biopipen 0.32.1__py3-none-any.whl → 0.33.0__py3-none-any.whl

biopipen/scripts/delim/SampleInfo.R

@@ -1,14 +1,11 @@
-{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
-{{ biopipen_dir | joinpaths: "utils", "mutate_helpers.R" | source_r }}
-
 library(rlang)
 library(dplyr)
-library(ggplot2)
-library(ggprism)
-library(ggrepel)
+library(biopipen.utils)
+library(plotthis)
 
 infile <- {{in.infile | r}}
 outfile <- {{out.outfile | r}}
+joboutdir <- {{job.outdir | r}}
 sep <- {{envs.sep | r}}
 mutaters <- {{envs.mutaters | r}}
 save_mutated <- {{envs.save_mutated | r}}
@@ -16,6 +13,9 @@ defaults <- {{envs.defaults | r}}
 stats <- {{envs.stats | r}}
 exclude_cols <- {{envs.exclude_cols | r}}
 
+log <- get_logger()
+reporter <- get_reporter()
+
 if (is.null(exclude_cols)) {
     exclude_cols <- c()
 } else {
@@ -29,6 +29,50 @@ if (colnames(indata)[1] == "row.names") {
     stop("Wrong number of column names. Do you have the right `sep`?")
 }
 
+#' Get plotthis function from plot_type
+#'
+#' @param plot_type The plot type
+#' @param gglogger_register Register the plotthis function to gglogger
+#' @param return_name Return the name of the function instead of the function
+#' @return The plotthis function
+#' @export
+get_plotthis_fn <- function(plot_type, gglogger_register = TRUE, return_name = FALSE) {
+    fn_name <- switch(plot_type,
+        hist = "Histogram",
+        histo = "Histogram",
+        histogram = "Histogram",
+        featuredim = "FeatureDimPlot",
+        splitbar = "SplitBarPlot",
+        enrichmap = "EnrichMap",
+        enrichnet = "EnrichNetwork",
+        enrichnetwork = "EnrichNetwork",
+        gsea = "GSEAPlot",
+        gseasummary = "GSEASummaryPlot",
+        gseasum = "GSEASummaryPlot",
+        heatmap = "Heatmap",
+        network = "Network",
+        pie = "PieChart",
+        wordcloud = "WordCloudPlot",
+        venn = "VennDiagram",
+        paste0(tools::toTitleCase(plot_type), "Plot")
+    )
+    if (return_name) {
+        return(fn_name)
+    }
+    fn <- tryCatch({
+        utils::getFromNamespace(fn_name, "plotthis")
+    }, error = function(e) {
+        stop("Unknown plot type: ", plot_type)
+    })
+
+    if (gglogger_register) {
+        gglogger::register(fn, fn_name)
+    } else {
+        fn
+    }
+}
+
+log$info("Applying mutaters to the data if any ...")
 if (!is.null(mutaters) && length(mutaters) > 0) {
     mutdata <- indata %>%
         mutate(!!!lapply(mutaters, parse_expr))
@@ -44,7 +88,9 @@ write.table(
     col.names = TRUE,
     quote = FALSE
 )
-add_report(
+
+
+reporter$add(
     list(
         kind = "descr",
         content = "The samples used in the analysis. Each row is a sample, and columns are the meta information about the sample. This is literally the input sample information file, but the paths to the scRNA-seq and scTCR-seq data are hidden.",
@@ -59,144 +105,44 @@ add_report(
     h1 = "Sample Information"
 )
 
-theme_set(theme_prism())
-for (name in names(stats)) {
-    stat <- list_update(defaults, stats[[name]])
-    plotfile <- file.path(outdir, paste0(name, ".png"))
-
-    is_continuous <- FALSE
-    if (!is.null(stat$subset)) {
-        data <- mutdata %>% filter(!!parse_expr(stat$subset))
-    } else {
-        data <- mutdata
-    }
-    if (!is.null(stat$group) && !stat$na_group) {
-        data <- data %>% filter(!is.na(!!sym(stat$group)))
-    }
-    if (!is.null(stat$each) && !stat$na_each) {
-        data <- data %>% filter(!is.na(!!sym(stat$each)))
-    }
+if (length(stats) > 0) {
+    cases <- expand_cases(stats, defaults)
+    for (name in names(cases)) {
+        log$info("- Statistic: {name}")
 
