biopipen 0.31.5__py3-none-any.whl → 0.31.7__py3-none-any.whl

biopipen/scripts/regulatory/VariantMotifPlot.R

@@ -0,0 +1,76 @@
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
+{{ biopipen_dir | joinpaths: "scripts", "regulatory", "motifs-common.R" | source_r }}
+
+library(BSgenome)
+library(GenomicRanges)
+
+infile <- {{in.infile | r}}
+outdir <- {{out.outdir | r}}
+genome <- {{envs.genome | r}}
+motifdb <- {{envs.motifdb | r}}
+motif_col <- {{envs.motif_col | r}}
+regulator_col <- {{envs.regulator_col | r}}
+regmotifs <- {{envs.regmotifs | r}}
+notfound <- {{envs.notfound | r}}
+devpars <- {{envs.devpars | r}}
+plot_vars <- {{envs.plot_vars | r}}
+
+if (is.null(motifdb) || !file.exists(motifdb)) {
+    stop("Motif database (envs.motifdb) is required and must exist")
+}
+
+if (is.null(genome)) {
+    stop("Reference genome (envs.ref) is required and must exist")
+}
+
+if (is.null(motif_col) && is.null(regulator_col)) {
+    stop("Either motif (envs.motif_col) or regulator (envs.regulator_col) column must be provided")
+}
+
+log_info("Reading input data ...")
+indata <- read.table(infile, header=TRUE, sep="\t", stringsAsFactors=FALSE, check.names = FALSE)
+
+log_info("Ensuring regulators in the input data ...")
+indata <- ensure_regulator_motifs(indata, outdir, motif_col, regulator_col, regmotifs, notfound = notfound)
+genome_pkg <- get_genome_pkg(genome)
+
+log_info("Reading motif database ...")
+meme <- read_meme_to_motifdb(motifdb, indata, motif_col, regulator_col, notfound, outdir)
+
+log_info("Composing motifbreakR results from input data ...")
+indata$chr <- indata$chrom %||% indata$chr %||% indata$seqnames
+indata$seqnames <- NULL
+indata$strand <- indata$strand %||% "+"
+indata$varType <- indata$varType %||% "SNV"
+indata$geneSymbol <- indata$geneSymbol %||% indata$Regulator
+indata$providerId <- indata$providerId %||% indata$motif
+indata$providerName <- indata$providerName %||% indata$providerId
+indata$dataSource <- indata$dataSource %||% strsplit(basename(motifdb), "\\.")[[1]][1]
+indata$effect <- indata$effect %||% "strong"
+indata$altPos <- indata$altPos %||% 1
+indata$alleleDiff <- indata$alleleDiff %||% indata$score %||% 0
+
+# check other required columns
+for (col in c("start", "end", "SNP_id", "REF", "ALT", "motifPos")) {
+    if (!(col %in% colnames(indata))) {
+        stop("Column '", col, "' is required in the input data")
+    }
+}
+indata$motifPos <- lapply(indata$motifPos, function(x) as.integer(unlist(strsplit(x, ","))))
+indata <- makeGRangesFromDataFrame(indata, keep.extra.columns = TRUE, starts.in.df.are.0based = TRUE)
+genome(indata) <- genome
+attributes(indata)$genome.package <- genome_pkg
+attributes(indata)$motifs <- meme
+
+log_info("Plotting variants ...")
+if (is.null(plot_vars)) {
+    plot_vars <- unique(indata$SNP_id)
+} else if (length(plot_vars) > 1) {
+    plot_vars <- unique(plot_vars)
+} else {
+    plot_vars <- strsplit(plot_vars, ",")[[1]]
+}
+for (pvar in plot_vars) {
+    log_info("- Variant: {pvar}")
+    plot_variant_motifs(indata, pvar, devpars, outdir)
+}

