Пример #1
0
    def _plot_with_rpy2(self, regions, filename):
        from rpy2 import robjects
        import rpy2.robjects.lib.ggplot2 as ggplot2
        from rpy2.robjects.lib import grid
        from rpy2.robjects.packages import importr
        grdevices = importr('grDevices')
        base = importr('base')
        grdevices.pdf(file=filename + '.pdf')

        t = [x for x in range(-self.num_bins, self.num_bins + 1)]
        for region in regions[:self.num_regs]:
            if not np.any(region.weighted):
                logger.warning(
                    "Warning: No data for region located on bin " + str(region.bin) + ". Not plotting this one.")
                continue
            middle = (len(region.weighted[0]) - 1) / 2
            if middle < self.num_bins:
                logger.error("Warning: There are less bins calculated for regions than you want to plot.")
                sys.exit(1)
            d = {'map': robjects.StrVector(
                [str(m) for sublist in [[x] * len(t) for x in range(len(region.weighted))] for m in sublist]),
                't': robjects.FloatVector(t * len(region.weighted)),
                'e': robjects.FloatVector([i for sublist in region.weighted for i in
                                           sublist[middle - self.num_bins:middle + self.num_bins + 1]]),
                'p': robjects.FloatVector([-np.log10(x) for sublist in region.pvalues for x in
                                           sublist[middle - self.num_bins:middle + self.num_bins + 1]]),
                'c': robjects.FloatVector([-np.log10(x) for sublist in region.corrected_pvalues for x in
                                           sublist[middle - self.num_bins:middle + self.num_bins + 1]])}
            dataf = robjects.DataFrame(d)
            gp = ggplot2.ggplot(dataf)  # first yellow second red
            p1 = gp + ggplot2.geom_line(mapping=ggplot2.aes_string(x='t', y='e', group='map', colour='map'),
                                        alpha=0.8) + ggplot2.scale_y_continuous(trans='log2') + ggplot2.ggtitle(
                "\n".join(wrap("Bin " + str(region.bin) + " : " + str(region.positions)))) + ggplot2.labs(
                y="log Intensity") + ggplot2.theme_classic() + ggplot2.theme(
                **{'axis.title.x': ggplot2.element_blank(), 'axis.text.y': ggplot2.element_text(angle=45),
                   'axis.text.x': ggplot2.element_blank(),
                   'legend.position': 'none'}) + ggplot2.scale_colour_brewer(palette="Set1")
            p2 = gp + ggplot2.geom_line(mapping=ggplot2.aes_string(x='t', y='p', group='map', colour='map'),
                                        alpha=0.8) + ggplot2.labs(
                y="-log10(p-value)") + ggplot2.theme_classic() + ggplot2.theme(
                **{'axis.title.x': ggplot2.element_blank(), 'axis.text.x': ggplot2.element_blank(),
                   'legend.position': 'none'}) + ggplot2.scale_colour_brewer(palette="Set1")
            p3 = gp + ggplot2.geom_line(mapping=ggplot2.aes_string(x='t', y='c', group='map', colour='map'),
                                        alpha=0.8) + ggplot2.labs(y="-log10(q-value)",
                                                                  x='bins (' + str(self.bin_res) + ' bp each)') + \
                 ggplot2.geom_hline(mapping=ggplot2.aes_string(yintercept=str(-np.log10(self.threshold))),
                                    colour='black', alpha=0.8, linetype='dashed') + ggplot2.theme_classic() + \
                 ggplot2.theme(**{'legend.position': 'none'}) + ggplot2.scale_colour_brewer(palette="Set1")
            g1 = ggplot2.ggplot2.ggplotGrob(p1)
            g2 = ggplot2.ggplot2.ggplotGrob(p2)
            g3 = ggplot2.ggplot2.ggplotGrob(p3)
            robjects.globalenv["g"] = base.rbind(g1, g2, g3, size='first')
            robjects.r("grid::grid.draw(g)")
            grid.newpage()
            logger.debug('Plotted region ' + str(region.bin))

