mikelove

load_all("../biocmask")

suppressPackageStartupMessages(library(airway))
data(airway)
rowData(airway)$group <- sort(rep(1:10, length=nrow(airway)))

library(tibble)
suppressPackageStartupMessages(library(dplyr))
suppressPackageStartupMessages(library(purrr))
airway |>

mikelove

library(jsonlite)
library(readr)
dat <- read_csv("IGVF MPRA FG designed sequence metadata - Sheet1.csv")
dat$constraints <- as.list(dat$constraints)
dat$constraints[[1]] <- list(required=TRUE)
dat$constraints[[2]] <- list(required=TRUE)
dat$constraints[[3]] <- list(
  required=TRUE,
  enum=strsplit(sub(".*enum: \\[(.*)\\]","\\1",dat$constraints[[3]]),", ")[[1]]
)

mikelove

---
title: "Differential chromatin accessibility and gene expression"
format: html
---

# Differential expression from RNA-seq

```{r}
#| eval: FALSE
dir <- system.file("extdata", package="macrophage")

mikelove

mikelove

library(plyranges)
library(nullranges)

x <- data.frame(
  seqnames=rep(c("1","2","3"), each=10),
  start=rep(c(0:4, 10:14) * 1000 + 1, times=3),
  width=100) |>
  as_granges()

seqlengths(x) <- c("1"=20123, "2"=20123, "3"=20123)

mikelove

library(SummarizedExperiment)
library(plyranges)

# example data
m <- matrix(rnorm(600), nrow=100)
r1 <- data.frame(seqnames=1, start=1:50 * 100 + 2501,
                 width=5, id1=paste0("u",formatC(1:50,width=3,flag="0"))) |>
  as_granges()
r2 <- data.frame(seqnames=1, start=1:100 * 100 + 1,
                 width=5, id2=paste0("v",formatC(1:100,width=3,flag="0"))) |>

mikelove

library(shiny)
library(UpSetR)
library(dplyr)
library(tidyr)
library(readr)
library(ggplot2)
library(pheatmap)
dat <- read_delim("ancestry_dataframe.tsv")

ui <- fluidPage(

mikelove

mat <- matrix(rnbinom(2e5, mu=100, size=1/.01), ncol=100)

library(DESeq2)

d <- DESeqDataSetFromMatrix(mat, DataFrame(x=rep(1,100)), ~1)
# library size correction, centered log ratio to reference sample
d <- estimateSizeFactors(d)
# variance
d <- estimateDispersionsGeneEst(d)
# trend

mikelove

set.seed(5)

n <- 1000
reps <- 10
rna <- matrix(
  rnbinom(n * reps, mu = 10, size = 100),
  ncol=reps
)
dna <- matrix(
  rnbinom(n * reps, mu = 10, size = 100),

mikelove

# dataframes vs lm S3 vs Bioc S4
# Michael Love
# Nov 1 2023

dat <- data.frame(genotype=c("wt","wt","mut","mut"),
                  count=c(10,20,30,40),
                  score=c(-1.2,0,3.4,-5),
                  gene=c("Abc","Abc","Xyz","Xyz"))
library(tibble)
dat |> as_tibble()