def mismatches(args): """ %prog mismatches blastfile Print out histogram of mismatches of HSPs, usually for evaluating SNP level. """ from jcvi.utils.cbook import percentage from jcvi.graphics.histogram import stem_leaf_plot p = OptionParser(mismatches.__doc__) opts, args = p.parse_args(args) if len(args) != 1: sys.exit(not p.print_help()) blastfile, = args data = [] matches = 0 b = Blast(blastfile) for query, bline in b.iter_best_hit(): mm = bline.nmismatch + bline.ngaps data.append(mm) nonzeros = [x for x in data if x != 0] title = "Polymorphic sites: {0}".\ format(percentage(len(nonzeros), len(data))) stem_leaf_plot(data, 0, 20, 20, title=title)
def count(args): """ %prog count cdhit.consensus.fasta Scan the headers for the consensus clusters and count the number of reads. """ from jcvi.formats.fasta import Fasta from jcvi.graphics.histogram import stem_leaf_plot from jcvi.utils.cbook import SummaryStats p = OptionParser(count.__doc__) opts, args = p.parse_args(args) if len(args) != 1: sys.exit(not p.print_help()) fastafile, = args f = Fasta(fastafile, lazy=True) sizes = [] for desc, rec in f.iterdescriptions_ordered(): if desc.startswith("singleton"): sizes.append(1) continue # consensus_for_cluster_0 with 63 sequences name, w, size, seqs = desc.split() assert w == "with" sizes.append(int(size)) s = SummaryStats(sizes) print >> sys.stderr, s stem_leaf_plot(s.data, 0, 100, 20, title="Cluster size")
def mismatches(args): """ %prog mismatches blastfile Print out histogram of mismatches of HSPs, usually for evaluating SNP level. """ from jcvi.utils.cbook import percentage from jcvi.graphics.histogram import stem_leaf_plot p = OptionParser(mismatches.__doc__) opts, args = p.parse_args(args) if len(args) != 1: sys.exit(not p.print_help()) blastfile, = args data = [] b = Blast(blastfile) for query, bline in b.iter_best_hit(): mm = bline.nmismatch + bline.ngaps data.append(mm) nonzeros = [x for x in data if x != 0] title = "Polymorphic sites: {0}".\ format(percentage(len(nonzeros), len(data))) stem_leaf_plot(data, 0, 20, 20, title=title)
def count(args): """ %prog count cdhit.consensus.fasta Scan the headers for the consensus clusters and count the number of reads. """ from jcvi.graphics.histogram import stem_leaf_plot from jcvi.utils.cbook import SummaryStats p = OptionParser(count.__doc__) opts, args = p.parse_args(args) if len(args) != 1: sys.exit(not p.print_help()) fastafile, = args f = Fasta(fastafile, lazy=True) sizes = [] for desc, rec in f.iterdescriptions_ordered(): if desc.startswith("singleton"): sizes.append(1) continue # consensus_for_cluster_0 with 63 sequences name, w, size, seqs = desc.split() assert w == "with" sizes.append(int(size)) s = SummaryStats(sizes) print >> sys.stderr, s stem_leaf_plot(s.data, 0, 100, 20, title="Cluster size")
def report(args): ''' %prog report ksfile generate a report given a Ks result file (as produced by synonymous_calc.py). describe the median Ks, Ka values, as well as the distribution in stem-leaf plot ''' from jcvi.utils.cbook import SummaryStats from jcvi.graphics.histogram import stem_leaf_plot p = OptionParser(report.__doc__) p.add_option("--pdf", default=False, action="store_true", help="Generate graphic output for the histogram [default: %default]") p.add_option("--components", default=1, type="int", help="Number of components to decompose peaks [default: %default]") add_plot_options(p) opts, args, iopts = p.set_image_options(args, figsize="5x5") if len(args) != 1: sys.exit(not p.print_help()) ks_file, = args data = read_ks_file(ks_file) ks_min = opts.vmin ks_max = opts.vmax bins = opts.bins for f in fields.split(",")[1:]: columndata = [getattr(x, f) for x in data] ks = ("ks" in f) if not ks: continue columndata = [x for x in columndata if ks_min <= x <= ks_max] st = SummaryStats(columndata) title = "{0} ({1}): ".format(descriptions[f], ks_file) title += "Median:{0:.3f} (1Q:{1:.3f}|3Q:{2:.3f}||".