        grdevices.dev_off()
Пример #2
0
def get_nogrid_theme():
    """
    Get no grid theme for ggplot2.
    """
    nogrid_x_theme = theme(**{'panel.grid.major.x': element_blank(),
                              'panel.grid.minor.x': element_blank(),
                              'panel.grid.major.y': element_blank(),
                              'panel.grid.minor.y': element_blank()})
    return nogrid_x_theme
Пример #3
0
def generate_histogram(subgroups_to_sses_to_n_count, tname, file_name):
    columns_to_data = {'subgroup': [], tname: [], 'count': []}
    max_count = 0
    for subgroup, sses_to_n_count in subgroups_to_sses_to_n_count.items():
        for ss, n_count in sses_to_n_count.items():
            columns_to_data['subgroup'].append(subgroup)
            columns_to_data[tname].append(ss)
            columns_to_data['count'].append(n_count)
            if n_count > max_count:
                max_count = n_count
    r_columns_to_data = {
        'subgroup':
        ro.FactorVector(columns_to_data['subgroup'],
                        levels=ro.StrVector(
                            _sort_subgroup(set(columns_to_data['subgroup'])))),
        tname:
        ro.StrVector(columns_to_data[tname]),
        'count':
        ro.IntVector(columns_to_data['count'])
    }
    df = ro.DataFrame(r_columns_to_data)

    max_count = int(max_count / 1000 * 1000 + 1000)
    histogram_file_path = os.path.join(OUTPUT_PATH, file_name)
    logging.debug(
        str.format("The Data Frame for file {}: \n{}", histogram_file_path,
                   df))

    grdevices.png(file=histogram_file_path, width=1200, height=800)
    gp = ggplot2.ggplot(df)
    pp = gp + \
         ggplot2.aes_string(x='subgroup', y='count', fill=tname) + \
         ggplot2.geom_bar(position="dodge",width=0.8, stat="identity") + \
         ggplot2.theme_bw() + \
         ggplot2.theme_classic() + \
         ggplot2.theme(**{'legend.title': ggplot2.element_blank()}) + \
         ggplot2.theme(**{'legend.text': ggplot2.element_text(size=40)}) + \
         ggplot2.theme(**{'axis.text.x': ggplot2.element_text(size=40,angle=45)}) + \
         ggplot2.theme(**{'axis.text.y': ggplot2.element_text(size=40)}) + \
         ggplot2.scale_y_continuous(expand=ro.IntVector([0, 0]),
                                    limits=ro.IntVector([0, max_count])) + \
         ggplot2.geom_text(ggplot2.aes_string(label='count'), size=6, angle=35, hjust=-0.1,
                           position=ggplot2.position_dodge(width=0.8),
                           vjust=-0.2)

    pp.plot()
    logging.info(str.format("Output step3 file {}", histogram_file_path))
    grdevices.dev_off()
Пример #4
0
def generate_step3_5_lrr_acc20_line_chart(subgroups_to_lrrs_acc20mean,
                                          prefix=''):
    pandas2ri.activate()
    subgroups_to_lrr_count = {}
    columns_to_data = {'subgroup': [], 'pos': [], 'acc20': []}
    for subgroup, (acc20means,
                   acc20_count) in subgroups_to_lrrs_acc20mean.items():
        subgroups_to_lrr_count[subgroup] = acc20_count
        for index, acc20mean in enumerate(acc20means):
            columns_to_data['subgroup'].append(subgroup)
            columns_to_data['pos'].append(index + 1)
            columns_to_data['acc20'].append(acc20mean)

    # Write the count of LRRs for each subgroup to file
    with open(os.path.join(OUTPUT_PATH, prefix + "step3_5_lrr_count.txt"),
              'w') as f:
        for subgroup, lrr_count in subgroups_to_lrr_count.items():
            f.write(str.format("{}: {}\n", subgroup, lrr_count))

