Survival Analysis

Colorectal Cancer | Necroptosis | Unique Genes per RCD Type | Gene Expression of Normal 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.

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) {
  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 == "normal")))

  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

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=9, 13 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 6        6     6.81    0.0973     0.446
strata=LOW  3        3     2.19    0.3034     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 0.5083    1.6625   0.7688 0.661 0.509

Likelihood ratio test=0.42  on 1 df, p=0.5155
n= 9, number of events= 9 
   (13 observations deleted due to missingness)


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

TCGA-COAD RBCK1 

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

n=10, 12 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 7        7     5.58     0.361     0.979
strata=LOW  3        3     4.42     0.456     0.979

 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 -0.7826    0.4572   0.8102 -0.966 0.334

Likelihood ratio test=1.06  on 1 df, p=0.3042
n= 10, number of events= 10 
   (12 observations deleted due to missingness)


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

TCGA-COAD JAK2 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     2.05     1.842      3.31
strata=LOW  3        3     4.95     0.765      3.31

 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 -1.8395    0.1589   1.1393 -1.615 0.106

Likelihood ratio test=3.35  on 1 df, p=0.06722
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD ZBP1 

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

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     5.89     0.134     0.566
strata=LOW  3        3     2.11     0.375     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 0.585     1.795    0.787 0.743 0.457

Likelihood ratio test=0.53  on 1 df, p=0.4654
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD RNF31 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     4.14   0.00461    0.0131
strata=LOW  3        3     2.86   0.00666    0.0131

 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 0.09465   1.09927  0.82764 0.114 0.909

Likelihood ratio test=0.01  on 1 df, p=0.909
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD IFNB1 



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

TCGA-COAD TRAF5 

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

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     5.46    0.0393     0.149
strata=LOW  3        3     2.54    0.0845     0.149

 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 0.3162    1.3719   0.8231 0.384 0.701

Likelihood ratio test=0.15  on 1 df, p=0.7014
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD BIRC2 

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

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 1        1    0.367    1.0939      1.34
strata=LOW  5        5    5.633    0.0712      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 -1.4979    0.2236   1.4164 -1.058 0.29

Likelihood ratio test=1.03  on 1 df, p=0.3107
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD TRAF2 

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

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5    7.173     0.658      8.18
strata=LOW  3        3    0.827     5.705      8.18

 Chisq= 8.2  on 1 degrees of freedom, p= 0.004 

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

               coef exp(coef)  se(coef)     z     p
strataLOW 2.189e+01 3.219e+09 1.874e+04 0.001 0.999

Likelihood ratio test=8.05  on 1 df, p=0.004549
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD BCL2 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     4.59    0.0754     0.248
strata=LOW  3        3     2.41    0.1434     0.248

 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 0.4115    1.5090   0.8315 0.495 0.621

Likelihood ratio test=0.24  on 1 df, p=0.6217
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD STAT4 

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

n=4, 18 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 1        1     1.08   0.00641    0.0105
strata=LOW  3        3     2.92   0.00238    0.0105

 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 0.1285    1.1372   1.2535 0.103 0.918

Likelihood ratio test=0.01  on 1 df, p=0.9178
n= 4, number of events= 4 
   (18 observations deleted due to missingness)


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

TCGA-COAD BIRC3 

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

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 2        2     2.82     0.237     0.594
strata=LOW  4        4     3.18     0.210     0.594

 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 0.8475    2.3338   1.1303 0.75 0.453

Likelihood ratio test=0.65  on 1 df, p=0.4198
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD STAT1 

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

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     5.05  0.000495   0.00353
strata=LOW  1        1     0.95  0.002632   0.00353

 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 0.06936   1.07182  1.16790 0.059 0.953

Likelihood ratio test=0  on 1 df, p=0.9529
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD STAT2 

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

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     4.43    0.0734     0.192
strata=LOW  3        3     3.57    0.0911     0.192

 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 -0.3391    0.7124   0.7767 -0.437 0.662

Likelihood ratio test=0.19  on 1 df, p=0.6607
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD TNFSF10 

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

n=10, 12 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     2.41    0.1440     0.209
strata=LOW  7        7     7.59    0.0458     0.209

 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 -0.3347    0.7155   0.7357 -0.455 0.649

Likelihood ratio test=0.2  on 1 df, p=0.6541
n= 10, number of events= 10 
   (12 observations deleted due to missingness)


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

TCGA-COAD TYK2 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     5.09     0.233      1.03
strata=LOW  3        3     1.91     0.619      1.03

 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 0.9149    2.4966   0.9283 0.986 0.324

Likelihood ratio test=1  on 1 df, p=0.3178
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD PPIA 

