biopipen 0.27.1__tar.gz → 0.27.2__tar.gz

{biopipen-0.27.1 → biopipen-0.27.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.27.1
+Version: 0.27.2
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

biopipen-0.27.2/biopipen/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.27.2"

{biopipen-0.27.1 → biopipen-0.27.2}/biopipen/ns/snp.py

@@ -7,12 +7,15 @@ from ..core.config import config
 class PlinkSimulation(Proc):
     """Simulate SNPs using PLINK v1.9
 
-    See also <https://www.cog-genomics.org/plink/1.9/input#simulate>.
+    See also <https://www.cog-genomics.org/plink/1.9/input#simulate> and
+    <https://pwwang.github.io/biopipen/api/biopipen.ns.snp/#biopipen.ns.snp.PlinkSimulation>
 
     Input:
-        nsnps: Number of SNPs to simulate
-        ncases: Number of cases to simulate
-        nctrls: Number of controls to simulate
+        configfile: Configuration file containing the parameters for the simulation.
+            The configuration file (in toml, yaml or json format) should contain a
+            dictionary of parameters.  The parameters are listed in `envs` except
+            `ncores`, which is used for parallelization. You can set parameters
+            in `envs` and override them in the configuration file.
 
     Output:
         outdir: Output directory containing the simulated data
@@ -21,9 +24,11 @@ class PlinkSimulation(Proc):
             SNPs and columns representing samples.
 
     Envs:
+        nsnps (type=int): Number of SNPs to simulate
+        ncases (type=int): Number of cases to simulate
+        nctrls (type=int): Number of controls to simulate
         plink: Path to PLINK v1.9
-        seed (type=int): Random seed.
-            If not set, seed will not be set.
+        seed (type=int): Random seed. If not set, seed will not be set.
         label: Prefix label for the SNPs.
         prevalence  (type=float): Disease prevalence.
         minfreq (type=float): Minimum allele frequency.
@@ -41,19 +46,17 @@ class PlinkSimulation(Proc):
             This only affects the sample names in the genotype matrix file
             (`out.gtmat`).
     """
-    input = "nsnps:var, ncases:var, nctrls:var"
+    input = "configfile:file"
     output = [
-        (
-            "outdir:dir:{{in.nsnps | int}}_"
-            "{{in.ncases | int}}xcases_{{in.nctrls | int}}xctrls.plink_sim"
-        ),
-        (
-            "gtmat:file:{{in.nsnps | int}}_"
-            "{{in.ncases | int}}xcases_{{in.nctrls | int}}xctrls.plink_sim/gtmat.txt"
-        ),
+        "outdir:dir:{{in.configfile | stem}}.plink_sim",
+        "gtmat:file:{{in.configfile | stem}}.plink_sim/"
+        "{{in.configfile | stem}}-gtmat.txt",
     ]
     lang = config.lang.python
     envs = {
+        "nsnps": None,
+        "ncases": None,
+        "nctrls": None,
         "plink": config.exe.plink,
         "seed": None,
         "label": "SNP",