biopipen/scripts/regulatory/motifs-common.R

@@ -0,0 +1,322 @@
+# make sure biopipen/utils/misc.R is loaded, log_warn is defined, and slugify is defined
+
+library(rlang)
+library(universalmotif)
+library(MotifDb)
+
+#' @title Common functions for regulatory analysis
+#' @name regulatory-common
+#' @author Panwen Wang
+
+#' Read a regulator-motif mapping file
+#'
+#' @param rmfile Regulator-motif mapping file
+#' @param motif_cols_allowed Allowed motif columns
+#' @param reg_cols_allowed Allowed regulator columns
+#' @return Data frame with regulators and motifs in the first and second columns, respectively
+.read_regmotifs <- function(
+    rmfile,
+    motif_cols_allowed = c("Motif", "motif", "MOTIF", "Model", "model", "MODEL"),
+    reg_cols_allowed = c("Regulator", "regulator", "REGULATOR", "TF", "tf", "TF")
+) {
+    if (!file.exists(rmfile)) {
+        stop("Regulator-motif mapping file does not exist.")
+    }
+    regmotifs <- read.table(rmfile, header=TRUE, sep="\t", stringsAsFactors=FALSE, check.names = FALSE)
+    rm_motif_col <- intersect(motif_cols_allowed, colnames(regmotifs))
+    rm_reg_col <- intersect(reg_cols_allowed, colnames(regmotifs))
+    if (length(rm_motif_col) == 0) {
+        stop(paste0("No motif column found in the regulator-motif mapping file, provide one of: ", paste(motif_cols_allowed, collapse = ", ")))
+    }
+    if (length(rm_reg_col) == 0) {
+        stop(paste0("No regulator column found in the regulator-motif mapping file, provide one of: ", paste(reg_cols_allowed, collapse = ", ")))
+    }
+    if (length(rm_motif_col) > 1) {
+        stop(paste0("Multiple motif columns found (", paste(rm_motif_col, collapse = ", "), ") in the regulator-motif mapping file, provide only one"))
+    }
+    if (length(rm_reg_col) > 1) {
+        stop(paste0("Multiple regulator columns found (", paste(rm_reg_col, collapse = ", "), ") in the regulator-motif mapping file, provide only one"))
+    }
+    rm_motif_col <- rm_motif_col[1]
+    rm_reg_col <- rm_reg_col[1]
+    regmotifs <- regmotifs[, c(rm_motif_col, rm_reg_col), drop = FALSE]
+
+    return(regmotifs)
+}
+
+#' Handle not found items
+#'
+#' @param notfound_items Items that were not found
+#' @param log_warn Function to log warnings
+#' @param msg Message to display
+#' @param notfound Action to take if items are not found
+#' @param notfound_file File to save the full list of not found items
+#' @param log_indent Indentation for log messages
+.handle_notfound_items <- function (notfound_items, log_warn, msg, notfound, notfound_file, log_indent = "") {
+    if (length(notfound_items) > 0) {
+        first_notfound <- head(notfound_items, 3)
+        if (length(notfound_items) > 3) {
+            first_notfound <- c(first_notfound, "...")
+            writeLines(notfound_items, notfound_file)
+            msg1 <- paste0(log_indent, msg, ": ", paste(first_notfound, collapse = ", "))
+            msg2 <- paste0(log_indent, "Check the full list in ", notfound_file)
+            if (notfound == "error") {
+                stop(msg1, "\n", msg2)
+            } else if (notfound == "ignore") {
+                log_warn(msg1)
+                log_warn(msg2)
+            }
+        } else {
+            msg <- paste0(log_indent, msg, ": ", paste(first_notfound, collapse = ", "))
+            if (notfound == "error") {
+                stop(msg)
+            } else if (notfound == "ignore") {
+                log_warn(msg)
+            }
+        }
+    }
+}
+
+#' Read a MEME file to a MotifDb object
+#' and filter the motifs based on the input data
+#' and return the filtered MotifDb object
+#' with metadata
+#'
+#' @param motifdb MEME file
+#' @param indata Input data frame
+#' @param motif_col Column name for the motif
+#' @param regulator_col Column name for the regulator
+#' @param notfound Action to take if motifs are not found
+#' @param outdir Output directory, used to save un-matched motifs
+#' @return MotifDb object
+#' @export
+read_meme_to_motifdb <- function(motifdb, indata, motif_col, regulator_col, notfound, outdir) {
+    meme <- read_meme(motifdb)
+    motifdb_names <- sapply(meme, function(m) m@name)
+    motifs <- check_motifs(indata[[motif_col]], motifdb_names, notfound, outdir)
+    meme <- filter_motifs(meme, name = motifs)
+    # Get the right order of motif names
+    motifs <- sapply(meme, function(m) m@name)
+    motifdb_matrices <- lapply(meme, function(m) m@motif)
+    names(motifdb_matrices) <- motifs
+    motifdb_meta <- do.call(rbind, lapply(meme, function(m) {
+            ats <- attributes(m)
+            ats$dataSource <- strsplit(basename(motifdb), "\\.")[[1]][1]
+            ats$class <- NULL
+            ats$motif <- NULL
+            ats$gapinfo <- NULL
+            ats$sequenceCount <- ats$nsites
+            ats$providerId <- ats$name
+            ats$providerName <- ats$name
+            ats$organism <- if (is.null(ats$organism) || length(ats$organism) == 0) "Unknown" else ats$organism
+            if (!is.null(regulator_col)) {
+                ats$geneSymbol <- indata[
+                    indata[[motif_col]] == ats$name,
+                    regulator_col,
+                    drop = TRUE
+                ]
+            }
+            unlist(ats)
+        })
+    )
+    rownames(motifdb_meta) <- motifs
+    MotifDb:::MotifList(motifdb_matrices, tbl.metadata = motifdb_meta)
+}
+
+#' Convert a MotifDb object to a motif library
+#' with motif names as keys
+#' and PWMs as values
+#' @param motifdb MotifDb object
+#' @return Motif library
+#' @export
+motifdb_to_motiflib <- function(motifdb) {
+    lapply(motifdb, t)
+}
+
+#' Make sure the regulators and motifs in the input data from a regulator-motif mappings
+#'
+#' @param indata Input data frame
+#' @param outdir Output directory, used to save un-matched regulators
+#' @param motif_col Column name for the motif
+#' @param regulator_col Column name for the regulator
+#' @param regmotifs Regulator-motif mapping file
+#' @param log_indent Indentation for log messages
+#' @param notfound Action to take if regulators are not found in the mapping file
+#' @return Data frame with regulators and motifs
+#' @export
+ensure_regulator_motifs <- function (indata, outdir, motif_col, regulator_col, regmotifs, log_indent = "", notfound = "error") {
+    if (is.null(motif_col)) {
+        if (is.null(regmotifs)) {
+            stop("Regulator-motif mapping file (envs.regmotifs) is required when no motif column (envs.motif_col) is provided")
+        }
+        regmotifs <- .read_regmotifs(regmotifs)
+        rm_motif_col <- colnames(regmotifs)[1]
+        rm_reg_col <- colnames(regmotifs)[2]
+        # check regulators
+        rm_regs <- regmotifs[[rm_reg_col]]
+        regulators <- indata[[regulator_col]]
+        notfound_regs <- setdiff(regulators, rm_regs)
