def ilr_phylogenetic( table: pd.DataFrame, tree: skbio.TreeNode, pseudocount: float = 0.5) -> (pd.DataFrame, skbio.TreeNode): t = tree.copy() t.bifurcate() t = rename_internal_nodes(t) return ilr_transform(add_pseudocount(table, pseudocount), t), t
def test_add_pseudocount_3(self): table = pd.DataFrame([[1.7, 1.3, 0.5], [1.5, 3.2, 1.1]], columns=['a', 'b', 'c'], index=[1, 2]) obs = add_pseudocount(table, 2.0) exp = pd.DataFrame([[1.7, 1.3, 0.5], [1.5, 3.2, 1.1]], columns=['a', 'b', 'c'], index=[1, 2]) pdt.assert_frame_equal(obs, exp)
def test_add_pseudocount_2(self): table = pd.DataFrame( [[1.0, 2.0, 2.5], [0.5, 0.0, 1.0], [0.0, 0.5, 1.0]], columns=['a', 'b', 'c'], index=[1, 2, 3]) obs = add_pseudocount(table, 0.5) exp = pd.DataFrame( [[1.0, 2.0, 2.5], [0.5, 0.5, 1.0], [0.5, 0.5, 1.0]], columns=['a', 'b', 'c'], index=[1, 2, 3]) pdt.assert_frame_equal(obs, exp)
def test_add_pseudocount(self): table = pd.DataFrame( [[1., 2., 3., 4.], [1., 0., 2., 1.], [0., 2., 1., 3.]], columns=['a', 'b', 'c', 'd'], index=[1, 2, 3]) obs = add_pseudocount(table) exp = pd.DataFrame( [[1., 2., 3., 4.], [1., 0.5, 2., 1.], [0.5, 2., 1., 3.]], columns=['a', 'b', 'c', 'd'], index=[1, 2, 3]) pdt.assert_frame_equal(obs, exp)
def correlation_clustering(table: pd.DataFrame, pseudocount: float = 0.5 ) -> skbio.TreeNode: """ Builds a tree for features based on correlation. Parameters ---------- table : pd.DataFrame Contingency table where rows are samples and columns are features. In addition, the table must have strictly nonzero values. Returns ------- skbio.TreeNode Represents the partitioning of features with respect to correlation. """ t = correlation_linkage(add_pseudocount(table, pseudocount)) return t
def ilr_phylogenetic_ordination( table: pd.DataFrame, tree: skbio.TreeNode, pseudocount: float = 0.5, top_k_var: int = 10, clades: list = None ) -> (OrdinationResults, skbio.TreeNode, pd.DataFrame): t = tree.copy() t.bifurcate() _table, _tree = match_tips(table, t) _tree = rename_internal_nodes(_tree) if not clades: in_nodes = [n.name for n in _tree.levelorder() if not n.is_tip()] basis = _balance_basis(_tree)[0] _table = add_pseudocount(_table, pseudocount) basis = pd.DataFrame(basis.T, index=_table.columns, columns=in_nodes) balances = np.log(_table) @ basis var = balances.var(axis=0).sort_values(ascending=False) clades = var.index[:top_k_var] balances = balances[clades] basis = basis[clades] else: clades = clades[0].split(',') balances, basis = _fast_ilr(_tree, _table, clades, pseudocount=0.5) var = balances.var(axis=0).sort_values(ascending=False) balances.index.name = 'sampleid' # feature metadata eigvals = var prop = var[clades] / var.sum() balances = OrdinationResults( short_method_name='ILR', long_method_name='Phylogenetic Isometric Log Ratio Transform', samples=balances, features=pd.DataFrame(np.eye(len(clades)), index=clades), eigvals=eigvals, proportion_explained=prop) basis.index.name = 'featureid' return balances, _tree, basis
def dendrogram_heatmap(output_dir: str, table: pd.DataFrame, tree: TreeNode, metadata: qiime2.CategoricalMetadataColumn, pseudocount: float = 0.5, ndim: int = 10, method: str = 'clr', color_map: str = 'viridis'): table, tree = match_tips(add_pseudocount(table, pseudocount), tree) nodes = [n.name for n in tree.levelorder() if not n.is_tip()] nlen = min(ndim, len(nodes)) numerator_color, denominator_color = '#fb9a99', '#e31a1c' highlights = pd.DataFrame([[numerator_color, denominator_color]] * nlen, index=nodes[:nlen]) if method == 'clr': mat = pd.DataFrame(clr(centralize(table)), index=table.index, columns=table.columns) elif method == 'log': mat = pd.DataFrame(np.log(table), index=table.index, columns=table.columns) c = metadata.to_series() table, c = match(table, c) # TODO: There are a few hard-coded constants here # will need to have some adaptive defaults set in the future fig = heatmap(mat, tree, c, highlights, cmap=color_map, highlight_width=0.01, figsize=(12, 8)) fig.savefig(os.path.join(output_dir, 'heatmap.svg')) fig.savefig(os.path.join(output_dir, 'heatmap.pdf')) css = r""" .square { float: left; width: 100px; height: 20px; margin: 5px; border: 1px solid rgba(0, 0, 0, .2); } .numerator { background: %s; } .denominator { background: %s; } """ % (numerator_color, denominator_color) index_fp = os.path.join(output_dir, 'index.html') with open(index_fp, 'w') as index_f: index_f.write('<html><body>\n') index_f.write('<h1>Dendrogram heatmap</h1>\n') index_f.write('<img src="heatmap.svg" alt="heatmap">') index_f.write('<a href="heatmap.pdf">') index_f.write('Download as PDF</a><br>\n') index_f.write('<style>%s</style>' % css) index_f.write('<div class="square numerator">' 'Numerator<br/></div>') index_f.write('<div class="square denominator">' 'Denominator<br/></div>') index_f.write('</body></html>\n')
