vsbuffalo

library(tidyverse)
library(MASS)

pcov <- function(x) {
  xs <- scale(x, scale=FALSE)
  dd <- as.integer(!is.na(x))
  dim(dd)  <- dim(x)
  denom <- (t(dd) %*% dd) - 1L
  no_obs <- denom == 0L
  xs[is.na(xs)] <- 0

vsbuffalo

Title: Using Bioconductor to Analyze your 23andme Data

Bioconductor is one of the open source projects of which I am most
fond. The documentation is excellent, the community wonderful, the
development fast-paced, and the software *very* well written.

There's a new package in the development branch (due to be released as
2.10 very soon) called `gwascat`. `gwascat` is a package that serves
as an interface to the [NHGRI's](http://www.genome.gov/) database of
genome-wide association studies.

vsbuffalo

# Thanks https://github.com/EBI-predocs/latex-thesis/blob/master/Makefile for
# some tips
LATEXMK = latexmk -xelatex

# CONFIG
target = manuscript
references = bib.bib

# SETUP
includes := $(shell ls *.tex) ${references}

vsbuffalo

library(purrr)

foo <- function(x) {
  return(function(y) {
    y + x
  })
}

args <- list(1, 2)
foos_map <- map(args, foo)

vsbuffalo

# This file is NOT licensed under the GPLv3, which is the license for the rest
# of YouCompleteMe.
#
# Here's the license text for this file:
#
# This is free and unencumbered software released into the public domain.
#
# Anyone is free to copy, modify, publish, use, compile, sell, or
# distribute this software, either in source code form or as a compiled
# binary, for any purpose, commercial or non-commercial, and by any

vsbuffalo

var fs = require('fs');
var d3 = require('d3');
var jsdom = require('node-jsdom');
var xmlserializer = require('xmlserializer');

var margin = {top: 2, right: 4, bottom: 2, left: 4};
var width = 200 - margin.left - margin.right,
    height = 14 - margin.top - margin.bottom;

vsbuffalo

library(GenomicRanges)

summarizeByTile <-
# given a GRanges (or some sort of ranged data) object `x`, and a
# *corresponding* vector values to summarize `y` (these *must*
# correspond), calculate the summary per tile with the function `fun`.
# Note: this is still beta; wider tests coming, use with caution.
function(x, y, tiles, fun, mcol_name="y") {
    stopifnot(length(x) == length(y))

vsbuffalo

from __future__ import division
from collections import Counter
from math import log

def entropy(seq, unit="bit"):
    """
    Returns entropy of DNA sequence.

    The entropy formula is: 
    entropy = -sum_i (log(p_i) * p_i)

vsbuffalo

"""
entropy.py

Calculate entropy of a given list.
"""
from math import log, log10
from collections import Counter
import pdb

def entropy(x, logfun=lambda x: log(x, 2)):

vsbuffalo

import sys
from readfq import readfq
from itertools import combinations
from datetime import datetime

def num_shared(seq_a, seq_b, consensus_seq):
    """
    Given two alignment sequences in multiple alignment FASTA format,
    calculate the number of shared SNPs (for minor alleles only, not 
    in consensus).