pycmplot 0.2.4__tar.gz → 0.2.5__tar.gz

{pycmplot-0.2.4/pycmplot.egg-info → pycmplot-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pycmplot
-Version: 0.2.4
+Version: 0.2.5
 Summary: Multi-track circular and linear Manhattan plot generation for GWAS summary statistics
 Author: Kevin Esoh
 Author-email: Kevin Esoh <kesohku1@jh.edu>

{pycmplot-0.2.4 → pycmplot-0.2.5}/pycmplot/__init__.py

@@ -12,7 +12,7 @@ Command-line::
 Python API::
 
     from pycmplot.io import prep_pycmplot_input_info, get_sumstats_and_merged_sector_list
-    from pycmplot.plotting import plot_linear, plot_circular
+    from pycmplot.plotting import plot_linear, plot_circular, plot_qq_single, plot_qq_separate, plot_qq_overlay, plot_qq_combined
     from pycmplot.stats import get_lead_snps
     from pycmplot.annotation import get_hits_summary_table
 
@@ -22,6 +22,7 @@ Public surface
 
 from pycmplot.plotting.linear import plot_linear
 from pycmplot.plotting.circular import plot_circular, compute_track_radii_dict
+from pycmplot.plotting.qq import plot_qq_single, plot_qq_separate, plot_qq_overlay, plot_qq_combined
 from pycmplot.stats import get_lead_snps, get_highlight_snps
 from pycmplot.io import prep_pycmplot_input_info, get_sumstats_and_merged_sector_list
 from pycmplot.annotation import get_hits_summary_table
@@ -31,6 +32,10 @@ from pycmplot.resources import ResourceConfig
 __all__ = [
     "plot_linear",
     "plot_circular",
+    "plot_qq_single",
+    "plot_qq_separate",
+    "plot_qq_overlay",
+    "plot_qq_combined",
     "compute_track_radii_dict",
     "get_lead_snps",
     "get_highlight_snps",
@@ -42,4 +47,4 @@ __all__ = [
     "ResourceConfig",
 ]
 
-__version__ = "0.2.4"
+__version__ = "0.2.5"

pycmplot-0.2.5/pycmplot/__main__.py

@@ -0,0 +1,6 @@
+"""Entry point for ``python -m pycmplot`` invocation."""
+
+from pycmplot._core import main
+
+if __name__ == "__main__":
+    main()

{pycmplot-0.2.4 → pycmplot-0.2.5}/pycmplot/_core.py

@@ -1,62 +1,62 @@
-from __future__ import annotations
-
-CORE_MODULE = """
+"""
 pycmplot._core
 ==============
 
 Main entry point that orchestrates CLI argument parsing, data loading, and
 plot dispatch.  This module is intentionally thin: it delegates all heavy
-work to :mod:`pycmplot.io`, :mod:`pycmplot.plotting.linear`, and
-:mod:`pycmplot.plotting.circular`.
+work to :mod:`pycmplot.io`, :mod:`pycmplot.plotting.linear`,
+:mod:`pycmplot.plotting.circular`, and :mod:`pycmplot.plotting.qq`.
 
 All imports are deferred inside :func:`main` so that
 ``import pycmplot`` remains fast regardless of the size of the dependency
 tree.
 """
 
+from __future__ import annotations
+
 import logging
 import warnings
+import sys
 
 # Suppress noisy font-manager warnings before any matplotlib import
 logging.getLogger("matplotlib.font_manager").setLevel(logging.ERROR)
 warnings.filterwarnings("ignore")
 
-logging.basicConfig(level=logging.INFO, format="[%(levelname)s] %(message)s")
+logging.basicConfig(level=logging.INFO, format="[%(levelname)s] %(message)s", stream=sys.stdout)
 logger = logging.getLogger(__name__)
 
 
 def main() -> None:
-    MAIN = """Orchestrate the full pycmplot pipeline from the command line.
+    """Orchestrate the full pycmplot pipeline from the command line.
 
     This function is registered as the ``pycmplot`` console-script entry point
     in ``pyproject.toml`` / ``setup.cfg``.  It performs the following steps in
     order:
 
