gsMap 1.73.3__py3-none-any.whl → 1.73.4__py3-none-any.whl

gsMap/utils/regression_read.py

@@ -1,201 +1,175 @@
+import glob
+import logging
 import os
 
-import numpy as np
 import pandas as pd
 
+logger = logging.getLogger("gsMap.utils.regression_read")
 
-# Fun for reading gwas data
-def _read_sumstats(fh, alleles=False, dropna=False):
-    """
-    Parse gwas summary statistics.
-    """
-    print(f"Reading summary statistics from {fh} ...")
-    sumstats = ps_sumstats(fh, alleles=alleles, dropna=dropna)
-    print(f"Read summary statistics for {len(sumstats)} SNPs.")
-
-    m = len(sumstats)
-    sumstats = sumstats.drop_duplicates(subset="SNP")
-    if m > len(sumstats):
-        print(f"Dropped {m - len(sumstats)} SNPs with duplicated rs numbers.")
 
-    return sumstats
+def _read_sumstats(fh, alleles=False, dropna=False):
+    """Parse GWAS summary statistics."""
+    logger.info(f"Reading summary statistics from {fh} ...")
 
+    # Determine compression type
+    compression = None
+    if fh.endswith("gz"):
+        compression = "gzip"
+    elif fh.endswith("bz2"):
+        compression = "bz2"
 
-def ps_sumstats(fh, alleles=False, dropna=True):
-    """
-    Parses .sumstats files. See docs/file_formats_sumstats.txt.
-    """
+    # Define columns and dtypes
     dtype_dict = {"SNP": str, "Z": float, "N": float, "A1": str, "A2": str}
-    compression = get_compression(fh)
     usecols = ["SNP", "Z", "N"]
     if alleles:
         usecols += ["A1", "A2"]
 
+    # Read the file
     try:
-        x = read_csv(fh, usecols=usecols, dtype=dtype_dict, compression=compression)
+        sumstats = pd.read_csv(
+            fh,
+            sep=r"\s+",
+            na_values=".",
+            usecols=usecols,
+            dtype=dtype_dict,
+            compression=compression,
+        )
     except (AttributeError, ValueError) as e:
+        logger.error(f"Failed to parse sumstats file: {str(e.args)}")
         raise ValueError("Improperly formatted sumstats file: " + str(e.args)) from e
 
+    # Drop NA values if specified
     if dropna:
-        x = x.dropna(how="any")
+        sumstats = sumstats.dropna(how="any")
 
-    return x
+    logger.info(f"Read summary statistics for {len(sumstats)} SNPs.")
 
+    # Drop duplicates
+    m = len(sumstats)
+    sumstats = sumstats.drop_duplicates(subset="SNP")
+    if m > len(sumstats):
+        logger.info(f"Dropped {m - len(sumstats)} SNPs with duplicated rs numbers.")
 
-def get_compression(fh):
-    """
-    Determin the format of compression used with read_csv?
-    """
-    if fh.endswith("gz"):
-        compression = "gzip"
-    elif fh.endswith("bz2"):
-        compression = "bz2"
-    else:
-        compression = None
-    # -
-    return compression
-
-
-def read_csv(fh, **kwargs):
-    """
-    Read the csv data
-    """
-    return pd.read_csv(fh, sep=r"\s+", na_values=".", **kwargs)
-
-
-# Fun for reading loading LD scores
-def which_compression(fh):
-    """
-    Given a file prefix, figure out what sort of compression to use.
-    """
-    if os.access(fh + ".bz2", 4):
-        suffix = ".bz2"
-        compression = "bz2"
-    elif os.access(fh + ".gz", 4):
-        suffix = ".gz"
-        compression = "gzip"
-    elif os.access(fh + ".parquet", 4):
-        suffix = ".parquet"
-        compression = "parquet"
-    elif os.access(fh + ".feather", 4):
-        suffix = ".feather"
-        compression = "feather"
-    elif os.access(fh, 4):
-        suffix = ""
-        compression = None
-    else:
-        raise OSError(f"Could not open {fh}[./gz/bz2/parquet/feather]")
-    # -
-    return suffix, compression
+    return sumstats
+
+
+def _read_chr_files(base_path, suffix, expected_count=22):
+    """Read chromosome files using glob pattern matching."""
+    # Create the pattern to search for files
+    file_pattern = f"{base_path}[1-9]*{suffix}*"
+
+    # Find all matching files
+    all_files = glob.glob(file_pattern)
+
+    # Extract chromosome numbers
+    chr_files = []
+    for file in all_files:
+        try:
+            # Extract the chromosome number from filename
+            file_name = os.path.basename(file)
+            base_name = os.path.basename(base_path)
+            chr_part = file_name.replace(base_name, "").split(suffix)[0]
+            chr_num = int(chr_part)
+            if 1 <= chr_num <= expected_count:
+                chr_files.append((chr_num, file))
+        except (ValueError, IndexError):
+            continue
+
+    # Check if we have the expected number of chromosome files
+    if len(chr_files) != expected_count:
+        logger.warning(
+            f"❗ SEVERE WARNING ❗ Expected {expected_count} chromosome files, but found {len(chr_files)}! "
+            f"⚠️ For human GWAS data, all 22 autosomes must be present. Please verify your input files."
+        )
+
+    # Sort by chromosome number and return file paths
+    chr_files.sort()
+    return [file for _, file in chr_files]
+
+
+def _read_file(file_path):
+    """Read a file based on its format/extension."""
+    try:
+        if file_path.endswith(".feather"):
+            return pd.read_feather(file_path)
+        elif file_path.endswith(".parquet"):
+            return pd.read_parquet(file_path)
+        elif file_path.endswith(".gz"):
+            return pd.read_csv(file_path, compression="gzip", sep="\t")
+        elif file_path.endswith(".bz2"):
+            return pd.read_csv(file_path, compression="bz2", sep="\t")
+        else:
+            return pd.read_csv(file_path, sep="\t")
+    except Exception as e:
+        logger.error(f"Failed to read file {file_path}: {str(e)}")
+        raise
 