\ format(st.median, st.firstq, st.thirdq) title += "Mean:{0:.3f}|Std:{1:.3f}||N:{2})".\ format(st.mean, st.sd, st.size) tbins = (0, ks_max, bins) if ks else (0, .6, 10) digit = 2 if (ks_max * 1. / bins) < .1 else 1 stem_leaf_plot(columndata, *tbins, digit=digit, title=title) if not opts.pdf: return components = opts.components data = [x.ng_ks for x in data] data = [x for x in data if ks_min <= x <= ks_max] fig = plt.figure(1, (iopts.w, iopts.h)) ax = fig.add_axes([.12, .1, .8, .8]) kp = KsPlot(ax, ks_max, opts.bins, legendp=opts.legendp) kp.add_data(data, components, fill=opts.fill) kp.draw(title=opts.title)
def report(args): ''' %prog report ksfile generate a report given a Ks result file (as produced by synonymous_calc.py). describe the median Ks, Ka values, as well as the distribution in stem-leaf plot ''' from jcvi.utils.cbook import SummaryStats from jcvi.graphics.histogram import stem_leaf_plot p = OptionParser(report.__doc__) p.add_option("--pdf", default=False, action="store_true", help="Generate graphic output for the histogram [default: %default]") p.add_option("--components", default=1, type="int", help="Number of components to decompose peaks [default: %default]") add_plot_options(p) opts, args, iopts = p.set_image_options(args, figsize="5x5") if len(args) != 1: sys.exit(not p.print_help()) ks_file, = args data = KsFile(ks_file) ks_min = opts.vmin ks_max = opts.vmax bins = opts.bins for f in fields.split(",")[1:]: columndata = [getattr(x, f) for x in data] ks = ("ks" in f) if not ks: continue columndata = [x for x in columndata if ks_min <= x <= ks_max] st = SummaryStats(columndata) title = "{0} ({1}): ".format(descriptions[f], ks_file) title += "Median:{0:.3f} (1Q:{1:.3f}|3Q:{2:.3f}||".\ format(st.median, st.firstq, st.thirdq) title += "Mean:{0:.3f}|Std:{1:.3f}||N:{2})".\ format(st.mean, st.sd, st.size) tbins = (0, ks_max, bins) if ks else (0, .6, 10) digit = 2 if (ks_max * 1. / bins) < .1 else 1 stem_leaf_plot(columndata, *tbins, digit=digit, title=title) if not opts.pdf: return components = opts.components data = [x.ng_ks for x in data] data = [x for x in data if ks_min <= x <= ks_max] fig = plt.figure(1, (iopts.w, iopts.h)) ax = fig.add_axes([.12, .1, .8, .8]) kp = KsPlot(ax, ks_max, opts.bins, legendp=opts.legendp) kp.add_data(data, components, fill=opts.fill, fitted=opts.fit) kp.draw(title=opts.title)
def location(args): """ %prog location bedfile fastafile Given SNP locations, summarize the locations in the sequences. For example, find out if there are more 3`-SNPs than 5`-SNPs. """ from jcvi.formats.bed import BedLine from jcvi.graphics.histogram import stem_leaf_plot p = OptionParser(location.__doc__) p.add_option( "--dist", default=100, type="int", help="Distance cutoff to call 5` and 3` [default: %default]", ) opts, args = p.parse_args(args) if len(args) != 2: sys.exit(not p.print_help()) bedfile, fastafile = args dist = opts.dist sizes = Sizes(fastafile).mapping fp = open(bedfile) fiveprime = threeprime = total = 0 percentages = [] for row in fp: b = BedLine(row) pos = b.start size = sizes[b.seqid] if pos < dist: fiveprime += 1 if size - pos < dist: threeprime += 1 total += 1 percentages.append(100 * pos / size) m = "Five prime (within {0}bp of start codon): {1}\n".format( dist, fiveprime) m += "Three prime (within {0}bp of stop codon): {1}\n".format( dist, threeprime) m += "Total: {0}".format(total) print(m, file=sys.stderr) bins = 10 title = "Locations within the gene [0=Five-prime, 100=Three-prime]" stem_leaf_plot(percentages, 0, 100, bins, title=title)