-    if (is.numeric(data[[stat$on]])) {
-        is_continuous <- TRUE
-    }
+        case <- cases[[name]]
+        info <- case_info(name, outdir, is_dir = FALSE, create = TRUE)
+        case <- extract_vars(case, "plot_type", "more_formats", "save_code", "section", "subset", "devpars", "descr")
 
-    if (is.null(stat$plot)) {
-        stat$plot <- if (is_continuous) "boxplot" else "pie"
-    }
+        plot_fn <- get_plotthis_fn(plot_type)
+        more_formats <- unique(c("png", more_formats))
 
-    data$..group <- "All"
-    group <- if (is.null(stat$group)) sym("..group") else sym(stat$group)
-    count_on <- paste0("..count.", stat$on)
-    if (!is_continuous) {
-        if (!is.null(stat$each)) {
-            data <- data %>% add_count(!!group, !!sym(stat$each), name = count_on)
+        if (!is.null(subset)) {
+            case$data <- mutdata %>% dplyr::filter(!!parse_expr(subset))
         } else {
-            data <- data %>% add_count(!!group, name = count_on)
+            case$data <- mutdata
         }
-    }
-
-    if (is.null(stat$devpars)) {
-        stat$devpars <- list()
-    }
-    if (is.null(stat$devpars$width)) {
-        stat$devpars$width <- 800
-    }
-    if (is.null(stat$devpars$height)) {
-        stat$devpars$height <- 600
-    }
-    if (is.null(stat$devpars$res)) {
-        stat$devpars$res <- 100
-    }
 
-    png(
-        plotfile,
-        width = stat$devpars$width,
-        height = stat$devpars$height,
-        res = stat$devpars$res
-    )
-    if (stat$plot == "boxplot" || stat$plot == "box") {
-        p <- ggplot(data, aes(x=!!group, y=!!sym(stat$on), fill=!!group)) +
-            geom_boxplot(position = "dodge") +
-            scale_fill_biopipen(alpha = .6) +
-            xlab("")
-    } else if (stat$plot == "violin" ||
-               stat$plot == "violinplot" ||
-               stat$plot == "vlnplot") {
-        p <- ggplot(data, aes(x = !!group, y = !!sym(stat$on), fill=!!group)) +
-            geom_violin(position = "dodge") +
-            scale_fill_biopipen(alpha = .6) +
-            xlab("")
-    } else if (
-        (grepl("violin", stat$plot) || grepl("vln", stat$plot)) &&
-        grepl("box", stat$plot)
-    ) {
-        p <- ggplot(data, aes(x = !!group, y = !!sym(stat$on), fill = !!group)) +
-            geom_violin(position = "dodge") +
-            geom_boxplot(width = 0.1, position = position_dodge(0.9), fill="white") +
-            scale_fill_biopipen(alpha = .6) +
-            xlab("")
-    } else if (stat$plot == "histogram" || stat$plot == "hist") {
-        p <- ggplot(data, aes(x = !!sym(stat$on), fill = !!group)) +
-            geom_histogram(bins = 10, position = "dodge", alpha = 0.8, color = "white") +
-            scale_fill_biopipen(alpha = .6)
-    } else if (stat$plot == "pie" || stat$plot == "piechart") {
-        if (is.null(stat$each)) {
-            data <- data %>% distinct(!!group, .keep_all = TRUE)
-        } else {
-            data <- data %>%
-                distinct(!!group, !!sym(stat$each), .keep_all = TRUE) %>%
-                mutate(!!group := factor(!!group, levels = unique(!!group))) %>%
-                group_by(!!sym(stat$each))
+        p <- do_call(gglogger::register(plot_fn, name = plot_type), case)
+        save_plot(p, info$prefix, devpars, formats = more_formats)
+        if (save_code) {
+            save_plotcode(
+                p,
+                setup = c('library(plotthis)', '', 'load("data.RData")', 'list2env(case, envir = .GlobalEnv)'),
+                prefix = info$caseprefix,
+                "case",
+                auto_data_setup = FALSE
+            )
         }
-        p <- ggplot(
-            data %>% mutate(.size = sum(!!sym(count_on))),
-            aes(x = sqrt(.size) / 2, width = sqrt(.size), y = !!sym(count_on), fill = !!group, label = !!sym(count_on))
-        ) +
-            geom_bar(stat="identity", color="white", position = position_fill(reverse = TRUE)) +
-            coord_polar("y", start = 0) +
-            theme_void() +
-            theme(plot.title = element_text(hjust = 0.5)) +
-            geom_label_repel(
-                position = position_fill(reverse = TRUE,vjust = .5),
-                color="#333333",
-                fill="#EEEEEE",
-                size=4
-            ) +
-            scale_fill_biopipen(alpha = .6, name = group) +
-            ggtitle(paste0("# ", stat$on))
-    } else if (stat$plot == "bar" || stat$plot == "barplot") {
-        if (is.null(stat$each)) {
-            data <- data %>% distinct(!!group, .keep_all = TRUE)
-        } else {
-            data <- data %>% distinct(!!group, !!sym(stat$each), .keep_all = TRUE)
-        }
-        p <- ggplot(
-            data,
-            aes(x = !!group, y = !!sym(count_on), fill = !!group)) +
-            geom_bar(stat = "identity") +
-            scale_fill_biopipen(alpha = .6) +
-            ylab(paste0("# ", stat$on))
-    } else {
-        stop("Unknown plot type: ", stat$plot)
-    }
-    if (!is.null(stat$each)) {
-        p <- p + facet_wrap(vars(!!sym(stat$each)), ncol = stat$ncol)
+
+        reporter$add(
+            reporter$image(
+                info$prefix,
+                c("png", more_formats),
+                save_code,
+                kind = "table_image"
+            ),
+            h1 = "Statistics", ui = "table_of_images:2"
+        )
     }
-    print(p)
-    dev.off()
-
-    by_desc <- ifelse(is.null(stat$by), "", paste0(" by ", stat$by))
-    descr <- ifelse(
-        is_continuous,
-        paste0("The distribution of ", stat$on, by_desc),
-        paste0("The number of ", stat$on, by_desc)
-    )
-    add_report(
-        list(kind = "table_image", src = plotfile, name = name, descr = descr),
-        h1 = "Statistics",
-        ui = "table_of_images:2"
-    )
 }
-
-save_report(outdir)

