sr320

cd /Volumes/Shoelace/Dropbox/Public/nb
wget --no-check-certificate -N http://genefish.wikispaces.com/Sam%27s+Notebook?f=print
mv Sam\'s\+Notebook\?f\=print _sam.html
tail -n +106 /Volumes/Shoelace/Dropbox/Public/nb/_sam.html > /Volumes/Shoelace/Dropbox/Public/nb/__sam.html
sed 's/h1/h3/g' </Volumes/Shoelace/Dropbox/Public/nb/__sam.html> /Volumes/Shoelace/Dropbox/Public/nb/sam.html

sr320

cd /Volumes/Shoelace/Dropbox/Steven/ipython_nb
rsync -avzr *.ipynb /Volumes/Shoelace/Dropbox/Public/ip/nbview/

sr320

{
 "metadata": {
  "name": "",
  "signature": "sha256:a998131beddc729ad529da2eb5f1f69ca26b8ef8a1cfb8a2d294d41b2393c04c"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [

sr320

#!/bin/bash

#script to start the morning right!
#below line not needed if already mounted.
#open afp://usr:password@maxene.fhl.washington.edu/Students

cd /Volumes/Students/diseases/steven
say lets get ready to have some fun!
ipython notebook 

sr320

{
 "metadata": {
  "name": "",
  "signature": "sha256:6a2c4937c9f7b56d5a87f63f909673244ddf55041c4a61246dc2d1054b142b7d"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [

sr320

{
 "metadata": {
  "name": "",
  "signature": "sha256:43e451368edace0e55cb05d7b11cb77dfffa12b132a73a6993fbf7eaeee0826c"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [

sr320

There have not been many posts recently, but that is not to say I have not been doing any science. Much of what I have been doing is numerous burst commits on the Panopea transcriptome paper / project. This can be found @ https://github.com/sr320/paper-pano-go.

You can see all the Jupyter nbs in this sub-directory. I will highlight some of my proudest cell moments here:

Ok the first one is so good I will just give you the whole thing except that I will provide just a little more comments ##

!wc -l analyses/Geoduck-transcriptome-v2.tab

sr320

cat file.txt | awk -F"\t" '{ sum+=$10} END {print sum}'

sr320

SELECT 
  CGI_ID,
  len(sequence)- len(REPLACE(sequence, 'C', '')) as Ccount,
  len(sequence)- len(REPLACE(sequence, 'G', '')) as Gcount,
  (len(sequence)- len(REPLACE(sequence, 'G', ''))) + (len(sequence)- len(REPLACE(sequence, 'C', ''))) as C_Gcount,
  len(sequence)- len(REPLACE(sequence, 'CG', ' ')) as CpGcount,
  len(sequence) as sequence_len,
  sequence
  FROM [sr320@washington.edu].[qDOD_Cgigas_gene_fasta]​

sr320

SELECT [chr]
     , CAST([pos] as INTEGER) as [pos]
     , [strand]
     , [context]
     , CAST([ratio] as FLOAT) as [ratio]
     , CAST([eff_CT_count] as INTEGER) as [eff_CT_count]
     , CAST([C_count] as INTEGER) as [C_count]
     , CAST([CT_count] as INTEGER) as [CT_count]
     , CAST([rev_G_count] as INTEGER) as [rev_G_count]
     , CAST([CI_lower] as FLOAT) as [CI_lower]