coleoguy

foo <- gsub("T", "U", as.character(read.table("rosalind_rna.txt")[[1]]))
paste(foo)

coleoguy

foo <- unlist(strsplit(as.character(read.table("rosalind_revc.txt")[[1]]),""))
DNA <- c("A", "C", "G", "T")
rcDNA <- c("T", "G", "C", "A")
foo2 <- vector(length = length(foo))
for(i in 1:4){
  foo2[grep(DNA[i], unlist(foo))] <- rcDNA[i]
}
paste(foo2[length(foo2):1], collapse = "", sep = "")

coleoguy

data <- as.numeric(read.table("rosalind_iprb.txt"))
k<-data[1]
m<-data[2]
n<-data[3]
t<-sum(data)
# Sire is AA Dam is anything
t.prob <- k/(t)
# Sire is Aa Dam is AA, Aa, aa
t.prob <- t.prob + (((m/(t))  * (k/(t-1))) +     #Aa x AA  
((m/(t))  * ((m-1)/(t-1)) * .75) +               #Aa x Aa

coleoguy

dna <- read.table("rosalind_hamm.txt")
dna1 <- unlist(strsplit(as.character(dna[1,1]),""))
dna2 <- unlist(strsplit(as.character(dna[2,1]),""))
ham.dist <- 0
for(i in 1:length(dna1)){
  if(dna1[i] != dna2[i]){
    ham.dist <- ham.dist +1
  }
}
cat(ham.dist)

coleoguy

lifespan <- 18
months <- 85
pop <- vector(mode="numeric", length=months)  # this will hold the population each month as we build it up
pop[1:2] <- 1                                 # rabbits take a month to mature so we go ahead and fill in month 1 and 2
for(i in 3:months){                           # this loop will just build our population month by month
  if(i-(lifespan+1) < 0){                     # if we are early on none have died yet this if statement takes care of that
    pop[i] <- pop[i-1]+pop[i-2]-0       
  }
  if(i-(lifespan+1) == 0){                    # this one takes care of the first rabbit dying
    pop[i] <- pop[i-1]+pop[i-2]-1

coleoguy

##  ABBA BABA tests
##  Heath Blackmon
##  [email protected]
##  28 July 2013
##  This file has algorithms found in:

##  Durand, Eric Y., et al. "Testing for ancient admixture between 
##  closely related populations." Molecular biology and evolution 
##  28.8 (2011): 2239-2252.

coleoguy

# the gff3 file that was used as input for this script was downloaded from:
# ftp://ftp.ensemblgenomes.org/pub/metazoa/release-21/gff3/tribolium_castaneum
# on January 10, 2014

import re
## This script is just to parse out the part of the gff file that we
## are interested in, (i.e. lines describing exons or protein coding genes


## Here we specify the name of the gff3 

coleoguy

from Bio import SeqIO  # to deal with the fast files

# lets pull in our exon table
datafile = open('exons.csv', 'r')
data = []
for row in datafile:
    data.append(row.strip().split(','))

# now lets start the process of creating all of our exon-exon sequences
# by first creating a list that has the name we want to assign and the LG and 

coleoguy

setwd("~/Desktop/retrogenes/data/")
gff <- read.csv("exons.csv", header = F, as.is=T) #This is a parsed GFF3 file that contains the lines for exons

# lets get big ones >300 bp

gff <- gff[gff[, 3] - gff[, 2] > 300, ]
setwd("~/Desktop/retrogenes/data/chromosomes") #This is the directory that contains the chromosomes of the genome

library(ape)
seq <- name <- list()

coleoguy

# to construct database from an assembly in the file
# conf.scaf.fa run this in the terminal
# it will create a blast database call confscaf

makeblastdb -in conf.scaf.fa -dbtype nucl -out confscaf

# next we want to blast our large exons against this db
blastn -query=/outputs/300+bpExons.fa -db=/blastDB/confscaf -outfmt='6 qseqid qstart sseqid sstart qlen length pident' -max_target_seqs=2 -out=info

# this produces the lookup table that we can then use to analyze the degree of synteny conservation