biopipen/scripts/misc/Config2File.py

@@ -1,8 +1,8 @@
 import json
 import rtoml
 
-configstr = {{in.config | repr}}  # pyright: ignore
-outfile = {{out.outfile | quote}}  # pyright: ignore
+configstr: str = {{in.config | quote}}  # pyright: ignore  # noqa
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
 infmt = {{envs.infmt | quote}}  # pyright: ignore
 outfmt = {{envs.outfmt | quote}}  # pyright: ignore
 

biopipen/scripts/misc/Str2File.py

@@ -1,6 +1,6 @@
-instr = {{in.str | repr}}  # pyright: ignore
+instr: str = {{in.str | quote}}  # pyright: ignore  # noqa
 name = {{repr(in.name or envs.name)}}  # pyright: ignore
-outfile = {{out.outfile | quote}}  # pyright: ignore
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
 
 with open(outfile, "wt") as fout:
     fout.write(instr)

biopipen/scripts/protein/MMCIF2PDB.py

@@ -0,0 +1,33 @@
+from pathlib import Path
+from shutil import which
+from diot import Diot  # noqa: F401
+from biopipen.utils.misc import run_command, dict_to_cli_args
+
+infile: str = {{in.infile | quote}}  # pyright: ignore # noqa
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
+envs: dict = {{envs | repr}}  # pyright: ignore
+tool: str = envs.pop("tool", "maxit")
+maxit: str = envs.pop("maxit", "maxit")
+beem = envs.pop("beem", "BeEM")
+
+if tool == "maxit":
+    maxit_found = which(maxit)
+    if not maxit_found:
+        raise ValueError(f"maxit executable not found: {maxit}")
+
+    maxit_exe = Path(maxit_found).expanduser().resolve()
+    rcsbroot = maxit_exe.parent.parent
+    envs["input"] = infile
+    envs["output"] = outfile
+    envs["o"] = 2
+    envs["log"] = Path(outfile).with_suffix(".log")
+    run_command([maxit, *dict_to_cli_args(envs, prefix="-")], fg=True, env={"RCSBROOT": rcsbroot})
+
+else:
+    outfile: Path = Path(outfile)  # type: ignore
+    envs["_"] = infile
+    envs["p"] = outfile.parent.joinpath(outfile.stem)
+    envs["outfmt"] = 3
+    args = dict_to_cli_args(envs, prefix="-", sep="=")
+
+    run_command([beem, *args], fg=True)