    # Generate the line chart file
    r_columns_to_data = {
        'subgroup': ro.StrVector(columns_to_data['subgroup']),
        'pos': ro.IntVector(columns_to_data['pos']),
        'acc20': ro.FloatVector(columns_to_data['acc20'])
    }
    df = ro.DataFrame(r_columns_to_data)

    line_chart_file_path = os.path.join(OUTPUT_PATH,
                                        prefix + "step3_5_lrr_acc20_line.png")
    logging.debug(
        str.format("The Data Frame for file {}: \n{}", line_chart_file_path,
                   df))
    grdevices.png(file=line_chart_file_path, width=1024, height=512)
    gp = ggplot2.ggplot(df)
    pp = gp + \
         ggplot2.theme_bw() + \
         ggplot2.theme_classic() + \
         ggplot2.theme(**{'axis.text.x': ggplot2.element_text(size=35)}) + \
         ggplot2.theme(**{'axis.text.y': ggplot2.element_text(size=35)}) + \
         ggplot2.aes_string(x='pos', y='acc20', group='subgroup', colour='subgroup') + \
         ggplot2.geom_point(size=4, shape=20) + \
         ggplot2.geom_line(size=3) + \
         ggplot2.theme(**{'legend.title': ggplot2.element_blank()}) + \
         ggplot2.theme(**{'legend.text': ggplot2.element_text(size=20)}) + \
         ggplot2.scale_x_continuous(breaks=ro.IntVector(range(1, 25)), labels=ro.StrVector(list('LxxLxLxxNxLsGxIPxxLxxLxx')))
    pp.plot()
    logging.info(str.format("Output step3 file {}", line_chart_file_path))
    grdevices.dev_off()
Пример #5
0
def _generate_step3_5_ss_acc20_line_chart(ts_to_acc20s, tname,
                                          line_chart_file_path):
    logging.debug(
        str.format("Begin to generate {}, data {}", line_chart_file_path,
                   ts_to_acc20s))
    ts_to_acc20mean = calc_acc20mean_by_types(ts_to_acc20s)
    columns_to_data = {tname: [], 'site': [], 'acc20': []}
    for ss, acc20means in ts_to_acc20mean.items():
        for index, acc20mean in enumerate(acc20means):
            columns_to_data[tname].append(ss)
            columns_to_data['site'].append(index - 5)
            columns_to_data['acc20'].append(acc20mean)

    # Generate the line chart file
    r_columns_to_data = {
        tname: ro.StrVector(columns_to_data[tname]),
        'site': ro.IntVector(columns_to_data['site']),
        'acc20': ro.FloatVector(columns_to_data['acc20'])
    }
    df = ro.DataFrame(r_columns_to_data)

