Survival Analysis

Colorectal Cancer | Necroptosis | 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)
}

Necroptosis

Fetch the gene set of interest.

genes <- read.csv(paste0(RCDdb, "Necroptosis.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 1 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

MLKL is the primary executor of necroptosis.

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

ctr <- 1
for (project in projects) {
  for (gene in c("MLKL", 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 MLKL 

[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  2        2    0.737     2.167      2.49
strata=LOW  10       10   11.263     0.142      2.49

 Chisq= 2.5  on 1 degrees of freedom, p= 0.1 

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

             coef exp(coef) se(coef)      z    p
strataLOW -1.2855    0.2765   0.8715 -1.475 0.14

Likelihood ratio test=1.82  on 1 df, p=0.1779
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD RBCK1 

[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  2        2     0.66     2.724      3.29
strata=LOW  10       10    11.34     0.158      3.29

 Chisq= 3.3  on 1 degrees of freedom, p= 0.07 

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

             coef exp(coef) se(coef)     z     p
strataLOW -1.6435    0.1933   1.0086 -1.63 0.103

Likelihood ratio test=2.41  on 1 df, p=0.1203
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD JAK2 

[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 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 ZBP1 

[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 5        5     4.17     0.165     0.276
strata=LOW  7        7     7.83     0.088     0.276

 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 -0.3230    0.7240   0.6175 -0.523 0.601

Likelihood ratio test=0.27  on 1 df, p=0.6032
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD RNF31 

[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 4        4     4.63    0.0867     0.156
strata=LOW  8        8     7.37    0.0545     0.156

 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 0.2517    1.2862   0.6392 0.394 0.694

Likelihood ratio test=0.16  on 1 df, p=0.6909
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD IFNB1 

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

n=3, 43 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 2        2    2.167    0.0128    0.0588
strata=LOW  1        1    0.833    0.0333    0.0588

 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 0.3466    1.4142   1.4355 0.241 0.809

Likelihood ratio test=0.06  on 1 df, p=0.8096
n= 3, number of events= 3 
   (43 observations deleted due to missingness)


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

TCGA-COAD TRAF5 

[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 3        3     1.68     1.038      1.34
strata=LOW  9        9    10.32     0.169      1.34

 Chisq= 1.3  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 -0.8359    0.4335   0.7415 -1.127 0.26

Likelihood ratio test=1.17  on 1 df, p=0.2804
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD BIRC2 

[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     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 TRAF2 

[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  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 BCL2 

[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 5        5     4.86   0.00424   0.00847
strata=LOW  7        7     7.14   0.00288   0.00847

 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 -0.05903   0.94268  0.64134 -0.092 0.927

Likelihood ratio test=0.01  on 1 df, p=0.9267
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD STAT4 

[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 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 BIRC3 

[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 6        6     5.86   0.00315   0.00687
strata=LOW  6        6     6.14   0.00301   0.00687

 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 -0.05068   0.95058  0.61129 -0.083 0.934

Likelihood ratio test=0.01  on 1 df, p=0.9339
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD STAT1 

[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 3        3     4.58     0.543      1.06
strata=LOW  9        9     7.42     0.335      1.06

 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 0.7950    2.2144   0.7905 1.006 0.315

Likelihood ratio test=1.17  on 1 df, p=0.2785
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD STAT2 

[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  2        2     1.47    0.1885     0.241
strata=LOW  10       10    10.53    0.0264     0.241

 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 -0.4107    0.6632   0.8420 -0.488 0.626

Likelihood ratio test=0.22  on 1 df, p=0.6362
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD TNFSF10 

[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 6        6     5.13     0.147     0.311
strata=LOW  6        6     6.87     0.110     0.311

 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 -0.3637    0.6951   0.6551 -0.555 0.579

Likelihood ratio test=0.31  on 1 df, p=0.5752
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD TYK2 

[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  2        2    0.927     1.240      1.48
strata=LOW  10       10   11.073     0.104      1.48

 Chisq= 1.5  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 -1.0164    0.3619   0.8716 -1.166 0.244

Likelihood ratio test=1.18  on 1 df, p=0.2764
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD PPIA 

[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  2        2     1.84   0.01396    0.0184
strata=LOW  10       10    10.16   0.00253    0.0184

 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 -0.1117    0.8943   0.8234 -0.136 0.892

Likelihood ratio test=0.02  on 1 df, p=0.8931
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD TNFRSF1A 

[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 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 CAPN2 

[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 6        6     6.96     0.132     0.372
strata=LOW  6        6     5.04     0.183     0.372

