Survival Analysis

Colorectal Cancer | Pyroptosis | Unique Genes per RCD Type | Gene Expression of Tumor Samples

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.

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 line below

  # GDCdownload(query_project)

  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]], 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 <- "temp/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) {
  gene_df <- vsd[[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")))

  q1 <- quantile(gene_df$counts, probs = 0.25)
  q3 <- quantile(gene_df$counts, probs = 0.75)
  gene_df$strata <- ifelse(gene_df$counts >= q3, "HIGH", ifelse(gene_df$counts <= q1, "LOW", "MIDDLE"))
  gene_df <- gene_df %>% dplyr::filter(strata %in% c("LOW", "HIGH"))
  gene_df$case_id <- paste0(sapply(strsplit(as.character(gene_df$case_id), "-"), `[`, 1), '-',
                          sapply(strsplit(as.character(gene_df$case_id), "-"), `[`, 2), '-', 
                          sapply(strsplit(as.character(gene_df$case_id), "-"), `[`, 3))
  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 Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        2     1.33     0.334     0.602
strata=LOW  12        1     1.67     0.267     0.602

 Chisq= 0.6  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 -0.9181    0.3993   1.2253 -0.749 0.454

Likelihood ratio test=0.6  on 1 df, p=0.4378
n= 24, number of events= 3 


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

TCGA-COAD CHMP7 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3     1.37      1.94      3.06
strata=LOW  12        1     2.63      1.01      3.06

 Chisq= 3.1  on 1 degrees of freedom, p= 0.08 

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

             coef exp(coef) se(coef)      z     p
strataLOW -1.8282    0.1607   1.1780 -1.552 0.121

Likelihood ratio test=2.89  on 1 df, p=0.08925
n= 24, number of events= 4 


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

TCGA-COAD GSDMC 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        4     4.37    0.0309    0.0791
strata=LOW  12        4     3.63    0.0371    0.0791

 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 0.2172    1.2426   0.7737 0.281 0.779

Likelihood ratio test=0.08  on 1 df, p=0.778
n= 24, number of events= 8 


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

TCGA-COAD ELANE 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3     2.17     0.320     0.566
strata=LOW  12        3     3.83     0.181     0.566

 Chisq= 0.6  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 -0.6750    0.5092   0.9141 -0.738 0.46

Likelihood ratio test=0.56  on 1 df, p=0.4543
n= 24, number of events= 6 


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

TCGA-COAD IRF1 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3     3.78     0.160     0.497
strata=LOW  12        3     2.22     0.272     0.497

 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 0.6379    1.8926   0.9196 0.694 0.488

Likelihood ratio test=0.49  on 1 df, p=0.4822
n= 24, number of events= 6 


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

TCGA-COAD CYCS 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        2     3.04     0.356      1.09
strata=LOW  12        3     1.96     0.551      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 1.147     3.149    1.158 0.99 0.322

Likelihood ratio test=1.14  on 1 df, p=0.2864
n= 24, number of events= 5 


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

TCGA-COAD GSDMA 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        4     4.06  0.000756   0.00317
strata=LOW  12        2     1.94  0.001577   0.00317

 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 0.05722   1.05889  1.01643 0.056 0.955

Likelihood ratio test=0  on 1 df, p=0.9551
n= 24, number of events= 6 


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

TCGA-COAD CASP4 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        5     4.12     0.186     0.446
strata=LOW  12        3     3.88     0.198     0.446

 Chisq= 0.4  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 -0.5063    0.6027   0.7663 -0.661 0.509

Likelihood ratio test=0.44  on 1 df, p=0.5059
n= 24, number of events= 8 


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

TCGA-COAD BAK1 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3     2.04     0.455      0.77
strata=LOW  12        2     2.96     0.313      0.77

 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 -0.7824    0.4573   0.9141 -0.856 0.392

Likelihood ratio test=0.75  on 1 df, p=0.3856
n= 24, number of events= 5 


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

TCGA-COAD NOD1 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        5     4.18     0.161     0.452
strata=LOW  12        2     2.82     0.239     0.452