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

n=5, 17 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 2        2     1.73    0.0410    0.0739
strata=LOW  3        3     3.27    0.0218    0.0739

 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 -0.2739    0.7604   1.0107 -0.271 0.786

Likelihood ratio test=0.07  on 1 df, p=0.7866
n= 5, number of events= 5 
   (17 observations deleted due to missingness)


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

TCGA-COAD TNFRSF1A 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     2.81      1.70       4.2
strata=LOW  2        2     4.19      1.14       4.2

 Chisq= 4.2  on 1 degrees of freedom, p= 0.04 

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

                coef  exp(coef)   se(coef)      z     p
strataLOW -2.118e+01  6.332e-10  1.860e+04 -0.001 0.999

Likelihood ratio test=6.09  on 1 df, p=0.0136
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD CAPN2 

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

n=9, 13 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3      3.9     0.209     0.427
strata=LOW  6        6      5.1     0.160     0.427

 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 0.4829    1.6208   0.7457 0.648 0.517

Likelihood ratio test=0.43  on 1 df, p=0.5111
n= 9, number of events= 9 
   (13 observations deleted due to missingness)


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

TCGA-COAD FAS 

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

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 1        1    0.367    1.0939      1.34
strata=LOW  5        5    5.633    0.0712      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 -1.4979    0.2236   1.4164 -1.058 0.29

Likelihood ratio test=1.03  on 1 df, p=0.3107
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD PGAM5 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     5.76     0.101      0.64
strata=LOW  2        2     1.24     0.473      0.64

 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 0.7244    2.0636   0.9243 0.784 0.433

Likelihood ratio test=0.58  on 1 df, p=0.4477
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD MLKL 

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

n=9, 13 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 6        6     6.81    0.0973     0.446
strata=LOW  3        3     2.19    0.3034     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 0.5083    1.6625   0.7688 0.661 0.509

Likelihood ratio test=0.42  on 1 df, p=0.5155
n= 9, number of events= 9 
   (13 observations deleted due to missingness)


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

TCGA-COAD FADD 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     2.67     0.661       1.5
strata=LOW  3        3     4.33     0.408       1.5

 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 -1.3134    0.2689   1.1415 -1.151 0.25

Likelihood ratio test=1.62  on 1 df, p=0.2028
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD TRPM7 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 2        2      1.4    0.2547     0.359
strata=LOW  5        5      5.6    0.0638     0.359

 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 -0.5445    0.5801   0.9202 -0.592 0.554

Likelihood ratio test=0.33  on 1 df, p=0.5629
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD FASLG 

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

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     2.77    0.0197    0.0449
strata=LOW  3        3     3.23    0.0168    0.0449

 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 -0.1950    0.8229   0.9213 -0.212 0.832

Likelihood ratio test=0.05  on 1 df, p=0.8315
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD TNFRSF10B 

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

n=9, 13 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     7.11     0.627      3.55
strata=LOW  4        4     1.89     2.361      3.55

 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 1.5219    4.5809   0.8798 1.73 0.0837

Likelihood ratio test=3.23  on 1 df, p=0.07236
n= 9, number of events= 9 
   (13 observations deleted due to missingness)


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

TCGA-COAD VPS4A 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3      3.5    0.0702     0.172
strata=LOW  4        4      3.5    0.0700     0.172

 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 0.3601    1.4335   0.8738 0.412 0.68

Likelihood ratio test=0.18  on 1 df, p=0.6751
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD TNFRSF10A 

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

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4      4.3    0.0216    0.0544
strata=LOW  4        4      3.7    0.0251    0.0544

 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 0.1798    1.1970   0.7718 0.233 0.816

Likelihood ratio test=0.05  on 1 df, p=0.8152
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD GLUD1 

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

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     1.15     2.976      5.05
strata=LOW  3        3     4.85     0.706      5.05

 Chisq= 5.1  on 1 degrees of freedom, p= 0.02 

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

                coef  exp(coef)   se(coef)      z     p
strataLOW -2.194e+01  2.957e-10  2.480e+04 -0.001 0.999

Likelihood ratio test=5.99  on 1 df, p=0.01438
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD EIF2AK2 

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

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     3.93   0.00113   0.00375
strata=LOW  2        2     2.07   0.00215   0.00375

 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 -0.05656   0.94501  0.92349 -0.061 0.951

Likelihood ratio test=0  on 1 df, p=0.9511
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD CYLD 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     2.25     0.254     0.417
strata=LOW  4        4     4.75     0.120     0.417

 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 -0.5293    0.5890   0.8287 -0.639 0.523