 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 0.3740    1.4536   0.6162 0.607 0.544

Likelihood ratio test=0.36  on 1 df, p=0.547
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD FAS 

[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 5        5     5.35    0.0234    0.0466
strata=LOW  7        7     6.65    0.0188    0.0466

 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 0.1322    1.1413   0.6127 0.216 0.829

Likelihood ratio test=0.05  on 1 df, p=0.8289
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD PGAM5 

[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  1        1   0.0833   10.0833        11
strata=LOW  11       11  11.9167    0.0705        11

 Chisq= 11  on 1 degrees of freedom, p= 9e-04 

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

                coef  exp(coef)   se(coef)      z     p
strataLOW -2.100e+01  7.582e-10  1.095e+04 -0.002 0.998

Likelihood ratio test=4.97  on 1 df, p=0.02579
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD MLKL 

[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  2        2    0.737     2.167      2.49
strata=LOW  10       10   11.263     0.142      2.49

 Chisq= 2.5  on 1 degrees of freedom, p= 0.1 

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

             coef exp(coef) se(coef)      z    p
strataLOW -1.2855    0.2765   0.8715 -1.475 0.14

Likelihood ratio test=1.82  on 1 df, p=0.1779
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD FADD 

[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  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 TRPM7 

[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 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 FASLG 

[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 7        7     6.95  0.000398   0.00103
strata=LOW  5        5     5.05  0.000547   0.00103

 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 -0.01963   0.98056  0.61141 -0.032 0.974

Likelihood ratio test=0  on 1 df, p=0.9744
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD TNFRSF10B 

[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     1.63     1.158      1.43
strata=LOW  9        9    10.37     0.182      1.43

 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 -0.8334    0.4346   0.7153 -1.165 0.244

Likelihood ratio test=1.22  on 1 df, p=0.2695
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD VPS4A 

[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  2        2     1.16    0.6013     0.752
strata=LOW  10       10    10.84    0.0646     0.752

 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 -0.7387    0.4777   0.8710 -0.848 0.396

Likelihood ratio test=0.65  on 1 df, p=0.4188
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD TNFRSF10A 

[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  2        2    0.358     7.544      8.66
strata=LOW  10       10   11.642     0.232      8.66

 Chisq= 8.7  on 1 degrees of freedom, p= 0.003 

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

              coef exp(coef) se(coef)      z      p
strataLOW -2.74604   0.06418  1.23645 -2.221 0.0264

Likelihood ratio test=5.03  on 1 df, p=0.02488
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD GLUD1 

[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 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 EIF2AK2 

[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  2        2     1.47    0.1885     0.241
strata=LOW  10       10    10.53    0.0264     0.241

 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 -0.4107    0.6632   0.8420 -0.488 0.626

Likelihood ratio test=0.22  on 1 df, p=0.6362
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD CYLD 

[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 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 SPATA2 

[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 5        5     2.54     2.380      3.61
strata=LOW  7        7     9.46     0.639      3.61

 Chisq= 3.6  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 -1.3323    0.2639   0.7476 -1.782 0.0748

Likelihood ratio test=3.31  on 1 df, p=0.0688
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD DNM1L 

[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  2        2     1.47    0.1885     0.241
strata=LOW  10       10    10.53    0.0264     0.241

 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 -0.4107    0.6632   0.8420 -0.488 0.626

Likelihood ratio test=0.22  on 1 df, p=0.6362
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD CFLAR 

[1] 34
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     4.09  0.001837   0.00303
strata=LOW  8        8     7.91  0.000949   0.00303

 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 0.03513   1.03575  0.63806 0.055 0.956

Likelihood ratio test=0  on 1 df, p=0.956
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD TICAM1 

[1] 35
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  2        2     1.16    0.6013     0.752
strata=LOW  10       10    10.84    0.0646     0.752

 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 -0.7387    0.4777   0.8710 -0.848 0.396

Likelihood ratio test=0.65  on 1 df, p=0.4188
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD HSP90AA1 

[1] 36
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     2.74   0.02409    0.0354
strata=LOW  9        9     9.26   0.00714    0.0354

 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 -0.1344    0.8742   0.7150 -0.188 0.851

Likelihood ratio test=0.03  on 1 df, p=0.852
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD IL33 

[1] 37
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     5.25      1.44       3.3
strata=LOW  4        4     6.75      1.12       3.3

 Chisq= 3.3  on 1 degrees of freedom, p= 0.07 

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

             coef exp(coef) se(coef)      z      p
strataLOW -1.3950    0.2478   0.8181 -1.705 0.0881