+        .handle_notfound_items(
+            notfound_regs,
+            log_warn,
+            "The following regulators were not found in the regulator-motif mapping file",
+            notfound,
+            file.path(outdir, "notfound_regulators.txt"),
+            log_indent
+        )
+        indata <- indata[indata[[regulator_col]] %in% rm_regs, , drop = FALSE]
+        # add motif column
+        indata <- merge(indata, regmotifs, by.x = regulator_col, by.y = rm_reg_col, all.x = TRUE, suffixes = c("", "_db"))
+        # update motif column
+        motif_col <<- rm_motif_col
+    } else if (is.null(regulator_col)) {
+        if (is.null(regmotifs) || (is.character(regmotifs) && nchar(regmotifs) == 0)) {
+            # make motifs unique
+            indata <- indata[!duplicated(indata[[motif_col]]), , drop = FALSE]
+        } else if (!file.exists(regmotifs)) {
+            stop("Regulator-motif mapping file (envs.regmotifs) does not exist.")
+        } else {
+            # map the regulators
+            regmotifs <- .read_regmotifs(regmotifs)
+            rm_motif_col <- colnames(regmotifs)[1]
+            rm_reg_col <- colnames(regmotifs)[2]
+            rm_motifs <- regmotifs[[rm_motif_col]]
+            motifs <- indata[[motif_col]]
+            notfound_motifs <- setdiff(motifs, rm_motifs)
+            .handle_notfound_items(
+                notfound_motifs,
+                log_warn,
+                "The following motifs were not found in the regulator-motif mapping file",
+                notfound,
+                file.path(outdir, "notfound_motifs.txt"),
+                log_indent
+            )
+            indata <- indata[indata[[motif_col]] %in% rm_motifs, , drop = FALSE]
+            # add regulator column
+            indata <- merge(indata, regmotifs, by.x = motif_col, by.y = rm_motif_col, all.x = TRUE, suffixes = c("", "_db"))
+            # update regulator column
+            regulator_col <<- rm_reg_col
+        }
+    } else {
+        indata <- indata[!duplicated(indata[, c(regulator_col, motif_col), drop = FALSE]), , drop = FALSE]
+    }
+
+    return(indata)
+}
+
+#' Get the genome package name for a given genome
+#'
+#' @param genome Genome name
+#' @return Genome package name
+#' @export
+get_genome_pkg <- function(genome) {
+    if (!grepl(".", genome, fixed = TRUE)) {
+        genome_pkg = sprintf("BSgenome.Hsapiens.UCSC.%s", genome)
+    } else {
+        genome_pkg = genome
+    }
+    if (!requireNamespace(genome_pkg, quietly = TRUE)) {
+        stop(sprintf("Genome package %s is not installed", genome_pkg))
+    }
+
+    library(package = genome_pkg, character.only = TRUE)
+    return(genome_pkg)
+}
+
+#' Check if motifs are in the motif database
+#' and return the motifs that are found
+#'
+#' @param motifs Motifs to check
+#' @param all_motifs All motifs in the motif database
+#' @param notfound Action to take if motifs are not found
+#' @param outdir Output directory, used to save un-matched motifs
+#' @return Motifs that are found
+#' @export
+check_motifs <- function(motifs, all_motifs, notfound, outdir) {
+    notfound_motifs <- setdiff(motifs, all_motifs)
+    if (length(notfound_motifs) > 0) {
+        first_notfound <- head(notfound_motifs, 3)
+        if (length(notfound_motifs) > 3) {
+            first_notfound <- c(first_notfound, "...")
+            notfound_file <- file.path(outdir, "notfound_motifs.txt")
+            writeLines(notfound_motifs, notfound_file)
+            msg1 <- paste0("The following motifs were not found in the motif database: ", paste(first_notfound, collapse = ", "))
+            msg2 <- paste0("Check the full list in ", notfound_file)
+
+            if (notfound == "error") {
+                stop(msg1, "\n", msg2)
+            } else if (notfound == "ignore") {
+                log_warn(msg1)
+                log_warn(msg2)
+            }
+        } else {
+            msg <- paste0("The following motifs were not found in the motif database: ", paste(first_notfound, collapse = ", "))
+            if (notfound == "error") {
+                stop(msg)
+            } else if (notfound == "ignore") {
+                log_warn(msg)
+            }
+        }
+
+        motifs <- setdiff(motifs, notfound_motifs)
+    }
+    return(motifs)
+}
+
+#' Plot a genomic region surrounding a genomic variant, and
+#' potentially disrupted motifs.
+#'
+#' @param results The motifbreakR results.
+#'  A GRanges object with the following columns:
+#'  - seqnames: Chromosome
+#'  - ranges: Start and end positions
+#'  - strand: Strand
+#'  -------------------
+#'  - SNP_id: Variant ID
+#'  - REF: Reference allele
+#'  - ALT: Alternative allele
+#'  - varType: Variant type. By default, "SNV"
+#'  - motifPos: Motif positions
+#'  - geneSymbol: Gene symbol, if not provided, try to get from the Regulator column
+#'  - dataSource: Motif database source
+#'  - providerName: Motif name
+#'  - providerId: Motif ID
+#'  - effect: Effect of the variant. By default, "strong"
+#'  - altPos: Alternative allele position. By default, 1
+#'  - alleleDiff: Allele difference, default 0, does not affect the plot for SNVs
+#'
+#'  Attributes:
+#'  - genome.package: Genome package name
+#'  - motifs: Motif database, in MotifDb::MotifList format
+#' @param variant Variant ID to be plotted
+#' @param devpars List of device parameters
+#'  - res: Resolution, default 100
+#'  - width: Width of the plot, default NULL, calculated based on sequence length
+#'  - height: Height of the plot, default NULL, calculated based on the number of motifs
+#' @param outdir Output directory. Plots will be saved in the sub-directory "<outdir>/plots/"
+#' @export
+plot_variant_motifs <- function(results, variant, devpars, outdir) {
+    plotdir <- file.path(outdir, "plots")
+    dir.create(plotdir, showWarnings = FALSE)
+
+    res <- results[results$SNP_id == variant, , drop = FALSE]
+    devpars <- devpars %||% list(res = 100, width = NULL, height = NULL)
+    if (length(res) == 0) {
+        stop(sprintf("Variant %s not found in results", variant))
+    }
+    devpars$res <- devpars$res %||% 100
+    devpars$height <- devpars$height %||% 2.4 * devpars$res + length(res) * 1.2 * devpars$res
+    if (is.null(devpars$width)) {
+        left <- min(sapply(res$motifPos, `[`, 1))
+        right <- max(sapply(res$motifPos, `[`, 2))
+        devpars$width <- 1.5 * devpars$res + (right - left) * 0.3 * devpars$res
+        devpars$width <- max(devpars$width, 5 * devpars$res)
+    }
+
+    plotfile <- file.path(plotdir, sprintf("%s.png", slugify(variant)))
+    # fix motifBreakR 2.12 using names to filter in plotMB
+    names(res) <- res$SNP_id
+    png(plotfile, width = devpars$width, height = devpars$height, res = devpars$res)
+    motifbreakR::plotMB(res, variant)
+    dev.off()
+}