{biopipen-0.27.1 → biopipen-0.27.2}/biopipen/ns/tcr.py

@@ -983,6 +983,7 @@ class CloneResidency(Proc):
             before calculating the clone residency. For example, `Clones > 1` to filter
             out singletons.
         prefix: The prefix of the cell barcodes in the `Seurat` object.
+        upset_ymax: The maximum value of the y-axis in the upset bar plots.
         upset_trans: The transformation to apply to the y axis of upset bar plots.
             For example, `log10` or `sqrt`. If not specified, the y axis will be
             plotted as is. Note that the position of the bar plots will be dodged
@@ -1007,6 +1008,7 @@ class CloneResidency(Proc):
         "mutaters": {},
         "subset": None,
         "prefix": "{Sample}_",
+        "upset_ymax": None,
         "upset_trans": None,
         "cases": {},
     }
@@ -1595,3 +1597,74 @@ class TESSA(Proc):
     }
     script = "file://../scripts/tcr/TESSA.R"
     plugin_opts = {"report": "file://../reports/tcr/TESSA.svelte"}
+
+
+class TCRDock(Proc):
+    """Using TCRDock to predict the structure of MHC-peptide-TCR complexes
+
+    See <https://github.com/phbradley/TCRdock>.
+
+    Input:
+        configfile: The config file for TCRDock
+            It's should be a toml file with the keys listed in `envs`, including
+            `organism`, `mhc_class`, `mhc`, `peptide`, `va`, `ja`, `vb`, `jb`,
+            `cdr3a`, and `cdr3b`.
+            The values will overwrite the values in `envs`.
+
+    Output:
+        outdir: The output directory containing the results
+
+    Envs:
+        organism: The organism of the TCR, peptide and MHC
+        mhc_class (type=int): The MHC class, either `1` or `2`
+        mhc: The MHC allele, e.g., `A*02:01`
+        peptide: The peptide sequence
+        va: The V alpha gene
+        ja: The J alpha gene
+        vb: The V beta gene
+        jb: The J beta gene
+        cdr3a: The CDR3 alpha sequence
+        cdr3b: The CDR3 beta sequence
+        python: The path of python with dependencies for `tcrdock` installed.
+            If not provided, `TCRDock.lang` will be used (the same interpreter
+            used for the wrapper script).
+            It could also be a list to specify, for example, a python in a conda
+            environment (e.g., `["conda", "run", "-n", "myenv", "python"]`).
+        tmpdir: The temporary directory used to clone the `tcrdock` source code if
+            `envs.tcrdock` is not provided.
+        tcrdock: The path to the `tcrdock` source code repo.
+            You need to clone the source code from the github repository.
+            <https://github.com/phbradley/TCRdock> at
+            revision c5a7af42eeb0c2a4492a4d4fe803f1f9aafb6193 at main branch.
+            You also have to run `download_blast.py` after cloning to download the
+            blast database in the directory.
+            If not provided, we will clone the source code to the `envs.tmpdir`
+            directory and run the `download_blast.py` script.
+        model_name: The model name to use
+        model_file: The model file to use.
+            If provided as a relative path, it should be relative to the
+            `<envs.data_dir>/params/`, otherwise, it should be the full path.
+        data_dir: The data directory that contains the model files.
+            The model files should be in the `params` subdirectory.
+    """
+    input = "configfile:file"
+    output = "outdir:dir:{{in.configfile | stem}}.tcrdock"
+    lang = config.lang.python
+    envs = {
+        "tcrdock": None,
+        "organism": "human",
+        "mhc_class": 1,
+        "mhc": "A*02:01",
+        "peptide": None,
+        "va": None,
+        "ja": None,
+        "vb": None,
+        "jb": None,
+        "cdr3a": None,
+        "cdr3b": None,
+        "python": None,
+        "model_name": "model_2_ptm_ft4",
+        "model_file": "tcrpmhc_run4_af_mhc_params_891.pkl",
+        "data_dir": None,
+    }
+    script = "file://../scripts/tcr/TCRDock.py"

{biopipen-0.27.1 → biopipen-0.27.2}/biopipen/scripts/scrna/RadarPlots.R

@@ -74,10 +74,10 @@ expand_each <- function(name,  case) {
         }
     } else {
         if (is.null(case$subset)) {
-            eachs <- srtobj@meta.data %>%
+            eachs <- meta %>%
                 pull(case$each) %>% unique() %>% na.omit() %>% as.vector()
         } else {
-            eachs <- srtobj@meta.data %>% filter(!!parse_expr(case$subset)) %>%
+            eachs <- meta %>% filter(!!parse_expr(case$subset)) %>%
                 pull(case$each) %>% unique() %>% na.omit() %>% as.vector()
         }
         for (each in eachs) {