biopipen/scripts/protein/PDB2Fasta.py

@@ -0,0 +1,60 @@
+# """
+# LICENSE
+
+# GNU General Public License v2.0
+
+# The code is based on the script from:
+# https://github.com/kad-ecoli/pdb2fasta/blob/master/pdb2fasta.py
+
+# The original code is licensed under GNU General Public License v2.0.
+# The original code is modified by biopipen developers to fit the biopipen.
+# """
+from __future__ import annotations
+import re
+from collections import defaultdict
+from pathlib import Path
+
+infile: str = {{in.infile | quote}}  # pyright: ignore # noqa: E999
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
+chains: str | list | None = {{envs.chains | repr}}  # pyright: ignore
+wrap: int = {{envs.wrap | repr}}  # pyright: ignore
+
+if isinstance(chains, str):
+    chains = [chain.strip() for chain in chains.split(",")]
+
+aa3to1 = {
+   'ALA':'A', 'VAL':'V', 'PHE':'F', 'PRO':'P', 'MET':'M',
+   'ILE':'I', 'LEU':'L', 'ASP':'D', 'GLU':'E', 'LYS':'K',
+   'ARG':'R', 'SER':'S', 'THR':'T', 'TYR':'Y', 'HIS':'H',
+   'CYS':'C', 'ASN':'N', 'GLN':'Q', 'TRP':'W', 'GLY':'G',
+   'MSE':'M',
+}
+
+ca_pattern = re.compile(
+    r"^ATOM\s{2,6}\d{1,5}\s{2}CA\s[\sA]([A-Z]{3})\s([\s\w])|^HETATM\s{0,4}\d{1,5}\s{2}CA\s[\sA](MSE)\s([\s\w])"  # noqa: W605
+)
+
+filename = Path(infile).stem
+chain_dict = defaultdict(str)
+
+with open(infile, 'r') as fp:
+    for line in fp:
+        if line.startswith("ENDMDL"):
+            break
+
+        match_list = ca_pattern.findall(line)
+        if match_list:
+            resn = match_list[0][0] + match_list[0][2]
+            chain = match_list[0][1] + match_list[0][3]
+            if chains is None or chain in chains:
+                chain_dict[chain] += aa3to1[resn]
+
+with open(outfile, 'w') as fp:
+    for chain in chain_dict:
+        fp.write(f">{filename}:{chain}\n")
+        sequence = chain_dict[chain]
+        if wrap > 0:
+            for i in range(0, len(sequence), 80):
+                fp.write(sequence[i:i+80] + "\n")
+        else:
+            fp.write(sequence + "\n")

biopipen/scripts/protein/Prodigy.py

@@ -2,15 +2,15 @@ import json
 import logging
 import sys
 from pathlib import Path
-from prodigy_prot.predict_IC import (
+from prodigy_prot.predict_IC import (  # type: ignore
     Prodigy,
     check_path,
     parse_structure,
 )
 
-infile = {{in.infile | repr}}  # pyright: ignore # noqa
-outfile = {{out.outfile | repr}}  # pyright: ignore
-outdir = {{out.outdir | repr}}  # pyright: ignore
+infile: str = {{in.infile | quote}}  # pyright: ignore # noqa
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
 distance_cutoff = {{envs.distance_cutoff | float}}  # pyright: ignore
 acc_threshold = {{envs.acc_threshold | float}}  # pyright: ignore
 temperature = {{envs.temperature | float}}  # pyright: ignore