Likelihood ratio test=0.4  on 1 df, p=0.5252
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD SPATA2 

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

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     4.24     0.361     0.904
strata=LOW  5        5     3.76     0.407     0.904

 Chisq= 0.9  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 0.7860    2.1947   0.8464 0.929 0.353

Likelihood ratio test=0.94  on 1 df, p=0.3319
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD DNM1L 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     4.65    0.0267    0.0894
strata=LOW  2        2     2.35    0.0528    0.0894

 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 -0.2619    0.7696   0.8781 -0.298 0.766

Likelihood ratio test=0.09  on 1 df, p=0.7626
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD CFLAR 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     4.59    0.0754     0.248
strata=LOW  3        3     2.41    0.1434     0.248

 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 0.4115    1.5090   0.8315 0.495 0.621

Likelihood ratio test=0.24  on 1 df, p=0.6217
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD TICAM1 

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

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 2        2      3.4     0.576      1.65
strata=LOW  4        4      2.6     0.754      1.65

 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 1.370     3.934    1.139 1.202 0.229

Likelihood ratio test=1.78  on 1 df, p=0.1818
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD HSP90AA1 

[1] 35
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     2.23     0.263     0.485
strata=LOW  3        3     3.77     0.156     0.485

 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 -0.6321    0.5315   0.9220 -0.686 0.493

Likelihood ratio test=0.48  on 1 df, p=0.4874
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD IL33 

[1] 36
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     5.15   0.00423    0.0191
strata=LOW  2        2     1.85   0.01176    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 0.1278    1.1363   0.9241 0.138 0.89

Likelihood ratio test=0.02  on 1 df, p=0.8905
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD IRF9 

[1] 37
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=9, 13 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     4.55    0.0443     0.105
strata=LOW  4        4     4.45    0.0454     0.105

 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 -0.2313    0.7935   0.7162 -0.323 0.747

Likelihood ratio test=0.1  on 1 df, p=0.7469
n= 9, number of events= 9 
   (13 observations deleted due to missingness)


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

TCGA-COAD SHARPIN 

[1] 38
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     5.42     0.373      2.19
strata=LOW  3        3     1.58     1.280      2.19

 Chisq= 2.2  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 1.586     4.883    1.174 1.35 0.177

Likelihood ratio test=2.17  on 1 df, p=0.1411
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD IFNAR1 

[1] 39
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     2.57    0.0732     0.155
strata=LOW  3        3     3.43    0.0547     0.155

 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 -0.3625    0.6960   0.9256 -0.392 0.695

Likelihood ratio test=0.16  on 1 df, p=0.6928
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD XIAP 

[1] 40
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     5.25     0.300     0.974
strata=LOW  4        4     2.75     0.574     0.974

 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 0.7504    2.1178   0.7767 0.966 0.334

Likelihood ratio test=0.95  on 1 df, p=0.3309
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD VDAC3 

[1] 41
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     3.23    0.0168    0.0449
strata=LOW  3        3     2.77    0.0197    0.0449

 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 0.1950    1.2153   0.9213 0.212 0.832

Likelihood ratio test=0.05  on 1 df, p=0.8315
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD CAMK2A 

[1] 42
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     5.71     0.089     0.369
strata=LOW  3        3     2.29     0.222     0.369

 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 0.4981    1.6456   0.8281 0.601 0.548

Likelihood ratio test=0.36  on 1 df, p=0.5493
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD VDAC1 

[1] 43
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     3.24    0.0173    0.0332
strata=LOW  5        5     4.76    0.0118    0.0332

 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 0.1410    1.1514   0.7745 0.182 0.856

Likelihood ratio test=0.03  on 1 df, p=0.8552
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD RIPK3 

[1] 44
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 2        2     2.35    0.0528     0.082
strata=LOW  6        6     5.65    0.0220     0.082

 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 0.2427    1.2746   0.8491 0.286 0.775

Likelihood ratio test=0.08  on 1 df, p=0.7716
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD CAPN1 

[1] 45
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     4.52     0.509      2.56
strata=LOW  3        3     1.48     1.551      2.56

 Chisq= 2.6  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 1.688     5.408    1.172 1.44 0.15

Likelihood ratio test=2.47  on 1 df, p=0.1159
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD USP21 

[1] 46
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=4, 18 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 2        2     2.33    0.0476     0.154
strata=LOW  2        2     1.67    0.0667     0.154

 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 0.4812    1.6180   1.2380 0.389 0.697

Likelihood ratio test=0.16  on 1 df, p=0.6913
n= 4, number of events= 4 
   (18 observations deleted due to missingness)