biopipen/scripts/vcf/TruvariBench.sh

@@ -1,13 +1,15 @@
+# shellcheck disable=SC1083
 compvcf={{in.compvcf | quote}}
 basevcf={{in.basevcf | quote}}
 outdir={{out.outdir | quote}}
 truvari={{envs.truvari | quote}}
 ref={{envs.ref | quote}}
 refdist={{envs.refdist | quote}}
-pctsim={{envs.pctsim | quote}}
+pctseq={{envs.pctseq | quote}}
 pctsize={{envs.pctsize | quote}}
 pctovl={{envs.pctovl | quote}}
 sizemax={{envs.sizemax | default: 50000 | quote}}
+# shellcheck disable=SC1054
 {% if envs.typeignore %}
 typeignore="--typeignore"
 {% else %}
@@ -15,20 +17,25 @@ typeignore=""
 {% endif %}
 {% if envs.multimatch %}
 multimatch="--multimatch"
+# shellcheck disable=SC1009
 {% else %}
 multimatch=""
+# shellcheck disable=SC1073
 {% endif %}
 
 rm -rf $outdir
-$truvari bench \
-    -c "$compvcf" \
-    -b "$basevcf" \
-    -f "$ref" \
+cmd="$truvari bench \
+    -c '$compvcf' \
+    -b '$basevcf' \
+    -f '$ref' \
     --refdist $refdist \
-    --pctsim $pctsim \
+    --pctseq $pctseq \
     --pctsize $pctsize \
     --pctovl $pctovl \
     --sizemax $sizemax \
     $typeignore \
     $multimatch \
-    -o $outdir
+    -o $outdir"
+
+echo "$cmd"
+eval "$cmd"

biopipen/scripts/vcf/TruvariBenchSummary.R

@@ -17,7 +17,7 @@ read_summary = function() {
 
     summaries = NULL
     for (indir in indirs) {
-        summary = fromJSON(file=file.path(indir, "summary.txt"))
+        summary = fromJSON(file=file.path(indir, "summary.json"))
         summary$gt_matrix = NULL
         summary$Sample = sub(".truvari_bench", "", basename(indir), fixed=T)
         summaries = bind_rows(summaries, summary)
@@ -43,7 +43,6 @@ plot_summary = function(col) {
         summaries,
         "col",
         list(mapping = aes_string(x = "Sample", y = bQuote(col), fill = "Sample")),
-
         devpars = get_devpars(),
         outfile = outfile
     )

{biopipen-0.31.5.dist-info → biopipen-0.31.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biopipen
-Version: 0.31.5
+Version: 0.31.7
 Summary: Bioinformatics processes/pipelines that can be run from `pipen run`
 License: MIT
 Author: pwwang