Likelihood ratio test=3.57  on 1 df, p=0.05893
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD IRF9 

[1] 38
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     3.73   0.01944    0.0305
strata=LOW  8        8     8.27   0.00877    0.0305

 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 -0.1114    0.8946   0.6382 -0.175 0.861

Likelihood ratio test=0.03  on 1 df, p=0.8621
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD SHARPIN 

[1] 39
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 IFNAR1 

[1] 40
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 XIAP 

[1] 41
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 VDAC3 

[1] 42
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  2        2     1.47    0.1885     0.241
strata=LOW  10       10    10.53    0.0264     0.241

 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 -0.4107    0.6632   0.8420 -0.488 0.626

Likelihood ratio test=0.22  on 1 df, p=0.6362
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD CAMK2A 

[1] 43
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     6.97     0.153     0.428
strata=LOW  4        4     5.03     0.212     0.428

 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 -0.4443    0.6413   0.6844 -0.649 0.516

Likelihood ratio test=0.45  on 1 df, p=0.5038
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD VDAC1 

[1] 44
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     1.56      1.34      1.74
strata=LOW  9        9    10.44      0.20      1.74

 Chisq= 1.7  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 -0.9751    0.3771   0.7686 -1.269 0.205

Likelihood ratio test=1.49  on 1 df, p=0.2226
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD RIPK3 

[1] 45
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     3.67     0.482     0.787
strata=LOW  7        7     8.33     0.212     0.787

 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 -0.5649    0.5684   0.6445 -0.876 0.381

Likelihood ratio test=0.76  on 1 df, p=0.3834
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD CAPN1 

[1] 46
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 USP21 

[1] 47
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 AIFM1 

[1] 48
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     2.49     0.103     0.153
strata=LOW  9        9     9.51     0.027     0.153

 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 -0.2882    0.7496   0.7390 -0.39 0.697

Likelihood ratio test=0.15  on 1 df, p=0.7002
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD TRADD 

[1] 49
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 OPTN 

[1] 50
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 PPID 

[1] 51
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  2        2     1.47    0.1885     0.241
strata=LOW  10       10    10.53    0.0264     0.241

 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 -0.4107    0.6632   0.8420 -0.488 0.626

Likelihood ratio test=0.22  on 1 df, p=0.6362
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD RIPK1 

[1] 52
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     4.86   0.00424   0.00847
strata=LOW  7        7     7.14   0.00288   0.00847

 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 -0.05903   0.94268  0.64134 -0.092 0.927

Likelihood ratio test=0.01  on 1 df, p=0.9267
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD TLR3 

[1] 53
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     7.23   0.00757    0.0226
strata=LOW  5        5     4.77   0.01149    0.0226

 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 0.09535   1.10005  0.63420 0.15 0.88

Likelihood ratio test=0.02  on 1 df, p=0.881
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD FAF1 

[1] 54
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  2        2     1.47    0.1885     0.241
strata=LOW  10       10    10.53    0.0264     0.241

 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 -0.4107    0.6632   0.8420 -0.488 0.626

Likelihood ratio test=0.22  on 1 df, p=0.6362
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD JAK1 

[1] 55
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     3.86     0.336      0.57
strata=LOW  7        7     8.14     0.159      0.57

 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 -0.4847    0.6159   0.6474 -0.749 0.454

Likelihood ratio test=0.56  on 1 df, p=0.4557
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] "PGAM5"     "TNFRSF10A"

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 PGAM5 

Warning: Loglik converged before variable  1 ; coefficient may be infinite. 

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   0.0833   10.0833        11
strata=LOW  11       11  11.9167    0.0705        11

 Chisq= 11  on 1 degrees of freedom, p= 9e-04 

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

                coef  exp(coef)   se(coef)      z     p
strataLOW -2.100e+01  7.582e-10  1.095e+04 -0.002 0.998

Likelihood ratio test=4.97  on 1 df, p=0.02579
n= 12, number of events= 12 
   (34 observations deleted due to missingness)


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

TCGA-COAD TNFRSF10A 

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  2        2    0.358     7.544      8.66
strata=LOW  10       10   11.642     0.232      8.66

 Chisq= 8.7  on 1 degrees of freedom, p= 0.003 

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

              coef exp(coef) se(coef)      z      p
strataLOW -2.74604   0.06418  1.23645 -2.221 0.0264

Likelihood ratio test=5.03  on 1 df, p=0.02488
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↩︎