mikelove

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

ui <- fluidPage(
    titlePanel("IGVF Ancestry Dashboard"),

mikelove

n <- 200
m <- 40
set.seed(1)
x <- runif(n, -1, 1)
library(rafalib)
bigpar(2,2,mar=c(3,3,3,1))
library(RColorBrewer)
cols <- brewer.pal(11, "Spectral")[as.integer(cut(x, 11))]
plot(x, rep(0,n), ylim=c(-1,1), yaxt="n", xlab="", ylab="", 
     col=cols, pch=20, main="underlying data")

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

RUNS, = glob_wildcards("fastq/{run}_1.fastq.gz")

SALMON = "/proj/milovelab/bin/salmon-1.4.0_linux_x86_64/bin/salmon"

ANNO = "/proj/milovelab/anno"

rule all:
    input: expand("quants/{run}/quant.sf", run=RUNS)

rule salmon_index:

mikelove

library(splines)
library(DESeq2)

# make some demo data
dds <- makeExampleDESeqDataSet(n=100, m=40)
dds$condition <- sort(runif(40))
# make one gene where expression has a curve shape (just for demo)
s_shape <- round(500 * sin(dds$condition*2*pi) + 1000 + rnorm(40,0,50))
mode(s_shape) <- "integer"
counts(dds)[1,] <- s_shape

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()

mikelove

library(palmerpenguins) # penguins!
library(ggplot2) # "grammar of graphics" plots
suppressPackageStartupMessages(
  library(dplyr) # data pliers
)

penguins |> 
  slice(1:3) |>
  select(species, island)

mikelove

---
title: "Toy tree example for collapsing"
author: "Michael Love"
---
  
Example data with 20 inferential replicates, here we just have 1
sample per condition and we calculate the LFC at each level of the
tree.

From the below simulation setup (see first chunk), the true DE signal

mikelove

library(plyranges)
library(readr)

bindata <- read_tsv("bindata.40000.hg19.tsv.gz")

fire <- read_bed("fire-adult-hg19.txt")

# not necessary, but nice to have
si <- Seqinfo(genome="hg19")
si <- keepStandardChromosomes(si)