def count(args): """ %prog count cdhit.consensus.fasta Scan the headers for the consensus clusters and count the number of reads. """ from jcvi.graphics.histogram import stem_leaf_plot from jcvi.utils.cbook import SummaryStats p = OptionParser(count.__doc__) p.add_option("--csv", help="Write depth per contig to file") opts, args = p.parse_args(args) if len(args) != 1: sys.exit(not p.print_help()) (fastafile, ) = args csv = open(opts.csv, "w") if opts.csv else None f = Fasta(fastafile, lazy=True) sizes = [] for desc, rec in f.iterdescriptions_ordered(): if desc.startswith("singleton"): sizes.append(1) continue # consensus_for_cluster_0 with 63 sequences if "with" in desc: name, w, size, seqs = desc.split() if csv: print("\t".join(str(x) for x in (name, size, len(rec))), file=csv) assert w == "with" sizes.append(int(size)) # MRD85:00603:02472;size=167; else: name, size, tail = desc.split(";") sizes.append(int(size.replace("size=", ""))) if csv: csv.close() logging.debug("File written to `%s`.", opts.csv) s = SummaryStats(sizes) print(s, file=sys.stderr) stem_leaf_plot(s.data, 0, 100, 20, title="Cluster size")
def count(args): """ %prog count cdhit.consensus.fasta Scan the headers for the consensus clusters and count the number of reads. """ from jcvi.graphics.histogram import stem_leaf_plot from jcvi.utils.cbook import SummaryStats p = OptionParser(count.__doc__) p.add_option("--csv", help="Write depth per contig to file") opts, args = p.parse_args(args) if len(args) != 1: sys.exit(not p.print_help()) fastafile, = args csv = open(opts.csv, "w") if opts.csv else None f = Fasta(fastafile, lazy=True) sizes = [] for desc, rec in f.iterdescriptions_ordered(): if desc.startswith("singleton"): sizes.append(1) continue # consensus_for_cluster_0 with 63 sequences if "with" in desc: name, w, size, seqs = desc.split() if csv: print("\t".join(str(x) for x in (name, size, len(rec))), file=csv) assert w == "with" sizes.append(int(size)) # MRD85:00603:02472;size=167; else: name, size, tail = desc.split(";") sizes.append(int(size.replace("size=", ""))) if csv: csv.close() logging.debug("File written to `{0}`".format(opts.csv)) s = SummaryStats(sizes) print(s, file=sys.stderr) stem_leaf_plot(s.data, 0, 100, 20, title="Cluster size")
def location(args): """ %prog location bedfile fastafile Given SNP locations, summarize the locations in the sequences. For example, find out if there are more 3`-SNPs than 5`-SNPs. """ from jcvi.formats.bed import BedLine from jcvi.graphics.histogram import stem_leaf_plot p = OptionParser(location.__doc__) p.add_option("--dist", default=100, type="int", help="Distance cutoff to call 5` and 3` [default: %default]") opts, args = p.parse_args(args) if len(args) != 2: sys.exit(not p.print_help()) bedfile, fastafile = args dist = opts.dist sizes = Sizes(fastafile).mapping fp = open(bedfile) fiveprime = threeprime = total = 0 percentages = [] for row in fp: b = BedLine(row) pos = b.start size = sizes[b.seqid] if pos < dist: fiveprime += 1 if size - pos < dist: threeprime += 1 total += 1 percentages.append(100 * pos / size) m = "Five prime (within {0}bp of start codon): {1}\n".format(dist, fiveprime) m += "Three prime (within {0}bp of stop codon): {1}\n".format(dist, threeprime) m += "Total: {0}".format(total) print >> sys.stderr, m bins = 10 title = "Locations within the gene [0=Five-prime, 100=Three-prime]" stem_leaf_plot(percentages, 0, 100, bins, title=title)
def htg(args): """ %prog htg fastafile template.sbt Prepare sqnfiles for Genbank HTG submission to update existing records. `fastafile` contains the records to update, multiple records are allowed (with each one generating separate sqn file in the sqn/ folder). The record defline has the accession ID. For example, >AC148290.3 Internally, this generates two additional files (phasefile and namesfile) and download records from Genbank. Below is implementation details: `phasefile` contains, for each accession, phase information. For example: AC148290.3 3 HTG 2 mth2-45h12 which means this is a Phase-3 BAC. Record with only a single contig will be labeled as Phase-3 regardless of the info in the `phasefile`. Template file