biopipen 0.21.0__py3-none-any.whl → 0.34.26__py3-none-any.whl

biopipen/scripts/scrna_metabolic_landscape/MetabolicFeaturesIntraSubset.R

@@ -1,150 +0,0 @@
-source("{{biopipen_dir}}/utils/misc.R")
-source("{{biopipen_dir}}/utils/gsea.R")
-
-library(parallel)
-library(scater)
-library(Seurat)
-
-sobjfile <- {{ in.sobjfile | r }}
-outdir <- {{ out.outdir | r }}
-gmtfile <- {{ envs.gmtfile | r }}
-ncores <- {{ envs.ncores | r }}
-fgsea <- {{ envs.fgsea | r }}
-top <- {{ envs.top | r }}
-prerank_method <- {{ envs.prerank_method | r }}
-grouping <- {{ envs.grouping | r }}
-grouping_prefix <- {{ envs.grouping_prefix | r }}
-subsetting_cols <- {{ envs.subsetting | r }}
-subsetting_prefix <- {{ envs.subsetting_prefix | r }}
-subsetting_comparison <- {{ envs.subsetting_comparison | r }}
-
-if (!is.null(grouping_prefix) && nchar(grouping_prefix) > 0) {
-    grouping_prefix = paste0(grouping_prefix, "_")
-}
-
-if (!is.null(subsetting_prefix) && nchar(subsetting_prefix) > 0) {
-    subsetting_prefix = paste0(subsetting_prefix, "_")
-}
-
-set.seed(8525)
-
-## gmt_pathways is copied from fgsea package.
-gmt_pathways <- function(gmt_file) {
-    pathway_lines <- strsplit(readLines(gmt_file), "\t")
-    pathways <- lapply(pathway_lines, tail, -2)
-    names(pathways) <- sapply(pathway_lines, head, 1)
-    pathways
-}
-
-pathways <- gmt_pathways(gmtfile)
-metabolics <- unique(as.vector(unname(unlist(pathways))))
-sobj <- readRDS(sobjfile)
-
-do_one_comparison <- function(
-    obj,
-    compname,
-    case,
-    control,
-    groupdir,
-    subset_col,
-    subset_prefix
-) {
-    print(paste("  Design:", compname, "(", case, ",", control, ")"))
-    case_code = paste0("subset(obj, subset = ", subset_col, " == '", case, "')")
-    case_obj = tryCatch({
-        eval(parse(text = case_code))
-    }, error = function(e) {
-        NULL
-    })
-    if (is.null(case_obj)) {
-        print("          Skip (not enough cells in case)")
-        return (NULL)
-    }
-    control_code = paste0("subset(obj, subset = ", subset_col, " == '", control, "')")
-    control_obj = tryCatch({
-        eval(parse(text = control_code))
-    }, error = function(e) {
-        NULL
-    })
-    if (is.null(control_obj)) {
-        print("          Skip (not enough cells in control)")
-        return (NULL)
-    }
-    exprs_case = GetAssayData(case_obj)
-    exprs_control = GetAssayData(control_obj)
-
-    odir = file.path(groupdir, paste0(subset_prefix, compname))
-    dir.create(odir, showWarnings = FALSE)
-    if (ncol(exprs_case) < 3 || ncol(exprs_control) < 3) {
-        print("          Skip (not enough cells)")
-        return (NULL)
-    }
-    if (fgsea) {
-        ranks = prerank(
-            cbind(exprs_case, exprs_control),
-            case,
-            control,
-            c(rep(case, ncol(exprs_case)), rep(control, ncol(exprs_control))),
-            method = prerank_method
-        )
-
-        runFGSEA(
-            ranks,
-            gmtfile,
-            top = top,
-            outdir = odir,
-            envs = list(nproc = 1)
-        )
-    } else {
-        runGSEA(
-            cbind(exprs_case, exprs_control),
-            c(rep(case, ncol(exprs_case)), rep(control, ncol(exprs_control))),
-            gmtfile,
-            odir
-        )
-    }
-}
-
-do_one_group <- function(group) {
-    print(paste("- Group:", group, "..."))
