pycmplot 0.1.6__tar.gz → 0.1.7__tar.gz

{pycmplot-0.1.6/pycmplot.egg-info → pycmplot-0.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pycmplot
-Version: 0.1.6
+Version: 0.1.7
 Summary: Multi-track circular and linear Manhattan plot generation for GWAS summary statistics
 Author: Kevin Esoh
 Author-email: Kevin Esoh <kesohku1@jh.edu>

{pycmplot-0.1.6 → pycmplot-0.1.7}/pycmplot/__init__.py

@@ -11,6 +11,7 @@ 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.stats import get_lead_snps
     from pycmplot.annotation import get_hits_summary_table
@@ -22,7 +23,7 @@ Public surface
 from pycmplot.plotting.linear import plot_linear
 from pycmplot.plotting.circular import plot_circular, compute_track_radii_dict
 from pycmplot.stats import get_lead_snps, get_highlight_snps
-from pycmplot.io import get_sumstats_and_merged_sector_list
+from pycmplot.io import prep_pycmplot_input_info, get_sumstats_and_merged_sector_list
 from pycmplot.annotation import get_hits_summary_table
 from pycmplot.constants import hg38_chr_lengths, BIOTYPE_WEIGHTS
 from pycmplot.resources import ResourceConfig
@@ -33,6 +34,7 @@ __all__ = [
     "compute_track_radii_dict",
     "get_lead_snps",
     "get_highlight_snps",
+    "prep_pycmplot_input_info",
     "get_sumstats_and_merged_sector_list",
     "get_hits_summary_table",
     "hg38_chr_lengths",
@@ -40,4 +42,4 @@ __all__ = [
     "ResourceConfig",
 ]
 
-__version__ = "0.1.0"
+__version__ = "0.1.7"