is the Genbank sbt template. See jcvi.formats.sbt for generation of such files. Another problem is that Genbank requires the name of the sequence to stay the same when updating and will kick back with a table of name conflicts. For example: We are unable to process the updates for these entries for the following reason: Seqname has changed Accession Old seq_name New seq_name --------- ------------ ------------ AC239792 mtg2_29457 AC239792.1 To prepare a submission, this script downloads genbank and asn.1 format, and generate the phase file and the names file (use formats.agp.phase() and apps.gbsubmit.asn(), respectively). These get automatically run. However, use --phases if the genbank files contain outdated information. For example, the clone name changes or phase upgrades. In this case, run formats.agp.phase() manually, modify the phasefile and use --phases to override. """ from jcvi.formats.fasta import sequin, ids from jcvi.formats.agp import phase from jcvi.apps.fetch import entrez p = OptionParser(htg.__doc__) p.add_option("--phases", default=None, help="Use another phasefile to override [default: %default]") p.add_option("--comment", default="", help="Comments for this update [default: %default]") opts, args = p.parse_args(args) if len(args) != 2: sys.exit(not p.print_help()) fastafile, sbtfile = args pf = fastafile.rsplit(".", 1)[0] idsfile = pf + ".ids" phasefile = pf + ".phases" namesfile = pf + ".names" ids([fastafile, "--outfile={0}".format(idsfile)]) asndir = "asn.1" mkdir(asndir) entrez([idsfile, "--format=asn.1", "--outdir={0}".format(asndir)]) asn(glob("{0}/*".format(asndir)) + \ ["--outfile={0}".format(namesfile)]) if opts.phases is None: gbdir = "gb" mkdir(gbdir) entrez([idsfile, "--format=gb", "--outdir={0}".format(gbdir)]) phase(glob("{0}/*".format(gbdir)) + \ ["--outfile={0}".format(phasefile)]) else: phasefile = opts.phases assert op.exists(namesfile) and op.exists(phasefile) newphasefile = phasefile + ".new" newphasefw = open(newphasefile, "w") comment = opts.comment fastadir = "fasta" sqndir = "sqn" mkdir(fastadir) mkdir(sqndir) from jcvi.graphics.histogram import stem_leaf_plot names = DictFile(namesfile) assert len(set(names.keys())) == len(set(names.values())) phases = DictFile(phasefile) ph = [int(x) for x in phases.values()] # vmin 1, vmax 4, bins 3 stem_leaf_plot(ph, 1, 4, 3, title="Counts of phases before updates") logging.debug("Information loaded for {0} records.".format(len(phases))) assert len(names) == len(phases) newph = [] cmd = "faSplit byname {0} {1}/".format(fastafile, fastadir) sh(cmd, outfile="/dev/null", errfile="/dev/null") acmd = 'tbl2asn -a z -p fasta -r {sqndir}' acmd += ' -i {splitfile} -t {sbtfile} -C tigr' acmd += ' -j "{qualifiers}"' acmd += ' -A {accession_nv} -o {sqndir}/{accession_nv}.sqn -V Vbr' acmd += ' -y "{comment}" -W T -T T' qq = "[tech=htgs {phase}] [organism=Medicago truncatula] [strain=A17]" nupdated = 0 for row in open(phasefile): atoms = row.rstrip().split("\t") # see formats.agp.phase() for column contents accession, phase, clone = atoms[0], atoms[1], atoms[-1] fafile = op.join(fastadir, accession + ".fa") accession_nv = accession.split(".", 1)[0] newid = names[accession_nv] newidopt = "--newid={0}".format(newid) cloneopt = "--clone={0}".format(clone) splitfile, gaps = sequin([fafile, newidopt, cloneopt]) splitfile = op.basename(splitfile) phase = int(phase) assert phase in (1, 2, 3) oldphase = phase if gaps == 0 and phase != 3: phase = 3 if gaps != 0 and phase == 3: phase = 2 print("{0}\t{1}\t{2}".\ format(accession_nv, oldphase, phase), file=newphasefw) newph.append(phase) qualifiers = qq.format(phase=phase) if ";" in clone: qualifiers += " [keyword=HTGS_POOLED_MULTICLONE]" cmd = acmd.format(accession=accession, accession_nv=accession_nv, sqndir=sqndir, sbtfile=sbtfile, splitfile=splitfile, qualifiers=qualifiers, comment=comment) sh(cmd) verify_sqn(sqndir, accession) nupdated += 1 stem_leaf_plot(newph, 1, 4, 3, title="Counts of phases after updates") print("A total of {0} records updated.".format(nupdated), file=sys.stderr)