-
-    genes = intersect(metabolics, rownames(sobj))
-    group_code = paste0(
-        "subset(sobj, subset = ", grouping, " == '", group, "', features = genes)"
-    )
-    obj = eval(parse(text = group_code))
-    groupname = paste0(grouping_prefix, group)
-    groupdir = file.path(outdir, groupname)
-    dir.create(groupdir, showWarnings = FALSE)
-
-    for (i in seq_along(subsetting_comparison)) {
-        sci = subsetting_comparison[[i]]
-        if (is.null(sci) || length(sci) == 0) {
-            next
-        }
-        sapply(
-            names(sci),
-            function(compname) {
-                do_one_comparison(
-                    obj,
-                    compname,
-                    sci[[compname]][1],
-                    sci[[compname]][2],
-                    groupdir,
-                    subsetting_cols[i],
-                    subsetting_prefix[i]
-                )
-            }
-        )
-    }
-}
-
-groups = as.character(unique(sobj@meta.data[[grouping]]))
-if (ncores == 1) {
-    lapply(groups, do_one_group)
-} else {
-    x = mclapply(groups, do_one_group, mc.cores = ncores)
-    if (any(unlist(lapply(x, class)) == "try-error")) {
-        stop("mclapply error")
-    }
-}

biopipen/scripts/tcr/TCRClustering.R

@@ -1,280 +0,0 @@
-
-# # https://stackoverflow.com/questions/50145643/unable-to-change-python-path-in-reticulate
-# python = Sys.which({{envs.python | r}})
-# Sys.setenv(RETICULATE_PYTHON = python)
-# library(reticulate)
-
-library(immunarch)
-library(dplyr)
-library(tidyr)
-library(tibble)
-
-immfile = {{in.immfile | r}}
-outdir = normalizePath({{job.outdir | r}})
-outfile = {{out.immfile | r}}
-clusterfile = {{out.clusterfile | r}}
-tool = {{envs.tool | r}}
-python = {{envs.python | r}}
-on_multi = {{envs.on_multi | r}}
-args = {{envs.args | r}}
-
-setwd(outdir)
-
-immdata = readRDS(immfile)
-if (on_multi) {
-    seqdata = immdata$multi
-} else {
-    seqdata = immdata$data
-}
-
-get_cdr3aa_df = function() {
-    out = NULL
-    for (sample in names(immdata$data)) {
-        tmpdf = immdata$data[[sample]] %>%
-            select(Barcode, CDR3.aa) %>%
-            separate_rows(Barcode, sep = ";") %>%
-            mutate(Barcode = paste0(sample, "_", Barcode))
-        out = bind_rows(out, tmpdf)
-    }
-    out
-}
-cdr3aa_df = get_cdr3aa_df()
-
-prepare_clustcr = function(clustcr_dir) {
-    clustering_args = ""
-    for (name in names(args)) {
-        value = args[[name]]
-        if (is.logical(value)) {
-            value = tools::toTitleCase(as.character(value))
-        } else if (is.character(value)) {
-            value = paste0("'", value, "'")
-        }
-        clustering_args = paste(name, "=", value)
-    }
-    clustcr_source = '
-import sys
-import pandas as pd
-import clustcr
-
-clustcr_dir, clustcr_infile = sys.argv[1:3]
-cdr3df = pd.read_csv(clustcr_infile, index_col=None)
-cdr3 = cdr3df.iloc[:, 0]
-
-clustering = clustcr.Clustering(%s)
-output = clustering.fit(cdr3)
-output.clusters_df.to_csv(clustcr_dir + "/clusters.txt", sep="\\t", index=False)
-'
-    clustcr_file = file.path(clustcr_dir, "_clustcr.py")
-    cat(sprintf(clustcr_source, clustering_args), file=clustcr_file)
-    clustcr_file
-}
-
-clean_clustcr_output = function(clustcr_outfile, clustcr_input) {
-    clustcr_out = read.delim2(clustcr_outfile, header=TRUE, row.names = NULL)
