{ "cells": [ { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": false }, "outputs": [], "source": [ "from __future__ import print_function\n", "import dendropy\n", "from dendropy import popgenstat" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Genes" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": false }, "outputs": [], "source": [ "import os\n", "from collections import OrderedDict\n", "genes_species = OrderedDict()\n", "my_species = ['RESTV', 'SUDV']\n", "my_genes = ['NP', 'L', 'VP35', 'VP40']\n", "\n", "for name in my_genes:\n", " gene_name = name.split('.')[0]\n", " char_mat = dendropy.DnaCharacterMatrix.get_from_path('%s_align.fasta' % name, 'fasta')\n", " genes_species[gene_name] = {}\n", " \n", " for species in my_species:\n", " genes_species[gene_name][species] = dendropy.DnaCharacterMatrix()\n", " for taxon, char_map in char_mat.items():\n", " species = taxon.label.split('_')[0]\n", " if species in my_species:\n", " genes_species[gene_name][species].extend_map({taxon: char_map})" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "
\n", " | seg_sites (RESTV) | \n", "nuc_div (RESTV) | \n", "taj_d (RESTV) | \n", "wat_theta (RESTV) | \n", "seg_sites (SUDV) | \n", "nuc_div (SUDV) | \n", "taj_d (SUDV) | \n", "wat_theta (SUDV) | \n", "
---|---|---|---|---|---|---|---|---|
NP | \n", "113 | \n", "0.020659 | \n", "-0.482275 | \n", "49.489051 | \n", "118 | \n", "0.029630 | \n", "1.203522 | \n", "56.64 | \n", "
L | \n", "288 | \n", "0.018143 | \n", "-0.295386 | \n", "126.131387 | \n", "282 | \n", "0.024193 | \n", "1.412350 | \n", "135.36 | \n", "
VP35 | \n", "42 | \n", "0.017099 | \n", "-0.530330 | \n", "18.394161 | \n", "50 | \n", "0.027761 | \n", "1.069061 | \n", "24.00 | \n", "
VP40 | \n", "61 | \n", "0.026155 | \n", "-0.188135 | \n", "26.715328 | \n", "41 | \n", "0.023517 | \n", "1.269160 | \n", "19.68 | \n", "