dwinter

chars <- c("ABC", NA, "DEF")
(urls <- paste("web-api&id=", chars, sep=""))
## [1] "my-fav-web-api/id=ABC" "my-fav-web-api/id=NA"  "my-fav-web-api/id=DEF"

dwinter

library(ggplot2)

df0 <- data.frame(x=rnorm(100), y=rnorm(100), grp=factor(rep(letters[1:2], each=50)))
p <- ggplot(df0, aes(x,y, colour=grp, alpha=y))
p + geom_point() 



library(RColorBrewer)

dwinter

#calculate Cummings et al (2008) _gsi_ - a meaure of the exlusivity of a 
#predefiend group of leaves in a phylogenetic tree


#example
#
# tr <- rtree(10)
# grp <- paste("t", 1:5, sep="")
# gsi(tr, grp)

dwinter

#
# Code to parse the interesting bits of a PAML results file that contains
# statistics for several trees. Note, this approach contains some hacks that
# are probably specific to multiple-tree CODEML files, Biopython has a module
# for handling other PAML outputs, and it probably a better starting point for
# 'normal' (single tree) input files.
#
# TODO - should clean up handlng of resifues - use @property decorator and
# ._functions to simplify writing/reading.
#

dwinter

"""
Summarise a variable in a BEAST logfile

arguments:
  -h, --help              show this help message and exit
  -f or --file string     whats the name of the BEAST file
  -v or --variable string value you want to summarise                          
  -b or --burnin int      number of states to ignore
  -g                      export graphs to summarise the sample?
  -l                      export a logfile for just this variable

dwinter

entrez_search <- function(dbase, term, retmax=6,...){
    base_url <- "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=%s&term=%s&retmax=%i"
    search <- sprintf(base_url, dbase, term, retmax)
    raw_result <- getURL(search)
    ids <- unlist(getNodeSet(xmlParse(raw_result), "//Id", fun=xmlValue))
    return(as.integer(ids))
}

entrez_fetch <- function(dbase, ids, format, ...){

dwinter

from Bio import Entrez

#Let NCBI know who you are in case you do something stupid :)
Entrez.email = '[email protected]'

search_s ='"ectomycorrhizal root tip" AND "New Zealand"'
handle = Entrez.esearch(db='nucleotide', term=search_s, retmax=100)
ids = Entrez.read(handle)['IdList']

ids[:5]

dwinter

import numpy as np
from scipy import cluster
from matplotlib import pyplot

#fake some data
tests = np.reshape( np.random.uniform(0,100,60), (30,2) )

#plot remaining variance for each value for 'k' between 1,10
initial = [cluster.vq.kmeans(tests,i) for i in range(1,10)]
pyplot.plot([var for (cent,var) in initial])

dwinter

"""
Code written to answer stackoverflow question on substitution matrices:
http://stackoverflow.com/questions/5686211/
"""

from Bio.SubsMat import MatrixInfo

def score_match(pair, matrix):
    """ 
    Return score for a given pair of residues in a give matrix.

dwinter

"""
Code writted to answer this challenge at Biostar:
http://biostar.stackexchange.com/questions/5902/

(This code includes improvements from Brad Chapman)
"""

class ORFFinder:
    """Find the longest ORF in a given sequence
    "seq" is a string, if "start" is not provided any codon can be the start of