-    colnames(clustcr_out) = c("CDR3.aa", "TCR_Cluster")
-    in_cdr3 = read.delim2(clustcr_input, header=TRUE, row.names = NULL)
-    out = left_join(in_cdr3, distinct(clustcr_out), by=c("CDR3.aa")) %>%
-        mutate(
-            TCR_Cluster = if_else(
-                is.na(TCR_Cluster),
-                paste0("S_", row_number()),
-                paste0("M_", as.character(TCR_Cluster))
-            )
-        )
-    out = left_join(
-        cdr3aa_df,
-        out,
-        by = "CDR3.aa"
-    )
-    df = out %>%
-        select(Barcode, TCR_Cluster) %>%
-        add_count(TCR_Cluster, name="TCR_Cluster_Size") %>%
-        distinct(Barcode, .keep_all = TRUE) %>%
-        add_count(TCR_Cluster, name="TCR_Cluster_Size1") %>%
-        column_to_rownames("Barcode")
-
-    write.table(df, clusterfile, row.names=T, col.names=T, quote=F, sep="\t")
-    out
-}
-
-run_clustcr = function() {
-    print(paste("Using tool:", "ClusTCR"))
-    clustcr_dir = file.path(outdir, "ClusTCR_Output")
-    dir.create(clustcr_dir, showWarnings = FALSE)
-    clustcr_file = prepare_clustcr(clustcr_dir)
-    clustcr_input = prepare_input()
-    clustcr_cmd = paste(
-        python,
-        clustcr_file,
-        clustcr_dir,
-        clustcr_input
-    )
-    print("Running:")
-    print(clustcr_cmd)
-    rc = system(clustcr_cmd)
-    if (rc != 0) {
-        quit(status=rc)
-    }
-    clustcr_outfile = file.path(clustcr_dir, "clusters.txt")
-    clean_clustcr_output(clustcr_outfile, clustcr_input)
-}
-
-prepare_giana = function() {
-    giana_srcdir = "{{biopipen_dir}}/scripts/tcr/GIANA"
-
-    # # The source code of GIANA is downloaded now to giana_srcdir
-    # giana_file = file.path(giana_srcdir, "GIANA.py")
-    # giana4_file = file.path(giana_srcdir, "GIANA4.py")
-    # giana_query = file.path(giana_srcdir, "query.py")
-    # giana_trbv = file.path(giana_srcdir, "Imgt_Human_TRBV.fasta")
-    # if (!file.exists(giana_file)) {
-    #     download.file(paste(giana_repo, "GIANA4.1.py", sep="/"), giana_file)
-    #     download.file(paste(giana_repo, "GIANA4.py", sep="/"), giana4_file)
-    #     download.file(paste(giana_repo, "query.py", sep="/"), giana_query)
-    #     download.file(paste(giana_repo, "Imgt_Human_TRBV.fasta", sep="/"), giana_trbv)
-    # }
-
-    giana_srcdir
-}
-
-prepare_input = function() {
-    # prepare input file for GIANA
-    cdr3 = c()
-    # cdr3col = if (!on_multi) "cdr3" else "CDR3.aa"
-    cdr3col = "CDR3.aa"
-    for (sample in names(seqdata)) {
-        # cdr3 = bind_rows(cdr3, seqdata[[sample]] %>%
-        #     transmute(aminoAcid=CDR3.aa, vMaxResolved=paste0(V.name, "*01"), Sample=sample))
-        cdr3 = union(
-            cdr3,
-            seqdata[[sample]] %>% pull(cdr3col) %>% unique()
-        )
-    }
-    cdr3 = unique(cdr3)
-
-    # cdr3 = distinct(cdr3, aminoAcid, vMaxResolved)
-
-    cdr3file = file.path(outdir, "cdr3.csv")
-    write.table(
-        data.frame(CDR3.aa=cdr3),
-        cdr3file,
-        row.names=FALSE, col.names=TRUE, quote=FALSE
-    )
-    cdr3file
-}
-
-clean_giana_output = function(giana_outfile, giana_infile) {
-    # generate an output file with columns:
-    # CDR3.aa, TCR_Cluster, V.name, Sample
-    # If sequence doesn't exist in the input file,
-    # Then a unique cluster id is assigned to it.
