| def chunk_seq(seq_name, sequence, chunk_size, chunk_increment): | |
| """ | |
| Chunk up a sequence and return a list of tuples with the chunked up | |
| sequences and new sequence names with the position of the chunk in the | |
| original sequence. | |
| Args: | |
| seq_name: Sequence name. | |
| sequence: Nucleotide or amino acid sequence that is to be chunked up. | |
| chunk_size: Size of chunks (e.g. 30 bp) |
| ## {{{ http://code.activestate.com/recipes/578175/ (r1) | |
| ### hierarchical_clustering.py | |
| #Copyright 2005-2012 J. David Gladstone Institutes, San Francisco California | |
| #Author Nathan Salomonis - [email protected] | |
| #Permission is hereby granted, free of charge, to any person obtaining a copy | |
| #of this software and associated documentation files (the "Software"), to deal | |
| #in the Software without restriction, including without limitation the rights | |
| #to use, copy, modify, merge, publish, distribute, sublicense, and/or sell | |
| #copies of the Software, and to permit persons to whom the Software is furnished |
| from scipy.spatial.distance import * | |
| from scipy.cluster.hierarchy import * | |
| import pandas as pd | |
| import numpy | |
| import matplotlib as plt | |
| from matplotlib.pylab import figure | |
| import pylab as pl | |
| import pp | |
| def num_clusters(hc, d): |
| # This file contains a set of functions for parsing out some useful information | |
| # from BLAST results files saved in BLAST's tabular output format ("-outfmt 6"). | |
| # Biopython is required for reading multifasta files and storing sequences. | |
| from Bio.Seq import Seq | |
| from Bio.SeqRecord import SeqRecord | |
| from Bio.Alphabet import IUPAC | |
| # if all of your genome sequences are within one multifasta file | |
| recs = [rec for rec in SeqIO.parse('all_genomes.fasta', 'fasta')] |
| aln_snps = {} | |
| for aln in aln_files: | |
| recs = [f for f in SeqIO.parse(aln, 'fasta')] | |
| # strain names should be the last dash delimited element in fasta header | |
| strains = [rec.name.split('-')[-1] for rec in recs] | |
| # get a dictionary of strain names and sequences | |
| strain_seq = {rec.name.split('-')[-1]:''.join([nt for nt in rec.seq]) \ | |
| for rec in recs} | |
| # get length of the MSA and check that all of the seq are the same length |
| library(RColorBrewer) | |
| qualitative_colours <- function(n, light=FALSE) { | |
| # Get a specified number of qualitative colours if possible. | |
| # This function will default to a continuous color scheme if there are more | |
| # than 21 colours needed. | |
| # rainbow12equal <- c("#BF4D4D", "#BF864D", "#BFBF4D", "#86BF4D", "#4DBF4D", "#4DBF86", "#4DBFBF", "#4D86BF", "#4D4DBF", "#864DBF", "#BF4DBF", "#BF4D86") | |
| rich12equal <- c("#000040", "#000093", "#0020E9", "#0076FF", "#00B8C2", "#04E466", "#49FB25", "#E7FD09", "#FEEA02", "#FFC200", "#FF8500", "#FF3300") |
| """ | |
| SAM-based reboot | |
| """ | |
| import sys, os, subprocess, itertools, array, datetime, socket, heapq, tempfile | |
| import argparse | |
| import textwrap | |
| import os | |
| import sys | |
| from datetime import timedelta, datetime | |
| # function for reading a multifasta file | |
| # returns a dictionary with sequence headers and nucleotide sequences | |
| def get_seqs_from_fasta(filepath): |
This JS+D3 gist creates a scatterplot with zooming and panning enabled as well as a brush for selecting or deselecting points using the iris dataset within data.tsv.
The "Get Selection" button gets the current selection of points and prints their ids to the JS console (i.e. console.log(selection);).
The "Clear Selection" button clears the current selection.
| /*bitbucket.org dark css theme*/ | |
| body, aside { | |
| background: #222 !important; | |
| background-color: #222 !important; | |
| color: #bbb !important; | |
| } | |
| h1, h2, h3, h4, h5, span { | |
| background-color: transparent !important; | |
| color: #FFC963 !important; |