biopipen-0.27.2/biopipen/scripts/snp/PlinkSimulation.py

@@ -0,0 +1,124 @@
+from pathlib import Path
+from multiprocessing import Pool
+from slugify import slugify
+from simpleconf import Config
+from biopipen.utils.misc import logger, run_command, dict_to_cli_args
+
+configfile = {{in.configfile | repr}}  # pyright: ignore # noqa: E999
+outdir = {{out.outdir | repr}}  # pyright: ignore
+gtmatfile = {{out.gtmat | repr}}  # pyright: ignore
+config = Config.load(configfile)
+
+default_nsnps = {{envs.nsnps | repr}}  # pyright: ignore
+default_ncases = {{envs.ncases | repr}}  # pyright: ignore
+default_nctrls = {{envs.nctrls | repr}}  # pyright: ignore
+default_plink = {{envs.plink | repr}}  # pyright: ignore
+default_seed = {{envs.seed | repr}}  # pyright: ignore
+default_label = {{envs.label | repr}}  # pyright: ignore
+default_prevalence = {{envs.prevalence | repr}}  # pyright: ignore
+default_minfreq = {{envs.minfreq | repr}}  # pyright: ignore
+default_maxfreq = {{envs.maxfreq | repr}}  # pyright: ignore
+default_hetodds = {{envs.hetodds | repr}}  # pyright: ignore
+default_homodds = {{envs.homodds | repr}}  # pyright: ignore
+default_missing = {{envs.missing | repr}}  # pyright: ignore
+default_args = {{envs.args | repr}}  # pyright: ignore
+default_transpose_gtmat = {{envs.transpose_gtmat | repr}}  # pyright: ignore
+default_sample_prefix = {{envs.sample_prefix | repr}}  # pyright: ignore
+
+defaults = {
+    "nsnps": default_nsnps,
+    "ncases": default_ncases,
+    "nctrls": default_nctrls,
+    "plink": default_plink,
+    "seed": default_seed,
+    "label": default_label,
+    "prevalence": default_prevalence,
+    "minfreq": default_minfreq,
+    "maxfreq": default_maxfreq,
+    "hetodds": default_hetodds,
+    "homodds": default_homodds,
+    "missing": default_missing,
+    # "args": default_args,
+    "transpose_gtmat": default_transpose_gtmat,
+    "sample_prefix": default_sample_prefix,
+}
+
+def do_one_simulation(confitems):
+    args = default_args.copy()
+    args.update(confitems.pop("args", {}))
+    confs = defaults.copy()
+    confs.update(confitems)
+    transpose_gtmat = confs.pop("transpose_gtmat")
+    sample_prefix = confs.pop("sample_prefix")
+
+
+    logger.debug("  Generating parameters file")
+    params_file = Path(outdir) / "params.txt"
+    params_file.write_text(
+        f"{confs['nsnps']}\t{confs['label']}\t{confs['minfreq']}\t"
+        f"{confs['maxfreq']}\t{confs['hetodds']}\t{confs['homodds']}\n"
+    )
+
+    if confs.get('seed') is not None:
+        args["seed"] = confs['seed']
+
+    args["simulate"] = params_file
+    args["out"] = Path(outdir) / "sim_snps"
+    args["simulate-ncases"] = confs['ncases']
+    args["simulate-ncontrols"] = confs['nctrls']
+    args["simulate-prevalence"] = confs['prevalence']
+    args["simulate-missing"] = confs['missing']
+
+    cmd = [confs['plink']] + dict_to_cli_args(args)
+
+    logger.debug("  Running PLINK simulation ...")
+    run_command(cmd, fg=True)
+
+    # Transpose the genotype matrix
+    # CHR	SNP	(C)M	POS	COUNTED	ALT	per0_per0	per1_per1	per2_per2
+    # 1	SNP_0	0	1	D	d	1	0	1
+    # 1	SNP_1	0	2	d	D	0	1	0
+    # 1	SNP_2	0	3	d	D	0	0	0
+    # 1	SNP_3	0	4	d	D	0	0	0
+    # 1	SNP_4	0	5	D	d	1	2	1
+    cmd = [
+        confs['plink'],
+        "--recode",
+        "A" if transpose_gtmat else "A-transpose",
+        "tab",
+        "--bfile",
+        args["out"],
+        "--out",
+        gtmatfile + ".plink.recoded",
+    ]
+    logger.debug("- Recoding into genotype matrix ...")
+    run_command(cmd, fg=True)
+
+    logger.debug("  Saving genotype matrix ...")
+    ## transpose_gtmat = False
+    # SNP_COUNTED	per0_per0	per1_per1	per2_per2
+    # SNP_0_D	1	0	1
+    # SNP_1_d	0	1	0
+    # SNP_2_d	0	0	0
+    # SNP_3_d	0	0	0
+    # SNP_4_D	1	2	1
+    ## transpose_gtmat = True
+    # FID_IID SNP_0_D SNP_1_D SNP_2_D
+    # per0_per0 0 1 1
+    # per1_per1 0 2 0
+    # per2_per2 0 0 0
+    # per3_per3 1 1 0
+    # per4_per4 0 0 0
+    if transpose_gtmat:
+        cmd = f"cut -f1,2,7- {gtmatfile}.plink.recoded.raw | sed 's/\\t/_/'"
+    else:
+        cmd = f"cut -f2,5,7- {gtmatfile}.plink.recoded.traw | sed 's/\\t/_/'"
+
+    if sample_prefix:
+        cmd = f"{cmd} | sed 's/per[0-9]\\+_per/{sample_prefix}/g'"
+
+    cmd = f"{cmd} > {gtmatfile}"
+    run_command(cmd, fg=True)
+
+
+do_one_simulation(config)

