mgalardini · January 2, 2016 16:49
diff --git a/bacterial_genomes_report..ipynb b/bacterial_genomes_report..ipynb
 {
 "metadata": {
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "* **How many bacterial genomes are available?**\n",
      "\n",
      "* **What is the complete/draft ratio for each species?**\n",
      "\n",
      "Step 1: download data from NCBI FTP\n",
      "-----------------------------------\n",
      "\n",
      "    curl ftp://ftp.ncbi.nih.gov/genomes/Bacteria/ -l -s | grep \"uid\" | awk -F_ '{print $1\"_\"$2\" complete\"}' > genomes_2014_01_08\n",
      "    curl ftp://ftp.ncbi.nih.gov/genomes/Bacteria_DRAFT/ -l -s | grep \"uid\" | awk -F_ '{print $1\"_\"$2\" draft\"}' >> genomes_2014_01_08\n",
      "    \n",
      "Step 2: crunch some numbers\n",
      "---------------------------"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "genomes = {}\n",
      "\n",
      "for l in open('genomes_2014_01_08'):\n",
      "    species, kind = l.strip().split()\n",
      "    genomes[species] = genomes.get(species, [0, 0])\n",
      "    if kind == 'complete':\n",
      "        genomes[species][0] += 1\n",
      "    elif kind == 'draft':\n",
      "        genomes[species][1] += 1\n",
      "    else:\n",
      "        raise ValueError('Duh? %s'%kind)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print('Number of complete genomes: %d'%sum([genomes[x][0] for x in genomes]))\n",
      "print('Number of draft genomes: %d'%sum([genomes[x][1] for x in genomes]))\n",
      "print('Complete genomes ratio: %.2f%%'%( sum([genomes[x][0] for x in genomes])*100.0 / sum([sum(genomes[x]) for x in genomes]) )) \n",
      "\n",
      "print('\\n=======\\n')\n",
      "\n",
      "print('Number of sequenced species: %d'%len(genomes))\n",
      "comparative = len(filter(lambda x: sum(genomes[x])>1, genomes))\n",
      "print('Number of species having more than one genome sequenced: %d (%.2f%%)'%\n",
      "      (comparative, float(comparative)*100/len(genomes)))\n",
      "referenced = len(filter(lambda x: sum(genomes[x])>1 and genomes[x][0]>0, genomes))\n",
      "print('Number of species w/ multiple genomes and at least one complete reference: %d (%.2f%%)'%\n",
      "      (referenced, float(referenced)*100/len(genomes)))\n",
      "onecomplete = len(filter(lambda x: genomes[x][0]>0, genomes))\n",
      "print('Number of species w/ at least one complete reference: %d (%.2f%%)'%\n",
      "      (onecomplete, float(onecomplete)*100/len(genomes)))\n",
      "\n",
      "print('\\n=======\\n')\n",
      "\n",
      "print('Average number of genomes per species: %.2f'%( np.array([sum(genomes[x]) for x in genomes]).mean() ))\n",
      "print('Considering only the species having more than one genome: %.2f'%\n",
      "      np.array([sum(genomes[x]) for x in filter(lambda x: sum(genomes[x])>1 ,genomes)]).mean())\n",
      "\n",
      "print('\\n=======\\n')\n",
      "\n",
      "print('Average complete genomes ratio: %.2f%%'%\n",
      "          ( np.array( [float(genomes[x][0])*100/sum(genomes[x]) for x in genomes] ).mean() ))\n",
      "print('Considering only the species having more than one genome: %.2f%%'%\n",
      "      ( np.array( [float(genomes[x][0])*100/sum(genomes[x]) for x in filter(lambda x: sum(genomes[x])>1 ,genomes)] ).mean() ))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Number of complete genomes: 2774\n",
        "Number of draft genomes: 6970\n",
        "Complete genomes ratio: 28.47%"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "\n",
        "=======\n",
        "\n",
        "Number of sequenced species: 3376\n",
        "Number of species having more than one genome sequenced: 715 (21.18%)"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "Number of species w/ multiple genomes and at least one complete reference: 484 (14.34%)"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "Number of species w/ at least one complete reference: 1483 (43.93%)\n",
        "\n",
        "=======\n",
        "\n",
        "Average number of genomes per species: 2.89"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "Considering only the species having more than one genome: 9.91"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "\n",
        "=======\n",
        "\n",
        "Average complete genomes ratio: 37.85%"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "Considering only the species having more than one genome: 39.01%"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print('Species having more than one genome sequenced and at least one complete genome sequence\\n')\n",
      "\n",
      "for species in sorted(filter(lambda x: sum(genomes[x])>1 and genomes[x][0]>0, genomes)):\n",
      "    print species"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Species having more than one genome sequenced and at least one complete genome sequence\n",
        "\n",
        "Acetobacter_pasteurianus"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "Achromobacter_xylosoxidans\n",
        "Acidithiobacillus_caldus\n",
        "Acidithiobacillus_ferrooxidans\n",
        "Acidovorax_citrulli\n",