     1. **Parse CLI arguments** via :func:`~pycmplot.cli.get_arguments`.
-    2. **Parse comma-separated inputs** (files, labels, colours, track heights)
-    into Python lists via
-    :func:`~pycmplot.io.strip_comma_separated_input_streams`.
+    2. **Parse comma-separated inputs** (files, labels, colours, track heights,
+       builds) into Python lists via
+       :func:`~pycmplot.io.strip_comma_separated_input_streams`.
     3. **Construct output paths** (plot image and locus summary table TSV) via
-    :func:`~pycmplot.io.get_output_paths`.
+       :func:`~pycmplot.io.get_output_paths`.
     4. **Resolve column names** for every input file via
-    :func:`~pycmplot.io.prep_pycmplot_input_info`.
+       :func:`~pycmplot.io.prep_pycmplot_input_info`.
     5. **Load data** — reads summary statistics, normalises chromosome names,
-    runs hg19 → hg38 liftover if needed, extracts lead SNPs, generates the
-    hits summary table, and computes merged Circos sector sizes via
-    :func:`~pycmplot.io.get_sumstats_and_merged_sector_list`.
-    6. **Dispatch plotting** — calls
-    :func:`~pycmplot.plotting.circular.plot_circular` when ``--mode cm``,
-    or :func:`~pycmplot.plotting.linear.plot_linear` otherwise.
-
-    Parameters
-    ----------
-    None
-        All input is taken from ``sys.argv`` via :mod:`argparse`.
+       runs hg19 → hg38 liftover if needed, extracts lead SNPs, generates the
+       hits summary table, and computes merged Circos sector sizes via
+       :func:`~pycmplot.io.get_sumstats_and_merged_sector_list`.
+    6. **Dispatch Manhattan plot** — calls
+       :func:`~pycmplot.plotting.circular.plot_circular` when ``--mode cm``,
+       or :func:`~pycmplot.plotting.linear.plot_linear` otherwise.
+    7. **Optional QQ plot** — when ``--qq_plot`` is set, dispatches to one of
+       :func:`~pycmplot.plotting.qq.plot_qq_combined` (default),
+       :func:`~pycmplot.plotting.qq.plot_qq_separate` (``--qq_separate``), or
+       :func:`~pycmplot.plotting.qq.plot_qq_overlay` (``--qq_overlay``).
 
     Returns
     -------
     None
-        Saves the plot image and locus summary table to the directory
+        Saves the plot image(s) and locus summary table to the directory
         specified by ``--output_dir``.
 
     Raises
@@ -194,8 +194,8 @@ def main() -> None:
         pos = pos_arg,
         snp = snp_arg,
         pcol = pcol_arg,
-        buildc = buildc_arg,
-        build = builds
+        build_column = buildc_arg,
+        build_list = builds
     )
 
     # ------------------------------------------------------------------
@@ -206,38 +206,42 @@ def main() -> None:
     # ------------------------------------------------------------------
     # Load data, compute sectors, get hits table
     # ------------------------------------------------------------------
-    (
-        merged_assoc_sector_sizes,
-        sumstats_loaded,
-        hits_table,
-        signif_lines,
-        pval_dict,
-    ) = get_sumstats_and_merged_sector_list(
+    pycmplot_dict = get_sumstats_and_merged_sector_list(
         sum_stats=sum_stats,
         labels=labels,
         trim_pval=trim_pval,
         logp=logp,
         file_info=sumstats_hdr_dic,
         sort_tracks=sort_track,
-        table_out=table_out,
+        table_out=plt_base,
         signif_threshold=signif_threshold,
         signif_line=signif_line,
         suggest_threshold=suggest_threshold,
         resources=resources,
     )
 
+    merged_assoc_sector_sizes = pycmplot_dict["sectors"]
+    sumstats_loaded = pycmplot_dict["dfs"]
+    hits_table = pycmplot_dict["annot"]
+    signif_lines = pycmplot_dict["lines"]
+    pval_dict = pycmplot_dict["pvals"]
+
     # ------------------------------------------------------------------
     # ANNOTATE BY
     # ------------------------------------------------------------------
     label_col = 'SNP'
-    if annotate:
+    if annotate and not hits_table.empty:
         if str(annotate).upper() == "GENE" and 'top_gene' in hits_table.columns:
             label_col = 'top_gene'
-        elif label_col in hits_table.columns:
+        elif annotate in hits_table.columns:
             label_col = annotate
-        
+        else:
+            logger.warning(
+                "Annotation column '%s' not found in hits table; "
+                "falling back to 'SNP'.", annotate,
+            )
 
-        logger.info(f"Anotate by: {label_col}")
+        logger.info("Annotate by: %s", label_col)
 
     # ------------------------------------------------------------------
     # CIRCULAR MANHATTAN
@@ -316,6 +320,7 @@ def main() -> None:
         if qq_separate:
             plot_qq_separate(
                 pval_dict=pval_dict,
+                base_name=plot_title,
                 thin=qq_thin,
                 thin_below=thin_below,
                 max_points=qq_max_points,                

{pycmplot-0.2.4 → pycmplot-0.2.5}/pycmplot/annotation.py

@@ -1,6 +1,4 @@
-from __future__ import annotations
-
-MODULE_DOCSTRING = """
+"""
 pycmplot.annotation
 ====================
 
@@ -22,6 +20,8 @@ paths can be supplied via the ``PYCMPLOT_GENEINFO_HG38`` /
 ``PYCMPLOT_GENEINFO_HG19`` environment variables.
 """
 
+from __future__ import annotations
+
 import bisect
 import logging
 from typing import Optional
@@ -41,7 +41,7 @@ logger = logging.getLogger(__name__)
 # ---------------------------------------------------------------------------
 
 def _build_genes_dict(genes_df: pd.DataFrame) -> dict:
-    BUILD_GENES_DICT = """Build a chromosome-keyed interval dictionary with sorted start positions.
+    """Build a chromosome-keyed interval dictionary with sorted start positions.
 
