dBenedek

#!/bin/bash

###############################################################################
# Split PDF to the preferred PDFs by the specified pages                      #
###############################################################################

# Benedek Danko

# Variables:
input_file="$1"

dBenedek

library("tidyverse")
library("survival")
library("survminer")


# Fit model on survival data:
fit01 <- survfit(Surv(time=Time_survival, 
                      event=Status_survival) ~ as.factor(group), 
                 data = clin_dat)
fit01_cph <- coxph(Surv(time=Time_survival, 

dBenedek

library("tidyverse")
library("pheatmap")
library("fgsea")


# Load gene set data:
kegg_gs <- gmtPathways("/home/rstudio/san1/BD/datasets/kegg_metabolic_human_20211026.gmt")
pathways <- data.frame(name=names(kegg_gs)) %>% 
   mutate(category=str_replace(as.character(name), "^\\d+\\s", ""),
          category=str_replace(as.character(category), "\\s-\\s\\d+.+", "")) %>% 

dBenedek

library("GSVA")
library("fgsea")
library("tidyverse")


# Perform DESeq2 normalization on count data:
dds <- DESeqDataSetFromMatrix(countData = as.matrix(round(counts)), 
                              colData = col_dat, 
                              design = ~ 1)
dds <- estimateSizeFactors(dds)

dBenedek

library("tidyverse")
library("DESeq2")


# Create DESeq2 object:
dds <- DESeqDataSetFromMatrix(count_data,
                              colData = col_data,
                              design = ~ group)
# Run DE:
dds <- DESeq(dds)

dBenedek

# Example of the Mann-Whitney U Test
from scipy.stats import mannwhitneyu
data1 = [0.873, 2.817, 0.121, -0.945, -0.055, -1.436, 0.360, -1.478, -1.637, -1.869]
data2 = [1.142, -0.432, -0.938, -0.729, -0.846, -0.157, 0.500, 1.183, -1.075, -0.169]
stat, p = mannwhitneyu(data1, data2)
print('stat=%.3f, p=%.3f' % (stat, p))
if p > 0.05:
	print('Probably the same distribution')
else:
	print('Probably different distributions')

dBenedek

# Example of the Student's t-test
from scipy.stats import ttest_ind
data1 = [0.873, 2.817, 0.121, -0.945, -0.055, -1.436, 0.360, -1.478, -1.637, -1.869]
data2 = [1.142, -0.432, -0.938, -0.729, -0.846, -0.157, 0.500, 1.183, -1.075, -0.169]
stat, p = ttest_ind(data1, data2)
print('stat=%.3f, p=%.3f' % (stat, p))
if p > 0.05:
	print('Probably the same distribution')
else:
	print('Probably different distributions')

dBenedek

# Example of the Augmented Dickey-Fuller unit root test
from statsmodels.tsa.stattools import adfuller
data = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
stat, p, lags, obs, crit, t = adfuller(data)
print('stat=%.3f, p=%.3f' % (stat, p))
if p > 0.05:
	print('Probably not Stationary')
else:
	print('Probably Stationary')
    

dBenedek

# Example of the Pearson's Correlation test
from scipy.stats import pearsonr
data1 = [0.873, 2.817, 0.121, -0.945, -0.055, -1.436, 0.360, -1.478, -1.637, -1.869]
data2 = [0.353, 3.517, 0.125, -7.545, -0.555, -1.536, 3.350, -1.578, -3.537, -1.579]
stat, p = pearsonr(data1, data2)
print('stat=%.3f, p=%.3f' % (stat, p))
if p > 0.05:
	print('Probably independent')
else:
	print('Probably dependent')

dBenedek

# Example of the Shapiro-Wilk Normality Test
from scipy.stats import shapiro
data = [0.873, 2.817, 0.121, -0.945, -0.055, -1.436, 0.360, -1.478, -1.637, -1.869]
stat, p = shapiro(data)
print('stat=%.3f, p=%.3f' % (stat, p))
if p > 0.05:
	print('Probably Gaussian')
else:
	print('Probably not Gaussian')