        "Aciduliprofundum_boonei\n",
        "Acinetobacter_baumannii\n",
        "Acinetobacter_calcoaceticus\n",
        "Actinobacillus_pleuropneumoniae\n",
        "Aeromonas_hydrophila\n",
        "Aeromonas_salmonicida\n",
        "Aeromonas_veronii\n",
        "Aggregatibacter_actinomycetemcomitans\n",
        "Aggregatibacter_aphrophilus\n",
        "Alicycliphilus_denitrificans\n",
        "Alicyclobacillus_acidocaldarius\n",
        "Alteromonas_macleodii\n",
        "Amycolatopsis_mediterranei\n",
        "Anaerococcus_prevotii\n",
        "Anaeromyxobacter_dehalogenans\n",
        "Anaplasma_marginale\n",
        "Anaplasma_phagocytophilum\n",
        "Anoxybacillus_flavithermus\n",
        "Arcobacter_butzleri\n",
        "Arthrospira_platensis\n",
        "Azotobacter_vinelandii\n",
        "Bacillus_1NLA3E\n",
        "Bacillus_amyloliquefaciens\n",
        "Bacillus_anthracis\n",
        "Bacillus_atrophaeus\n",
        "Bacillus_cereus\n",
        "Bacillus_coagulans\n",
        "Bacillus_licheniformis\n",
        "Bacillus_megaterium\n",
        "Bacillus_pumilus\n",
        "Bacillus_subtilis\n",
        "Bacillus_thuringiensis\n",
        "Bacteroides_fragilis\n",
        "Bacteroides_uniformis\n",
        "Bacteroides_vulgatus\n",
        "Bacteroides_xylanisolvens\n",
        "Bartonella_bacilliformis\n",
        "Bartonella_quintana\n",
        "Bartonella_vinsonii\n",
        "Bdellovibrio_bacteriovorus\n",
        "Bifidobacterium_adolescentis\n",
        "Bifidobacterium_animalis\n",
        "Bifidobacterium_bifidum\n",
        "Bifidobacterium_breve\n",
        "Bifidobacterium_dentium\n",
        "Bifidobacterium_longum\n",
        "Blattabacterium_\n",
        "Bordetella_bronchiseptica\n",
        "Bordetella_parapertussis\n",
        "Bordetella_pertussis\n",
        "Borrelia_afzelii\n",
        "Borrelia_burgdorferi\n",
        "Borrelia_garinii\n",
        "Borrelia_valaisiana\n",
        "Brachyspira_pilosicoli\n",
        "Bradyrhizobium_ORS\n",
        "Bradyrhizobium_japonicum\n",
        "Brevibacillus_brevis\n",
        "Brucella_abortus\n",
        "Brucella_canis\n",
        "Brucella_ceti\n",
        "Brucella_melitensis\n",
        "Brucella_pinnipedialis\n",
        "Brucella_suis\n",
        "Buchnera_aphidicola\n",
        "Burkholderia_ambifaria\n",
        "Burkholderia_cenocepacia\n",
        "Burkholderia_gladioli\n",
        "Burkholderia_glumae\n",
        "Burkholderia_mallei\n",
        "Burkholderia_multivorans\n",
        "Burkholderia_pseudomallei\n",
        "Burkholderia_thailandensis\n",
        "Calothrix_PCC\n",
        "Campylobacter_coli\n",
        "Campylobacter_concisus\n",
        "Campylobacter_curvus\n",
        "Campylobacter_fetus\n",
        "Campylobacter_jejuni\n",
        "Candidatus_Arthromitus\n",
        "Candidatus_Blochmannia\n",
        "Candidatus_Carsonella\n",
        "Candidatus_Hamiltonella\n",
        "Candidatus_Kinetoplastibacterium\n",
        "Candidatus_Liberibacter\n",
        "Candidatus_Moranella\n",
        "Candidatus_Mycoplasma\n",
        "Candidatus_Nitrosopumilus\n",
        "Candidatus_Pelagibacter\n",
        "Candidatus_Phytoplasma\n",
        "Candidatus_Portiera\n",
        "Candidatus_Sulcia\n",
        "Candidatus_Tremblaya\n",
        "Capnocytophaga_ochracea\n",
        "Carnobacterium_maltaromaticum\n",
        "Caulobacter_crescentus\n",
        "Chlamydia_muridarum\n",
        "Chlamydia_pecorum\n",
        "Chlamydia_psittaci\n",
        "Chlamydia_trachomatis\n",
        "Chlamydophila_abortus\n",
        "Chlamydophila_pneumoniae\n",
        "Chlamydophila_psittaci\n",
        "Chlorobium_phaeobacteroides\n",
        "Clavibacter_michiganensis\n",
        "Clostridium_acetobutylicum\n",
        "Clostridium_beijerinckii\n",
        "Clostridium_botulinum\n",
        "Clostridium_cellulovorans\n",
        "Clostridium_difficile\n",
        "Clostridium_kluyveri\n",
        "Clostridium_pasteurianum\n",
        "Clostridium_perfringens\n",
        "Clostridium_saccharoperbutylacetonicum\n",
        "Clostridium_stercorarium\n",
        "Clostridium_tetani\n",
        "Clostridium_thermocellum\n",
        "Comamonas_testosteroni\n",
        "Corynebacterium_aurimucosum\n",
        "Corynebacterium_diphtheriae\n",
        "Corynebacterium_efficiens\n",
        "Corynebacterium_glutamicum\n",
        "Corynebacterium_jeikeium\n",
        "Corynebacterium_pseudotuberculosis\n",
        "Corynebacterium_ulcerans\n",
        "Corynebacterium_urealyticum\n",
        "Coxiella_burnetii\n",
        "Cronobacter_sakazakii\n",
        "Cronobacter_turicensis\n",
        "Cupriavidus_necator\n",
        "Cupriavidus_taiwanensis\n",
        "Cyanothece_ATCC\n",
        "Cyanothece_PCC\n",
        "Dehalococcoides_mccartyi\n",
        "Desulfitobacterium_hafniense\n",
        "Desulfotomaculum_gibsoniae\n",
        "Desulfovibrio_africanus\n",
        "Desulfovibrio_desulfuricans\n",
        "Desulfovibrio_magneticus\n",
        "Desulfovibrio_vulgaris\n",
        "Dickeya_dadantii\n",
        "Dickeya_zeae\n",
        "Ectothiorhodospiraceae_bacterium\n",