biopipen/scripts/protein/RMSD.py

@@ -0,0 +1,178 @@
+from pathlib import Path
+from shutil import which
+from diot import Diot  # noqa: F401
+from biopipen.utils.misc import run_command, dict_to_cli_args
+
+infile1: str = {{in.infile1 | quote}}  # pyright: ignore # noqa
+infile2: str = {{in.infile2 | quote}}  # pyright: ignore # noqa
+outfile: str = {{out.outfile | quote}}  # pyright: ignore # noqa
+outdir: str = {{job.outdir | quote}}  # pyright: ignore # noqa
+envs: dict = {{envs | repr}}  # pyright: ignore # noqa
+conv_tool = envs.pop("conv_tool", "maxit")
+maxit = envs.pop("maxit", "maxit")
+beem = envs.pop("beem", "BeEM")
+ca_only = envs.pop("ca_only", False)
+# aa20_only = envs.pop("aa20_only", False)
+duel = envs.pop("duel", "keep")
+calculate_rmsd = envs.pop("calculate_rmsd", "calculate_rmsd")
+
+
+def cif_to_pdb(cif_file, pdb_file:Path):
+    if conv_tool == "maxit":
+        maxit_bin = Path(which(maxit)).resolve()
+        rcsbroot = Path(maxit_bin).parent.parent
+        args = {"input": cif_file, "output": pdb_file, "o": 2, "log": pdb_file.with_suffix(".log")}
+        run_command([maxit, *dict_to_cli_args(args, prefix="-")], fg=True, env={"RCSBROOT": rcsbroot})
+    else:
+        args = {"_": cif_file, "p": pdb_file.parent.joinpath(pdb_file.stem)}
+        args = dict_to_cli_args(args, prefix="-", sep="=")
+        run_command([beem, *args], fg=True)
+
+
+def pdb_to_ca_pdb(pdb_file: Path, ca_pdb_file: Path):
+    """Extract C-alpha atoms from a PDB file and still keep the original order and metadata."""
+    with open(pdb_file, "r") as f, open(ca_pdb_file, "w") as fw:
+        for line in f:
+            if line.startswith("ATOM") and line[12:16].strip() == "CA":
+                fw.write(line)
+
+
+# def pdb_to_aa20_pdb(pdb_file: Path, aa20_pdb_file: Path):
+#     """Extract the 20 amino acids from a PDB file and still keep the original order and metadata."""
+#     with open(pdb_file, "r") as f, open(aa20_pdb_file, "w") as fw:
+#         for line in f:
+#             if line.startswith("ATOM") and line[17:20].strip() in (
+#                 "ALA", "ARG", "ASN", "ASP", "CYS", "GLN", "GLU", "GLY",
+#                 "HIS", "ILE", "LEU", "LYS", "MET", "PHE", "PRO", "SER",
+#                 "THR", "TRP", "TYR", "VAL",
+#             ):
+#                 fw.write(line)
+
+
+def deduel_pdb(pdb_file: Path, deduel_pdb_file: Path):
+    """Remove/Handle the duel atoms in a PDB file."""
+    def is_duel(atom1, atom2):
+        #           1         2
+        # 01234567890123456789012345
+        # ATOM    913  CA ATYR A 113
+        # ATOM    914  CA BTYR A 113
+        # The key should be "ATOM|CA |TYR| A| 113"
+        return (
+            atom1[:4] == atom2[:4] and
+            atom1[12:16] == atom2[12:16] and
+            atom1[17:20] == atom2[17:20] and
+            atom1[21] == atom2[21] and
+            atom1[22:26] == atom2[22:26] and
+            atom1[16] != atom2[16]
+        )
+
+    def clean_atom(atom):
+        return atom[:16] + " " + atom[17:]
+
+    last_atom = ""
+    with open(pdb_file, "r") as f, open(deduel_pdb_file, "w") as fw:
+        for line in f:
+            if not line.startswith("ATOM"):
+                fw.write(line)
+                continue
+            if not is_duel(last_atom, line):
+                if last_atom:
+                    fw.write(clean_atom(last_atom))
+                last_atom = line
+            # is duel
+            elif duel == "keep":
+                fw.write(clean_atom(last_atom))
+                fw.write(clean_atom(line))
+                last_atom = ""
+            elif duel == "keep_first":
+                fw.write(clean_atom(last_atom))
+                last_atom = ""
+            elif duel == "keep_last":
+                fw.write(clean_atom(line))
+                last_atom = ""
+            elif duel == "average":
+                # Average the coordinates
+                x1 = float(last_atom[30:38])
+                y1 = float(last_atom[38:46])
+                z1 = float(last_atom[46:54])
+                x2 = float(line[30:38])
+                y2 = float(line[38:46])
+                z2 = float(line[46:54])
+                x = (x1 + x2) / 2.0
+                y = (y1 + y2) / 2.0
+                z = (z1 + z2) / 2.0
+                fw.write(clean_atom(last_atom[:30] + f"{x:8.3f}{y:8.3f}{z:8.3f}" + last_atom[54:]))
+                last_atom = ""
+
+        if last_atom:
+            fw.write(last_atom)
+
+
+def index_of(lst, item) -> int:
+    try:
+        return lst.index(item)
+    except ValueError:
+        return -1
+
+
+if infile1.endswith(".cif"):
+    pdb1 = Path(outdir) / f"{Path(infile1).stem}.pdb"
+    cif_to_pdb(infile1, pdb1)
+    infile1 = pdb1  # type: ignore
+
+if infile2.endswith(".cif"):
+    pdb2 = Path(outdir) / f"{Path(infile2).stem}.pdb"
+    cif_to_pdb(infile2, pdb2)
+    infile2 = pdb2  # type: ignore
+
+if ca_only:
+    ca_pdb1 = Path(outdir) / f"{Path(infile1).stem}.ca.pdb"
+    pdb_to_ca_pdb(infile1, ca_pdb1) # type: ignore
+    infile1 = ca_pdb1  # type: ignore
+
+    ca_pdb2 = Path(outdir) / f"{Path(infile2).stem}.ca.pdb"
+    pdb_to_ca_pdb(infile2, ca_pdb2) # type: ignore
+    infile2 = ca_pdb2  # type: ignore
+
+# if aa20_only:
+#     aa20_pdb1 = Path(outdir) / f"{Path(infile1).stem}.aa20.pdb"
+#     pdb_to_aa20_pdb(infile1, aa20_pdb1) # type: ignore
+#     infile1 = aa20_pdb1  # type: ignore
+
+#     aa20_pdb2 = Path(outdir) / f"{Path(infile2).stem}.aa20.pdb"
+#     pdb_to_aa20_pdb(infile2, aa20_pdb2) # type: ignore
+#     infile2 = aa20_pdb2  # type: ignore
+
+if duel != "keep":
+    deduel_pdb1 = Path(outdir) / f"{Path(infile1).stem}.deduel.pdb"
+    deduel_pdb(infile1, deduel_pdb1) # type: ignore
+    infile1 = deduel_pdb1  # type: ignore
+
+    deduel_pdb2 = Path(outdir) / f"{Path(infile2).stem}.deduel.pdb"
+    deduel_pdb(infile2, deduel_pdb2) # type: ignore
+    infile2 = deduel_pdb2  # type: ignore
+
+envs["_"] = [infile1, infile2]
+envs = dict_to_cli_args(envs, dashify=True)
+
+idx_ur = index_of(envs, "--ur")
+if idx_ur != -1:
+    envs[idx_ur] = "-ur"
+
+idx_urks = index_of(envs, "--urks")
+if idx_urks != -1:
+    envs[idx_urks] = "-urks"
+
+idx_nh = index_of(envs, "--nh")
+if idx_nh != -1:
+    envs[idx_nh] = "-nh"
+
+out: str = run_command([calculate_rmsd, *envs], stdout="return")  # type: ignore
+out = out.strip()
+
+try:
+    float(out)
+except (ValueError, TypeError):
+    raise ValueError(out)
+
+Path(outfile).write_text(out)