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

TCGA-COAD AIFM1 

[1] 47
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     4.95     0.765      3.31
strata=LOW  4        4     2.05     1.842      3.31

 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 1.840     6.294    1.139 1.615 0.106

Likelihood ratio test=3.35  on 1 df, p=0.06722
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD TRADD 

[1] 48
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     2.23     0.263     0.485
strata=LOW  3        3     3.77     0.156     0.485

 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 -0.6321    0.5315   0.9220 -0.686 0.493

Likelihood ratio test=0.48  on 1 df, p=0.4874
n= 6, number of events= 6 
   (16 observations deleted due to missingness)


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

TCGA-COAD OPTN 

[1] 49
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=9, 13 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     2.56     0.803      1.29
strata=LOW  5        5     6.44     0.320      1.29

 Chisq= 1.3  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 -0.8509    0.4270   0.7710 -1.104 0.27

Likelihood ratio test=1.23  on 1 df, p=0.2671
n= 9, number of events= 9 
   (13 observations deleted due to missingness)


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

TCGA-COAD PPID 

[1] 50
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 2        2      1.6    0.0987     0.147
strata=LOW  5        5      5.4    0.0293     0.147

 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 -0.3505    0.7044   0.9188 -0.381 0.703

Likelihood ratio test=0.14  on 1 df, p=0.7067
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD RIPK1 

[1] 51
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4     3.17     0.216      0.48
strata=LOW  4        4     4.83     0.142      0.48

 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 -0.6053    0.5459   0.8851 -0.684 0.494

Likelihood ratio test=0.49  on 1 df, p=0.483
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD TLR3 

[1] 52
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 4        4      2.5     0.893      1.85
strata=LOW  3        3      4.5     0.497      1.85

 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 -1.4295    0.2394   1.1334 -1.261 0.207

Likelihood ratio test=1.98  on 1 df, p=0.159
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD FAF1 

[1] 53
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=4, 18 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 2        2    0.833      1.63      2.88
strata=LOW  2        2    3.167      0.43      2.88

 Chisq= 2.9  on 1 degrees of freedom, p= 0.09 

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

                coef  exp(coef)   se(coef)      z     p
strataLOW -2.168e+01  3.848e-10  2.943e+04 -0.001 0.999

Likelihood ratio test=3.58  on 1 df, p=0.05836
n= 4, number of events= 4 
   (18 observations deleted due to missingness)


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

TCGA-COAD JAK1 

[1] 54
Call:
survdiff(formula = Surv(overall_survival, deceased) ~ strata, 
    data = gene_df)

n=5, 17 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     2.27     0.237     0.559
strata=LOW  2        2     2.73     0.197     0.559

 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 -0.8455    0.4293   1.1634 -0.727 0.467

Likelihood ratio test=0.59  on 1 df, p=0.4413
n= 5, number of events= 5 
   (17 observations deleted due to missingness)


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

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

significant_genes

[1] "TRAF2"    "TNFRSF1A" "GLUD1"   

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")
  } 
}

TCGA-COAD TRAF2 

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

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

n=8, 14 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5    7.173     0.658      8.18
strata=LOW  3        3    0.827     5.705      8.18

 Chisq= 8.2  on 1 degrees of freedom, p= 0.004 

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

               coef exp(coef)  se(coef)     z     p
strataLOW 2.189e+01 3.219e+09 1.874e+04 0.001 0.999

Likelihood ratio test=8.05  on 1 df, p=0.004549
n= 8, number of events= 8 
   (14 observations deleted due to missingness)


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

TCGA-COAD TNFRSF1A 

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

n=7, 15 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 5        5     2.81      1.70       4.2
strata=LOW  2        2     4.19      1.14       4.2

 Chisq= 4.2  on 1 degrees of freedom, p= 0.04 

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

                coef  exp(coef)   se(coef)      z     p
strataLOW -2.118e+01  6.332e-10  1.860e+04 -0.001 0.999

Likelihood ratio test=6.09  on 1 df, p=0.0136
n= 7, number of events= 7 
   (15 observations deleted due to missingness)


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

TCGA-COAD GLUD1 

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

n=6, 16 observations deleted due to missingness.

            N Observed Expected (O-E)^2/E (O-E)^2/V
strata=HIGH 3        3     1.15     2.976      5.05
strata=LOW  3        3     4.85     0.706      5.05

 Chisq= 5.1  on 1 degrees of freedom, p= 0.02 

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

                coef  exp(coef)   se(coef)      z     p
strataLOW -2.194e+01  2.957e-10  2.480e+04 -0.001 0.999

Likelihood ratio test=5.99  on 1 df, p=0.01438
n= 6, number of events= 6 
   (16 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↩︎