{biopipen-0.27.1 → biopipen-0.27.2}/biopipen/scripts/stats/DiffCoexpr.R

@@ -42,21 +42,21 @@ diffcoex_score <- function(group) {
 
     gvals <- unique(gdata[, group, drop = TRUE])
     if (length(gvals) < 2) {
-        log_warn("  Less than 2 groups in the input. Skipping ...")
+        log_debug("  Less than 2 groups in the input. Skipping ...")
         return(NULL)
     }
     rs <- lapply(gvals, function(gval) {
         samples <- rownames(gdata[gdata[[group]] == gval, , drop = FALSE])
         expr <- indata[samples, , drop = FALSE]
         if (length(samples) < 3) {
-            log_warn("  Less than 3 samples in one of the groups. Skipping ...")
+            log_debug("  Less than 3 samples in one of the groups. Skipping ...")
             return(NULL)
         }
         cor.pairs(as.matrix(expr), cor.method = method)
     })
     rs[sapply(rs, is.null)] <- NULL
     if (length(rs) < 2) {
-        log_warn("  Less than 2 groups with at least 3 samples. Skipping ...")
+        log_debug("  Less than 2 groups with at least 3 samples. Skipping ...")
         return(NULL)
     }
     N <- length(rs)

{biopipen-0.27.1 → biopipen-0.27.2}/biopipen/scripts/tcr/CloneResidency.R

@@ -26,6 +26,7 @@ section <- {{ envs.section | r }}
 mutaters <- {{ envs.mutaters | r }}
 subset <- {{ envs.subset | r }}
 prefix <- {{ envs.prefix | r }}
+upset_ymax <- {{ envs.upset_ymax | r }}
 upset_trans <- {{ envs.upset_trans | r }}
 cases <- {{ envs.cases | r }}
 
@@ -40,6 +41,7 @@ if (is.null(cases) || length(cases) == 0) {
             order = sample_order,
             subset = subset,
             section = section,
+            upset_ymax = upset_ymax,
             upset_trans = upset_trans
         )
     )
@@ -50,6 +52,7 @@ if (is.null(cases) || length(cases) == 0) {
         cases[[key]]$order <- cases[[key]]$order %||% sample_order
         cases[[key]]$section <- cases[[key]]$section %||% section
         cases[[key]]$subset <- cases[[key]]$subset %||% subset
+        cases[[key]]$upset_ymax <- cases[[key]]$upset_ymax %||% upset_ymax
         cases[[key]]$upset_trans <- cases[[key]]$upset_trans %||% upset_trans
     }
 }
@@ -320,7 +323,7 @@ plot_venndg <- function(counts, groups, singletons) {
     venn_p
 }
 