    logging.debug(
        str.format("The Data Frame for file {}: \n{}", line_chart_file_path,
                   df))
    grdevices.png(file=line_chart_file_path, width=1024, height=512)
    gp = ggplot2.ggplot(df)
    pp = gp + \
         ggplot2.theme_bw() + \
         ggplot2.theme_classic() + \
         ggplot2.theme(**{'axis.text.x': ggplot2.element_text(size=35)}) + \
         ggplot2.theme(**{'axis.text.y': ggplot2.element_text(size=35)}) + \
         ggplot2.aes_string(x='site', y='acc20', group=tname, colour=tname) + \
         ggplot2.geom_point(size=4, shape=20) + \
         ggplot2.geom_line(size=3) + \
         ggplot2.theme(**{'legend.title': ggplot2.element_blank()}) + \
         ggplot2.theme(**{'legend.text': ggplot2.element_text(size=20)}) + \
         ggplot2.scale_x_continuous(breaks=ro.IntVector(list(range(-5, 6))),
                                    labels=ro.StrVector(['-5', '-4', '-3', '-2', '-1', 'N', '1', '2', '3', '4', '5']))
    pp.plot()
    logging.info(str.format("Output step3 file {}", line_chart_file_path))
    grdevices.dev_off()
Пример #6
0
 def test_element_blank(self):
     eb = ggplot2.element_blank()
     assert isinstance(eb, ggplot2.ElementBlank)
Пример #7
0
                                  y = 'lat', \
                                  group = 'group', \
                                  color = 'ObamaShare', \ 
                                  fill = 'ObamaShare')) + \
 ggplot2.scale_fill_gradient(high = 'blue', \
                             low = 'red') + \
 ggplot2.scale_fill_continuous(name = "Obama Vote Share") + \
 ggplot2.scale_colour_continuous(name = "Obama Vote Share") + \
 ggplot2.theme(**{ 'legend.position': 'left', \ 
                   'legend.key.size': R.r.unit(2, 'lines'), \
                   'legend.title' : ggplot2.element_text(size = 14, hjust=0), \
                   'legend.text': ggplot2.element_text(size = 12), \ 
                   'title' : ggplot2.element_text('Obama Vote Share and Distance to Railroads in IL'), \
                   'plot.title': ggplot2.element_text(size = 24),
                   'plot.margin': R.r.unit(R.r.rep(0,4),'lines'), \
                   'panel.background': ggplot2.element_blank(), \
                   'panel.grid.minor': ggplot2.element_blank(), \
                   'panel.grid.major': ggplot2.element_blank(), \
                   'axis.ticks': ggplot2.element_blank(), \ 
                   'axis.title.x': ggplot2.element_blank(), \
                   'axis.title.y': ggplot2.element_blank(), \
                   'axis.title.x': ggplot2.element_blank(), \
                   'axis.title.x': ggplot2.element_blank(), \
                   'axis.text.x': ggplot2.element_blank(), \
                   'axis.text.y': ggplot2.element_blank()} ) + \
 ggplot2.geom_line(ggplot2.aes(x='long',
                               y='lat',
                               group='group'),
                   data=IL_railroads,
                   color='grey',
                   size=0.2) + \
def plot_volcano_with_r(
    data,
    xlabel='Estimated effect (change in H/L ratio)',
    title='',
    max_labels=20,
    color_background='#737373',
    color_significant='#252525',
    color_significant_muted='#252525',
    label_only_large_fc=False,
    special_labels=None,
    special_palette=None,
    base_size=12,
    label_size=3,
    x='logFC',
    y='neg_log10_p_adjust',
    special_labels_mode='all',
    xlim=None,
    skip_labels=None,
    nudges=None,
):

    r_data, r_like_data = transform_data_for_ggplot(
        data,
        label_only_large_fc=label_only_large_fc,
        special_labels=special_labels,
        max_labels=max_labels,
        special_labels_mode=special_labels_mode,
        skip_labels=skip_labels,
        nudges=nudges)

    plot = r_ggplot2.ggplot(r_data)
    plot += r_ggplot2.theme_minimal(base_size=base_size)
    plot += r_ggplot2.theme(
        **{
            'panel.grid.major':
            r_ggplot2.element_blank(),
            'panel.grid.minor':
            r_ggplot2.element_blank(),
            'panel.border':
            r_ggplot2.element_rect(fill=robjects.rinterface.NA, color="black")
        })
    plot += r_ggplot2.theme(
        text=r_ggplot2.element_text(family='Helvetica', face='plain'))
    plot += r_ggplot2.theme(
        **{
            'plot.title': r_ggplot2.element_text(hjust=0.5),
            #                               'axis.title.y': r_ggplot2.element_text((t = 0, r = 20, b = 0, l = 0)),
        })

    aes_points = r_ggplot2.aes_string(x=x, y=y, color='group')
    scale_points = r_ggplot2.scale_colour_manual(
        aes_points,
        values=r_label_palette(
            r_like_data,
            special_palette,
            color_background=color_background,
            color_significant=color_significant,
            color_significant_muted=color_significant_muted))

    plot += aes_points
    plot += scale_points

    if xlim is not None:
        plot += r_ggplot2.scale_x_continuous(
            labels=r_custom.formatterFunTwoDigits, limits=robjects.r.c(*xlim))
    else:
        plot += r_ggplot2.scale_x_continuous(
            labels=r_custom.formatterFunTwoDigits)

    plot += r_ggplot2.scale_y_continuous(labels=r_custom.formatterFunOneDigit)