        "Edwardsiella_tarda\n",
        "Ehrlichia_chaffeensis\n",
        "Ehrlichia_ruminantium\n",
        "Enterobacter_aerogenes\n",
        "Enterobacter_cloacae\n",
        "Enterobacteriaceae_bacterium\n",
        "Enterococcus_casseliflavus\n",
        "Enterococcus_faecalis\n",
        "Enterococcus_faecium\n",
        "Erwinia_amylovora\n",
        "Erwinia_pyrifoliae\n",
        "Erysipelothrix_rhusiopathiae\n",
        "Escherichia_blattae\n",
        "Escherichia_coli\n",
        "Escherichia_fergusonii\n",
        "Eubacterium_rectale\n",
        "Eubacterium_siraeum\n",
        "Faecalibacterium_prausnitzii\n",
        "Ferroplasma_acidarmanus\n",
        "Fibrobacter_succinogenes\n",
        "Finegoldia_magna\n",
        "Flavobacteriaceae_bacterium\n",
        "Flavobacteriales_bacterium\n",
        "Francisella_cf\n",
        "Francisella_noatunensis\n",
        "Francisella_novicida\n",
        "Francisella_philomiragia\n",
        "Francisella_tularensis\n",
        "Fusobacterium_3\n",
        "Fusobacterium_4\n",
        "Fusobacterium_nucleatum\n",
        "Gallibacterium_anatis\n",
        "Gardnerella_vaginalis\n",
        "Geitlerinema_PCC\n",
        "Geobacter_metallireducens\n",
        "Geobacter_sulfurreducens\n",
        "Glaciecola_psychrophila\n",
        "Gloeocapsa_PCC\n",
        "Gluconacetobacter_diazotrophicus\n",
        "Gluconobacter_oxydans\n",
        "Gordonia_polyisoprenivorans\n",
        "Haemophilus_influenzae\n",
        "Haemophilus_parainfluenzae\n",
        "Haemophilus_parasuis\n",
        "Haemophilus_somnus\n",
        "Halalkalicoccus_jeotgali\n",
        "Haloarcula_hispanica\n",
        "Haloferax_mediterranei\n",
        "Haloferax_volcanii\n",
        "Halogeometricum_borinquense\n",
        "Haloquadratum_walsbyi\n",
        "Halorhabdus_tiamatea\n",
        "Helicobacter_bizzozeronii\n",
        "Helicobacter_cetorum\n",
        "Helicobacter_cinaedi\n",
        "Helicobacter_pylori\n",
        "Herbaspirillum_seropedicae\n",
        "Hydrogenobacter_thermophilus\n",
        "Hyphomicrobium_denitrificans\n",
        "Idiomarina_loihiensis\n",
        "Ketogulonicigenium_vulgare\n",
        "Klebsiella_oxytoca\n",
        "Klebsiella_pneumoniae\n",
        "Lactobacillus_acidophilus\n",
        "Lactobacillus_amylovorus\n",
        "Lactobacillus_brevis\n",
        "Lactobacillus_buchneri\n",
        "Lactobacillus_casei\n",
        "Lactobacillus_crispatus\n",
        "Lactobacillus_delbrueckii\n",
        "Lactobacillus_fermentum\n",
        "Lactobacillus_gasseri\n",
        "Lactobacillus_helveticus\n",
        "Lactobacillus_johnsonii\n",
        "Lactobacillus_paracasei\n",
        "Lactobacillus_plantarum\n",
        "Lactobacillus_reuteri\n",
        "Lactobacillus_rhamnosus\n",
        "Lactobacillus_ruminis\n",
        "Lactobacillus_salivarius\n",
        "Lactococcus_garvieae\n",
        "Lactococcus_lactis\n",
        "Lawsonia_intracellularis\n",
        "Legionella_longbeachae\n",
        "Legionella_pneumophila\n",
        "Leifsonia_xyli\n",
        "Leptolyngbya_PCC\n",
        "Leptospira_biflexa\n",
        "Leptospira_borgpetersenii\n",
        "Leptospira_interrogans\n",
        "Leuconostoc_carnosum\n",
        "Leuconostoc_citreum\n",
        "Leuconostoc_gelidum\n",
        "Leuconostoc_mesenteroides\n",
        "Listeria_innocua\n",
        "Listeria_ivanovii\n",
        "Listeria_monocytogenes\n",
        "Listeria_seeligeri\n",
        "Mannheimia_haemolytica\n",
        "Meiothermus_ruber\n",
        "Melissococcus_plutonius\n",
        "Mesoplasma_florum\n",
        "Methanobrevibacter_smithii\n",
        "Methanococcus_maripaludis\n",
        "Methanosarcina_mazei\n",
        "Methylobacterium_extorquens\n",
        "Methylococcus_capsulatus\n",
        "Micrococcus_luteus\n",
        "Microcystis_aeruginosa\n",
        "Mobiluncus_curtisii\n",
        "Moraxella_catarrhalis\n",
        "Morganella_morganii\n",
        "Mycobacterium_abscessus\n",
        "Mycobacterium_avium\n",
        "Mycobacterium_bovis\n",
        "Mycobacterium_canettii\n",
        "Mycobacterium_gilvum\n",
        "Mycobacterium_intracellulare\n",
        "Mycobacterium_kansasii\n",
        "Mycobacterium_leprae\n",
        "Mycobacterium_massiliense\n",
        "Mycobacterium_rhodesiae\n",
        "Mycobacterium_smegmatis\n",
        "Mycobacterium_tuberculosis\n",
        "Mycoplasma_agalactiae\n",
        "Mycoplasma_bovis\n",
        "Mycoplasma_fermentans\n",
        "Mycoplasma_gallisepticum\n",
        "Mycoplasma_genitalium\n",
        "Mycoplasma_haemofelis\n",
        "Mycoplasma_hyopneumoniae\n",
        "Mycoplasma_hyorhinis\n",
        "Mycoplasma_leachii\n",
        "Mycoplasma_mycoides\n",
        "Mycoplasma_pneumoniae\n",
        "Mycoplasma_putrefaciens\n",
        "Mycoplasma_suis\n",
        "Myxococcus_xanthus\n",
        "Natrinema_pellirubrum\n",
        "Natronobacterium_gregoryi\n",
        "Neisseria_gonorrhoeae\n",
        "Neisseria_lactamica\n",
        "Neisseria_meningitidis\n",
        "Nitrosococcus_oceani\n",