 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 -0.5757    0.5623   0.8677 -0.664 0.507

Likelihood ratio test=0.46  on 1 df, p=0.496
n= 24, number of events= 7 


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

TCGA-COAD NLRP7 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        2     2.77     0.215     0.401
strata=LOW  12        4     3.23     0.185     0.401

 Chisq= 0.4  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 0.5422    1.7199   0.8671 0.625 0.532

Likelihood ratio test=0.41  on 1 df, p=0.5215
n= 24, number of events= 6 


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

TCGA-COAD CASP3 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        2     2.31    0.0424     0.102
strata=LOW  12        2     1.69    0.0582     0.102

 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 0.3187    1.3754   1.0046 0.317 0.751

Likelihood ratio test=0.1  on 1 df, p=0.7515
n= 24, number of events= 4 


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

TCGA-COAD GSDMB 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3      3.1   0.00318    0.0106
strata=LOW  12        2      1.9   0.00518    0.0106

 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 0.1072    1.1131   1.0393 0.103 0.918

Likelihood ratio test=0.01  on 1 df, p=0.9178
n= 24, number of events= 5 


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

TCGA-COAD GZMB 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3     2.58    0.0669     0.144
strata=LOW  12        2     2.42    0.0716     0.144

 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 -0.3520    0.7033   0.9316 -0.378 0.706

Likelihood ratio test=0.15  on 1 df, p=0.703
n= 24, number of events= 5 


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

TCGA-COAD GSDME 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        1     2.16     0.625      1.37
strata=LOW  12        3     1.84     0.735      1.37

 Chisq= 1.4  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 1.270     3.562    1.158 1.097 0.273

Likelihood ratio test=1.41  on 1 df, p=0.2352
n= 24, number of events= 4 


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

TCGA-COAD CHMP3 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        2     1.33     0.333     0.633
strata=LOW  12        2     2.67     0.167     0.633

 Chisq= 0.6  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 -0.9629    0.3818   1.2512 -0.77 0.442

Likelihood ratio test=0.63  on 1 df, p=0.4267
n= 24, number of events= 4 


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

TCGA-COAD DPP9 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        2     1.94   0.00159   0.00621
strata=LOW  12        1     1.06   0.00292   0.00621

 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 -0.1116    0.8944   1.4164 -0.079 0.937

Likelihood ratio test=0.01  on 1 df, p=0.9372
n= 24, number of events= 3 


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

TCGA-COAD NOD2 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        1      2.5     0.901      1.86
strata=LOW  12        4      2.5     0.901      1.86

 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 1.422     4.144    1.127 1.261 0.207

Likelihood ratio test=1.98  on 1 df, p=0.159
n= 24, number of events= 5 


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

TCGA-COAD NLRC4 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3     3.28    0.0246    0.0827
strata=LOW  12        2     1.72    0.0472    0.0827

 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 0.2869    1.3323   1.0008 0.287 0.774

Likelihood ratio test=0.08  on 1 df, p=0.7747
n= 24, number of events= 5 


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

TCGA-COAD GSDMD 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        2     1.33     0.334     0.602
strata=LOW  12        1     1.67     0.267     0.602

 Chisq= 0.6  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 -0.9181    0.3993   1.2253 -0.749 0.454

Likelihood ratio test=0.6  on 1 df, p=0.4378
n= 24, number of events= 3 


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

TCGA-COAD TIRAP 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        2     3.12     0.405     0.849
strata=LOW  12        5     3.88     0.327     0.849

 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 0.7802    2.1820   0.8680 0.899 0.369

Likelihood ratio test=0.86  on 1 df, p=0.3535
n= 24, number of events= 7 


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

TCGA-COAD SCAF11 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        1     2.64      1.02      3.66
strata=LOW  12        3     1.36      1.99      3.66

 Chisq= 3.7  on 1 degrees of freedom, p= 0.06 

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

               coef exp(coef)  se(coef)     z     p
strataLOW 2.143e+01 2.020e+09 2.343e+04 0.001 0.999