     Pre-processes the gene reference DataFrame into a structure that supports
     efficient O(log N) binary-search lookup of genes near a query position.
@@ -98,7 +98,7 @@ def _annotate_variant(
     window: int = 500_000,
     promoter_window: int = 2_000,
 ) -> dict:
-    ANNOTATE_VARIANT = """Return strand-aware nearest-gene annotation for a single variant.
+    """Return strand-aware nearest-gene annotation for a single variant.
 
     Searches the pre-built *genes_dict* within *window* bp of *pos* on
     *chrom*.  Reports the nearest upstream and downstream genes (relative to
@@ -238,8 +238,7 @@ def _annotate_and_prioritize_variant(
     promoter_window: int = 2_000,
     biotype_weights: Optional[dict] = None,
 ) -> Optional[dict]:
-    ANNOTATE_PRIORITIZE = """Score and rank candidate genes for a single variant using a composite
-    priority metric.
+    """Score and rank candidate genes for a single variant using a composite priority metric.
 
     Builds a candidate gene set within *window* bp of *pos* on *chrom*, then
     scores each candidate on four additive components:
@@ -386,7 +385,7 @@ def _annotate_and_prioritize_variant(
 # ---------------------------------------------------------------------------
 
 def _clump_by_distance(df: pd.DataFrame, window_kb: int = 500) -> pd.DataFrame:
-    CLUMP_BY_DISTANCE = """Reduce a lead-SNP table to one representative SNP per locus.
+    """Reduce a lead-SNP table to one representative SNP per locus.
 
     Applies greedy distance-based clumping within each chromosome group,
     starting from the most significant SNP (lowest ``P`` or highest ``logP``).
@@ -438,7 +437,7 @@ def get_hits_summary_table(
     table_out: Optional[str] = None,
     resources: Optional[ResourceConfig] = None,
 ) -> pd.DataFrame:
-    GET_HITS_SUMMARY_TABLE = """Annotate lead SNPs with nearest genes and write the locus summary table.
+    """Annotate lead SNPs with nearest genes and write the locus summary table.
 
     For each lead SNP in *leads_df*, runs two complementary annotation passes:
 
@@ -475,33 +474,21 @@ def get_hits_summary_table(
         Clumped locus summary table.  Contains all columns from *leads_df*
         plus annotation fields from both passes, including:
 
-        .. list-table::
-        :widths: 30 70
-        :header-rows: 1
-
-        * - Column
-            - Description
-        * - ``genic``
-            - ``True`` when the lead SNP overlaps a gene body
-        * - ``nearest_upstream_gene``
-            - Nearest upstream gene symbol (strand-aware)
-        * - ``upstream_distance``
-            - Distance to ``nearest_upstream_gene`` in bp
-        * - ``nearest_downstream_gene``
-            - Nearest downstream gene symbol (strand-aware)
-        * - ``downstream_distance``
-            - Distance to ``nearest_downstream_gene`` in bp
-        * - ``promoter_upstream_flag``
-            - ``True`` when the SNP is within 2 kb upstream of a TSS
-        * - ``gene_density``
-            - Number of genes within the search window
-        * - ``top_gene``
-            - Top-priority gene from the scoring pass
-        * - ``biotype``
-            - Ensembl biotype of ``top_gene`` (``'intergenic'`` when no
-            genic overlap)
-        * - ``priority_score``
-            - Composite priority score (genic hits only)
+        - ``genic`` — ``True`` when the lead SNP overlaps a gene body.
+        - ``nearest_upstream_gene`` — nearest upstream gene symbol
+          (strand-aware).
+        - ``upstream_distance`` — distance to ``nearest_upstream_gene`` in bp.
+        - ``nearest_downstream_gene`` — nearest downstream gene symbol
+          (strand-aware).
+        - ``downstream_distance`` — distance to ``nearest_downstream_gene`` in
+          bp.
+        - ``promoter_upstream_flag`` — ``True`` when the SNP is within 2 kb
+          upstream of a TSS.
+        - ``gene_density`` — number of genes within the search window.
+        - ``top_gene`` — top-priority gene from the scoring pass.
+        - ``biotype`` — Ensembl biotype of ``top_gene`` (``'intergenic'`` when
+          no genic overlap).
+        - ``priority_score`` — composite priority score (genic hits only).
 
     Notes
     -----
@@ -578,7 +565,8 @@ def get_hits_summary_table(
         locus_table = leads_df
 
     if table_out is not None:
-        locus_table.to_csv(table_out, index=False, sep="\t", na_rep="None")
-        logger.info("Locus summary written to: %s", table_out)
+        outpath = table_out.replace(" ", "_").lower() + '.tsv'
+        locus_table.to_csv(outpath, index=False, sep="\t", na_rep="None")
+        logger.info("Locus summary written to: %s", outpath)
 
     return _clump_by_distance(locus_table, window_kb=window_kb)