        "Nocardia_brasiliensis\n",
        "Nocardia_cyriacigeorgica\n",
        "Nocardiopsis_alba\n",
        "Nostoc_PCC\n",
        "Ochrobactrum_anthropi\n",
        "Oenococcus_oeni\n",
        "Oligotropha_carboxidovorans\n",
        "Orientia_tsutsugamushi\n",
        "Oscillatoria_PCC\n",
        "Paenibacillus_larvae\n",
        "Paenibacillus_mucilaginosus\n",
        "Paenibacillus_polymyxa\n",
        "Pantoea_ananatis\n",
        "Parabacteroides_distasonis\n",
        "Parachlamydia_acanthamoebae\n",
        "Pasteurella_multocida\n",
        "Pectobacterium_carotovorum\n",
        "Pectobacterium_wasabiae\n",
        "Pediococcus_pentosaceus\n",
        "Phaeobacter_gallaeciensis\n",
        "Photobacterium_profundum\n",
        "Polynucleobacter_necessarius\n",
        "Porphyromonas_asaccharolytica\n",
        "Porphyromonas_gingivalis\n",
        "Prevotella_dentalis\n",
        "Prevotella_denticola\n",
        "Prevotella_melaninogenica\n",
        "Prevotella_oral\n",
        "Prochlorococcus_marinus\n",
        "Propionibacterium_acnes\n",
        "Propionibacterium_avidum\n",
        "Proteus_mirabilis\n",
        "Providencia_stuartii\n",
        "Pseudoalteromonas_haloplanktis\n",
        "Pseudomonas_aeruginosa\n",
        "Pseudomonas_fluorescens\n",
        "Pseudomonas_mendocina\n",
        "Pseudomonas_monteilii\n",
        "Pseudomonas_putida\n",
        "Pseudomonas_stutzeri\n",
        "Pseudomonas_syringae\n",
        "Pyrococcus_furiosus\n",
        "Rahnella_aquatilis\n",
        "Ralstonia_eutropha\n",
        "Ralstonia_pickettii\n",
        "Ralstonia_solanacearum\n",
        "Rhizobium_etli\n",
        "Rhizobium_leguminosarum\n",
        "Rhodobacter_sphaeroides\n",
        "Rhodococcus_equi\n",
        "Rhodococcus_erythropolis\n",
        "Rhodococcus_opacus\n",
        "Rhodococcus_pyridinivorans\n",
        "Rhodopirellula_baltica\n",
        "Rhodopseudomonas_palustris\n",
        "Rhodospirillum_rubrum\n",
        "Rhodothermus_marinus\n",
        "Rickettsia_australis\n",
        "Rickettsia_bellii\n",
        "Rickettsia_canadensis\n",
        "Rickettsia_conorii\n",
        "Rickettsia_japonica\n",
        "Rickettsia_massiliae\n",
        "Rickettsia_prowazekii\n",
        "Rickettsia_rickettsii\n",
        "Rickettsia_slovaca\n",
        "Rickettsia_typhi\n",
        "Riemerella_anatipestifer\n",
        "Roseburia_intestinalis\n",
        "Rothia_dentocariosa\n",
        "Rothia_mucilaginosa\n",
        "Rubrivivax_gelatinosus\n",
        "Ruminococcus_albus\n",
        "Saccharopolyspora_erythraea\n",
        "Salinibacter_ruber\n",
        "Salinispora_arenicola\n",
        "Salinispora_tropica\n",
        "Salmonella_bongori\n",
        "Salmonella_enterica\n",
        "Saprospira_grandis\n",
        "Selenomonas_sputigena\n",
        "Serratia_marcescens\n",
        "Serratia_odorifera\n",
        "Serratia_plymuthica\n",
        "Serratia_symbiotica\n",
        "Shewanella_MR\n",
        "Shewanella_baltica\n",
        "Shewanella_putrefaciens\n",
        "Shigella_boydii\n",
        "Shigella_dysenteriae\n",
        "Shigella_flexneri\n",
        "Shigella_sonnei\n",
        "Singulisphaera_acidiphila\n",
        "Sinorhizobium_fredii\n",
        "Sinorhizobium_medicae\n",
        "Sinorhizobium_meliloti\n",
        "Sorangium_cellulosum\n",
        "Sphingomonas_wittichii\n",
        "Spirochaeta_thermophila\n",
        "Staphylococcus_aureus\n",
        "Staphylococcus_epidermidis\n",
        "Staphylococcus_haemolyticus\n",
        "Staphylococcus_lugdunensis\n",
        "Staphylococcus_pseudintermedius\n",
        "Staphylococcus_saprophyticus\n",
        "Staphylococcus_warneri\n",
        "Stenotrophomonas_maltophilia\n",
        "Stigmatella_aurantiaca\n",
        "Streptococcus_I\n",
        "Streptococcus_agalactiae\n",
        "Streptococcus_anginosus\n",
        "Streptococcus_constellatus\n",
        "Streptococcus_dysgalactiae\n",
        "Streptococcus_equi\n",
        "Streptococcus_gallolyticus\n",
        "Streptococcus_infantarius\n",
        "Streptococcus_iniae\n",
        "Streptococcus_intermedius\n",
        "Streptococcus_mitis\n",
        "Streptococcus_mutans\n",
        "Streptococcus_oralis\n",
        "Streptococcus_parasanguinis\n",
        "Streptococcus_parauberis\n",
        "Streptococcus_pneumoniae\n",
        "Streptococcus_pseudopneumoniae\n",
        "Streptococcus_pyogenes\n",
        "Streptococcus_salivarius\n",
        "Streptococcus_sanguinis\n",
        "Streptococcus_suis\n",
        "Streptococcus_thermophilus\n",
        "Streptomyces_albus\n",
        "Streptomyces_cattleya\n",
        "Streptomyces_hygroscopicus\n",
        "Sulfobacillus_acidophilus\n",
        "Sulfolobus_acidocaldarius\n",
        "Sulfolobus_islandicus\n",
        "Sulfolobus_solfataricus\n",
        "Sulfuricella_denitrificans\n",
        "Synechococcus_JA\n",
        "Synechococcus_PCC\n",
        "Synechococcus_WH\n",
        "Synechococcus_elongatus\n",
        "Synechocystis_PCC\n",
        "Taylorella_asinigenitalis\n",
        "Taylorella_equigenitalis\n",