 
 def _read_ref_ld_v2(ld_file):
+    """Read reference LD scores for all chromosomes."""
     suffix = ".l2.ldscore"
-    file = ld_file
-    first_fh = f"{file}1{suffix}"
-    s, compression = which_compression(first_fh)
-    print(f"Reading ld score annotations from {file}[1-22]{suffix}.{compression}")
-    ref_ld = pd.concat(
-        [pd.read_feather(f"{file}{chr}{suffix}{s}") for chr in range(1, 23)], axis=0
-    )
-    # set first column as index
-    ref_ld.rename(columns={"index": "SNP"}, inplace=True)
-    ref_ld.set_index("SNP", inplace=True)
-    return ref_ld
+    logger.info(f"Reading LD score annotations from {ld_file}[1-22]{suffix}...")
 
+    # Get the chromosome files
+    chr_files = _read_chr_files(ld_file, suffix)
 
-def _read_M_v2(ld_file, n_annot, not_M_5_50):
-    suffix = ".l2.M"
-    if not not_M_5_50:
-        suffix += "_5_50"
-    M_annot = np.array(
-        [
-            np.loadtxt(
-                f"{ld_file}{chr}{suffix}",
-            )
-            for chr in range(1, 23)
-        ]
-    )
-    assert M_annot.shape == (22, n_annot)
-    return M_annot.sum(axis=0).reshape((1, n_annot))
+    # Read and concatenate all files
+    df_list = [_read_file(file) for file in chr_files]
 
+    if not df_list:
+        logger.error(f"No LD score files found matching pattern: {ld_file}*{suffix}*")
+        raise FileNotFoundError(f"No LD score files found matching pattern: {ld_file}*{suffix}*")
 
-# Fun for reading M annotations
-def _read_M(ld_file, n_annot, not_M_5_50):
-    """
-    Read M (--M, --M-file, etc).
-    """
-    M_annot = M(ld_file, common=(not not_M_5_50))
+    ref_ld = pd.concat(df_list, axis=0)
+    logger.info(f"Loaded {len(ref_ld)} SNPs from LD score files")
 
-    try:
-        M_annot = np.array(M_annot).reshape((1, n_annot))
-    except ValueError as e:
-        raise ValueError(
-            "# terms in --M must match # of LD Scores in --ref-ld.\n" + str(e.args)
-        ) from e
-    return M_annot
-
-
-def M(fh, common=False):
-    """
-    Parses .l{N}.M files, split across num chromosomes.
-    """
-    suffix = ".l2.M"
-    if common:
-        suffix += "_5_50"
-    # -
-    M_array = []
-    for i in range(1, 23):
-        M_current = pd.read_csv(f"{fh}{i}" + suffix, header=None)
-        M_array.append(M_current)
-
-    M_array = pd.concat(M_array, axis=1).sum(axis=1)
-    # -
-    return np.array(M_array).reshape((1, len(M_array)))
-
-
-def _check_variance_v2(M_annot, ref_ld):
-    ii = ref_ld.var() == 0
-    if ii.all():
-        raise ValueError("All LD Scores have zero variance.")
-    elif not ii.any():
-        print("No partitioned LD Scores have zero variance.")
-    else:
-        ii_snp = ii_m = np.array(~ii)
-        print(f"Removing {sum(ii)} partitioned LD Scores with zero variance.")
-        ref_ld = ref_ld.iloc[:, ii_snp]
-        M_annot = M_annot[:, ii_m]
-    return M_annot, ref_ld
+    # Set SNP as index
+    if "index" in ref_ld.columns:
+        ref_ld.rename(columns={"index": "SNP"}, inplace=True)
+    if "SNP" in ref_ld.columns:
+        ref_ld.set_index("SNP", inplace=True)
+
+    return ref_ld
 