def histogram(args): """ %prog histogram [reads.fasta|reads.fastq] Plot read length distribution for reads. The plot would be similar to the one generated by SMRT-portal, for example: http://blog.pacificbiosciences.com/2013/10/data-release-long-read-shotgun.html Plot has two axes - corresponding to pdf and cdf, respectively. Also adding number of reads, average/median, N50, and total length. """ from jcvi.utils.cbook import human_size, thousands, SUFFIXES from jcvi.formats.fastq import fasta from jcvi.graphics.histogram import stem_leaf_plot from jcvi.graphics.base import plt, markup, human_formatter, \ human_base_formatter, savefig, set2, set_ticklabels_helvetica p = OptionParser(histogram.__doc__) p.set_histogram(vmax=50000, bins=100, xlabel="Read length", title="Read length distribution") p.add_option("--ylabel1", default="Counts", help="Label of y-axis on the left") p.add_option("--color", default='0', choices=[str(x) for x in range(8)], help="Color of bars, which is an index 0-7 in brewer set2") opts, args, iopts = p.set_image_options(args, figsize="6x6", style="dark") if len(args) != 1: sys.exit(not p.print_help()) fastafile, = args fastafile, qualfile = fasta([fastafile, "--seqtk"]) sizes = Sizes(fastafile) all_sizes = sorted(sizes.sizes) xmin, xmax, bins = opts.vmin, opts.vmax, opts.bins left, height = stem_leaf_plot(all_sizes, xmin, xmax, bins) plt.figure(1, (iopts.w, iopts.h)) ax1 = plt.gca() width = (xmax - xmin) * .5 / bins color = set2[int(opts.color)] ax1.bar(left, height, width=width, linewidth=0, fc=color, align="center") ax1.set_xlabel(markup(opts.xlabel)) ax1.set_ylabel(opts.ylabel1) ax2 = ax1.twinx() cur_size = 0 total_size, l50, n50 = sizes.summary cdf = {} hsize = human_size(total_size) tag = hsize[-2:] unit = 1000 ** SUFFIXES[1000].index(tag) for x in all_sizes: if x not in cdf: cdf[x] = (total_size - cur_size) * 1. / unit cur_size += x x, y = zip(*sorted(cdf.items())) ax2.plot(x, y, '-', color="darkslategray") ylabel2 = "{0} above read length".format(tag) ax2.set_ylabel(ylabel2) for ax in (ax1, ax2): set_ticklabels_helvetica(ax) ax.set_xlim((xmin - width / 2, xmax + width / 2)) tc = "gray" axt = ax1.transAxes xx, yy = .95, .95 ma = "Total bases: {0}".format(hsize) mb = "Total reads: {0}".format(thousands(len(sizes))) mc = "Average read length: {0}bp".format(thousands(np.mean(all_sizes))) md = "Median read length: {0}bp".format(thousands(np.median(all_sizes))) me = "N50 read length: {0}bp".format(thousands(l50)) for t in (ma, mb, mc, md, me): print >> sys.stderr, t ax1.text(xx, yy, t, color=tc, transform=axt, ha="right") yy -= .05 ax1.set_title(markup(opts.title)) # Seaborn removes ticks for all styles except 'ticks'. Now add them back: ax1.tick_params(axis="x", direction="out", length=3, left=False, right=False, top=False, bottom=True) ax1.xaxis.set_major_formatter(human_base_formatter) ax1.yaxis.set_major_formatter(human_formatter) figname = sizes.filename + ".pdf" savefig(figname)
def histogram(args): """ %prog histogram [reads.fasta|reads.fastq] Plot read length distribution for reads. The plot would be similar to the one generated by SMRT-portal, for example: http://blog.pacificbiosciences.com/2013/10/data-release-long-read-shotgun.html Plot has two axes - corresponding to pdf and cdf, respectively. Also adding number of reads, average/median, N50, and total length. """ from jcvi.utils.cbook import human_size, thousands, SUFFIXES from jcvi.formats.fastq import fasta from jcvi.graphics.histogram import stem_leaf_plot from jcvi.graphics.base import ( plt, markup, human_formatter, human_base_formatter, savefig, set2, set_ticklabels_helvetica, ) p = OptionParser(histogram.