pycmplot-0.1.7/pycmplot/_core.py

@@ -0,0 +1,218 @@
+"""
+pycmplot._core
+==============
+Main entry point — orchestrates CLI parsing, data loading, and plotting.
+"""
+
+from __future__ import annotations
+
+import logging
+import warnings
+
+# 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")
+logger = logging.getLogger(__name__)
+
+
+def main() -> None:
+    """CLI entry point — ``pycmplot`` console script."""
+
+    # ------------------------------------------------------------------
+    # Deferred imports so ``import pycmplot`` remains fast
+    # ------------------------------------------------------------------
+    from pycmplot.cli import get_arguments, DESCMSG
+    from pycmplot.io import (
+        get_sumstats_and_merged_sector_list,
+        prep_pycmplot_input_info,
+        get_output_paths,
+        strip_comma_separated_input_streams,
+        #detect_delimiter,
+        #resolve_delimiter,
+        #get_file_header,
+    )
+    from pycmplot.plotting.linear import plot_linear
+    from pycmplot.plotting.circular import plot_circular
+    from pycmplot.resources import ResourceConfig
+
+    # ------------------------------------------------------------------
+    # Parse CLI
+    # ------------------------------------------------------------------
+    args = get_arguments(DESCMSG)
+    print(DESCMSG)
+
+    mode             = args.mode
+    sum_stats_raw    = args.sum_stats
+    chrom_arg        = args.chrom_column
+    pos_arg          = args.pos_column
+    snp_arg          = args.snp_column
+    build_arg        = args.build_column
+    labels_raw       = args.labels
+    pcol_arg         = args.pval_column
+    logp             = args.logp
+    chrom_label_size = args.chrom_label_size
+    chrom_label_side = args.chrom_label_side
+    track_label_size = args.track_label_size
+    track_label_orientation = args.track_label_orientation
+    sort_track       = args.sort_track
+    trim_pval        = args.trim_pval
+    signif_threshold = args.signif_threshold
+    signif_line      = args.signif_line
+    suggest_threshold= args.suggest_threshold
+    annotate         = args.annotate
+    annotation_size  = args.annotation_size
+    point_size       = args.point_size
+    highlight        = args.highlight
+    highlight_thresh = args.highlight_thresh
+    highlight_line   = args.highlight_line
+    colors_raw       = args.colors
+    r_min            = args.r_min
+    r_max            = args.r_max
+    pad              = args.pad
+    output_format    = args.output_format
+    output_dir       = args.output_dir
+    dpi              = args.dpi
+    plot_title       = args.plot_title
+    plot_title_size  = args.plot_title_size
+    track_heights    = args.track_heights
+    track_spacing    = args.track_spacing
+    no_track_labels  = args.no_track_labels
+    chr_spacing      = args.chr_spacing
+
+
+    # ------------------------------------------------------------------
+    # Sumstat, labels, colours, track heights str to list
+    # ------------------------------------------------------------------
+    (
+        sum_stats, 
+        labels, 
+        colors, 
+        t_heights
+    ) = strip_comma_separated_input_streams(
+        sum_stats = sum_stats_raw,
+        labels = labels_raw,
+        colors_raw = colors_raw,
+        track_heights = track_heights,
+    )
+
+    # ------------------------------------------------------------------
+    # Output paths
+    # ------------------------------------------------------------------
+    (
+        plt_name, 
+        table_out 
+    ) = get_output_paths(
+        labels,
+        mode = mode,
+        logp = logp,
+        output_dir = output_dir,
+        plot_title = plot_title,
+        output_format = output_format
+    )
+
+    # ------------------------------------------------------------------
+    # Resolve column names
+    # ------------------------------------------------------------------
+    sumstats_hdr_dic = prep_pycmplot_input_info(
+        sum_stats = sum_stats,
+        labels = labels,
+        delim = args.delim,
+        chrom = chrom_arg,
+        pos = pos_arg,
+        snp = snp_arg,
+        pcol = pcol_arg,
+        build = build_arg
+    )
+
+    # ------------------------------------------------------------------
+    # ResourceConfig — picks up environment variables automatically
+    # ------------------------------------------------------------------
+    resources = ResourceConfig()
+
+    # ------------------------------------------------------------------
+    # Load data, compute sectors, get hits table
+    # ------------------------------------------------------------------
+    (
+        merged_assoc_sector_sizes,
+        sumstats_loaded,
+        hits_table,
+        signif_lines,
+    ) = 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,
+        signif_threshold=signif_threshold,
+        signif_line=signif_line,
+        suggest_threshold=suggest_threshold,
+        resources=resources,
+    )
+
+    # ------------------------------------------------------------------
+    # CIRCULAR MANHATTAN
+    # ------------------------------------------------------------------
+    if mode.upper() == "CM":
+        logger.info("Generating CIRCULAR MANHATTAN Plot ...")
+        plot_circular(
+            sumstats_loaded = sumstats_loaded,
+            logp = logp,
+            signif_line = signif_line,
+            signif_lines = signif_lines,
+            highlight = highlight,
+            highlight_thresh = highlight_thresh,
+            highlight_line = highlight_line,
+            colors = colors,
+            chrom_label_side = chrom_label_side,
+            chrom_label_size = chrom_label_size,
+            track_label_size = track_label_size,
+            track_label_orientation = track_label_orientation,
+            annotate = annotate,
+            annotation_size = annotation_size,
+            hits_table = hits_table,
+            sector_sizes = merged_assoc_sector_sizes,
+            pad = pad,
+            r_min = r_min,
+            r_max = r_max,
+            plot_title = plot_title,
+            plot_title_size = plot_title_size,
+            no_track_labels = no_track_labels,
+            dpi = dpi,
+            output_format=output_format,
+            output_dir=output_dir
+        )
+
+    # ------------------------------------------------------------------
+    # LINEAR MANHATTAN
+    # ------------------------------------------------------------------
+    else:
+        logger.info("Generating LINEAR MANHATTAN Plot ...")
+        plot_linear(
+            sumstats_loaded = sumstats_loaded,
+            track_heights = t_heights,
+            trim_pval=trim_pval,
+            logp=True if logp else False,
+            point_size=point_size,
+            highlight=highlight,
+            highlight_thresh=highlight_thresh,
+            annot_df=hits_table if not hits_table.empty else None,
+            label_col="top_gene",
+            chr_spacing=chr_spacing,
+            track_spacing=track_spacing,
+            colors=colors,
+            signif_lines=signif_lines,
+            plot_title=plot_title,
+            no_track_labels = no_track_labels,
+            dpi=dpi,
+            output_format=output_format,
+            output_dir=output_dir,
+            figsize=(15, 9)
+        )
+
+
+if __name__ == "__main__":
+    main()

{pycmplot-0.1.6 → pycmplot-0.1.7}/pycmplot/cli.py

@@ -147,6 +147,13 @@ def get_arguments(descmsg: str = DESCMSG) -> argparse.Namespace:
         const="chrom_len", default=None, type=str, #metavar="str",
         help="Sort tracks by chromosome count or label."
     )
+    opt.add_argument(
+        "-ntl", "--no_track_labels",
+        help=(
+            "Exclude track labels from plot. (default: False)"
+        ),
+        action="store_true"
+    )    
     opt.add_argument(
         "-plt", "--plot_title", default="MyCMplot", type=str, metavar="str",
         help="Plot plot_title / output file stem."

