1] 16
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     1.98     0.521     0.741
strata=LOW  9        9    10.02     0.103     0.741

 Chisq= 0.7  on 1 degrees of freedom, p= 0.4 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.6540    0.5200   0.7729 -0.846 0.397

Likelihood ratio test=0.68  on 1 df, p=0.4079
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD DPP9 

[1] 17
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH  1        1    0.653    0.1841     0.207
strata=LOW  11       11   11.347    0.0106     0.207

 Chisq= 0.2  on 1 degrees of freedom, p= 0.6 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.4955    0.6093   1.0988 -0.451 0.652

Likelihood ratio test=0.18  on 1 df, p=0.6697
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD NOD2 

[1] 18
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     5.88     0.133     0.297
strata=LOW  7        7     6.12     0.128     0.297

 Chisq= 0.3  on 1 degrees of freedom, p= 0.6 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

            coef exp(coef) se(coef)     z     p
strataLOW 0.3458    1.4132   0.6372 0.543 0.587

Likelihood ratio test=0.3  on 1 df, p=0.5824
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD NLRC4 

[1] 19
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     5.26    0.0129    0.0271
strata=LOW  7        7     6.74    0.0101    0.0271

 Chisq= 0  on 1 degrees of freedom, p= 0.9 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

            coef exp(coef) se(coef)     z     p
strataLOW 0.1049    1.1106   0.6381 0.164 0.869

Likelihood ratio test=0.03  on 1 df, p=0.8688
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD GSDMD 

[1] 20
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     2.77   0.01966    0.0277
strata=LOW  9        9     9.23   0.00589    0.0277

 Chisq= 0  on 1 degrees of freedom, p= 0.9 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.1159    0.8906   0.6967 -0.166 0.868

Likelihood ratio test=0.03  on 1 df, p=0.8689
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD TIRAP 

[1] 21
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     3.59    0.0476    0.0767
strata=LOW  8        8     8.41    0.0203    0.0767

 Chisq= 0.1  on 1 degrees of freedom, p= 0.8 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.1816    0.8339   0.6566 -0.277 0.782

Likelihood ratio test=0.08  on 1 df, p=0.7834
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD SCAF11 

[1] 22
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     3.08  0.001892   0.00279
strata=LOW  9        9     8.92  0.000652   0.00279

 Chisq= 0  on 1 degrees of freedom, p= 1 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)     z     p
strataLOW 0.03677   1.03746  0.69665 0.053 0.958

Likelihood ratio test=0  on 1 df, p=0.9578
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD NLRP6 

[1] 23
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 9        9     8.11    0.0984     0.353
strata=LOW  3        3     3.89    0.2048     0.353

 Chisq= 0.4  on 1 degrees of freedom, p= 0.6 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)     z     p
strataLOW -0.4170    0.6590   0.7063 -0.59 0.555

Likelihood ratio test=0.36  on 1 df, p=0.5458
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD AIM2 

[1] 24
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 7        7      3.9      2.47      4.69
strata=LOW  5        5      8.1      1.19      4.69

 Chisq= 4.7  on 1 degrees of freedom, p= 0.03 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z      p
strataLOW -1.6468    0.1927   0.8295 -1.985 0.0471

Likelihood ratio test=4.82  on 1 df, p=0.02808
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD CASP6 

[1] 25
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     1.98     0.521     0.741
strata=LOW  9        9    10.02     0.103     0.741

 Chisq= 0.7  on 1 degrees of freedom, p= 0.4 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.6540    0.5200   0.7729 -0.846 0.397

Likelihood ratio test=0.68  on 1 df, p=0.4079
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD NLRP2 



============================

TCGA-COAD IRF2 

[1] 26
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     1.98     0.521     0.741
strata=LOW  9        9    10.02     0.103     0.741

 Chisq= 0.7  on 1 degrees of freedom, p= 0.4 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.6540    0.5200   0.7729 -0.846 0.397

Likelihood ratio test=0.68  on 1 df, p=0.4079
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD PJVK 