-    giana_out = read.delim2(giana_outfile, header=FALSE, comment.char = "#", row.names = NULL)[, 1:2, drop=FALSE]
-    colnames(giana_out) = c("CDR3.aa", "TCR_Cluster")
-    in_cdr3 = read.delim2(giana_infile, header=TRUE, row.names = NULL)
-    out = left_join(in_cdr3, distinct(giana_out), by=c("CDR3.aa")) %>%
-        mutate(
-            TCR_Cluster = if_else(
-                is.na(TCR_Cluster),
-                paste0("S_", row_number()),
-                paste0("M_", as.character(TCR_Cluster))
-            )
-        )
-
-    out = left_join(
-        cdr3aa_df,
-        out,
-        by = "CDR3.aa"
-    )
-    df = out %>%
-        select(Barcode, TCR_Cluster) %>%
-        add_count(TCR_Cluster, name="TCR_Cluster_Size") %>%
-        distinct(Barcode, .keep_all = TRUE) %>%
-        add_count(TCR_Cluster, name="TCR_Cluster_Size1") %>%
-        column_to_rownames("Barcode")
-
-    write.table(df, clusterfile, row.names=T, col.names=T, quote=F, sep="\t")
-    out
-}
-
-run_giana = function() {
-    print(paste("Using tool:", "GIANA"))
-    giana_srcdir = prepare_giana()
-    giana_input = prepare_input()
-    giana_outdir = file.path(outdir, "GIANA_Output")
-    dir.create(giana_outdir, showWarnings = FALSE)
-    args_str = ""
-    for (argname in names(args)) {
-        argvalue = args[[argname]]
-        if (!startsWith(argname, "-")) {
-            if (nchar(argname) == 1) {
-                argname = paste0("-", argname)
-            } else {
-                argname = paste0("--", argname)
-            }
-        }
-        if (isTRUE(argvalue) || toupper(as.character(argvalue)) == "TRUE") {
-            argvalue = ""
-        } else {
-            argvalue = as.character(argvalue)
-        }
-        args_str = paste(args_str, argname, argvalue)
-    }
-    giana_cmd = paste(
-        python,
-        file.path(giana_srcdir, "GIANA.py"),
-        "-f", giana_input,
-        "-o", giana_outdir,
-        "-v", # TRBV mutation not supported
-        args_str
-    )
-    print("Running:")
-    print(giana_cmd)
-    rc = system(giana_cmd)
-    if (rc != 0) {
-        quit(status=rc)
-    }
-    giana_outfile = file.path(giana_outdir, "cdr3--RotationEncodingBL62.txt")
-    clean_giana_output(giana_outfile, giana_input)
-}
-
-attach_to_immdata = function(out) {
-    seqdata2 = list()
-    # by = if (!on_multi) c(cdr3 = "CDR3.aa") else "CDR3.aa"
-    by = "CDR3.aa"
-    for (sample in names(seqdata)) {
-        sample_out = left_join(seqdata[[sample]], out, by=by)
-        seqdata2[[sample]] = sample_out
-        if (!on_multi) {
-            immdata$data[[sample]] = immdata$data[[sample]] %>% left_join(
-                out, by = "CDR3.aa"
-            )
-        } else {
-            immdata$multi[[sample]] = immdata$multi[[sample]] %>% left_join(
-                out, by = c(cdr3 = "CDR3.aa")
-            )
-        }
-        # if ("single" %in% names(immdata)) {
-        #     immdata$data[[sample]] = immdata$data[[sample]] %>% left_join(
-        #         out, by = "CDR3.aa"
-        #     )
-        # }
-    }
-    if (!on_multi) {
-        immdata$data = seqdata2
-    } else {
-        immdata$multi = seqdata2
-    }
-    saveRDS(immdata, file = outfile)
-    # seqdata2
-}
-
-
-if (tolower(tool) == "clustcr") {
-    out = run_clustcr()
-} else if (tolower(tool) == "giana") {
-    out = run_giana()
-} else {
-    stop(paste("Unknown tool:", tool))
-}
-
-attach_to_immdata(out)

biopipen/utils/common_docstrs.py

@@ -1,61 +0,0 @@
-"""Common docstrings for biopipen procs."""
-import textwrap
-from typing import Callable
-
-
-def indent_docstr(docstr: str, indent: str) -> str:
-    """Indent the docstring.
-
-    Args:
-        docstr: The docstring.
-        indent: The indent.
-
-    Returns:
-        The indented docstring.
-    """
-    return textwrap.indent(docstr, indent).strip()
-
-
-def format_placeholder(**kwargs) -> Callable[[type], type]:
-    """A decorator to format a docstring placeholder.