        "Teredinibacter_turnerae\n",
        "Thermoanaerobacterium_thermosaccharolyticum\n",
        "Thermococcus_litoralis\n",
        "Thermoplasmatales_archaeon\n",
        "Thermosipho_africanus\n",
        "Thermotoga_maritima\n",
        "Thermus_oshimai\n",
        "Thermus_thermophilus\n",
        "Thiobacillus_denitrificans\n",
        "Treponema_denticola\n",
        "Treponema_pallidum\n",
        "Treponema_primitia\n",
        "Tropheryma_whipplei\n",
        "Ureaplasma_parvum\n",
        "Ureaplasma_urealyticum\n",
        "Variovorax_paradoxus\n",
        "Veillonella_parvula\n",
        "Vibrio_Ex25\n",
        "Vibrio_alginolyticus\n",
        "Vibrio_cholerae\n",
        "Vibrio_fischeri\n",
        "Vibrio_furnissii\n",
        "Vibrio_harveyi\n",
        "Vibrio_nigripulchritudo\n",
        "Vibrio_parahaemolyticus\n",
        "Vibrio_splendidus\n",
        "Vibrio_vulnificus\n",
        "Weissella_koreensis\n",
        "Wigglesworthia_glossinidia\n",
        "Wolbachia_endosymbiont\n",
        "Xanthomonas_axonopodis\n",
        "Xanthomonas_campestris\n",
        "Xanthomonas_citri\n",
        "Xanthomonas_oryzae\n",
        "Xylella_fastidiosa\n",
        "Yersinia_enterocolitica\n",
        "Yersinia_pestis\n",
        "Yersinia_pseudotuberculosis\n",
        "Zymomonas_mobilis\n",
        "_Ruminococcus\n",
        "alpha_proteobacterium\n",
        "beta_proteobacterium\n",
        "butyrate_producing\n",
        "candidate_division\n",
        "delta_proteobacterium\n",
        "gamma_proteobacterium\n",
        "secondary_endosymbiont\n"
       ]
      }
     ],
     "prompt_number": 3
    }
   ],
   "metadata": {}
  }
 ]
 }
	{
	"metadata": {
	"name": ""
	},
	"nbformat": 3,
	"nbformat_minor": 0,
	"worksheets": [
	{
	"cells": [
	{
	"cell_type": "markdown",
	"metadata": {},
	"source": [
	"* How many bacterial genomes are available?\n",
	"\n",
	"* What is the complete/draft ratio for each species?\n",
	"\n",
	"Step 1: download data from NCBI FTP\n",
	"-----------------------------------\n",
	"\n",
	" curl ftp://ftp.ncbi.nih.gov/genomes/Bacteria/ -l -s \| grep \"uid\" \| awk -F_ '{print $1\"_\"$2\" complete\"}' > genomes_2014_01_08\n",
	" curl ftp://ftp.ncbi.nih.gov/genomes/Bacteria_DRAFT/ -l -s \| grep \"uid\" \| awk -F_ '{print $1\"_\"$2\" draft\"}' >> genomes_2014_01_08\n",
	" \n",
	"Step 2: crunch some numbers\n",
	"---------------------------"
	]
	},
	{
	"cell_type": "code",
	"collapsed": false,
	"input": [
	"genomes = {}\n",
	"\n",
	"for l in open('genomes_2014_01_08'):\n",
	" species, kind = l.strip().split()\n",
	" genomes[species] = genomes.get(species, [0, 0])\n",
	" if kind == 'complete':\n",
	" genomes[species][0] += 1\n",
	" elif kind == 'draft':\n",
	" genomes[species][1] += 1\n",
	" else:\n",
	" raise ValueError('Duh? %s'%kind)"
	],
	"language": "python",
	"metadata": {},
	"outputs": [],
	"prompt_number": 1
	},
	{
	"cell_type": "code",
	"collapsed": false,
	"input": [
	"print('Number of complete genomes: %d'%sum([genomes[x][0] for x in genomes]))\n",
	"print('Number of draft genomes: %d'%sum([genomes[x][1] for x in genomes]))\n",
	"print('Complete genomes ratio: %.2f%%'%( sum([genomes[x][0] for x in genomes])*100.0 / sum([sum(genomes[x]) for x in genomes]) )) \n",
	"\n",
	"print('\\n=======\\n')\n",
	"\n",
	"print('Number of sequenced species: %d'%len(genomes))\n",
	"comparative = len(filter(lambda x: sum(genomes[x])>1, genomes))\n",
	"print('Number of species having more than one genome sequenced: %d (%.2f%%)'%\n",
	" (comparative, float(comparative)*100/len(genomes)))\n",
	"referenced = len(filter(lambda x: sum(genomes[x])>1 and genomes[x][0]>0, genomes))\n",
	"print('Number of species w/ multiple genomes and at least one complete reference: %d (%.2f%%)'%\n",
	" (referenced, float(referenced)*100/len(genomes)))\n",
	"onecomplete = len(filter(lambda x: genomes[x][0]>0, genomes))\n",
	"print('Number of species w/ at least one complete reference: %d (%.2f%%)'%\n",
	" (onecomplete, float(onecomplete)*100/len(genomes)))\n",
	"\n",
	"print('\\n=======\\n')\n",
	"\n",
	"print('Average number of genomes per species: %.2f'%( np.array([sum(genomes[x]) for x in genomes]).mean() ))\n",
	"print('Considering only the species having more than one genome: %.2f'%\n",
	" np.array([sum(genomes[x]) for x in filter(lambda x: sum(genomes[x])>1 ,genomes)]).mean())\n",
	"\n",
	"print('\\n=======\\n')\n",
	"\n",
	"print('Average complete genomes ratio: %.2f%%'%\n",
	" ( np.array( [float(genomes[x][0])*100/sum(genomes[x]) for x in genomes] ).mean() ))\n",
	"print('Considering only the species having more than one genome: %.2f%%'%\n",
	" ( np.array( [float(genomes[x][0])*100/sum(genomes[x]) for x in filter(lambda x: sum(genomes[x])>1 ,genomes)] ).mean() ))"
	],
	"language": "python",
	"metadata": {},
	"outputs": [
	{
	"output_type": "stream",
	"stream": "stdout",
	"text": [
	"Number of complete genomes: 2774\n",
	"Number of draft genomes: 6970\n",
	"Complete genomes ratio: 28.47%"
	]
	},
	{
	"output_type": "stream",
	"stream": "stdout",
	"text": [
	"\n",
	"\n",
	"=======\n",
	"\n",
	"Number of sequenced species: 3376\n",