{biopipen-0.31.5.dist-info → biopipen-0.31.7.dist-info}/RECORD

@@ -1,4 +1,4 @@
-biopipen/__init__.py,sha256=VSx4_WLVLq_7UtX4GtNLbObe0lMQRa5JR9eh0ofSz4A,23
+biopipen/__init__.py,sha256=APQVRwZptBFPacKCHqg_tW4g4--qdUtMJoA6GprSuSI,23
 biopipen/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 biopipen/core/config.py,sha256=edK5xnDhM8j27srDzsxubi934NMrglLoKrdcC8qsEPk,1069
 biopipen/core/config.toml,sha256=7IXvviRicZ2D1h6x3BVgbLJ96nsh-ikvZ0sVlQepqFE,1944
@@ -7,8 +7,8 @@ biopipen/core/filters.py,sha256=5bZsbpdW7DCxqiteRdb2gelmXvfqWPmPsFxrpHdWsoE,1298
 biopipen/core/proc.py,sha256=60lUP3PcUAaKbDETo9N5PEIoeOYrLgcSmuytmrhcx8g,912
 biopipen/core/testing.py,sha256=lZ_R5ZbYPO2NPuLHdbzg6HbD_f4j8paVVbyeUqwg6FE,3411
 biopipen/ns/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-biopipen/ns/bam.py,sha256=-xVagotsURyOtwKzv72L-2f9P7467OVzgvP96syfHZc,10628
-biopipen/ns/bed.py,sha256=HsTCJge7XNfCZyCBJ4iifNKQ5we4VZSpRx8XL8--y5A,6689
+biopipen/ns/bam.py,sha256=OtvzEadx-zpr98PoZoozbQszcQBvtFDMuAtuwH-3JUw,11394
+biopipen/ns/bed.py,sha256=EqpSa7Hx6GImvJNghtV4uDo2PnPXeUt1Yq9AFWJP9_8,8159
 biopipen/ns/cellranger.py,sha256=yPBoNzVSY74J7uyVucaob5lqZKKru5-hYSM4f4Nr2OY,5553
 biopipen/ns/cellranger_pipeline.py,sha256=EWkPJTujamNSMQoRnKfhUiIj6TkMfRmCSUbPfd8Tv8E,4011
 biopipen/ns/cnv.py,sha256=ssQAHf2MB675avoXVRkYy0vGiqIpRpRExywjhbymmBI,7811
@@ -20,7 +20,7 @@ biopipen/ns/gsea.py,sha256=EsNRAPYsagaV2KYgr4Jv0KCnZGqayM209v4yOGGTIOI,7423
 biopipen/ns/misc.py,sha256=qXcm0RdR6W-xpYGgQn3v7JBeYRWwVm5gtgSj2tdVxx4,2935
 biopipen/ns/plot.py,sha256=XzLq0A8qCIQRbxhPEdWhEfbRZ8g3e4KriVz0RP8enNY,18078
 biopipen/ns/protein.py,sha256=33pzM-gvBTw0jH60mvfqnriM6uw2zj3katZ82nC9owI,3309
-biopipen/ns/regulatory.py,sha256=qvc9QrwgwCI_lg0DQ2QOZbAhC8BAD1qnQXSGtAGlVcY,11750
+biopipen/ns/regulatory.py,sha256=gJjGVpJrdv-rg2t5UjK4AGuvtLNymaNYNvoD8PhlbvE,15929
 biopipen/ns/rnaseq.py,sha256=bKAa6friFWof4yDTWZQahm1MS-lrdetO1GqDKdfxXYc,7708
 biopipen/ns/scrna.py,sha256=fXP_h7gchcuk_Jwos0IgY_P8ON6Q995OgKHgdrxfvAY,112868
 biopipen/ns/scrna_metabolic_landscape.py,sha256=6AhaynGG3lNRi96N2tReVT46BJMuEwooSSd2irBoN80,28347
@@ -28,7 +28,7 @@ biopipen/ns/snp.py,sha256=-Jx5Hsv_7KV7TqLU0nHCaPkMEN0CFdi4tNVlyq0rUZ4,27259
 biopipen/ns/stats.py,sha256=DlPyK5Vsg6ZEkV9SDS3aAw21eXzvOHgqeZDkXPhg7go,20509
 biopipen/ns/tcgamaf.py,sha256=AFbUJIxiMSvsVY3RcHgjRFuMnNh2DG3Mr5slLNEyz6o,1455
 biopipen/ns/tcr.py,sha256=0PCF8iPZ629z6P3RHoAWEpMWmuDslomTGcMopjqvXmE,88304
-biopipen/ns/vcf.py,sha256=zidwskYZ3IIY1sAKYp6WXOiEOdrJjw438JQW1TC7l9s,22694
+biopipen/ns/vcf.py,sha256=OYWuAWADba1xLwvHmIPwXYin_rUaAFQq7N38DQvoYzs,22746
 biopipen/ns/web.py,sha256=4itJzaju8VBARIyZjDeh5rsVKpafFq_whixnvL8sXes,5368
 biopipen/reports/bam/CNAClinic.svelte,sha256=D4IxQcgDCPQZMbXog-aZP5iJEQTK2N4i0C60e_iXyfs,213