__doc__) p.set_histogram(vmax=50000, bins=100, xlabel="Read length", title="Read length distribution") p.add_option("--ylabel1", default="Counts", help="Label of y-axis on the left") p.add_option( "--color", default="0", choices=[str(x) for x in range(8)], help="Color of bars, which is an index 0-7 in brewer set2", ) opts, args, iopts = p.set_image_options(args, figsize="6x6", style="dark") if len(args) != 1: sys.exit(not p.print_help()) (fastafile, ) = args fastafile, qualfile = fasta([fastafile, "--seqtk"]) sizes = Sizes(fastafile) all_sizes = sorted(sizes.sizes) xmin, xmax, bins = opts.vmin, opts.vmax, opts.bins left, height = stem_leaf_plot(all_sizes, xmin, xmax, bins) plt.figure(1, (iopts.w, iopts.h)) ax1 = plt.gca() width = (xmax - xmin) * 0.5 / bins color = set2[int(opts.color)] ax1.bar(left, height, width=width, linewidth=0, fc=color, align="center") ax1.set_xlabel(markup(opts.xlabel)) ax1.set_ylabel(opts.ylabel1) ax2 = ax1.twinx() cur_size = 0 total_size, l50, n50 = sizes.summary cdf = {} hsize = human_size(total_size) tag = hsize[-2:] unit = 1000**SUFFIXES[1000].index(tag) for x in all_sizes: if x not in cdf: cdf[x] = (total_size - cur_size) * 1.0 / unit cur_size += x x, y = zip(*sorted(cdf.items())) ax2.plot(x, y, "-", color="darkslategray") ylabel2 = "{0} above read length".format(tag) ax2.set_ylabel(ylabel2) for ax in (ax1, ax2): set_ticklabels_helvetica(ax) ax.set_xlim((xmin - width / 2, xmax + width / 2)) tc = "gray" axt = ax1.transAxes xx, yy = 0.95, 0.95 ma = "Total bases: {0}".format(hsize) mb = "Total reads: {0}".format(thousands(len(sizes))) mc = "Average read length: {0}bp".format(thousands(np.mean(all_sizes))) md = "Median read length: {0}bp".format(thousands(np.median(all_sizes))) me = "N50 read length: {0}bp".format(thousands(l50)) for t in (ma, mb, mc, md, me): print(t, file=sys.stderr) ax1.text(xx, yy, t, color=tc, transform=axt, ha="right") yy -= 0.05 ax1.set_title(markup(opts.title)) # Seaborn removes ticks for all styles except 'ticks'. Now add them back: ax1.tick_params( axis="x", direction="out", length=3, left=False, right=False, top=False, bottom=True, ) ax1.xaxis.set_major_formatter(human_base_formatter) ax1.yaxis.set_major_formatter(human_formatter) figname = sizes.filename + ".pdf" savefig(figname)
def report(args): ''' %prog report ksfile generate a report given a Ks result file (as produced by synonymous_calc.py). describe the median Ks, Ka values, as well as the distribution in stem-leaf plot ''' from jcvi.graphics.histogram import stem_leaf_plot p = OptionParser(report.__doc__) p.add_option("--vmax", default=2., type="float", help="Maximum value, inclusive [default: %default]") p.add_option("--bins", default=20, type="int", help="Number of bins to plot in the histogram [default: %default]") p.add_option("--pdf", default=False, action="store_true", help="Generate graphic output for the histogram [default: %default]") p.add_option("--components", default=1, type="int", help="Number of components to decompose peaks [default: %default]") opts, args = p.parse_args(args) if len(args) != 1: sys.exit(not p.print_help()) ks_file, = args header, data = read_ks_file(ks_file) ks_max = opts.vmax for f in fields.split()[1:]: columndata = [getattr(x, f) for x in data] title = "{0}: {1:.2f}".format(descriptions[f], np.median(columndata)) title += " ({0:.2f} +/- {1:.2f})".