{pycmplot-0.1.6 → pycmplot-0.1.7}/pycmplot/io.py

@@ -8,6 +8,8 @@ from __future__ import annotations
 
 import csv
 import gzip
+import sys
+import re
 import logging
 from collections import defaultdict
 from pathlib import Path
@@ -109,6 +111,198 @@ def get_file_header(
     return list(hdr)
 
 
+
+def strip_comma_separated_input_streams(
+    sum_stats,
+    labels,
+    colors_raw = 'steelblue,grey',
+    track_heights = None,
+):
+
+    if len(sum_stats) != len(labels):
+        sys.exit(
+            "Error: number of summary stats files and labels must match.\n"
+            f"  Files:  {sum_stats}\n"
+            f"  Labels: {labels}"
+        )
+
+    # ------------------------------------------------------------------
+    # Sumstat, labels str to list
+    # ------------------------------------------------------------------
+    labels     = [lbl.strip() for lbl in labels.strip().split(",")]
+    
+    sum_stats  = [s.strip() for s in sum_stats.strip().split(",")]
+
+    # ------------------------------------------------------------------
+    # Colours str to list
+    # ------------------------------------------------------------------
+    colors = [c.strip() for c in colors_raw.strip().split(",")]
+
+    # ------------------------------------------------------------------
+    # Linear track heights str to list
+    # ------------------------------------------------------------------
+    t_heights = [float(x) for x in track_heights.strip().split(",")]
+
+    return sum_stats, labels, colors, t_heights
+
+
+# ------------------------------------------------------------------
+# Random string for output paths
+# ------------------------------------------------------------------
+def generate_random_string(length):
+    import random
+    import string        
+    # Combine uppercase, lowercase, and digits
+    characters = string.ascii_letters + string.digits
+    # random.choices picks multiple characters with replacement
+    return ''.join(random.choices(characters, k=length))
+
+
+# ------------------------------------------------------------------
+# Output paths
+# ------------------------------------------------------------------
+def get_output_paths(
+    labels,
+    mode: Optional[str] = 'lm',
+    logp: bool = False,
+    output_dir: Optional[str] = '.',
+    plot_title: Optional[str] = None,
+    output_format: Optional[str] = 'png'
+):
+
+    out_path = Path(output_dir).resolve()
+
+    out_path.mkdir(parents=True, exist_ok=True)
+
+    if plot_title:
+        pltitle = re.sub(r"[^a-zA-Z0-9\s]", "", plot_title).replace(" ", "_")
+    else:
+        pltitle = generate_random_string(10)
+
+    plt_base = str(out_path / f"{pltitle}_{'_'.join(labels)}_{mode.lower()}")
+
+    suffix     = "_logp" if logp else "_pval"
+
+    plt_name   = f"{plt_base}{suffix}.{output_format.lower()}"
+    
+    table_out  = f"{plt_base}{suffix}_locus_summary_table.tsv"
+
+    return plt_name, table_out
+
+
+
+# ---------------------------------------------------------------------------
+# input formatter
+# ---------------------------------------------------------------------------
+def prep_pycmplot_input_info(
+    sum_stats: list[str],
+    labels: list[str],
+    delim: Optional[str] = None,
+    chrom: Optional[str] = None,
+    pos: Optional[str] = None,
+    snp: Optional[str] = None,
+    pcol: Optional[str] = None,
+    build: Optional[str] = None
+):
+    """Resolve column names and delimiter
+
+    Parameters
+    ----------
+    sum_stats:
+        List of file paths to GWAS summary statistics (possibly gzip-compressed).
+    labels:
+        Track labels in the same order as *sum_stats*.
+    delim:
+        File delimiter (autodetected if omitted)
+    chrom:
+        Chromosome column
+    pos:
+        Position column
+    snp:
+        SNP or Marker ID column
+    pcol:
+        P-value column
+    build:
+        Build version column
+
+    Returns
+    -------
+    {old_columns, column_dtypes, new_columns, delim}
+
+    """
+    # ------------------------------------------------------------------
+    # Resolve delimiter
+    # ------------------------------------------------------------------
+    if delim:
+        sep = resolve_delimiter(delim)
+    else:
+        sep = None  # autodetect per file
+
+    # ------------------------------------------------------------------
+    # Column-name candidate lists for auto-resolution
+    # ------------------------------------------------------------------