 
 def _read_w_ld(w_file):
+    """Read LD weights for all chromosomes."""
     suffix = ".l2.ldscore"
-    file = w_file
-    first_fh = f"{file}1{suffix}"
-    s, compression = which_compression(first_fh)
-    #
+    logger.info(f"Reading LD score annotations from {w_file}[1-22]{suffix}...")
+
+    # Get the chromosome files
+    chr_files = _read_chr_files(w_file, suffix)
+
+    if not chr_files:
+        logger.error(f"No LD score files found matching pattern: {w_file}*{suffix}*")
+        raise FileNotFoundError(f"No LD score files found matching pattern: {w_file}*{suffix}*")
+
+    # Read and process each file
     w_array = []
-    print(f"Reading ld score annotations from {file}[1-22]{suffix}.{compression}")
-
-    for chr in range(1, 23):
-        file_chr = f"{file}{chr}{suffix}{s}"
-        #
-        if compression == "parquet":
-            x = pd.read_parquet(file_chr)
-        elif compression == "feather":
-            x = pd.read_feather(file_chr)
-        else:
-            x = pd.read_csv(file_chr, compression=compression, sep="\t")
+    for file in chr_files:
+        x = _read_file(file)
 
-        x = x.sort_values(by=["CHR", "BP"])
+        # Sort if possible
+        if "CHR" in x.columns and "BP" in x.columns:
+            x = x.sort_values(by=["CHR", "BP"])
 
+        # Drop unnecessary columns
         columns_to_drop = ["MAF", "CM", "Gene", "TSS", "CHR", "BP"]
         columns_to_drop = [col for col in columns_to_drop if col in x.columns]
-        x = x.drop(columns_to_drop, axis=1)
+        if columns_to_drop:
+            x = x.drop(columns=columns_to_drop, axis=1)
 
         w_array.append(x)
-    #
+
+    # Concatenate and set column names
     w_ld = pd.concat(w_array, axis=0)
-    w_ld.columns = ["SNP", "LD_weights"]
+    logger.info(f"Loaded {len(w_ld)} SNPs from LD weight files")
+
+    # Set column names
+    w_ld.columns = (
+        ["SNP", "LD_weights"] + list(w_ld.columns[2:])
+        if len(w_ld.columns) > 2
+        else ["SNP", "LD_weights"]
+    )
 
     return w_ld

{gsmap-1.73.3.dist-info → gsmap-1.73.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gsMap
-Version: 1.73.3
+Version: 1.73.4
 Summary: Genetics-informed pathogenic spatial mapping
 Author-email: liyang <songliyang@westlake.edu.cn>, wenhao <chenwenhao@westlake.edu.cn>
 Requires-Python: >=3.10

