pycmplot 0.2.2__tar.gz → 0.2.3__tar.gz

{pycmplot-0.2.2/pycmplot.egg-info → pycmplot-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pycmplot
-Version: 0.2.2
+Version: 0.2.3
 Summary: Multi-track circular and linear Manhattan plot generation for GWAS summary statistics
 Author: Kevin Esoh
 Author-email: Kevin Esoh <kesohku1@jh.edu>

{pycmplot-0.2.2 → pycmplot-0.2.3}/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 = "0.2.3"  # update to match PyPI version
 
 # -- General configuration -----------------------------------------------------
 extensions = [

{pycmplot-0.2.2 → pycmplot-0.2.3}/pycmplot/__init__.py

@@ -42,4 +42,4 @@ __all__ = [
     "ResourceConfig",
 ]
 
-__version__ = "0.2.1"
+__version__ = "0.2.3"

{pycmplot-0.2.2 → pycmplot-0.2.3}/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-0.2.3}/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__)
 
@@ -563,8 +564,9 @@ 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:
+    #if buildc:
+    bld_candidates = buildc
+    if not bld_candidates:
         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]
@@ -635,7 +637,7 @@ def prep_pycmplot_input_info(
             }
             col_dtypes = {
                 chrom_col: str,
-                pos_col:   int,
+                pos_col:   object,
                 snp_col:   str,
                 pcol:      float,
                 bcol:      str,
@@ -682,6 +684,7 @@ 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 +827,7 @@ 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 +837,7 @@ 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 +866,7 @@ 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 +963,15 @@ 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()
+            chrom_max = hi_val
+
+            # Ensure sector sizes are within chrom ranges if liftover
+            if liftover:
+                logger.info("Limiting sector sizes to chromosome ranges for liftover sumstats ...")
+                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-0.2.3/pycmplot.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pycmplot
-Version: 0.2.2
+Version: 0.2.3
 Summary: Multi-track circular and linear Manhattan plot generation for GWAS summary statistics
 Author: Kevin Esoh
 Author-email: Kevin Esoh <kesohku1@jh.edu>

{pycmplot-0.2.2 → pycmplot-0.2.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pycmplot"
-version = "0.2.2"
+version = "0.2.3"
 description = "Multi-track circular and linear Manhattan plot generation for GWAS summary statistics"
 readme = "README.md"
 license = "CC-BY-NC-SA-4.0"
@@ -36,7 +36,7 @@ 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-0.2.3}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pycmplot
-version = 0.2.2
+version = 0.2.3
 author = Kevin Esoh
 author_email = kesohku1@jh.edu
 description = Multi-track circular and linear Manhattan plot generation for GWAS summary statistics