    plot += r_ggplot2.geom_hline(
        yintercept=float(-np.log10(FDR_THRESHOLD_RESPONSE)),
        color='#BDBDBD',
        alpha=.3)
    plot += r_ggplot2.geom_vline(xintercept=float(FC_THRESHOLD_RESPONSE),
                                 color='#BDBDBD',
                                 alpha=.3)
    plot += r_ggplot2.geom_vline(xintercept=-float(FC_THRESHOLD_RESPONSE),
                                 color='#BDBDBD',
                                 alpha=.3)

    plot += r_ggplot2.geom_point(**{'show.legend': False})

    aes_text = r_ggplot2.aes_string(label='label')
    plot += aes_text
    plot += r_ggrepel.geom_text_repel(
        aes_text,
        nudge_x=r_dollar(r_data, 'nudgex'),
        nudge_y=r_dollar(r_data, 'nudgey'),
        size=label_size,
        family='Helvetica',
        **{
            'show.legend': False,
            'point.padding': 0.25,
            'min.segment.length': 0,
            #'max.iter':0,
            'segment.color': '#BDBDBD'
        },
    )

    plot += r_ggplot2.labs(x=xlabel,
                           y='Adjusted p value (-log10)',
                           title=title)

    plot.plot()
Пример #9
0
#print robjects.r('packageVersion("ggplot2")')

#--------------------------------------------------------------------#
#                               Annotation                           #
#--------------------------------------------------------------------#
mytheme = {
        'panel.background':ggplot2.element_rect(fill='white',colour='white'),
        'axis.text':ggplot2.element_text(colour="black",size=15,
                                         family=FONTFAM),
        'axis.line':ggplot2.ggplot2.element_line(size = 1.2, colour="black"),
        'axis.title':ggplot2.element_text(colour="black",size=15,
                                          family=FONTFAM),
        'plot.title':ggplot2.element_text(face="bold", size=20,
                                          colour="black",family=FONTFAM),
        'panel.grid.minor':ggplot2.element_blank(),
        'panel.grid.major':ggplot2.element_blank(),
        'legend.key':ggplot2.element_blank(),
        'legend.text':ggplot2.element_text(colour="black",size=15,
                                           family=FONTFAM),
        'strip.text.y':ggplot2.element_text(colour="black",face="bold",
                                            size=15,family=FONTFAM),
        'strip.text.x':ggplot2.element_text(colour="black",face="bold",
                                            size=15,family=FONTFAM),
        'text':ggplot2.element_text(colour="black",family=FONTFAM)
        }
        #'panel.grid.major':ggplot2.theme_line(colour = "grey90"),

pointtheme = {
        'panel.background':ggplot2.element_rect(fill='white',colour='black',size=2),
        'axis.text':ggplot2.element_text(colour="black",size=15,family=FONTFAM),
Пример #10
0
    #print(palette)
  color_background = "white"
  color_grid_major = palette[3]
  color_axis_text = palette[6]
  color_axis_title = palette[7]
  color_title = palette[9]
  #palette_lines <- brewer.pal("Dark2", n=3)
  palette_lines <- brewer.pal("Set2", n=8)
  palette_repeat <- c('#66C2A5', '#66C2A5', '#FC8D62','#FC8D62')
  linetype_repeat <- c("solid","dashed","solid","dashed")
''')

fte_theme = theme(
    **{
        'axis.ticks':
        element_blank(),
        'panel.background':
        element_rect(fill=robjects.r.color_background,
                     color=robjects.r.color_background),
        'plot.background':
        element_rect(fill=robjects.r.color_background,
                     color=robjects.r.color_background),
        'panel.border':
        element_rect(
            color=robjects.r.color_background
        ),  #'panel.grid.major':element_line(color=robjects.r.color_grid_major, size = 0.25),
        'panel.grid.minor':
        element_blank(),
        'axis.ticks':
        element_blank(),
        'legend.position':
Пример #11
0