 biopipen/reports/bam/CNVpytor.svelte,sha256=s03SlhbEPd8-_44Dy_cqE8FSErhUdqStLK39te5o7ZE,1364
@@ -79,6 +79,7 @@ biopipen/reports/vcf/TruvariConsistency.svelte,sha256=BBvtxi1EPmGH7j5M5zMOcLEhKW
 biopipen/scripts/bam/BamMerge.py,sha256=Gd5P8V-CSsTAA8ZrUxetR-I49GjJ3VJNjrqu7-EZwXQ,3642
 biopipen/scripts/bam/BamSampling.py,sha256=Pi6CXAbBFVRGh8-0WrkB-3v3oxinfahQk11H0IdBNmQ,2312
 biopipen/scripts/bam/BamSplitChroms.py,sha256=b7GS2I4X0dLOhlPg_r9-buoIHTWlq6zHI3Rox94LXR8,4893
+biopipen/scripts/bam/BamSubsetByBed.py,sha256=QpY6WDJfbO3k2FdMyfgstFKgTdtOc1beGoUF5FI5EAc,1027
 biopipen/scripts/bam/CNAClinic.R,sha256=mQXwtShL54HZXGCPqgPKPrU74_6K_8PqtOtG0mgA-F0,5062
 biopipen/scripts/bam/CNVpytor.py,sha256=hOUli9BDMOoth0or-tjUYC1AP3yNOuxUS6G3Rhcg99s,18000
 biopipen/scripts/bam/ControlFREEC.py,sha256=oX6iWsos-CfiT_ViDBrKeMOOIVdCKWrB-_MqzLgEF9s,3267
@@ -86,6 +87,7 @@ biopipen/scripts/bed/Bed2Vcf.py,sha256=u0mp_2Y4UtEA839zq9UENesH6Gyiwd4sZQW9wFnBV
 biopipen/scripts/bed/BedConsensus.py,sha256=gfAxuIalvCEpS0tiOyAJGPYGgHN0L-hm0K37Iteh5yw,2386
 biopipen/scripts/bed/BedLiftOver.sh,sha256=Y4gBsz9w4zhE29UmWojO6F4PXMMMWC1uCzjrxa19eOs,256
 biopipen/scripts/bed/BedtoolsIntersect.py,sha256=sFyXPL3kG59xa5eJwHumcQLw3lfabOXsq2-k8IgIqt4,1722
+biopipen/scripts/bed/BedtoolsMakeWindows.py,sha256=Ip4U0ORXti65g7znZeHEbvw2PGlCxoEfeucZmw4wb1o,1428
 biopipen/scripts/bed/BedtoolsMerge.py,sha256=7mt307V_wWa_ME0VfuMsVX0HgEwfDcZtY_bDvOPjFiQ,368
 biopipen/scripts/cellranger/CellRangerCount.py,sha256=b9kkHPpq-bFh-3XCUdxdMKg3SsZmEzZFrG3dbtb4fX8,2875
 biopipen/scripts/cellranger/CellRangerSummary.R,sha256=mVOCIHngEpJIKVD3tMG5UWqS0OQGGjY6yx6ikRcqQU4,11067
@@ -126,12 +128,12 @@ biopipen/scripts/plot/Scatter.R,sha256=fg4H5rgdr6IePTMAIysiElnZme0vCh1T0wrwH2Q9x
 biopipen/scripts/plot/VennDiagram.R,sha256=Am9umSGr2QxZc2MIMGMBhpoEqta3qt_ItF-9_Y53SXE,704
 biopipen/scripts/protein/Prodigy.py,sha256=W56e51SkaWqthrkCSr2HUqhE9NfJQWZj4y0HXIqaYRA,4459
 biopipen/scripts/protein/ProdigySummary.R,sha256=1s3ofk6Kvs--GAAvzV8SdAyq5LrYozWtIlL32b6ZarE,3806
-biopipen/scripts/regulatory/MotifAffinityTest.R,sha256=1sR3sWRZbxDeFO290LcpzZglzOLc13SSvibDON96PCg,8852
-biopipen/scripts/regulatory/MotifAffinityTest_AtSNP.R,sha256=SAyTm2-6g5qVJFRrLxEY0QJrLWTkwDi_J_9J7HhtTN8,4438
-biopipen/scripts/regulatory/MotifAffinityTest_MotifBreakR.R,sha256=wCK4tLx1iWh_OwW7ZvLTCjTGWCIfVqw-lYC0-JqIPqg,3338
+biopipen/scripts/regulatory/MotifAffinityTest.R,sha256=McAnbduE_6SMD_4RuftBemPdfJD9LeFYUYwqL3fzfjU,3047
+biopipen/scripts/regulatory/MotifAffinityTest_AtSNP.R,sha256=lzP3EtmpMucWviLDgXLeP_JvG4VADykBOl49CkftiR8,4366
+biopipen/scripts/regulatory/MotifAffinityTest_MotifBreakR.R,sha256=WpkPVNvWonmZqQ8khdDg2VHhda7ZHexvLFGRz4qgv88,3304