def balance_taxonomy(output_dir: str, table: pd.DataFrame, tree: TreeNode, taxonomy: pd.DataFrame, balance_name: str, pseudocount: float = 0.5, taxa_level: int = 0, n_features: int = 10, threshold: float = None, metadata: qiime2.MetadataColumn = None) -> None: if threshold is not None and isinstance(metadata, qiime2.CategoricalMetadataColumn): raise ValueError('Categorical metadata column detected. Only specify ' 'a threshold when using a numerical metadata column.') # make sure that the table and tree match up table, tree = match_tips(add_pseudocount(table, pseudocount), tree) # parse out headers for taxonomy taxa_data = list(taxonomy['Taxon'].apply(lambda x: x.split(';')).values) taxa_df = pd.DataFrame(taxa_data, index=taxonomy.index) # fill in NAs def f(x): y = np.array(list(map(lambda k: k is not None, x))) i = max(0, np.where(y)[0][-1]) x[np.logical_not(y)] = [x[i]] * np.sum(np.logical_not(y)) return x taxa_df = taxa_df.apply(f, axis=1) num_clade = tree.find(balance_name).children[NUMERATOR] denom_clade = tree.find(balance_name).children[DENOMINATOR] if num_clade.is_tip(): num_features = pd.DataFrame( {num_clade.name: taxa_df.loc[num_clade.name]} ).T r = 1 else: num_features = taxa_df.loc[num_clade.subset()] r = len(list(num_clade.tips())) if denom_clade.is_tip(): denom_features = pd.DataFrame( {denom_clade.name: taxa_df.loc[denom_clade.name]} ).T s = 1 else: denom_features = taxa_df.loc[denom_clade.subset()] s = len(list(denom_clade.tips())) b = (np.log(table.loc[:, num_features.index]).mean(axis=1) - np.log(table.loc[:, denom_features.index]).mean(axis=1)) b = b * np.sqrt(r * s / (r + s)) balances = pd.DataFrame(b, index=table.index, columns=[balance_name]) # the actual colors for the numerator and denominator num_color = sns.color_palette("Paired")[0] denom_color = sns.color_palette("Paired")[1] fig, (ax_num, ax_denom) = plt.subplots(2) balance_barplots(tree, balance_name, taxa_level, taxa_df, denom_color=denom_color, num_color=num_color, axes=(ax_num, ax_denom)) ax_num.set_title( r'$%s_{numerator} \; taxa \; (%d \; taxa)$' % ( balance_name, len(num_features))) ax_denom.set_title( r'$%s_{denominator} \; taxa \; (%d \; taxa)$' % ( balance_name, len(denom_features))) ax_denom.set_xlabel('Number of unique taxa') plt.tight_layout() fig.savefig(os.path.join(output_dir, 'barplots.svg')) fig.savefig(os.path.join(output_dir, 'barplots.pdf')) dcat = None multiple_cats = False if metadata is not None: fig2, ax = plt.subplots() c = metadata.to_series() data, c = match(balances, c) data[c.name] = c y = data[balance_name] # check if continuous if isinstance(metadata, qiime2.NumericMetadataColumn): ax.scatter(c.values, y) ax.set_xlabel(c.name) if threshold is None: threshold = c.mean() dcat = c.apply( lambda x: '%s < %f' % (c.name, threshold) if x < threshold else '%s > %f' % (c.name, threshold) ) sample_palette = pd.Series(sns.color_palette("Set2", 2), index=dcat.value_counts().index) elif isinstance(metadata, qiime2.CategoricalMetadataColumn): sample_palette = pd.Series( sns.color_palette("Set2", len(c.value_counts())), index=c.value_counts().index) try: pd.to_numeric(metadata.to_series()) except ValueError: pass else: raise ValueError('Categorical metadata column ' f'{metadata.name!r} contains only numerical ' 'values. At least one value must be ' 'non-numerical.') balance_boxplot(balance_name, data, y=c.name, ax=ax, palette=sample_palette) if len(c.value_counts()) > 2: warnings.warn( 'More than 2 categories detected in categorical metadata ' 'column. Proportion plots will not be displayed', stacklevel=2) multiple_cats = True else: dcat = c else: # Some other type of MetadataColumn raise NotImplementedError() ylabel = (r"$%s = \ln \frac{%s_{numerator}}" "{%s_{denominator}}$") % (balance_name, balance_name, balance_name) ax.set_title(ylabel, rotation=0) ax.set_ylabel('log