robjects.r('''
    library(RColorBrewer)
    library(grid)
    palette <- brewer.pal("Greys", n=9)
  color_background = palette[2]
  color_grid_major = palette[3]
  color_axis_text = palette[6]
  color_axis_title = palette[7]
  color_title = palette[9]
  palette_lines <- brewer.pal("Set2", n=8)
''')

size = 9
fte_theme = theme(**{'axis.ticks':element_blank(),
      'panel.background':element_rect(fill=robjects.r.color_background, color=robjects.r.color_background),
      'plot.background':element_rect(fill=robjects.r.color_background, color=robjects.r.color_background),
      'panel.border':element_rect(color=robjects.r.color_background),
      'panel.grid.minor':element_blank(),
      'axis.ticks':element_blank(),
      'legend.position':"right",
      'legend.background': element_rect(fill="transparent"),
      'legend.text': element_text(size=size,color=robjects.r.color_axis_title),
      'legend.title': element_text(size=size,color=robjects.r.color_axis_title),
      'plot.title':element_text(color=robjects.r.color_title, size=10, vjust=1.25),
      'axis.text.x':element_text(size=size,color=robjects.r.color_axis_text),
      'axis.text.y':element_text(size=size,color=robjects.r.color_axis_text),
      'axis.title.x':element_text(size=size,color=robjects.r.color_axis_title, vjust=0),
      #'panel.grid.major':element_line(color=robjects.r.color_grid_major,size=.25),
      'axis.title.y':element_text(size=size,color=robjects.r.color_axis_title,angle=90)})
Пример #12
0
def plot_qc_reads(qc_df):
    """
    Plot number of reads part of a pipeline QC file.
    """
    # Record NA values as 0
    qc_df = qc_df.fillna(0)#.set_index("sample")
    cols = ["sample",
            "num_reads",
            "num_mapped",
            "num_unique_mapped",
            "num_junctions"]
    qc_df = qc_df[cols]
    melted_qc = pandas.melt(qc_df, id_vars=["sample"])
    qc_r = conversion_pydataframe(melted_qc)
    labels = tuple(["num_reads",
                    "num_mapped",
                    "num_unique_mapped",
                    "num_junctions"])
    labels = robj.StrVector(labels)
    variable_i = qc_r.names.index('variable')
    qc_r[variable_i] = robj.FactorVector(qc_r[variable_i],
                                         levels = labels)
    ggplot2.theme_set(ggplot2.theme_bw(12))
    scales = importr("scales")
    r_opts = r.options(scipen=4)
    p = ggplot2.ggplot(qc_r) + \
        ggplot2.geom_point(aes_string(x="sample", y="value")) + \
        ggplot2.scale_y_continuous(trans=scales.log10_trans(),
                                   breaks=scales.trans_breaks("log10",
                                                              robj.r('function(x) 10^x')),
                                   labels=scales.trans_format("log10",
                                                              robj.r('math_format(10^.x)'))) + \
        r.xlab("CLIP-Seq samples") + \
        r.ylab("No. reads") + \
        ggplot2.coord_flip() + \
        ggplot2.facet_wrap(Formula("~ variable"), ncol=1) + \
        theme(**{"panel.grid.major.x": element_blank(),
                 "panel.grid.minor.x": element_blank(),
                 "panel.grid.major.y": theme_line(size=0.5,colour="grey66",linetype=3)})
    p.plot()

    return
    r.par(mfrow=np.array([1,2]))
    num_samples = len(qc_df.num_reads)
    r.par(bty="n", lwd=1.7, lty=2)
    r_opts = r.options(scipen=4)
    r.options(r_opts)
    r.dotchart(convert_to_r_matrix(qc_df[["num_reads",
                                          "num_mapped",
                                          "num_unique_mapped"]]),
               xlab="No. reads",
               lcolor="black",
               pch=19,
               gcolor="darkblue",
               cex=0.8)
    r.par(bty="n")
    r.dotchart(convert_to_r_matrix(qc_df[["num_ribosub_mapped",
                                          "num_ribo",
                                          "num_junctions"]]),
               xlab="No. reads",
               lcolor="black",
               pch=19,
               gcolor="darkblue",
               cex=0.8)