 biopipen/scripts/regulatory/MotifScan.py,sha256=WtSbs8z08oeTgzjr0LfIDmjbUdknAh1raa_QPQ_NCFg,5336
-biopipen/scripts/regulatory/atSNP.R,sha256=TXJARbE0rDIzSq6Spacz_HsM_DXdREJ95ZsBg26trgw,1288
-biopipen/scripts/regulatory/motifBreakR.R,sha256=trzvvTvwc5gSO427wkqx93FecuQxLGa9kNqodKa8S0U,70236
+biopipen/scripts/regulatory/VariantMotifPlot.R,sha256=RNnBc0bboGfrJOPk5CsUbFRBMBvVX8zgGsrI5eybNyo,2874
+biopipen/scripts/regulatory/motifs-common.R,sha256=7deFrEzZKYzNhmYTsBqqb91CbIj2vtF7lRiPX0yGkO8,13277
 biopipen/scripts/rnaseq/Simulation-ESCO.R,sha256=68cEHDdJclX8P8Q7ey9yBOfK09M_kxlL6zgYXsEL2Rs,6378
 biopipen/scripts/rnaseq/Simulation-RUVcorr.R,sha256=6C6Ke5RLF0fC2V9WQPoFEdqoDabCnhslZBIyB6zhIxc,1155
 biopipen/scripts/rnaseq/Simulation.R,sha256=PK9tZS88AcBPStcFalZlMU0KE0gSqFSQvhUoQ-8eg90,871
@@ -250,8 +252,8 @@ biopipen/scripts/vcf/BcftoolsAnnotate.py,sha256=iS-T6IhumqePW5kdyi_Tb6rubyIiCMjS
 biopipen/scripts/vcf/BcftoolsFilter.py,sha256=AdQMXFTNLCS5eqYWMNIMbkK8qXJ5j8GYm7HdPopVk0c,2573
 biopipen/scripts/vcf/BcftoolsSort.py,sha256=tU0pTrEIB-7x6iOSfU-KpYY1rEidi6Q4179NntY3cGc,3778
 biopipen/scripts/vcf/BcftoolsView.py,sha256=Sj3KkYPpwQFo5kmZC5MRxItrSE5KVZi0jNYrRFck3Ow,2465
-biopipen/scripts/vcf/TruvariBench.sh,sha256=80yLQ73OzSgsJ4ltzgpcWxYvvX1hFnCG8YSBhhhRQ9Y,765
-biopipen/scripts/vcf/TruvariBenchSummary.R,sha256=Q1VCYqOZ-VI8lgXW6Yqmw6NkLH168e7V6eYFbr0W4EE,1516
+biopipen/scripts/vcf/TruvariBench.sh,sha256=5M7lZhO4laNJvCVCHudf8DYArKNXoiPWuSkXgRi2t_A,908
+biopipen/scripts/vcf/TruvariBenchSummary.R,sha256=rdNNIPoiwqnK6oEOlQUUhnL1MF958W_nDjRCkA5ubz4,1516
 biopipen/scripts/vcf/TruvariConsistency.R,sha256=6h20v8qztbl1KZInJwoSK_t5XwqhKMTMzPWNPhoAjlM,2314
 biopipen/scripts/vcf/Vcf2Bed.py,sha256=LzyJ9qW1s5mbfF8maLc77_0rE98KMc2lq1R94_NFbSU,855
 biopipen/scripts/vcf/VcfAnno.py,sha256=FW626rAs_WSU7AHQMKjfkYoByUGh_gVyJM97neGfOMo,802
@@ -284,7 +286,7 @@ biopipen/utils/reference.py,sha256=oi5evicLwHxF0KAIPNZohBeHJLJQNWFJH0cr2y5pgcg,5
 biopipen/utils/rnaseq.R,sha256=Ro2B2dG-Z2oVaT5tkwp9RHBz4dp_RF-JcizlM5GYXFs,1298
 biopipen/utils/single_cell.R,sha256=pJjYP8bIZpNAtTQ32rOXhZxaM1Y-6D-xUcK3pql9tbk,4316
 biopipen/utils/vcf.py,sha256=ajXs0M_QghEctlvUlSRjWQIABVF02wPdYd-0LP4mIsU,9377
-biopipen-0.31.5.dist-info/METADATA,sha256=mRJi-cY3E8tLValjumEgu28oAiy5NNpFMQRsrNiRPVg,882
-biopipen-0.31.5.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-biopipen-0.31.5.dist-info/entry_points.txt,sha256=BYqHGBQJxyFDNLYqgH64ycI5PYwnlqwYcCFsMvJgzAU,653
-biopipen-0.31.5.dist-info/RECORD,,
+biopipen-0.31.7.dist-info/METADATA,sha256=dmsDb7Q7iTWvkZjChqUgVqhb2CiQP4j8OA0jBzRYgGY,882
+biopipen-0.31.7.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+biopipen-0.31.7.dist-info/entry_points.txt,sha256=BYqHGBQJxyFDNLYqgH64ycI5PYwnlqwYcCFsMvJgzAU,653
+biopipen-0.31.7.dist-info/RECORD,,