Likelihood ratio test=4.78  on 1 df, p=0.02875
n= 24, number of events= 4 


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

TCGA-COAD NLRP6 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        4     4.39    0.0355     0.113
strata=LOW  12        3     2.61    0.0599     0.113

 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 0.2839    1.3283   0.8468 0.335 0.737

Likelihood ratio test=0.11  on 1 df, p=0.7375
n= 24, number of events= 7 


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

TCGA-COAD AIM2 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        4     3.21     0.193     0.438
strata=LOW  12        2     2.79     0.223     0.438

 Chisq= 0.4  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 -0.5768    0.5617   0.8826 -0.653 0.513

Likelihood ratio test=0.45  on 1 df, p=0.5038
n= 24, number of events= 6 


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

TCGA-COAD CASP6 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3     3.11   0.00421   0.00883
strata=LOW  12        4     3.89   0.00338   0.00883

 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 0.07705   1.08009  0.81992 0.094 0.925

Likelihood ratio test=0.01  on 1 df, p=0.9251
n= 24, number of events= 7 


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

TCGA-COAD NLRP2 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        2     2.84     0.246     0.578
strata=LOW  12        3     2.16     0.322     0.578

 Chisq= 0.6  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 0.6869    1.9875   0.9206 0.746 0.456

Likelihood ratio test=0.57  on 1 df, p=0.4496
n= 24, number of events= 5 


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

TCGA-COAD IRF2 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3     1.83     0.749      1.41
strata=LOW  12        1     2.17     0.631      1.41

 Chisq= 1.4  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 -1.2992    0.2727   1.1665 -1.114 0.265

Likelihood ratio test=1.45  on 1 df, p=0.2283
n= 24, number of events= 4 


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

TCGA-COAD PJVK 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3     3.07   0.00182   0.00344
strata=LOW  12        4     3.93   0.00143   0.00344

 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 0.04607   1.04715  0.78529 0.059 0.953

Likelihood ratio test=0  on 1 df, p=0.9532
n= 24, number of events= 7 


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

TCGA-COAD CASP5 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3     2.57    0.0706     0.246
strata=LOW  12        1     1.43    0.1274     0.246

 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 -0.6015    0.5480   1.2310 -0.489 0.625

Likelihood ratio test=0.25  on 1 df, p=0.6159
n= 24, number of events= 4 


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

TCGA-COAD NLRP1 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        4     4.58    0.0729     0.194
strata=LOW  12        4     3.42    0.0975     0.194

 Chisq= 0.2  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 0.3383    1.4026   0.7710 0.439 0.661

Likelihood ratio test=0.19  on 1 df, p=0.659
n= 24, number of events= 8 


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

TCGA-COAD CASP9 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        3     3.69     0.128      0.38
strata=LOW  12        3     2.31     0.204      0.38

 Chisq= 0.4  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 0.5564    1.7444   0.9139 0.609 0.543

Likelihood ratio test=0.38  on 1 df, p=0.5377
n= 24, number of events= 6 


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

TCGA-COAD PLCG1 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        2     2.19    0.0170    0.0386
strata=LOW  12        3     2.81    0.0133    0.0386

 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 0.1987    1.2198   1.0133 0.196 0.845

Likelihood ratio test=0.04  on 1 df, p=0.8446
n= 24, number of events= 5 


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

TCGA-COAD IL18 

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

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        5      4.7    0.0196    0.0546
strata=LOW  12        3      3.3    0.0279    0.0546

 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 -0.1811    0.8343   0.7764 -0.233 0.816

Likelihood ratio test=0.05  on 1 df, p=0.8149
n= 24, number of events= 8 


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

TCGA-COAD DPP8 

[1] 34
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

             N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 12        1     1.63     0.245     0.537
strata=LOW  12        4     3.37     0.119     0.537

 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 0.870     2.387    1.225 0.71 0.478

Likelihood ratio test=0.54  on 1 df, p=0.4626
n= 24, number of events= 5 


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

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

significant_genes

NULL

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)
    
    fit <- compute_surival_fit(gene_df)
    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")
  } 
}

---

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

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