\ format(np.mean(columndata), np.std(columndata)) ks = ("ks" in f) if not ks: continue bins = (0, ks_max, opts.bins) if ks else (0, .6, 10) digit = 1 if ks else 2 stem_leaf_plot(columndata, *bins, digit=digit, title=title) if not opts.pdf: return from jcvi.graphics.base import mpl, _, tex_formatter, tex_1digit_formatter from matplotlib.backends.backend_agg import FigureCanvasAgg as FigureCanvas fig = mpl.figure.Figure(figsize=(5, 5)) canvas = FigureCanvas(fig) ax = fig.add_axes([.12, .1, .8, .8]) components = opts.components data = [x.ng_ks for x in data] interval = ks_max / opts.bins line, line_mixture = plot_ks_dist(ax, data, interval, components, ks_max, color='r') leg = ax.legend((line, line_mixture), ("Ks", "Ks (fitted)"), shadow=True, fancybox=True, prop={"size": 10}) leg.get_frame().set_alpha(.5) ax.set_xlim((0, ks_max)) ax.set_title(_('Ks distribution'), fontweight="bold") ax.set_xlabel(_('Synonymous substitutions per site (Ks)')) ax.set_ylabel(_('Percentage of gene pairs')) ax.xaxis.set_major_formatter(tex_1digit_formatter) ax.yaxis.set_major_formatter(tex_formatter) image_name = "Ks_plot.pdf" canvas.print_figure(image_name, dpi=300) logging.debug("Print image to `{0}`.".format(image_name))
def htg(args): """ %prog htg fastafile template.sbt Prepare sqnfiles for Genbank HTG submission to update existing records. `fastafile` contains the records to update, multiple records are allowed (with each one generating separate sqn file in the sqn/ folder). The record defline has the accession ID. For example, >AC148290.3 Internally, this generates two additional files (phasefile and namesfile) and download records from Genbank. Below is implementation details: `phasefile` contains, for each accession, phase information. For example: AC148290.3 3 HTG 2 mth2-45h12 which means this is a Phase-3 BAC. Record with only a single contig will be labeled as Phase-3 regardless of the info in the `phasefile`. Template file is the Genbank sbt template. See jcvi.formats.sbt for generation of such files. Another problem is that Genbank requires the name of the sequence to stay the same when updating and will kick back with a table of name conflicts. For example: We are unable to process the updates for these entries for the following reason: Seqname has changed Accession Old seq_name New seq_name --------- ------------ ------------ AC239792 mtg2_29457 AC239792.1 To prepare a submission, this script downloads genbank and asn.1 format, and generate the phase file and the names file (use formats.agp.phase() and apps.gbsubmit.asn(), respectively). These get automatically run. However, use --phases if the genbank files contain outdated information. For example, the clone name changes or phase upgrades. In this case, run formats.agp.phase() manually, modify the phasefile and use --phases to override. """ from jcvi.formats.fasta import sequin, ids from jcvi.formats.agp import phase from jcvi.apps.fetch import entrez p = OptionParser(htg.__doc__) p.add_option( "--phases", default=None, help="Use another phasefile to override", ) p.add_option("--comment", default="", help="Comments for this update") opts, args = p.parse_args(args) if len(args) != 2: sys.exit(not p.print_help()) fastafile, sbtfile = args pf = fastafile.rsplit(".", 1)[0] idsfile = pf + ".ids" phasefile = pf + ".phases" namesfile = pf + ".names" ids([fastafile, "--outfile={0}".format(idsfile)]) asndir = "asn.1" mkdir(asndir) entrez([idsfile, "--format=asn.1", "--outdir={0}".format(asndir)]) asn(glob("{0}/*".format(asndir)) + ["--outfile={0}".format(namesfile)]) if opts.phases is None: gbdir = "gb" mkdir(gbdir) entrez([idsfile, "--format=gb", "--outdir={0}".format(gbdir)]) phase( glob("{0}/*".format(gbdir)) + ["--outfile={0}".format(phasefile)]) else: phasefile = opts.phases assert op.exists(namesfile) and op.exists(phasefile) newphasefile = phasefile + ".new" newphasefw = open(newphasefile, "w") comment = opts.comment fastadir = "fasta" sqndir = "sqn" mkdir(fastadir) mkdir(sqndir) from jcvi.graphics.histogram import stem_leaf_plot names = DictFile(namesfile) assert len(set(names.keys())) == len(set(names.values())) phases = DictFile(phasefile) ph = [int(x) for x in phases.values()] # vmin 1, vmax 4, bins 3 stem_leaf_plot(ph, 1, 4, 3, title="Counts of phases before updates") logging.debug("Information loaded for {0} records.".format(len(phases))) assert len(names) == len(phases) newph = [] cmd = "faSplit byname {0} {1}/".format(fastafile, fastadir) sh(cmd, outfile="/dev/null", errfile="/dev/null") acmd = "tbl2asn -a z -p fasta -r {sqndir}" acmd += " -i {splitfile} -t {sbtfile} -C tigr" acmd += ' -j "{qualifiers}"' acmd += " -A {accession_nv} -o {sqndir}/{accession_nv}.sqn -V Vbr" acmd += ' -y "{comment}" -W T -T T' qq = "[tech=htgs {phase}] [organism=Medicago truncatula] [strain=A17]" nupdated = 0 for row in open(phasefile): atoms = row.rstrip().split("\t") # see formats.agp.phase() for column contents accession, phase, clone = atoms[0], atoms[1], atoms[-1] fafile = op.join(fastadir, accession + ".fa") accession_nv = accession.split(".", 1)[0] newid = names[accession_nv] newidopt = "--newid={0}".format(newid) cloneopt = "--clone={0}".format(clone) splitfile, gaps = sequin([fafile, newidopt, cloneopt]) splitfile = op.basename(splitfile) phase = int(phase) assert phase in (1, 2, 3) oldphase = phase if gaps == 0 and phase != 3: phase = 3 if gaps != 0 and phase == 3: phase = 2 print("{0}\t{1}\t{2}".format(accession_nv, oldphase, phase), file=newphasefw) newph.append(phase) qualifiers = qq.format(phase=phase) if ";" in clone: qualifiers += " [keyword=HTGS_POOLED_MULTICLONE]" cmd = acmd.format( accession=accession, accession_nv=accession_nv, sqndir=sqndir, sbtfile=sbtfile, splitfile=splitfile, qualifiers=qualifiers, comment=comment, ) sh(cmd) verify_sqn(sqndir, accession) nupdated += 1 stem_leaf_plot(newph, 1, 4, 3, title="Counts of phases after updates") print("A total of {0} records updated.".format(nupdated), file=sys.stderr)
def report(args): ''' %prog report ksfile generate a report given a Ks result file (as produced by synonymous_calc.py). describe the median Ks, Ka values, as well as the distribution in stem-leaf plot ''' from jcvi.graphics.histogram import stem_leaf_plot p = OptionParser(report.__doc__) p.add_option("--vmax", default=2., type="float", help="Maximum value, inclusive [default: %default]") p.add_option( "--bins", default=20, type="int", help="Number of bins to plot in the histogram [default: %default]") p.add_option( "--pdf", default=False, action="store_true", help="Generate graphic output for the histogram [default: %default]") p.add_option( "--components", default=1, type="int", help="Number of components to decompose peaks [default: %default]") opts, args = p.parse_args(args) if len(args) != 1: sys.exit(not p.print_help()) ks_file, = args header, data = read_ks_file(ks_file) ks_max = opts.vmax for f in fields.split()[1:]: columndata = [getattr(x, f) for x in data] title = "{0}: {1:.2f}".format(descriptions[f], np.median(columndata)) title += " ({0:.2f} +/- {1:.2f})".\ format(np.mean(columndata), np.std(columndata)) ks = ("ks" in f) if not ks: continue bins = (0, ks_max, opts.bins) if ks else (0, .6, 10) digit = 1 if ks else 2 stem_leaf_plot(columndata, *bins, digit=digit, title=title) if not opts.pdf: return from jcvi.graphics.base import mpl, _, tex_formatter, tex_1digit_formatter from matplotlib.backends.backend_agg import FigureCanvasAgg as FigureCanvas fig = mpl.figure.Figure(figsize=(5, 5)) canvas = FigureCanvas(fig) ax = fig.add_axes([.12, .1, .8, .8]) components = opts.components data = [x.ng_ks for x in data] interval = ks_max / opts.bins line, line_mixture = plot_ks_dist(ax, data, interval, components, ks_max, color='r') leg = ax.legend((line, line_mixture), ("Ks", "Ks (fitted)"), shadow=True, fancybox=True, prop={"size": 10}) leg.get_frame().set_alpha(.5) ax.set_xlim((0, ks_max)) ax.set_title(_('Ks distribution'), fontweight="bold") ax.set_xlabel(_('Synonymous substitutions per site (Ks)')) ax.set_ylabel(_('Percentage of gene pairs')) ax.xaxis.set_major_formatter(tex_1digit_formatter) ax.yaxis.set_major_formatter(tex_formatter) image_name = "Ks_plot.pdf" canvas.print_figure(image_name, dpi=300) logging.debug("Print image to `{0}`.".format(image_name))