biopipen 0.28.1__py3-none-any.whl → 0.29.1__py3-none-any.whl

biopipen/scripts/bcftools/BcftoolsFilter.py

@@ -1,79 +0,0 @@
-import shutil
-from pathlib import Path
-from hashlib import md5
-
-from biopipen.core.filters import dict_to_cli_args, run_command
-
-infile = {{in.infile | repr}}  # pyright: ignore
-outfile = {{out.outfile | repr}}  # pyright: ignore
-bcftools = {{envs.bcftools | repr}}  # pyright: ignore
-keep = {{envs.keep | repr}}  # pyright: ignore
-args = {{envs.args | repr}}  # pyright: ignore
-ncores = {{envs.ncores | repr}}  # pyright: ignore
-tmpdir = {{envs.tmpdir | repr}}  # pyright: ignore
-includes = {{envs.includes | repr}}  # pyright: ignore
-excludes = {{envs.excludes | repr}}  # pyright: ignore
-
-args[""] = bcftools
-args["_"] = infile
-args["o"] = outfile
-args["threads"] = ncores
-if "O" not in args and "output-type" not in args:
-    args["O"] = "z" if infile.endswith(".gz") else "v"
-if "m" not in args and "mode" not in args:
-    args["m"] = "+"
-
-tmpdir = (
-    Path(tmpdir) / f"biopipen-bcftoolsfilter-{md5(infile.encode()).hexdigest()}"
-)
-tmpdir.mkdir(parents=True, exist_ok=True)
-# a.vcf.gz -> a
-# a.vcf -> a
-stem = Path(infile).stem
-if stem.endswith(".vcf"):
-    stem = stem[:-4]
-# .vcf.gz
-# .gz
-ext = Path(infile).name[len(stem):]
-
-FILTER_INDEX = [1]
-
-def handle_filter(vcf, fname, filt, flag):
-    print("- Handling filter ", fname, ": ", filt, " ...")
-
-    arguments = args.copy()
-    arguments[flag] = filt
-    arguments["_"] = vcf
-    arguments["o"] = tmpdir / f"{stem}.{fname}{ext}"
-    if keep:
-        arguments["s"] = fname
-
-    run_command(dict_to_cli_args(arguments, dashify=True), fg=True)
-    return arguments["o"]
-
-
-def normalize_expr(expr, flag):
-    out = {}
-    if not expr:
-        return out
-    if isinstance(expr, list):
-        for ex in expr:
-            out[f"FILTER{FILTER_INDEX[0]}"] = (ex, flag)
-            FILTER_INDEX[0] += 1
-    elif isinstance(expr, dict):
-        for name, ex in expr.items():
-            out[name] = (ex, flag)
-    else: # str
-        out[f"FILTER{FILTER_INDEX[0]}"] = (expr, flag)
-        FILTER_INDEX[0] += 1
-    return out
-
-includes = normalize_expr(includes, "include")
-excludes = normalize_expr(excludes, "exclude")
-includes.update(excludes)
-
-# bcftools can be only done once at one filter
-for fname, (filt, flag) in includes.items():
-    infile = handle_filter(infile, fname, filt, flag)
-
-shutil.copy2(infile, outfile)

biopipen/scripts/bcftools/BcftoolsSort.py

@@ -1,19 +0,0 @@
-from biopipen.utils.misc import run_command, dict_to_cli_args
-
-infile = {{in.infile | quote}}  # pyright: ignore
-outfile = {{out.outfile | quote}}  # pyright: ignore
-bcftools = {{envs.bcftools | quote}}  # pyright: ignore
-gz = {{envs.gz | repr}}  # pyright: ignore
-args = {{envs.args | repr}}  # pyright: ignore
-tmpdir = {{envs.tmpdir | quote}}  # pyright: ignore
-index = {{envs.index | repr}}  # pyright: ignore
-
-args[""] = bcftools
-args["_"] = infile
-args["o"] = outfile
-args["O"] = "z" if gz or index else "v"
-
-run_command(dict_to_cli_args(args, dashify=True), fg=True)
-
-if index:
-    run_command([bcftools, "index", outfile], fg=True)

biopipen/scripts/gene/GeneNameConversion.py

@@ -1,66 +0,0 @@
-import pandas
-from datar.all import c, right_join, select, relocate
-from biopipen.utils.gene import gene_name_conversion
-
-infile = {{in.infile | quote}}  # pyright: ignore
-outfile = {{out.outfile | quote}}  # pyright: ignore
-inopts = {{envs.inopts | repr}}  # pyright: ignore
-outopts = {{envs.outopts | repr}}  # pyright: ignore
-notfound = {{envs.notfound | repr}}  # pyright: ignore
-genecol = {{envs.genecol | repr}}  # pyright: ignore
-output = {{envs.output | repr}}  # pyright: ignore
-infmt = {{envs.infmt | repr}}  # pyright: ignore
-outfmt = {{envs.outfmt | repr}}  # pyright: ignore
-species = {{envs.species | quote}}  # pyright: ignore
-
-df = pandas.read_csv(infile, **inopts)
-
-if isinstance(genecol, int):
-    genes = df.iloc[:, genecol]
-else:
-    genes = df.loc[:, genecol]
-
-colname = genes.name
-genes = genes.tolist()
-
-#        query  `outfmt`
-#     <object> <object>
-# 0  1255_g_at   GUCA1A
-# 1    1316_at     THRA
-# 2    1320_at   PTPN21
-# 3    1294_at  MIR5193
-converted = gene_name_conversion(
-    genes=genes,
-    species=species,
-    infmt=infmt,
-    outfmt=outfmt,
-    notfound=notfound,
-)
-converted.columns = [colname] + converted.columns[1:].tolist()
-
-if output == "only":
-    out = converted
-
-elif output == "keep":
-    out = df >> right_join(converted, by=colname, suffix=["", "_converted"])
-
-elif output == "drop":
-    out = df >> right_join(
-        converted,
-        by=colname, suffix=["", "_converted"]
-    ) >> select(~c(colname))
-
-elif output == "replace":
-    out = df >> right_join(
-        converted, by=colname, suffix=["", "_converted"]
-    )
-    converted_cols = out.columns[-len(converted.columns)+1:].tolist()
-    pos = df.columns.get_indexer([colname])[0]
-    out = out >> relocate(
-        converted_cols, _after=pos+1
-    ) >> select(~c(colname))
-
-else:
-    raise ValueError(f"Unknown output mode: {output}.")
-
-out.to_csv(outfile, **outopts)