biopipen/scripts/regulatory/MotifScan.py

@@ -5,20 +5,20 @@ import re
 from pathlib import PosixPath  # noqa: F401
 from biopipen.utils.misc import run_command, dict_to_cli_args, logger
 
-motiffile = {{in.motiffile | repr}}  # pyright: ignore # noqa: #999
-seqfile = {{in.seqfile | repr}}  # pyright: ignore
-outdir = {{out.outdir | repr}}  # pyright: ignore
+motiffile: str = {{in.motiffile | quote}}  # pyright: ignore # noqa: #999
+seqfile: str = {{in.seqfile | quote}}  # pyright: ignore
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
 
 tool = {{envs.tool | repr}}  # pyright: ignore
 fimo = {{envs.fimo | repr}}  # pyright: ignore
-motif_col = {{envs.motif_col | repr}}  # pyright: ignore
-regulator_col = {{envs.regulator_col | repr}}  # pyright: ignore
+motif_col: str | int = {{envs.motif_col | repr}}  # pyright: ignore
+regulator_col: str | int = {{envs.regulator_col | repr}}  # pyright: ignore
 notfound = {{envs.notfound | repr}}  # pyright: ignore
-motifdb = {{envs.motifdb | repr}}  # pyright: ignore
+motifdb: str | None = {{envs.motifdb | repr}}  # pyright: ignore
 cutoff = {{envs.cutoff | repr}}  # pyright: ignore
 q = {{envs.q | repr}}  # pyright: ignore
 q_cutoff = {{envs.q_cutoff | repr}}  # pyright: ignore
-args = {{envs.args | dict | repr}}  # pyright: ignore
+args: dict = {{envs.args | dict | repr}}  # pyright: ignore
 
 # Check if the tool is supported
 if tool != "fimo":
@@ -41,7 +41,7 @@ if isinstance(motif_col, str) or isinstance(regulator_col, str):
     with open(motiffile, "r") as f:
         header = f.readline().strip().split("\t")
         if isinstance(motif_col, str):
-            motif_col = header.index(motif_col) + 1
+            motif_col: int = header.index(motif_col) + 1
         if isinstance(regulator_col, str):
             regulator_col = header.index(regulator_col) + 1
 if isinstance(motif_col, int):