	"Number of species having more than one genome sequenced: 715 (21.18%)"
	]
	},
	{
	"output_type": "stream",
	"stream": "stdout",
	"text": [
	"\n",
	"Number of species w/ multiple genomes and at least one complete reference: 484 (14.34%)"
	]
	},
	{
	"output_type": "stream",
	"stream": "stdout",
	"text": [
	"\n",
	"Number of species w/ at least one complete reference: 1483 (43.93%)\n",
	"\n",
	"=======\n",
	"\n",
	"Average number of genomes per species: 2.89"
	]
	},
	{
	"output_type": "stream",
	"stream": "stdout",
	"text": [
	"\n",
	"Considering only the species having more than one genome: 9.91"
	]
	},
	{
	"output_type": "stream",
	"stream": "stdout",
	"text": [
	"\n",
	"\n",
	"=======\n",
	"\n",
	"Average complete genomes ratio: 37.85%"
	]
	},
	{
	"output_type": "stream",
	"stream": "stdout",
	"text": [
	"\n",
	"Considering only the species having more than one genome: 39.01%"
	]
	},
	{
	"output_type": "stream",
	"stream": "stdout",
	"text": [
	"\n"
	]
	}
	],
	"prompt_number": 2
	},
	{
	"cell_type": "code",
	"collapsed": false,
	"input": [
	"print('Species having more than one genome sequenced and at least one complete genome sequence\\n')\n",
	"\n",
	"for species in sorted(filter(lambda x: sum(genomes[x])>1 and genomes[x][0]>0, genomes)):\n",
	" print species"
	],
	"language": "python",
	"metadata": {},
	"outputs": [
	{
	"output_type": "stream",
	"stream": "stdout",
	"text": [
	"Species having more than one genome sequenced and at least one complete genome sequence\n",
	"\n",
	"Acetobacter_pasteurianus"
	]
	},
	{
	"output_type": "stream",
	"stream": "stdout",
	"text": [
	"\n",
	"Achromobacter_xylosoxidans\n",
	"Acidithiobacillus_caldus\n",
	"Acidithiobacillus_ferrooxidans\n",
	"Acidovorax_citrulli\n",
	"Aciduliprofundum_boonei\n",
	"Acinetobacter_baumannii\n",
	"Acinetobacter_calcoaceticus\n",
	"Actinobacillus_pleuropneumoniae\n",
	"Aeromonas_hydrophila\n",
	"Aeromonas_salmonicida\n",
	"Aeromonas_veronii\n",
	"Aggregatibacter_actinomycetemcomitans\n",
	"Aggregatibacter_aphrophilus\n",
	"Alicycliphilus_denitrificans\n",
	"Alicyclobacillus_acidocaldarius\n",
	"Alteromonas_macleodii\n",
	"Amycolatopsis_mediterranei\n",
	"Anaerococcus_prevotii\n",
	"Anaeromyxobacter_dehalogenans\n",
	"Anaplasma_marginale\n",
	"Anaplasma_phagocytophilum\n",
	"Anoxybacillus_flavithermus\n",
	"Arcobacter_butzleri\n",
	"Arthrospira_platensis\n",
	"Azotobacter_vinelandii\n",
	"Bacillus_1NLA3E\n",
	"Bacillus_amyloliquefaciens\n",
	"Bacillus_anthracis\n",
	"Bacillus_atrophaeus\n",
	"Bacillus_cereus\n",
	"Bacillus_coagulans\n",
	"Bacillus_licheniformis\n",
	"Bacillus_megaterium\n",
	"Bacillus_pumilus\n",
	"Bacillus_subtilis\n",
	"Bacillus_thuringiensis\n",
	"Bacteroides_fragilis\n",
	"Bacteroides_uniformis\n",
	"Bacteroides_vulgatus\n",
	"Bacteroides_xylanisolvens\n",
	"Bartonella_bacilliformis\n",
	"Bartonella_quintana\n",
	"Bartonella_vinsonii\n",
	"Bdellovibrio_bacteriovorus\n",
	"Bifidobacterium_adolescentis\n",
	"Bifidobacterium_animalis\n",
	"Bifidobacterium_bifidum\n",
	"Bifidobacterium_breve\n",
	"Bifidobacterium_dentium\n",
	"Bifidobacterium_longum\n",
	"Blattabacterium_\n",
	"Bordetella_bronchiseptica\n",
	"Bordetella_parapertussis\n",
	"Bordetella_pertussis\n",
	"Borrelia_afzelii\n",
	"Borrelia_burgdorferi\n",
	"Borrelia_garinii\n",
	"Borrelia_valaisiana\n",
	"Brachyspira_pilosicoli\n",
	"Bradyrhizobium_ORS\n",
	"Bradyrhizobium_japonicum\n",
	"Brevibacillus_brevis\n",
	"Brucella_abortus\n",
	"Brucella_canis\n",
	"Brucella_ceti\n",
	"Brucella_melitensis\n",
	"Brucella_pinnipedialis\n",
	"Brucella_suis\n",
	"Buchnera_aphidicola\n",
	"Burkholderia_ambifaria\n",
	"Burkholderia_cenocepacia\n",
	"Burkholderia_gladioli\n",
	"Burkholderia_glumae\n",
	"Burkholderia_mallei\n",
	"Burkholderia_multivorans\n",
	"Burkholderia_pseudomallei\n",
	"Burkholderia_thailandensis\n",
	"Calothrix_PCC\n",
	"Campylobacter_coli\n",
	"Campylobacter_concisus\n",
	"Campylobacter_curvus\n",
	"Campylobacter_fetus\n",
	"Campylobacter_jejuni\n",
	"Candidatus_Arthromitus\n",
	"Candidatus_Blochmannia\n",
	"Candidatus_Carsonella\n",
	"Candidatus_Hamiltonella\n",
	"Candidatus_Kinetoplastibacterium\n",
	"Candidatus_Liberibacter\n",
	"Candidatus_Moranella\n",
	"Candidatus_Mycoplasma\n",
	"Candidatus_Nitrosopumilus\n",
	"Candidatus_Pelagibacter\n",
	"Candidatus_Phytoplasma\n",
	"Candidatus_Portiera\n",
	"Candidatus_Sulcia\n",
	"Candidatus_Tremblaya\n",
	"Capnocytophaga_ochracea\n",
	"Carnobacterium_maltaromaticum\n",
	"Caulobacter_crescentus\n",
	"Chlamydia_muridarum\n",
	"Chlamydia_pecorum\n",
	"Chlamydia_psittaci\n",
	"Chlamydia_trachomatis\n",
	"Chlamydophila_abortus\n",
	"Chlamydophila_pneumoniae\n",
	"Chlamydophila_psittaci\n",
	"Chlorobium_phaeobacteroides\n",
	"Clavibacter_michiganensis\n",
	"Clostridium_acetobutylicum\n",
	"Clostridium_beijerinckii\n",
	"Clostridium_botulinum\n",
	"Clostridium_cellulovorans\n",
	"Clostridium_difficile\n",
	"Clostridium_kluyveri\n",
	"Clostridium_pasteurianum\n",
	"Clostridium_perfringens\n",
	"Clostridium_saccharoperbutylacetonicum\n",
	"Clostridium_stercorarium\n",
	"Clostridium_tetani\n",
	"Clostridium_thermocellum\n",
	"Comamonas_testosteroni\n",
	"Corynebacterium_aurimucosum\n",
