pycmplot 0.2.2__tar.gz → 0.2.4__tar.gz

{pycmplot-0.2.2/pycmplot.egg-info → pycmplot-0.2.4}/PKG-INFO

@@ -1,10 +1,15 @@
 Metadata-Version: 2.4
 Name: pycmplot
-Version: 0.2.2
+Version: 0.2.4
 Summary: Multi-track circular and linear Manhattan plot generation for GWAS summary statistics
 Author: Kevin Esoh
 Author-email: Kevin Esoh <kesohku1@jh.edu>
 License-Expression: CC-BY-NC-SA-4.0
+Project-URL: Homepage, https://github.com/esohkevin/pycmplot
+Project-URL: Issues, https://github.com/esohkevin/pycmplot/issues
+Project-URL: Docs, https://pycmplot.readthedocs.io/en/latest/
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -101,6 +106,9 @@ pip install pycmplot
 ```bash
 git clone https://github.com/esohkevin/pycmplot.git
 
+# or with most recent updates from development branch
+# git clone -b dev https://github.com/esohkevin/pycmplot.git
+
 cd pycmplot
 
 pip install -e .
@@ -207,26 +215,12 @@ A demonstration of how to use the python API is provided in this notebook: https
 
 ---
 
-## Package structure
+## Contributing
+
+See how to contribute here https://github.com/esohkevin/pycmplot?tab=contributing-ov-file
+
+
+## Contributors
+
+- [Kevin Esoh](https://github.com/esohkevin)
 
-```
-pycmplot/
-├── pyproject.toml
-├── setup.py
-├── setup.cfg
-├── README.md
-└── pycmplot/
-      ├── __init__.py          # public API exports
-      ├── __main__.py          # python -m pycmplot
-      ├── _core.py             # main() orchestration
-      ├── cli.py               # argparse definitions
-      ├── constants.py         # chromosome lengths, biotype weights
-      ├── resources.py         # external resource path config
-      ├── io.py                # sumstat loading, delimiter detection
-      ├── stats.py             # get_lead_snps, get_highlight_snps
-      ├── liftover.py          # lazy hg19→hg38 liftover
-      ├── annotation.py        # nearest-gene annotation, hits table
-      └── plotting/
-          ├── __init__.py
-          ├── linear.py        # plot_linear
-          └── circular.py      # plot_circular, compute_track_radii_dict

{pycmplot-0.2.2 → pycmplot-0.2.4}/README.md

@@ -75,6 +75,9 @@ pip install pycmplot
 ```bash
 git clone https://github.com/esohkevin/pycmplot.git
 
+# or with most recent updates from development branch
+# git clone -b dev https://github.com/esohkevin/pycmplot.git
+
 cd pycmplot
 
 pip install -e .
@@ -181,26 +184,12 @@ A demonstration of how to use the python API is provided in this notebook: https
 
 ---
 
-## Package structure
+## Contributing
+
+See how to contribute here https://github.com/esohkevin/pycmplot?tab=contributing-ov-file
+
+
+## Contributors
+
+- [Kevin Esoh](https://github.com/esohkevin)
 
-```
-pycmplot/
-├── pyproject.toml
-├── setup.py
-├── setup.cfg
-├── README.md
-└── pycmplot/
-      ├── __init__.py          # public API exports
-      ├── __main__.py          # python -m pycmplot
-      ├── _core.py             # main() orchestration
-      ├── cli.py               # argparse definitions
-      ├── constants.py         # chromosome lengths, biotype weights
-      ├── resources.py         # external resource path config
-      ├── io.py                # sumstat loading, delimiter detection
-      ├── stats.py             # get_lead_snps, get_highlight_snps
-      ├── liftover.py          # lazy hg19→hg38 liftover
-      ├── annotation.py        # nearest-gene annotation, hits table
-      └── plotting/
-          ├── __init__.py
-          ├── linear.py        # plot_linear
-          └── circular.py      # plot_circular, compute_track_radii_dict

{pycmplot-0.2.2 → pycmplot-0.2.4}/docs/conf.py

@@ -12,7 +12,7 @@ sys.path.insert(0, os.path.abspath(".."))
 project = "pycmplot"
 copyright = "2026, Kevin Esoh"
 author = "Kevin Esoh"
-release = "0.2.2"  # update to match PyPI version
+release = "0.2.4"  # update to match PyPI version
 