[1] 27
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     3.27   0.02179    0.0321
strata=LOW  9        9     8.73   0.00815    0.0321

 Chisq= 0  on 1 degrees of freedom, p= 0.9 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

            coef exp(coef) se(coef)     z     p
strataLOW 0.1234    1.1313   0.6889 0.179 0.858

Likelihood ratio test=0.03  on 1 df, p=0.8566
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD CASP5 

[1] 28
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 9        9     9.43    0.0194    0.0986
strata=LOW  3        3     2.57    0.0713    0.0986

 Chisq= 0.1  on 1 degrees of freedom, p= 0.8 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

            coef exp(coef) se(coef)     z     p
strataLOW 0.2187    1.2445   0.6979 0.313 0.754

Likelihood ratio test=0.1  on 1 df, p=0.7577
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD NLRP1 

[1] 29
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 8        8     7.41    0.0473     0.148
strata=LOW  4        4     4.59    0.0763     0.148

 Chisq= 0.1  on 1 degrees of freedom, p= 0.7 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.2624    0.7692   0.6840 -0.384 0.701

Likelihood ratio test=0.15  on 1 df, p=0.696
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD CASP9 

[1] 30
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     1.98     0.521     0.741
strata=LOW  9        9    10.02     0.103     0.741

 Chisq= 0.7  on 1 degrees of freedom, p= 0.4 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.6540    0.5200   0.7729 -0.846 0.397

Likelihood ratio test=0.68  on 1 df, p=0.4079
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD PLCG1 

[1] 31
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3      1.8     0.792      1.04
strata=LOW  9        9     10.2     0.140      1.04

 Chisq= 1  on 1 degrees of freedom, p= 0.3 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.7354    0.4793   0.7377 -0.997 0.319

Likelihood ratio test=0.92  on 1 df, p=0.3372
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD IL18 

[1] 32
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 6        6     5.54    0.0387    0.0793
strata=LOW  6        6     6.46    0.0332    0.0793

 Chisq= 0.1  on 1 degrees of freedom, p= 0.8 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z     p
strataLOW -0.1718    0.8422   0.6107 -0.281 0.778

Likelihood ratio test=0.08  on 1 df, p=0.7781
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

TCGA-COAD DPP8 

[1] 33
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     5.18     0.269     0.525
strata=LOW  8        8     6.82     0.204     0.525

 Chisq= 0.5  on 1 degrees of freedom, p= 0.5 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

            coef exp(coef) se(coef)     z     p
strataLOW 0.4584    1.5815   0.6373 0.719 0.472

Likelihood ratio test=0.53  on 1 df, p=0.4649
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

Display the results only for genes where a significant difference in survival has been reported.

significant_genes

[1] "AIM2"

num_significant_genes <- length(significant_genes)

if (num_significant_genes > 0) {
  for (i in 1 : num_significant_genes) {
    project <- significant_projects[[i]]
    gene <- significant_genes[[i]]
    
    cat(project, gene, "\n\n")
    gene_df <- construct_gene_df(gene, project)
    
    survival <- compute_survival_diff(gene_df)
    cox <- compute_cox(gene_df)
    print(survival)
    cat("\n")
    print(cox)
    print(plot_survival(fit))
    
    cat("\n\n============================\n\n")
  } 
}

TCGA-COAD AIM2 

Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=12, 34 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 7        7      3.9      2.47      4.69
strata=LOW  5        5      8.1      1.19      4.69

 Chisq= 4.7  on 1 degrees of freedom, p= 0.03 

Call:
coxph(formula = Surv(overall_survival, deceased) ~ strata, data = gene_df)

             coef exp(coef) se(coef)      z      p
strataLOW -1.6468    0.1927   0.8295 -1.985 0.0471

Likelihood ratio test=4.82  on 1 df, p=0.02808
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


============================

---

1. De La Salle University, Manila, Philippines, gonzales.markedward@gmail.com↩︎

2. De La Salle University, Manila, Philippines, anish.shrestha@dlsu.edu.ph↩︎