-
-    Args:
-        **kwargs: The docstring placeholder.
-
-    Returns:
-        The decorated function.
-    """
-
-    def decorator(klass: type) -> type:
-        klass.__doc__ = klass.__doc__ % kwargs
-        return klass
-
-    return decorator
-
-
-MUTATE_HELPERS_CLONESIZE = """
-There are also also 4 helper functions, `expanded`, `collapsed`, `emerged` and `vanished`,
-which can be used to identify the expanded/collpased/emerged/vanished groups (i.e. TCR clones).
-For example, you can use
-`{"Patient1_Tumor_Collapsed_Clones": "expanded(., Source, 'Tumor', subset = Patent == 'Patient1', uniq = FALSE)"}`
-to create a new column in metadata named `Patient1_Tumor_Collapsed_Clones`
-with the collapsed clones in the tumor sample (compared to the normal sample) of patient 1.
-The values in this columns for other clones will be `NA`.
-Those functions take following arguments:
-* `df`: The metadata data frame. You can use the `.` to refer to it.
-* `group-by`: The column name in metadata to group the cells.
-* `idents`: The first group or both groups of cells to compare (value in `group-by` column). If only the first group is given, the rest of the cells (with non-NA in `group-by` column) will be used as the second group.
-* `subset`: An expression to subset the cells, will be passed to `dplyr::filter()`. Default is `TRUE` (no filtering).
-* `id`: The column name in metadata for the group ids (i.e. `CDR3.aa`).
-* `compare`: Either a (numeric) column name (i.e. `Clones`) in metadata to compare between groups, or `.n` to compare the number of cells in each group.
-    If numeric column is given, the values should be the same for all cells in the same group.
-    This will not be checked (only the first value is used).
-* `uniq`: Whether to return unique ids or not. Default is `TRUE`. If `FALSE`, you can mutate the meta data frame with the returned ids. For example, `df |> mutate(expanded = expanded(...))`.
-* `order`: The order of the returned ids. It could be `sum` or `diff`, which is the sum or diff of the `compare` between idents.
-    Two kinds of modifiers can be added, including `desc` and `abs`.
-    For example, `sum,desc` means the sum of `compare` between idents in descending order.
-    Default is `diff,abs,desc`. It only works when `uniq` is `TRUE`. If `uniq` is `FALSE`, the returned
-    ids will be in the same order as in `df`.
-* `include_emerged`: Whether to include the emerged group for `expanded` (only works for `expanded`). Default is `FALSE`.
-* `include_vanished`: Whether to include the vanished group for `collapsed` (only works for `collapsed`). Default is `FALSE`.
-"""

biopipen/utils/gene.R

@@ -1,49 +0,0 @@
-library(mygene)
-library(dplyr)
-
-gene_name_conversion = function(
-    genes,
-    species,
-    infmt,
-    outfmt,
-    notfound
-) {
-    out = queryMany(
-        genes,
-        scopes=infmt,
-        fields=outfmt,
-        species=species
-    ) %>% as.data.frame() %>% group_by(
-        query
-    ) %>% arrange(
-        desc(X_score)
-    ) %>% slice_head(n=1) %>% select(
-        -c(X_id, X_score)
-    )
-
-    if ("notfound" %in% colnames(out)) {
-        out = out %>% select(-c("notfound"))
-    }
-
-    if (length(outfmt) == 1 && "," %in% outfmt) {
-        outfmt = trimws(unlist(strsplit(outfmt, ",", fixed=TRUE)))
-    }
-
-    out = tibble(query=genes) %>% left_join(out, by="query")
-    if (notfound == "use-query") {
-        out = out %>% mutate(
-            across(
-                outfmt,
-                function(col, query) if_else(is.na(col), query, col),
-                query=query
-            )
-        )
-    } else if (notfound == "error" && any(is.na(out[[outfmt[1]]]))) {
-        nagenes = out %>% filter(is.na(.[[outfmt[1]]])) %>% pull("query")
-        stop(paste("Query genes not found:", paste(nagenes, collapse=",")))
-    } else if (notfound == "skip") {
-        out = out %>% filter(!is.na(.[[outfmt[1]]]))
-    }
-
-    return out
-}