+    chr_candidates = [chrom, "CHR", "CHROM", "Chromosome", "#CHROM", "#CHR",
+                    "Chrom", "chrom", "chr", "chromosome", "#chr", "#chrom"]
+    pos_candidates = [pos,   "BP", "POS", "bp", "pos", "Basepair"]
+    snp_candidates = [snp,   "SNP", "RSID", "rsID", "MarkerName", "MarkerID",
+                    "Predictor", "Marker", "SNPID", "ID"]
+    pvl_candidates = [pcol,  "P", "P-value", "Wald_P", "pvalue", "p_val", "pval"]
+    bld_candidates = [build, "BUILD", "Genome", "Genome_Build", "Genome-build"]
+
+    # Remove None entries
+    chr_candidates = [c for c in chr_candidates if c]
+    pos_candidates = [c for c in pos_candidates if c]
+    snp_candidates = [c for c in snp_candidates if c]
+    pvl_candidates = [c for c in pvl_candidates if c]
+    bld_candidates = [c for c in bld_candidates if c]
+
+    # ------------------------------------------------------------------
+    # Resolve column names per file
+    # ------------------------------------------------------------------
+    sumstats_hdr_dic: dict = {}
+
+    for name, fpath in zip(labels, sum_stats):
+        if sep:
+            file_sep, dialect = sep, None
+        else:
+            file_sep, dialect = detect_delimiter(fpath, sample_size=5_000)
+
+        hdr = get_file_header(fpath, delim=file_sep, dialect=dialect)
+
+        try:
+            chrom_col = next(c for c in hdr if c in set(chr_candidates))
+            pos_col   = next(c for c in hdr if c in set(pos_candidates))
+            snp_col   = next(c for c in hdr if c in set(snp_candidates))
+            pcol      = next(c for c in hdr if c in set(pvl_candidates))
+            bcol      = next(c for c in hdr if c in set(bld_candidates))
+        except StopIteration as exc:
+            sys.exit(
+                f"Error: could not find a required column in {fpath}.\n"
+                f"  Header: {hdr}\n"
+                f"  Details: {exc}"
+            )
+
+        old_cols = [chrom_col, pos_col, snp_col, pcol, bcol]
+        new_cols = {
+            chrom_col: "CHR",
+            pos_col:   "POS",
+            snp_col:   "SNP",
+            pcol:      "P",
+            bcol:      "BUILD",
+        }
+        col_dtypes = {
+            chrom_col: str,
+            pos_col:   object,
+            snp_col:   str,
+            pcol:      float,
+            bcol:      str,
+        }
+
+        sumstats_hdr_dic[name] = [old_cols, col_dtypes, new_cols, file_sep]
+
+    return sumstats_hdr_dic
+
+
 # ---------------------------------------------------------------------------
 # Sector-size helpers
 # ---------------------------------------------------------------------------
@@ -134,8 +328,6 @@ def get_sumstats_and_merged_sector_list(
     file_info: Optional[dict] = None,
     sort_tracks: Optional[str] = "chrom_len",
     table_out: Optional[str] = None,
-    highlight: bool = False,
-    highlight_thresh: float = 5e-8,
     signif_threshold: Optional[float] = None,
     signif_line: Optional[float] = None,
     suggest_threshold: Optional[float] = None,
@@ -156,8 +348,8 @@ def get_sumstats_and_merged_sector_list(
         ``'label'`` — sort tracks alphabetically by label.
         ``'chrom_len'`` — sort by number of chromosomes (default).
         ``None`` — preserve input order.
-    highlight:
-        Whether to flag loci for highlighting.
+    signif_threshold:
+        Threshold of significance to create hits table.
     resources:
         :class:`~pycmplot.resources.ResourceConfig` instance.
 
@@ -225,21 +417,13 @@ def get_sumstats_and_merged_sector_list(
             logger.info("Converting hg19 coordinates to hg38 ...")
             sumstats_loaded[label][0] = liftover_position(df, resources=resources)
 
-        # Lead SNPs / highlight SNPs
-        if highlight:
-            logger.info("Extracting variants to highlight ...")
-            sumstats_loaded[label][0], leads = get_highlight_snps(
-                df=sumstats_loaded[label][0],
-                window=2_000_000,
-                highlight_thresh=highlight_thresh,
-                logp=True,
-            )
-        else:
-            leads = get_lead_snps(
-                df=sumstats_loaded[label][0],
-                highlight_thresh=signif_threshold or 5e-8,
-                logp=True,
-            )
+        # Lead SNPs
+        logger.info("Extracting variants to highlight ...")
+        leads = get_lead_snps(
+            df=sumstats_loaded[label][0],
+            signif_threshold=signif_threshold or 5e-8,
+            logp=True,
+        )
 
         all_lead_snps.append(leads)