Sclinker

src/cellink/io/_sgkit.py

@@ -375,6 +375,8 @@ def read_plink(
 
 def read_bgen(
     path: str | Path = None,
+    metafile_path: str | Path = None,
+    sample_path: str | Path = None,
     *,
     var_rename=None,
     obs_rename=None,
@@ -415,7 +417,5 @@ def read_bgen(
         raise ImportError("sgkit is required for `read_bgen`. Install with `pip install cellink[datasets]`.")
 
     sgkit_dataset = sg_bgen.read_bgen(path=path, **kwargs)
-    gdata = from_sgkit_dataset(
-        sgkit_dataset, var_rename=var_rename, obs_rename=obs_rename, X_field=X_field, hard_call=hard_call, keep_multiallelic=keep_multiallelic, load_call_fields=load_call_fields
-    )
+    gdata = from_sgkit_dataset(sgkit_dataset, metafile_path=metafile_path, sample_path=sample_path, var_rename=var_rename, obs_rename=obs_rename, hard_call=hard_call)
     return gdata

src/cellink/resources/__init__.py

@@ -8,4 +8,10 @@
     get_pgs_catalog_score,
     get_pgs_catalog_scores,
 )
-from ._ld import get_1000genomes_ld_scores, get_1000genomes_ld_weights
+from ._ld import (
+    get_1000genomes_ld_scores, 
+    get_1000genomes_ld_weights, 
+    get_1000genomes_plink_files,
+    get_1000genomes_frq,
+    get_1000genomes_hapmap3,
+)

src/cellink/resources/_datasets.py

@@ -6,11 +6,12 @@
 import pandas as pd
 
 import cellink as cl
-from cellink._core import DonorData
 from cellink.io import read_h5_dd, read_zarr_dd
 from cellink.resources._datasets_utils import plink_filter_prune, plink_kinship, preprocess_vcf_to_plink, try_liftover
 from cellink.resources._utils import _download_file, _load_config, _run, get_data_home
 
+from .._core import DonorData
+
 logging.basicConfig(level=logging.INFO)
 
 

src/cellink/resources/_gwas_prs_qtl.py

@@ -98,109 +98,6 @@ def get_gwas_catalog_study(accession_id: str, **params: Any) -> dict:
     """
     return _fetch(f"studies/{accession_id}", params=params, paginate=False)
 
-"""
-def get_gwas_catalog_study_summary_stats(
-    accession_id: str, dest: str | Path | None = None, return_path: bool = False, **params: Any
-) -> pd.DataFrame | Path:
-
-    study_meta = _fetch(f"{GWAS_API_BASE}/studies/{accession_id}", params=params, paginate=False)
-
-    if "full_summary_stats" not in study_meta:
-        raise ValueError(f"Study {accession_id} does not have full summary statistics available")
-
-    base_url = study_meta["full_summary_stats"]
-    harmonised_url = f"{base_url}/harmonised"
-
-    import re
-
-    try:
-        r = requests.get(harmonised_url)
-        r.raise_for_status()
-
-        all_files = re.findall(r'href="([^"]*\.tsv\.gz)"', r.text)
-
-        h_files = [f for f in all_files if f.endswith(".h.tsv.gz") and not f.endswith(".h.tsv.gz-meta.yaml")]
-
-        if h_files:
-
-            def build_priority(filename):
-                filename_lower = filename.lower()
-                if "build38" in filename_lower or "hg38" in filename_lower or "grch38" in filename_lower:
-                    return 2
-                elif "build37" in filename_lower or "hg19" in filename_lower or "grch37" in filename_lower:
-                    return 1
-                else:
-                    return 0
-
-            h_files.sort(key=build_priority, reverse=True)
-            filename = h_files[0]
-            url = f"{harmonised_url}/{filename}"
-            logging.info(f"Found harmonised file: {filename}")
-        else:
-            raise ValueError("No harmonised .h.tsv.gz files found")
-
-    except Exception as e:
-        logging.warning(f"Could not find harmonised files ({e}), trying base directory")
-
-        try:
-            r = requests.get(base_url)
-            r.raise_for_status()
-            files = re.findall(r'href="([^"]*\.tsv\.gz)"', r.text)
-
-            if files:
-
-                def build_priority(filename):
-                    filename_lower = filename.lower()
-                    if "build38" in filename_lower or "hg38" in filename_lower or "grch38" in filename_lower:
-                        return 2
-                    elif "build37" in filename_lower or "hg19" in filename_lower or "grch37" in filename_lower:
-                        return 1
-                    else:
-                        return 0
-
-                files.sort(key=build_priority, reverse=True)
-                filename = files[0]
-                url = f"{base_url}/{filename}"
-            else:
-                possible_files = [
-                    f"{accession_id}_buildGRCh38.tsv.gz",
-                    f"{accession_id}_buildGRCh37.tsv.gz",
-                    f"{accession_id}.tsv.gz",
-                ]
-
-                for filename in possible_files:
-                    test_url = f"{base_url}/{filename}"
-                    try:
-                        test_r = requests.head(test_url)
-                        if test_r.status_code == 200:
-                            url = test_url
-                            break
-                    except:
-                        continue
-                else:
-                    raise ValueError(f"Could not find summary statistics file for {accession_id}")
-
-        except Exception as e2:
-            raise ValueError(f"Could not find summary statistics for {accession_id}: {e2}")
-
-    if not dest:
-        data_home = get_data_home()
-        dest = data_home / f"{accession_id}_summary_stats.tsv.gz"
-
-    logging.info(f"Downloading {url} to {dest}")
-
-    try:
-        urlretrieve(url, dest)
-    except Exception as e:
-        raise RuntimeError(f"Failed to download summary statistics from {url}: {e}")
-
-    if return_path:
-        return dest
-
-    data = pd.read_csv(dest, compression="gzip", delimiter="\t")
-    return data
-"""
-
 def get_gwas_catalog_study_summary_stats(
     accession_id: str,
     dest: str | Path | None = None,