-plot_upset <- function(counts, singletons, upset_trans) {
+plot_upset <- function(counts, singletons, upset_ymax, upset_trans) {
 
     cnts <- column_to_rownames(counts, "CDR3.aa") %>%
         mutate(across(everything(), ~ as.integer(as.logical(.x))))
@@ -345,12 +348,21 @@ plot_upset <- function(counts, singletons, upset_trans) {
             geom_text(
                 aes(label = ..count.., vjust = ifelse(..type == "Multiplets", -0.25, +1.25)),
                 stat = "count", position = "stack", size = 2.8)
+        if (!is.null(upset_ymax)) {
+            p <- p + ylim(0, upset_ymax)
+        }
     } else {
         p <- p + geom_bar(stat = "count", position = "dodge2") +
             geom_text(
                 aes(label = ..count..),
-                stat = "count", position = position_dodge(width = 0.9), vjust = -0.25, size = 2.5) +
-            scale_y_continuous(trans = "log10")
+                stat = "count", position = position_dodge(width = 0.9), vjust = -0.25, size = 2.5)
+
+        # limit the y and do log10 transformation
+        if (!is.null(upset_ymax)) {
+            p <- p + scale_y_continuous(trans = "log10", limits = c(1, upset_ymax))
+        } else {
+            p <- p + scale_y_continuous(trans = "log10")
+        }
     }
 
     upset(
@@ -519,7 +531,7 @@ handle_subject <- function(i, subjects, casename, case) {
     upset_dir <- file.path(casedir, "upset")
     upset_png <- file.path(upset_dir, paste0("upset_", slugify(subject), ".png"))
     png(upset_png, res = 100, height = 600, width = 800)
-    print(plot_upset(counts, singletons, case$upset_trans))
+    print(plot_upset(counts, singletons, case$upset_ymax, case$upset_trans))
     dev.off()
 
     h <- headings(case$section, casename, "Overlapping Clones (UpSet Plots)")

biopipen-0.27.2/biopipen/scripts/tcr/TCRDock.py

@@ -0,0 +1,106 @@
+import os
+import sys
+from pathlib import Path
+
+import rtoml
+import pandas as pd
+from tempfile import gettempdir
+from biopipen.utils.misc import logger, run_command
+
+configfile = {{in.configfile | repr}}  # pyright: ignore
+outdir = Path({{out.outdir | repr}})  # pyright: ignore
+envs = {{envs | dict | repr}}  # pyright: ignore
+python = sys.executable
+
+args = envs.copy()
+config = rtoml.load(Path(configfile))
+args.update(config)
+model_name = args.pop("model_name")
+model_file = Path(args.pop("model_file"))
+data_dir = args.pop("data_dir", None)
+tcrdock = args.pop("tcrdock", None)
+tmpdir = args.pop("tmpdir", gettempdir())
+python = args.pop("python", python)
+
+if not isinstance(python, (list, tuple)):
+    python = [python]
+
+if not data_dir:
+    raise ValueError("`envs.data_dir` is required")
+
+if not tcrdock:
+    logger.info("- `envs.tcrdock` is not provided, cloning the repository ... ")
+    repo_url = "https://github.com/phbradley/TCRdock"
+    commit_id = "c5a7af42eeb0c2a4492a4d4fe803f1f9aafb6193"
+    branch = "main"
+
+    from git import Repo
+    repo = Repo.clone_from(repo_url, tmpdir, branch=branch, no_checkout=True)
+    repo.git.checkout(commit_id)
+    tcrdock = Path(tmpdir) / "TCRdock"
+
+    logger.info("- Running download_blast.py ...")
+    cmd = [
+        *python,
+        tcrdock / "download_blast.py",
+    ]
+    run_command(cmd, fg=True, cwd=str(tcrdock))
+
+if not model_file.is_absolute():
+    model_file = Path(data_dir) / "params" / model_file
+
+os.environ['TF_FORCE_UNIFIED_MEMORY'] = '1'
+os.environ['XLA_PYTHON_CLIENT_MEM_FRACTION'] = '4.0'
+
+logger.info("- Composing targets file ... ")
+targets_file = outdir / "user_targets.tsv"
+targets = pd.DataFrame(
+    [
+        dict(
+            organism=args['organism'],
+            mhc_class=args['mhc_class'],
+            mhc=args['mhc'],
+            peptide=args['peptide'],
+            va=args['va'],
+            ja=args['ja'],
+            cdr3a=args['cdr3a'],
+            vb=args['vb'],
+            jb=args['jb'],
+            cdr3b=args['cdr3b'],
+        )
+    ]
+)
+targets.to_csv(targets_file, sep="\t", index=False)
+
+logger.info("- Generating inputs for AlphaFold modeling ... ")
+cmd = [
+    *python,
+    tcrdock + "/setup_for_alphafold.py",
+    "--targets_tsvfile", targets_file,
+    "--output_dir", outdir / "user_output",
+    "--new_docking",
+]
+run_command(cmd, fg=True)
+
+logger.info("- Running AlphaFold modeling ... ")
+cmd = [
+    *python,
+    tcrdock + "/run_prediction.py",
+    "--verbose",
+    "--targets", outdir / "user_output/targets.tsv",
+    "--outfile_prefix", f"{outdir}/{args['peptide']}",
+    "--model_names", model_name,
+    "--data_dir", data_dir,
+    "--model_params_files", model_file,
+]
+run_command(cmd, fg=True, env={"XLA_FLAGS": "--xla_gpu_force_compilation_parallelism=1"})
+
+logger.info("- Calculating the PAE ... ")
+cmd = [
+    *python,
+    tcrdock + "/add_pmhc_tcr_pae_to_tsvfile.py",
+    "--infile", f"{outdir}/{args['peptide']}_final.tsv",
+    "--outfile", f"{outdir}/{args['peptide']}_w_pae.tsv",
+]
+
+run_command(cmd, fg=True)