	"Corynebacterium_diphtheriae\n",
	"Corynebacterium_efficiens\n",
	"Corynebacterium_glutamicum\n",
	"Corynebacterium_jeikeium\n",
	"Corynebacterium_pseudotuberculosis\n",
	"Corynebacterium_ulcerans\n",
	"Corynebacterium_urealyticum\n",
	"Coxiella_burnetii\n",
	"Cronobacter_sakazakii\n",
	"Cronobacter_turicensis\n",
	"Cupriavidus_necator\n",
	"Cupriavidus_taiwanensis\n",
	"Cyanothece_ATCC\n",
	"Cyanothece_PCC\n",
	"Dehalococcoides_mccartyi\n",
	"Desulfitobacterium_hafniense\n",
	"Desulfotomaculum_gibsoniae\n",
	"Desulfovibrio_africanus\n",
	"Desulfovibrio_desulfuricans\n",
	"Desulfovibrio_magneticus\n",
	"Desulfovibrio_vulgaris\n",
	"Dickeya_dadantii\n",
	"Dickeya_zeae\n",
	"Ectothiorhodospiraceae_bacterium\n",
	"Edwardsiella_tarda\n",
	"Ehrlichia_chaffeensis\n",
	"Ehrlichia_ruminantium\n",
	"Enterobacter_aerogenes\n",
	"Enterobacter_cloacae\n",
	"Enterobacteriaceae_bacterium\n",
	"Enterococcus_casseliflavus\n",
	"Enterococcus_faecalis\n",
	"Enterococcus_faecium\n",
	"Erwinia_amylovora\n",
	"Erwinia_pyrifoliae\n",
	"Erysipelothrix_rhusiopathiae\n",
	"Escherichia_blattae\n",
	"Escherichia_coli\n",
	"Escherichia_fergusonii\n",
	"Eubacterium_rectale\n",
	"Eubacterium_siraeum\n",
	"Faecalibacterium_prausnitzii\n",
	"Ferroplasma_acidarmanus\n",
	"Fibrobacter_succinogenes\n",
	"Finegoldia_magna\n",
	"Flavobacteriaceae_bacterium\n",
	"Flavobacteriales_bacterium\n",
	"Francisella_cf\n",
	"Francisella_noatunensis\n",
	"Francisella_novicida\n",
	"Francisella_philomiragia\n",
	"Francisella_tularensis\n",
	"Fusobacterium_3\n",
	"Fusobacterium_4\n",
	"Fusobacterium_nucleatum\n",
	"Gallibacterium_anatis\n",
	"Gardnerella_vaginalis\n",
	"Geitlerinema_PCC\n",
	"Geobacter_metallireducens\n",
	"Geobacter_sulfurreducens\n",
	"Glaciecola_psychrophila\n",
	"Gloeocapsa_PCC\n",
	"Gluconacetobacter_diazotrophicus\n",
	"Gluconobacter_oxydans\n",
	"Gordonia_polyisoprenivorans\n",
	"Haemophilus_influenzae\n",
	"Haemophilus_parainfluenzae\n",
	"Haemophilus_parasuis\n",
	"Haemophilus_somnus\n",
	"Halalkalicoccus_jeotgali\n",
	"Haloarcula_hispanica\n",
	"Haloferax_mediterranei\n",
	"Haloferax_volcanii\n",
	"Halogeometricum_borinquense\n",
	"Haloquadratum_walsbyi\n",
	"Halorhabdus_tiamatea\n",
	"Helicobacter_bizzozeronii\n",
	"Helicobacter_cetorum\n",
	"Helicobacter_cinaedi\n",
	"Helicobacter_pylori\n",
	"Herbaspirillum_seropedicae\n",
	"Hydrogenobacter_thermophilus\n",
	"Hyphomicrobium_denitrificans\n",
	"Idiomarina_loihiensis\n",
	"Ketogulonicigenium_vulgare\n",
	"Klebsiella_oxytoca\n",
	"Klebsiella_pneumoniae\n",
	"Lactobacillus_acidophilus\n",
	"Lactobacillus_amylovorus\n",
	"Lactobacillus_brevis\n",
	"Lactobacillus_buchneri\n",
	"Lactobacillus_casei\n",
	"Lactobacillus_crispatus\n",
	"Lactobacillus_delbrueckii\n",
	"Lactobacillus_fermentum\n",
	"Lactobacillus_gasseri\n",
	"Lactobacillus_helveticus\n",
	"Lactobacillus_johnsonii\n",
	"Lactobacillus_paracasei\n",
	"Lactobacillus_plantarum\n",
	"Lactobacillus_reuteri\n",
	"Lactobacillus_rhamnosus\n",
	"Lactobacillus_ruminis\n",
	"Lactobacillus_salivarius\n",
	"Lactococcus_garvieae\n",
	"Lactococcus_lactis\n",
	"Lawsonia_intracellularis\n",
	"Legionella_longbeachae\n",
	"Legionella_pneumophila\n",
	"Leifsonia_xyli\n",
	"Leptolyngbya_PCC\n",
	"Leptospira_biflexa\n",
	"Leptospira_borgpetersenii\n",
	"Leptospira_interrogans\n",
	"Leuconostoc_carnosum\n",
	"Leuconostoc_citreum\n",
	"Leuconostoc_gelidum\n",
	"Leuconostoc_mesenteroides\n",
	"Listeria_innocua\n",
	"Listeria_ivanovii\n",
	"Listeria_monocytogenes\n",
	"Listeria_seeligeri\n",
	"Mannheimia_haemolytica\n",
	"Meiothermus_ruber\n",
	"Melissococcus_plutonius\n",
	"Mesoplasma_florum\n",
	"Methanobrevibacter_smithii\n",
	"Methanococcus_maripaludis\n",
	"Methanosarcina_mazei\n",
	"Methylobacterium_extorquens\n",
	"Methylococcus_capsulatus\n",
	"Micrococcus_luteus\n",
	"Microcystis_aeruginosa\n",
	"Mobiluncus_curtisii\n",
	"Moraxella_catarrhalis\n",
	"Morganella_morganii\n",
	"Mycobacterium_abscessus\n",
	"Mycobacterium_avium\n",
	"Mycobacterium_bovis\n",
	"Mycobacterium_canettii\n",
	"Mycobacterium_gilvum\n",
	"Mycobacterium_intracellulare\n",
	"Mycobacterium_kansasii\n",
	"Mycobacterium_leprae\n",
	"Mycobacterium_massiliense\n",
	"Mycobacterium_rhodesiae\n",
	"Mycobacterium_smegmatis\n",
	"Mycobacterium_tuberculosis\n",
	"Mycoplasma_agalactiae\n",
	"Mycoplasma_bovis\n",
	"Mycoplasma_fermentans\n",
	"Mycoplasma_gallisepticum\n",
	"Mycoplasma_genitalium\n",
	"Mycoplasma_haemofelis\n",
	"Mycoplasma_hyopneumoniae\n",
	"Mycoplasma_hyorhinis\n",
	"Mycoplasma_leachii\n",
	"Mycoplasma_mycoides\n",
	"Mycoplasma_pneumoniae\n",
	"Mycoplasma_putrefaciens\n",
	"Mycoplasma_suis\n",
	"Myxococcus_xanthus\n",
	"Natrinema_pellirubrum\n",
	"Natronobacterium_gregoryi\n",
	"Neisseria_gonorrhoeae\n",
	"Neisseria_lactamica\n",
	"Neisseria_meningitidis\n",
	"Nitrosococcus_oceani\n",
	"Nocardia_brasiliensis\n",
	"Nocardia_cyriacigeorgica\n",
	"Nocardiopsis_alba\n",
	"Nostoc_PCC\n",
	"Ochrobactrum_anthropi\n",
	"Oenococcus_oeni\n",
	"Oligotropha_carboxidovorans\n",
	"Orientia_tsutsugamushi\n",
	"Oscillatoria_PCC\n",
	"Paenibacillus_larvae\n",
	"Paenibacillus_mucilaginosus\n",
