eclarke

public static String fixLinks(String src, Wiki target) {
    
    // add a marker to all the links so we can iterate through them (except the ones that point to wikipedia)
    String src2 = src.replaceAll("\\[\\[(?!(wikipedia))", "[[%");
    
    try {
        while (src2.contains("[[%")) {
            
            // extract the link text
            int a = src2.indexOf("[[%")+3;  // left inner bound

eclarke

        postParams.add(new BasicNameValuePair("longestOnly","false"));
        postParams.add(new BasicNameValuePair("wholeWordOnly","true"));
        postParams.add(new BasicNameValuePair("filterNumber", "true"));
        postParams.add(new BasicNameValuePair("stopWords","protein,gene,disease,disorder,cell,syndrome,CAN"));
        postParams.add(new BasicNameValuePair("withDefaultStopWords","true"));
        postParams.add(new BasicNameValuePair("isTopWordsCaseSensitive","false"));
        postParams.add(new BasicNameValuePair("mintermSize","3"));
        postParams.add(new BasicNameValuePair("scored", "true"));
        postParams.add(new BasicNameValuePair("withSynonyms","true")); 
        postParams.add(new BasicNameValuePair("ontologiesToExpand", ""));

eclarke

#!/usr/bin/env python

import re
import json
import clint

def import_go(gofile='go.json'):
    try:
        return json.loads(json.load(open(gofile)))
    except IOError:

eclarke

import sqlite3
import multiprocessing

store_results_sql = """ some sql code here """
select_results_sql = """ some other sql code here """

def find_enriched(**kwargs):
    # do some heavy computation task here
    results = enrichment_analysis(**kwargs)
    # sqlite is not ideal for parallel processing, but with a timeout it should be fine

eclarke

#!/usr/bin/env python
"""Usage: python taxonomy_fixer.py [FILE]

Converts an ITS taxonomy file to eliminate taxa marked as unidentified,
swaps [kpcofg]__unidentified;s__Fungi to k__Fungi, and eliminates species
taxa that are simply s__[genus]_sp.

Writes to stdout.
"""
# Erik Clarke <ecl@mail.med.upenn.edu>

eclarke

function toggleproxy {
  # checks to see if SOCKS proxy is enabled
  if [[ $(networksetup -getsocksfirewallproxy Wi-Fi | grep '^Enabled') == "Enabled: No" ]]; then
    networksetup -setsocksfirewallproxystate Wi-Fi on
    echo "SOCKS on!"
      # checks to see if there's an existing SSH tunnel and if not, it starts one
      if [[ -z $(ps aux | grep '[0-9] ssh -D 8080') ]]; then
  	    echo -ne "Don't see a ssh tunnel on 8080 active, starting one now..."
  	    ssh -D 8080 -f -C -q -N USERNAME@HOSTNAME.EDU   # Change this from the defaults!
  	    [[ $? == 0 ]] && echo " success!" || echo " failed :("

eclarke

prop_presence_absence <- function(otu.pa, groups) {
  # Creates a proportional presence-absence melted dataframe suitable for use in
  # ggplot heatmaps to show varying within-group proportions of species.
  # 
  # Args:
  #   otu.pa: Matrix of presence-absence data. Columns are samples, rows are 
  #           species.
  #   groups: Grouping data frame. A column named "SampleID" should be unique 
  #           list of sample identifiers that match the column names of otu.pa. 
  #           The other column, named "group", should correspond to the group 

eclarke

# Multiple plot function
#
# ggplot objects can be passed in ..., or to plotlist (as a list of ggplot objects)
# - cols:   Number of columns in layout
# - layout: A matrix specifying the layout. If present, 'cols' is ignored.
#
# If the layout is something like matrix(c(1,2,3,3), nrow=2, byrow=TRUE),
# then plot 1 will go in the upper left, 2 will go in the upper right, and
# 3 will go all the way across the bottom.
#

eclarke

plot_ggheatmap <- function(obj, n=nrow(obj), norm=TRUE, log=TRUE, 
                           colnames.in.pdata="NewSampleID", 
                           col.labels=NULL,
                           row.labels=NULL,
                           facet.by=NULL,
                           annotate.cols=NULL,
                           dendrogram=FALSE,
                           col.annotation.offset=1,
                           col.annotation.width=4) {
  ##

eclarke

(defun ensure-in-vc-or-checkin ()
  (interactive)
  (if (file-exists-p (format "%s" (buffer-file-name)))
      (progn (vc-next-action nil) (message "Committed"))
    (ding) (message "File not checked in.")))

(defun export-bibtex ()
  "Exports Papers library using a custom applescript."
  (interactive)
  (message "Exporting papers library...")