{biopipen-0.27.1 → biopipen-0.27.2}/biopipen/utils/misc.py

@@ -1,13 +1,14 @@
 from __future__ import annotations
 from pathlib import Path
 
+import os
 import sys
 import logging
 from typing import List
 from biopipen.core.filters import dict_to_cli_args  # noqa: F401
 
 logger = logging.getLogger("biopipen_job")
-logger.setLevel(logging.INFO)
+logger.setLevel(logging.DEBUG)
 _handler = logging.StreamHandler(sys.stdout)
 # Use same log format as in R
 # {sprintf("%-7s", level)} [{format(time, "%Y-%m-%d %H:%M:%S")}] {msg}
@@ -100,6 +101,9 @@ def run_command(
         kwargs["stderr"] = sys.stderr
         kwargs["universal_newlines"] = True
 
+    if "env" in kwargs:
+        kwargs["env"] = {**os.environ, **kwargs["env"]}
+
     try:
         p = Popen(cmd, **kwargs)
     except Exception as e:

{biopipen-0.27.1 → biopipen-0.27.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "biopipen"
-version = "0.27.1"
+version = "0.27.2"
 description = "Bioinformatics processes/pipelines that can be run from `pipen run`"
 authors = ["pwwang <pwwang@pwwang.com>"]
 license = "MIT"

{biopipen-0.27.1 → biopipen-0.27.2}/setup.py

@@ -15,6 +15,7 @@ packages = \
  'biopipen.scripts.scrna',
  'biopipen.scripts.snp',
  'biopipen.scripts.tcgamaf',
+ 'biopipen.scripts.tcr',
  'biopipen.scripts.tcr.GIANA',
  'biopipen.scripts.tcr.TESSA_source',
  'biopipen.scripts.vcf',
@@ -40,8 +41,7 @@ package_data = \
               'scripts/plot/*',
               'scripts/rnaseq/*',
               'scripts/scrna_metabolic_landscape/*',
-              'scripts/stats/*',
-              'scripts/tcr/*']}
+              'scripts/stats/*']}
 
 install_requires = \
 ['datar[pandas]>=0.15.6,<0.16.0',
@@ -81,7 +81,7 @@ entry_points = \
 
 setup_kwargs = {
     'name': 'biopipen',
-    'version': '0.27.1',
+    'version': '0.27.2',
     'description': 'Bioinformatics processes/pipelines that can be run from `pipen run`',
     'long_description': 'None',
     'author': 'pwwang',

biopipen-0.27.1/biopipen/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.27.1"