 # -- General configuration -----------------------------------------------------
 extensions = [

{pycmplot-0.2.2 → pycmplot-0.2.4}/pycmplot/__init__.py

@@ -42,4 +42,4 @@ __all__ = [
     "ResourceConfig",
 ]
 
-__version__ = "0.2.1"
+__version__ = "0.2.4"

{pycmplot-0.2.2 → pycmplot-0.2.4}/pycmplot/_core.py

@@ -229,13 +229,13 @@ def main() -> None:
     # ------------------------------------------------------------------
     # ANNOTATE BY
     # ------------------------------------------------------------------
+    label_col = 'SNP'
     if annotate:
-        if str(annotate).upper() == "GENE":
+        if str(annotate).upper() == "GENE" and 'top_gene' in hits_table.columns:
             label_col = 'top_gene'
-        elif str(annotate).upper() == "SNP":
-            label_col = 'SNP'
-        else:
+        elif label_col in hits_table.columns:
             label_col = annotate
+        
 
         logger.info(f"Anotate by: {label_col}")
 

{pycmplot-0.2.2 → pycmplot-0.2.4}/pycmplot/cli.py

@@ -328,12 +328,12 @@ def get_arguments(descmsg: str = DESCMSG) -> argparse.Namespace:
         help="File delimiter (autodetected if omitted)."
     )
     opt.add_argument(
-        "-bc",   "--build_column",  required=False, type=str, metavar="str",
+        "-bc",   "--build_column", default=None, required=False, type=str, metavar="str",
                      help=("Name of column containing genome build (hg18/hg19/hg38)." 
                          "Or use ``--build`` below to supply genome builds per summary stat file."
                     ))
     opt.add_argument(
-        "-b","--build", required=False, type=str, metavar='str',
+        "-b","--build", default=None, required=False, type=str, metavar='str',
         help=
         """Comma-sperated list of genome build of summary stats file(s) listed 
         in the same order as sumstats files. e.g. hg19,hg38,hg38,hg19 means:

{pycmplot-0.2.2 → pycmplot-0.2.4}/pycmplot/io.py

@@ -39,6 +39,7 @@ import pandas as pd
 from pycmplot.stats import get_lead_snps, get_highlight_snps
 from pycmplot.annotation import get_hits_summary_table
 from pycmplot.resources import ResourceConfig, default_resources
+from pycmplot.constants import hg38_chr_lengths
 
 logger = logging.getLogger(__name__)
 
@@ -563,14 +564,6 @@ def prep_pycmplot_input_info(
     snp_candidates = [c for c in snp_candidates if c]
     pvl_candidates = [c for c in pvl_candidates if c]
 
-    bld_candidates = []
-    if buildc:
-        bld_candidates = ["BUILD", "Genome", "Genome_Build", "Genome-build"]
-        bld_candidates_l = [x.lower() for x in bld_candidates]
-        bld_candidates_u = [x.upper() for x in bld_candidates]
-        bld_candidates = [buildc] + bld_candidates + bld_candidates_l + bld_candidates_u
-        bld_candidates = [c for c in bld_candidates if c]
-
     # ------------------------------------------------------------------
     # Resolve column names per file
     # ------------------------------------------------------------------
@@ -610,21 +603,28 @@ def prep_pycmplot_input_info(
             pcol:      float,
         }
 
-    if not bld_candidates and isinstance(build, list):
+    # CHECK BUILD COLUMN
+    if buildc:
+        bld_candidates = buildc
+    else:
+        bld_candidates = ["BUILD", "Genome", "Genome_Build", "Genome-build"]
+        bld_candidates_l = [x.lower() for x in bld_candidates]
+        bld_candidates_u = [x.upper() for x in bld_candidates]
+        bld_candidates = [buildc] + bld_candidates + bld_candidates_l + bld_candidates_u
+        bld_candidates = [c for c in bld_candidates if c]
+
+    try:
+        bcol = next(c for c in hdr if c in set(bld_candidates))
+    except Exception:
+        bcol = False
+
+
+    if not bcol and isinstance(build, list):
         for name, fpath, build in zip(labels, sum_stats, build):
             sumstats_hdr_dic[name] = [old_cols, col_dtypes, new_cols, file_sep, build]
 