	"Paenibacillus_polymyxa\n",
	"Pantoea_ananatis\n",
	"Parabacteroides_distasonis\n",
	"Parachlamydia_acanthamoebae\n",
	"Pasteurella_multocida\n",
	"Pectobacterium_carotovorum\n",
	"Pectobacterium_wasabiae\n",
	"Pediococcus_pentosaceus\n",
	"Phaeobacter_gallaeciensis\n",
	"Photobacterium_profundum\n",
	"Polynucleobacter_necessarius\n",
	"Porphyromonas_asaccharolytica\n",
	"Porphyromonas_gingivalis\n",
	"Prevotella_dentalis\n",
	"Prevotella_denticola\n",
	"Prevotella_melaninogenica\n",
	"Prevotella_oral\n",
	"Prochlorococcus_marinus\n",
	"Propionibacterium_acnes\n",
	"Propionibacterium_avidum\n",
	"Proteus_mirabilis\n",
	"Providencia_stuartii\n",
	"Pseudoalteromonas_haloplanktis\n",
	"Pseudomonas_aeruginosa\n",
	"Pseudomonas_fluorescens\n",
	"Pseudomonas_mendocina\n",
	"Pseudomonas_monteilii\n",
	"Pseudomonas_putida\n",
	"Pseudomonas_stutzeri\n",
	"Pseudomonas_syringae\n",
	"Pyrococcus_furiosus\n",
	"Rahnella_aquatilis\n",
	"Ralstonia_eutropha\n",
	"Ralstonia_pickettii\n",
	"Ralstonia_solanacearum\n",
	"Rhizobium_etli\n",
	"Rhizobium_leguminosarum\n",
	"Rhodobacter_sphaeroides\n",
	"Rhodococcus_equi\n",
	"Rhodococcus_erythropolis\n",
	"Rhodococcus_opacus\n",
	"Rhodococcus_pyridinivorans\n",
	"Rhodopirellula_baltica\n",
	"Rhodopseudomonas_palustris\n",
	"Rhodospirillum_rubrum\n",
	"Rhodothermus_marinus\n",
	"Rickettsia_australis\n",
	"Rickettsia_bellii\n",
	"Rickettsia_canadensis\n",
	"Rickettsia_conorii\n",
	"Rickettsia_japonica\n",
	"Rickettsia_massiliae\n",
	"Rickettsia_prowazekii\n",
	"Rickettsia_rickettsii\n",
	"Rickettsia_slovaca\n",
	"Rickettsia_typhi\n",
	"Riemerella_anatipestifer\n",
	"Roseburia_intestinalis\n",
	"Rothia_dentocariosa\n",
	"Rothia_mucilaginosa\n",
	"Rubrivivax_gelatinosus\n",
	"Ruminococcus_albus\n",
	"Saccharopolyspora_erythraea\n",
	"Salinibacter_ruber\n",
	"Salinispora_arenicola\n",
	"Salinispora_tropica\n",
	"Salmonella_bongori\n",
	"Salmonella_enterica\n",
	"Saprospira_grandis\n",
	"Selenomonas_sputigena\n",
	"Serratia_marcescens\n",
	"Serratia_odorifera\n",
	"Serratia_plymuthica\n",
	"Serratia_symbiotica\n",
	"Shewanella_MR\n",
	"Shewanella_baltica\n",
	"Shewanella_putrefaciens\n",
	"Shigella_boydii\n",
	"Shigella_dysenteriae\n",
	"Shigella_flexneri\n",
	"Shigella_sonnei\n",
	"Singulisphaera_acidiphila\n",
	"Sinorhizobium_fredii\n",
	"Sinorhizobium_medicae\n",
	"Sinorhizobium_meliloti\n",
	"Sorangium_cellulosum\n",
	"Sphingomonas_wittichii\n",
	"Spirochaeta_thermophila\n",
	"Staphylococcus_aureus\n",
	"Staphylococcus_epidermidis\n",
	"Staphylococcus_haemolyticus\n",
	"Staphylococcus_lugdunensis\n",
	"Staphylococcus_pseudintermedius\n",
	"Staphylococcus_saprophyticus\n",
	"Staphylococcus_warneri\n",
	"Stenotrophomonas_maltophilia\n",
	"Stigmatella_aurantiaca\n",
	"Streptococcus_I\n",
	"Streptococcus_agalactiae\n",
	"Streptococcus_anginosus\n",
	"Streptococcus_constellatus\n",
	"Streptococcus_dysgalactiae\n",
	"Streptococcus_equi\n",
	"Streptococcus_gallolyticus\n",
	"Streptococcus_infantarius\n",
	"Streptococcus_iniae\n",
	"Streptococcus_intermedius\n",
	"Streptococcus_mitis\n",
	"Streptococcus_mutans\n",
	"Streptococcus_oralis\n",
	"Streptococcus_parasanguinis\n",
	"Streptococcus_parauberis\n",
	"Streptococcus_pneumoniae\n",
	"Streptococcus_pseudopneumoniae\n",
	"Streptococcus_pyogenes\n",
	"Streptococcus_salivarius\n",
	"Streptococcus_sanguinis\n",
	"Streptococcus_suis\n",
	"Streptococcus_thermophilus\n",
	"Streptomyces_albus\n",
	"Streptomyces_cattleya\n",
	"Streptomyces_hygroscopicus\n",
	"Sulfobacillus_acidophilus\n",
	"Sulfolobus_acidocaldarius\n",
	"Sulfolobus_islandicus\n",
	"Sulfolobus_solfataricus\n",
	"Sulfuricella_denitrificans\n",
	"Synechococcus_JA\n",
	"Synechococcus_PCC\n",
	"Synechococcus_WH\n",
	"Synechococcus_elongatus\n",
	"Synechocystis_PCC\n",
	"Taylorella_asinigenitalis\n",
	"Taylorella_equigenitalis\n",
	"Teredinibacter_turnerae\n",
	"Thermoanaerobacterium_thermosaccharolyticum\n",
	"Thermococcus_litoralis\n",
	"Thermoplasmatales_archaeon\n",
	"Thermosipho_africanus\n",
	"Thermotoga_maritima\n",
	"Thermus_oshimai\n",
	"Thermus_thermophilus\n",
	"Thiobacillus_denitrificans\n",
	"Treponema_denticola\n",
	"Treponema_pallidum\n",
	"Treponema_primitia\n",
	"Tropheryma_whipplei\n",
	"Ureaplasma_parvum\n",
	"Ureaplasma_urealyticum\n",
	"Variovorax_paradoxus\n",
	"Veillonella_parvula\n",
	"Vibrio_Ex25\n",
	"Vibrio_alginolyticus\n",
	"Vibrio_cholerae\n",
	"Vibrio_fischeri\n",
	"Vibrio_furnissii\n",
	"Vibrio_harveyi\n",
	"Vibrio_nigripulchritudo\n",
	"Vibrio_parahaemolyticus\n",
	"Vibrio_splendidus\n",
	"Vibrio_vulnificus\n",
	"Weissella_koreensis\n",
	"Wigglesworthia_glossinidia\n",
	"Wolbachia_endosymbiont\n",
	"Xanthomonas_axonopodis\n",
	"Xanthomonas_campestris\n",
	"Xanthomonas_citri\n",
	"Xanthomonas_oryzae\n",
	"Xylella_fastidiosa\n",
	"Yersinia_enterocolitica\n",
	"Yersinia_pestis\n",
	"Yersinia_pseudotuberculosis\n",
	"Zymomonas_mobilis\n",
	"_Ruminococcus\n",
	"alpha_proteobacterium\n",
	"beta_proteobacterium\n",
	"butyrate_producing\n",
	"candidate_division\n",
	"delta_proteobacterium\n",
	"gamma_proteobacterium\n",
	"secondary_endosymbiont\n"
	]
	}
	],
	"prompt_number": 3
	}
	],
	"metadata": {}
	}
	]
	}