biopipen/scripts/regulatory/atSNP.R

@@ -1,33 +0,0 @@
-snpinfo2atsnp <- function(snpinfo) {
-    # c("chrom", "start", "end", "name", "score", "strand", "ref", "alt", "ref_seq", "alt_seq")
-    if (any(nchar(snpinfo$ref) != 1) || any(nchar(snpinfo$alt) != 1)) {
-        stop("Only SNVs are supported by atSNP. Consider using motifbreakR instead if you have indels.")
-    }
-    base_encodings <- c(A = 1, C = 2, G = 3, T = 4)
-    transition <- matrix(
-        c(
-            0.3225035, 0.1738422, 0.24915044, 0.2545039,
-            0.3451410, 0.2642147, 0.05245011, 0.3381942,
-            0.2813089, 0.2136604, 0.26749171, 0.2375390,
-            0.2149776, 0.2071733, 0.25309238, 0.3247568
-        ),
-        nrow = 4,
-        byrow = TRUE
-    )
-    rownames(transition) <- colnames(transition) <- names(base_encodings)
-    list(
-        sequence_matrix = unname(sapply(
-            snpinfo$ref_seq,
-            function(s) as.integer(base_encodings[strsplit(s, "")[[1]]])
-        )),
-        ref_base = as.integer(base_encodings[snpinfo$ref]),
-        snp_base = as.integer(base_encodings[snpinfo$alt]),
-        snpids = snpinfo$name,
-        transition = transition,
-        prior = c(A = 0.287, C = 0.211, G = 0.213, T = 0.289),
-        rsid.na = NULL,
-        rsid.rm = NULL,
-        rsid.duplicate = NULL,
-        rsid.missing = NULL
-    )
-}