-    elif bld_candidates:
+    elif bcol:
         for name, fpath in zip(labels, sum_stats):
-            try:
-                bcol      = next(c for c in hdr if c in set(bld_candidates))
-            except StopIteration as exc:
-                sys.exit(
-                    f"Error: could not find build 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",
@@ -635,7 +635,7 @@ def prep_pycmplot_input_info(
             }
             col_dtypes = {
                 chrom_col: str,
-                pos_col:   int,
+                pos_col:   object,
                 snp_col:   str,
                 pcol:      float,
                 bcol:      str,
@@ -643,7 +643,7 @@ def prep_pycmplot_input_info(
 
             sumstats_hdr_dic[name] = [old_cols, col_dtypes, new_cols, file_sep]
     else:
-        logger.warning("""No build column or builds specified. Summary stats will be
+        logger.warning("""No build column or builds detected. Summary stats will be
         plotted in their respective coordinate systems.
         If your data are in different coordinate systems, putting them in one plot
         is not advisable, especially if ``--annotate`` is set!""")
@@ -682,6 +682,7 @@ def get_sumstats_and_merged_sector_list(
     signif_line: Optional[float] = None,
     suggest_threshold: Optional[float] = None,
     resources: Optional[ResourceConfig] = None,
+    hg38_chr_lengths = hg38_chr_lengths,
 ):
     GET_SUMSTATS = """Load summary statistics, run liftover, extract lead SNPs, and compute
     merged Circos sector sizes.
@@ -824,7 +825,7 @@ def get_sumstats_and_merged_sector_list(
         ).rename(columns=sumstat_newcols)
 
         # Get dict of p-values for qq-plotting before applying trim_pval
-        logger.info("Extracting raw p-values for qq-plotting ...")
+        logger.info("Extracting raw p-values for QQ-plotting ...")
         pval_dict[label] = df["P"].dropna().astype(float).values
 
 
@@ -834,7 +835,7 @@ def get_sumstats_and_merged_sector_list(
 
         # Trim insignificant variants for faster plotting
         if trim_pval:
-            logger.info("Excluding variants with p-value less than %s ...", trim_pval)
+            logger.info("Excluding variants with p-value less than %s to speed up Manhattan plotting ...", trim_pval)
             df = df[df["P"].astype(float) <= float(trim_pval)]
         else:
             df = df[df["P"].astype(float) <= 1]
@@ -863,6 +864,7 @@ def get_sumstats_and_merged_sector_list(
         if "BUILD" in df.columns and "hg19" in df["BUILD"].unique():
             logger.info("Converting hg19 coordinates to hg38 ...")
             sumstats_loaded[label][0] = liftover_position(df, resources=resources)
+            liftover = True
 
         # Lead SNPs
         logger.info("Extracting variants to highlight ...")
@@ -959,6 +961,14 @@ def get_sumstats_and_merged_sector_list(
             sub = assoc[assoc["CHR"] == chrom]
             lo_val = max(sub["POS"].min() - 1_000_000, 0)
             hi_val = sub["POS"].max()
+
+            # Ensure sector sizes are within chrom ranges if liftover
+            #chrom_max = hi_val
+            #if liftover:
+            #    hg38_chr_lengths = {k.replace("chr",""): v for k, v in hg38_chr_lengths.items()}
+            #    chrom_max = hg38_chr_lengths[chrom]
+            #hi_val = min(hi_val, chrom_max)
+
             assoc_dic[str(chrom)] = [lo_val, hi_val]
 
         min_dic_val = min(assoc_dic.values())

{pycmplot-0.2.2 → pycmplot-0.2.4}/pycmplot/liftover.py

@@ -30,6 +30,7 @@ import numpy as np
 import pandas as pd
 
 from pycmplot.resources import ResourceConfig, default_resources
+from pycmplot.constants import hg38_chr_lengths
 
 logger = logging.getLogger(__name__)
 
@@ -136,6 +137,7 @@ def liftover_hg19_to_hg38(
 
 def liftover_position(
     df: pd.DataFrame,
+    hg38_chr_lengths = hg38_chr_lengths,
     resources: Optional[ResourceConfig] = None,
 ) -> pd.DataFrame:
     LIFTOVER_POSITION = """Liftover all hg19 rows in *df* from hg19 to hg38 coordinates.
@@ -190,6 +192,8 @@ def liftover_position(
     True
     """
 
+    hg38_chr_lengths = {k.replace("chr",""): v for k, v in hg38_chr_lengths.items()}
+
     if resources is None:
         resources = default_resources
 