biopipen-0.27.1/biopipen/scripts/snp/PlinkSimulation.py

@@ -1,88 +0,0 @@
-from pathlib import Path
-from biopipen.utils.misc import logger, run_command, dict_to_cli_args
-
-nsnps = {{in.nsnps | repr}}  # pyright: ignore
-ncases = {{in.ncases | repr}}  # pyright: ignore
-nctrls = {{in.nctrls | repr}}  # pyright: ignore
-outdir = {{out.outdir | repr}}  # pyright: ignore
-gtmatfile = {{out.gtmat | repr}}  # pyright: ignore
-plink = {{envs.plink | repr}}  # pyright: ignore
-seed = {{envs.seed | repr}}  # pyright: ignore
-label = {{envs.label | repr}}  # pyright: ignore
-prevalence = {{envs.prevalence | repr}}  # pyright: ignore
-minfreq = {{envs.minfreq | repr}}  # pyright: ignore
-maxfreq = {{envs.maxfreq | repr}}  # pyright: ignore
-hetodds = {{envs.hetodds | repr}}  # pyright: ignore
-homodds = {{envs.homodds | repr}}  # pyright: ignore
-missing = {{envs.missing | repr}}  # pyright: ignore
-args = {{envs.args | repr}}  # pyright: ignore
-transpose_gtmat = {{envs.transpose_gtmat | repr}}  # pyright: ignore
-sample_prefix = {{envs.sample_prefix | repr}}  # pyright: ignore
-
-logger.info("Generating parameters file")
-params_file = Path(outdir) / "params.txt"
-params_file.write_text(
-    f"{nsnps}\t{label}\t{minfreq}\t{maxfreq}\t{hetodds}\t{homodds}\n"
-)
-
-if seed is not None:
-    args["seed"] = seed
-
-args["simulate"] = params_file
-args["out"] = Path(outdir) / "sim_snps"
-args["simulate-ncases"] = ncases
-args["simulate-ncontrols"] = nctrls
-args["simulate-prevalence"] = prevalence
-args["simulate-missing"] = missing
-
-cmd = [plink] + dict_to_cli_args(args)
-
-logger.info("Running PLINK simulation ...")
-run_command(cmd, fg=True)
-
-# Transpose the genotype matrix
-# CHR	SNP	(C)M	POS	COUNTED	ALT	per0_per0	per1_per1	per2_per2
-# 1	SNP_0	0	1	D	d	1	0	1
-# 1	SNP_1	0	2	d	D	0	1	0
-# 1	SNP_2	0	3	d	D	0	0	0
-# 1	SNP_3	0	4	d	D	0	0	0
-# 1	SNP_4	0	5	D	d	1	2	1
-cmd = [
-    plink,
-    "--recode",
-    "A" if transpose_gtmat else "A-transpose",
-    "tab",
-    "--bfile",
-    args["out"],
-    "--out",
-    gtmatfile + ".plink.recoded",
-]
-logger.info("Recoding into genotype matrix ...")
-run_command(cmd, fg=True)
-
-logger.info("Saving genotype matrix ...")
-## transpose_gtmat = False
-# SNP_COUNTED	per0_per0	per1_per1	per2_per2
-# SNP_0_D	1	0	1
-# SNP_1_d	0	1	0
-# SNP_2_d	0	0	0
-# SNP_3_d	0	0	0
-# SNP_4_D	1	2	1
-## transpose_gtmat = True
-# FID_IID SNP_0_D SNP_1_D SNP_2_D
-# per0_per0 0 1 1
-# per1_per1 0 2 0
-# per2_per2 0 0 0
-# per3_per3 1 1 0
-# per4_per4 0 0 0
-if transpose_gtmat:
-    cmd = f"cut -f1,2,7- {gtmatfile}.plink.recoded.raw | sed 's/\\t/_/'"
-else:
-    cmd = f"cut -f2,5,7- {gtmatfile}.plink.recoded.traw | sed 's/\\t/_/'"
-
-if sample_prefix:
-    cmd = f"{cmd} | sed 's/per[0-9]\\+_per/{sample_prefix}/g'"
-
-cmd = f"{cmd} > {gtmatfile}"
-
-run_command(cmd, fg=True)