ratio') fig2.savefig(os.path.join(output_dir, 'balance_metadata.svg')) fig2.savefig(os.path.join(output_dir, 'balance_metadata.pdf')) if not multiple_cats: # Proportion plots # first sort by clr values and calculate average fold change ctable = pd.DataFrame(clr(centralize(table)), index=table.index, columns=table.columns) left_group = dcat.value_counts().index[0] right_group = dcat.value_counts().index[1] lidx, ridx = (dcat == left_group), (dcat == right_group) if b.loc[lidx].mean() > b.loc[ridx].mean(): # double check ordering and switch if necessary # careful - the left group is also commonly associated with # the denominator. left_group = dcat.value_counts().index[1] right_group = dcat.value_counts().index[0] lidx, ridx = (dcat == left_group), (dcat == right_group) # we are not performing a statistical test here # we're just trying to figure out a way to sort the data. num_fold_change = ctable.loc[:, num_features.index].apply( lambda x: ttest_ind(x[ridx], x[lidx])[0]) num_fold_change = num_fold_change.sort_values( ascending=False ) denom_fold_change = ctable.loc[:, denom_features.index].apply( lambda x: ttest_ind(x[ridx], x[lidx])[0]) denom_fold_change = denom_fold_change.sort_values( ascending=True ) metadata = pd.DataFrame({dcat.name: dcat}) top_num_features = num_fold_change.index[:n_features] top_denom_features = denom_fold_change.index[:n_features] fig3, (ax_denom, ax_num) = plt.subplots(1, 2) proportion_plot( table, metadata, category=metadata.columns[0], left_group=left_group, right_group=right_group, feature_metadata=taxa_df, label_col=taxa_level, num_features=top_num_features, denom_features=top_denom_features, # Note that the syntax is funky and counter # intuitive. This will need to be properly # fixed here # https://github.com/biocore/gneiss/issues/244 num_color=sample_palette.loc[right_group], denom_color=sample_palette.loc[left_group], axes=(ax_num, ax_denom)) # The below is overriding the default colors in the # numerator / denominator this will also need to be fixed in # https://github.com/biocore/gneiss/issues/244 max_ylim, min_ylim = ax_denom.get_ylim() num_h, denom_h = n_features, n_features space = (max_ylim - min_ylim) / (num_h + denom_h) ymid = (max_ylim - min_ylim) * num_h ymid = ymid / (num_h + denom_h) - 0.5 * space ax_denom.axhspan(min_ylim, ymid, facecolor=num_color, zorder=0) ax_denom.axhspan(ymid, max_ylim, facecolor=denom_color, zorder=0) ax_num.axhspan(min_ylim, ymid, facecolor=num_color, zorder=0) ax_num.axhspan(ymid, max_ylim, facecolor=denom_color, zorder=0) fig3.subplots_adjust( # the left side of the subplots of the figure left=0.3, # the right side of the subplots of the figure right=0.9, # the bottom of the subplots of the figure bottom=0.1, # the top of the subplots of the figure top=0.9, # the amount of width reserved for blank space # between subplots wspace=0, # the amount of height reserved for white space # between subplots hspace=0.2, ) fig3.savefig(os.path.join(output_dir, 'proportion_plot.svg')) fig3.savefig(os.path.join(output_dir, 'proportion_plot.pdf')) index_fp = os.path.join(output_dir, 'index.html') with open(index_fp, 'w') as index_f: index_f.write('<html><body>\n') if metadata is not None: index_f.write('<h1>Balance vs %s </h1>\n' % c.name) index_f.write(('<img src="balance_metadata.svg" ' 'alt="barplots">\n\n' '<a href="balance_metadata.pdf">' 'Download as PDF</a><br>\n')) if not multiple_cats: index_f.write('<h1>Proportion Plot </h1>\n') index_f.write(('<img src="proportion_plot.svg" ' 'alt="proportions">\n\n' '<a href="proportion_plot.pdf">' 'Download as PDF</a><br>\n')) index_f.write(('<h1>Balance Taxonomy</h1>\n' '<img src="barplots.svg" alt="barplots">\n\n' '<a href="barplots.pdf">' 'Download as PDF</a><br>\n' '<h3>Numerator taxa</h3>\n' '<a href="numerator.csv">\n' 'Download as CSV</a><br>\n' '<h3>Denominator taxa</h3>\n' '<a href="denominator.csv">\n' 'Download as CSV</a><br>\n')) num_features.to_csv(os.path.join(output_dir, 'numerator.csv'), header=True, index=True) denom_features.to_csv(os.path.join(output_dir, 'denominator.csv'), header=True, index=True) index_f.write('</body></html>\n')
def ilr_hierarchical(table: pd.DataFrame, tree: skbio.TreeNode, pseudocount: float = 0.5) -> pd.DataFrame: return ilr_transform(add_pseudocount(table, pseudocount), tree)