@@ -208,4 +212,10 @@ def liftover_position(
     df["BUILD"] = "hg38"
     df["POS"] = new_positions
     df["POS"] = df["POS"].fillna(0).astype(int)
-    return df[df["POS"] != 0]
+    clean_df = []
+    for chrom in df["CHR"].unique():
+        chr_df = df[df["CHR"] == chrom]
+        chr_df = chr_df[chr_df["POS"] <= hg38_chr_lengths[chrom]]
+        clean_df = pd.concat([pd.DataFrame(clean_df), pd.DataFrame(chr_df)], axis = 0, ignore_index=True)
+
+    return clean_df[clean_df["POS"] != 0]

{pycmplot-0.2.2 → pycmplot-0.2.4/pycmplot.egg-info}/PKG-INFO

@@ -1,10 +1,15 @@
 Metadata-Version: 2.4
 Name: pycmplot
-Version: 0.2.2
+Version: 0.2.4
 Summary: Multi-track circular and linear Manhattan plot generation for GWAS summary statistics
 Author: Kevin Esoh
 Author-email: Kevin Esoh <kesohku1@jh.edu>
 License-Expression: CC-BY-NC-SA-4.0
+Project-URL: Homepage, https://github.com/esohkevin/pycmplot
+Project-URL: Issues, https://github.com/esohkevin/pycmplot/issues
+Project-URL: Docs, https://pycmplot.readthedocs.io/en/latest/
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -101,6 +106,9 @@ pip install pycmplot
 ```bash
 git clone https://github.com/esohkevin/pycmplot.git
 
+# or with most recent updates from development branch
+# git clone -b dev https://github.com/esohkevin/pycmplot.git
+
 cd pycmplot
 
 pip install -e .
@@ -207,26 +215,12 @@ A demonstration of how to use the python API is provided in this notebook: https
 
 ---
 
-## Package structure
+## Contributing
+
+See how to contribute here https://github.com/esohkevin/pycmplot?tab=contributing-ov-file
+
+
+## Contributors
+
+- [Kevin Esoh](https://github.com/esohkevin)
 
-```
-pycmplot/
-├── pyproject.toml
-├── setup.py
-├── setup.cfg
-├── README.md
-└── pycmplot/
-      ├── __init__.py          # public API exports
-      ├── __main__.py          # python -m pycmplot
-      ├── _core.py             # main() orchestration
-      ├── cli.py               # argparse definitions
-      ├── constants.py         # chromosome lengths, biotype weights
-      ├── resources.py         # external resource path config
-      ├── io.py                # sumstat loading, delimiter detection
-      ├── stats.py             # get_lead_snps, get_highlight_snps
-      ├── liftover.py          # lazy hg19→hg38 liftover
-      ├── annotation.py        # nearest-gene annotation, hits table
-      └── plotting/
-          ├── __init__.py
-          ├── linear.py        # plot_linear
-          └── circular.py      # plot_circular, compute_track_radii_dict

{pycmplot-0.2.2 → pycmplot-0.2.4}/pyproject.toml

@@ -4,13 +4,19 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pycmplot"
-version = "0.2.2"
+version = "0.2.4"
 description = "Multi-track circular and linear Manhattan plot generation for GWAS summary statistics"
 readme = "README.md"
 license = "CC-BY-NC-SA-4.0"
+license-files = ["LICEN[CS]E*"]
 authors = [{ name = "Kevin Esoh", email = "kesohku1@jh.edu" }]
 requires-python = ">=3.9"
 
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+
 dependencies = [
     "pandas>=1.5",
     "numpy>=1.23",
@@ -25,6 +31,12 @@ dependencies = [
 [project.optional-dependencies]
 dev = ["pytest", "black", "ruff", "towncrier", "sphinx"]
 
+
+[project.urls]
+Homepage = "https://github.com/esohkevin/pycmplot"
+Issues = "https://github.com/esohkevin/pycmplot/issues"
+Docs = "https://pycmplot.readthedocs.io/en/latest/"
+
 [tool.setuptools.package-data]
 pycmplot = ["data/*"]
 
@@ -36,7 +48,7 @@ where = ["."]
 exclude = [
     "dist*", "changelog.d*", "build-pypi-package.md", 
     "pycmplot_python_api.ipynb", "mit-license.txt", 
-    "pycmplot_docs", "docs"
+    "pycmplot_docs", "docs", "CHANGELOG.rst"
 ]
 
 

{pycmplot-0.2.2 → pycmplot-0.2.4}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pycmplot
-version = 0.2.2
+version = 0.2.4
 author = Kevin Esoh
 author_email = kesohku1@jh.edu
 description = Multi-track circular and linear Manhattan plot generation for GWAS summary statistics