{gsmap-1.73.3.dist-info → gsmap-1.73.4.dist-info}/RECORD

@@ -1,12 +1,12 @@
-gsMap/__init__.py,sha256=0XtiYZAbXor3EAyHAebfh1qGJuKOgeB3h1MPE6ukNNY,77
+gsMap/__init__.py,sha256=hRDqmAAKm9MYDtkkkVvoAJQDZAlG2yZ5nafywVU2Ufo,77
 gsMap/__main__.py,sha256=Vdhw8YA1K3wPMlbJQYL5WqvRzAKVeZ16mZQFO9VRmCo,62
 gsMap/cauchy_combination_test.py,sha256=SiUyqJKr4ATFtRgsCEJ43joGcSagCOnnurkB1FlQiB4,5105
-gsMap/config.py,sha256=LmBVMb0eda6bfrKkQuh7eZnZdvgecjCnozRd_clqvlY,51584
+gsMap/config.py,sha256=xQQJKqe-ZLohxzEZ0L_CEXXbbUK-U6-H6BnISteqrHs,51316
 gsMap/create_slice_mean.py,sha256=Nnmb7ACtS-9TurW5xQ4TqCinejPsYcvuT5Oxqa5Uges,5723
-gsMap/diagnosis.py,sha256=YyT_TkPbb3c22DLpRYu9yynbNGrhytcCgxCoPwz9Bpc,12962
+gsMap/diagnosis.py,sha256=Z-zJriPge0_kUbU-S41w7cPT2xYFlDVzbp6p6QMoKQc,13025
 gsMap/find_latent_representation.py,sha256=aZ5fFY2RhAsNaDeoehd5lN28556d6GGHK9xEUTvo6G4,5365
 gsMap/format_sumstats.py,sha256=1c9OgbqDQWOgXeSrbAhbJfChv_2IwXIgLE6Pbw2sx0s,13778
-gsMap/generate_ldscore.py,sha256=G108fVVdGj0Pn50TqFmAXLjQ7OTY9BWnilHoDeIn2D8,45348
+gsMap/generate_ldscore.py,sha256=9Qlx8na0w82U8UsSvdPCsDbNAxNFPHKYuUjY4M04fOg,35363
 gsMap/latent_to_gene.py,sha256=sDPvOU4iF-HkfQY0nnkIVXpjyTQ9-PjQflwEFWrPg-A,12869
 gsMap/main.py,sha256=SzfAXhrlr4LXnSD4gkvAtUUPYXyra6a_MzVCxDBZjr0,1170
 gsMap/report.py,sha256=_1FYkzGhVGMnvHgEQ8z51iMrVEVlh48a31jLqbV2o9w,6953
@@ -20,12 +20,12 @@ gsMap/GNN/model.py,sha256=75In9sxBkaqqpCQSrQEUO-zsQQVQnkXVbKsAgyAZjiQ,2918
 gsMap/GNN/train.py,sha256=4qipaxaz3rQOtlRpTYCfl1Oz4kz_A6vNB1aw8_gGK_k,3076
 gsMap/templates/report_template.html,sha256=QODZEbVxpW1xsLz7lDrD_DyUfzYoi9E17o2tLJlf8OQ,8016
 gsMap/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gsMap/utils/generate_r2_matrix.py,sha256=0zyoJDWUVavlQtR6_XXb7Ah9UhPyT3n0t6XCqlI1HXQ,17354
+gsMap/utils/generate_r2_matrix.py,sha256=0FEbSEiZhNj3nnnt9V-fp7WWPLpfBci3tP4ydBbG280,20114
 gsMap/utils/jackknife.py,sha256=w_qMj9GlqViouHuOw1U80N6doWuCTXuPoAVU4P-5mm8,17673
 gsMap/utils/manhattan_plot.py,sha256=4ok5CHAaT_MadyMPnFZMR_llmE8Vf4-KiEfametgHq0,25480
-gsMap/utils/regression_read.py,sha256=rKA0nkUpTJf6WuGddhKrsBCExchDNEyojOWu_qddZNw,5474
-gsmap-1.73.3.dist-info/entry_points.txt,sha256=s_P2Za22O077tc1FPLKMinbdRVXaN_HTcDBgWMYpqA4,41
-gsmap-1.73.3.dist-info/licenses/LICENSE,sha256=fb5WP6qQytSKO5rM0ZSqQXg_92Fdt0aAeFNwSi3Lpmc,1069
-gsmap-1.73.3.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
-gsmap-1.73.3.dist-info/METADATA,sha256=-MD9qe4n_qOVF1dAQ6gcSLtCl1DZDMeoRw2EVijGDms,8196
-gsmap-1.73.3.dist-info/RECORD,,
+gsMap/utils/regression_read.py,sha256=uBSKlvYVhUKmDSCBvKHQrE1wLNyvK-rbzc5TJV51oDI,5649
+gsmap-1.73.4.dist-info/entry_points.txt,sha256=s_P2Za22O077tc1FPLKMinbdRVXaN_HTcDBgWMYpqA4,41
+gsmap-1.73.4.dist-info/licenses/LICENSE,sha256=fb5WP6qQytSKO5rM0ZSqQXg_92Fdt0aAeFNwSi3Lpmc,1069
+gsmap-1.73.4.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
+gsmap-1.73.4.dist-info/METADATA,sha256=fyLpDSS5SEIyPj9rZ7ymcXPIOCLcAU2j-OW0D5xC2GA,8196
+gsmap-1.73.4.dist-info/RECORD,,