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

biopipen/scripts/bam/CNVpytor.py

@@ -1,15 +1,15 @@
 from pathlib import Path
 
+import warnings
 import pandas
-from biopipen.scripts.vcf.VcfFix_utils import HeaderContig, fix_vcffile
+from datetime import datetime
 from biopipen.utils.reference import bam_index
-from biopipen.utils.misc import run_command, dict_to_cli_args
+from biopipen.utils.misc import run_command, dict_to_cli_args, logger
 
-bamfile = {{in.bamfile | quote}}  # pyright: ignore
+bamfile = {{in.bamfile | quote}}  # pyright: ignore # noqa
 snpfile = {{in.snpfile | repr}}  # pyright: ignore
 outdir = Path({{out.outdir | quote}})  # pyright: ignore
 cnvpytor = {{envs.cnvpytor | quote}}  # pyright: ignore
-cnvnator2vcf = {{envs.cnvnator2vcf | quote}}  # pyright: ignore
 samtools = {{envs.samtools | quote}}  # pyright: ignore
 ncores = {{envs.ncores | int}}  # pyright: ignore
 refdir = {{envs.refdir | quote}}  # pyright: ignore
@@ -20,7 +20,6 @@ args = {{envs | repr}}  # pyright: ignore
 
 del args['cnvpytor']
 del args['ncores']
-del args['cnvnator2vcf']
 del args['samtools']
 del args['refdir']
 del args['genome']
@@ -236,47 +235,138 @@ def load_chrsize():
                 yield chrom, int(size)
 
 
-def cnvpytor2vcf(infile, snp, fix=True):
-    unfixedfile = Path(infile).with_suffix(f".unfixed.vcf")
-    outfile = Path(infile).with_suffix(f".vcf")
-    stdout = run_command(
-        dict_to_cli_args(
-            {
-                "": cnvpytor2vcf,
-                "reference": genome,
-                "_": [infile, refdir],
-            },
-            prefix="-",
-        ),
-        stdout="return",
-    )
-    if fix:
-        unfixedfile.write_text(stdout)
+def parse_chrom(chrom, chromdir):
+    file = Path(chromdir) / f"{chrom}.fa"
+    if not file.exists():
+        warnings.warn(f"Chromosome file not found in refdir: {chrom}")
+        return ""
 
-        fixes = [
-            {
-                "kind": "format",
-                "id": "PE",
-                "fix": lambda obj: setattr(obj, 'Type', 'String')
-            },
-            {
-                "kind": "fields",
-                "fix": lambda items: items.__setitem__(-1, Path(bamfile).stem)
-            }
-        ]
+    seq = ""
+    with open(file) as f:
+        for line in f:
+            line = line.strip()
+            if not line:
+                continue
+            if line.startswith(">"):
+                seq = ""
+            else:
+                seq += line
+    return seq
+
+
+def cnvpytor2vcf(infile, snp):
+    # snp: in case to be used in the future
+    outfile = Path(infile).with_suffix(f".vcf")
+    # stdout = run_command(
+    #     dict_to_cli_args(
+    #         {
+    #             "": cnvnator2vcf,
+    #             "reference": genome,
+    #             "_": [infile, refdir],
+    #         },
+    #         prefix="-",
+    #     ),
+    #     stdout="return",
+    # )
+    ## command hangs
+    with open(infile) as fin, open(outfile, "w") as fout:
+        fout.write("##fileformat=VCFv4.2\n")
+        fout.write(f"##fileDate={datetime.now().strftime('%Y%m%d')}\n")
+        fout.write(f"##reference={genome}\n")
+        fout.write(f"##source=CNVpytor\n")
         for chrom, size in load_chrsize():
-            fixes.append({
-                "kind": "contig",
-                "append": True,
-                "fix": (
-                    lambda obj, chrom=chrom, size=size:
-                    HeaderContig(ID=chrom, length=size)
-                )
-            })
+            fout.write(f"##contig=<ID={chrom},length={size}>\n")
+        fout.write('##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record">\n')
+        fout.write('##INFO=<ID=IMPRECISE,Number=0,Type=Flag,Description="Imprecise structural variation">\n')
+        fout.write('##INFO=<ID=SVLEN,Number=1,Type=Integer,Description="Difference in length between REF and ALT alleles">\n')
+        fout.write('##INFO=<ID=SVTYPE,Number=1,Type=String,Description="Type of structural variant">\n')
+        fout.write('##INFO=<ID=natorRD,Number=1,Type=Float,Description="Normalized RD">\n')
+        fout.write('##INFO=<ID=natorP1,Number=1,Type=Float,Description="e-val by t-test">\n')
+        fout.write('##INFO=<ID=natorP2,Number=1,Type=Float,Description="e-val by Gaussian tail">\n')
+        fout.write('##INFO=<ID=natorP3,Number=1,Type=Float,Description="e-val by t-test (middle)">\n')
+        fout.write('##INFO=<ID=natorP4,Number=1,Type=Float,Description="e-val by Gaussian tail (middle)">\n')
+        fout.write('##INFO=<ID=natorQ0,Number=1,Type=Float,Description="Fraction of reads with 0 mapping quality">\n')
+        fout.write('##INFO=<ID=natorPE,Number=1,Type=Integer,Description="Number of paired-ends support the event">\n')
+        fout.write('##INFO=<ID=SAMPLES,Number=.,Type=String,Description="Sample genotyped to have the variant">\n')
+        fout.write('##ALT=<ID=DEL,Description="Deletion">\n')
+        fout.write('##ALT=<ID=DUP,Description="Duplication">\n')
+        fout.write('##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n')
+        fout.write('##FORMAT=<ID=CN,Number=1,Type=Integer,Description="Copy number genotype for imprecise events">\n')
+        fout.write('##FORMAT=<ID=PE,Number=1,Type=String,Description="Number of paired-ends that support the event">\n')
+        fout.write(f"#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\t{Path(bamfile).stem}\n")
+        prev_chrom, chrom_seq, count = "", "", 0
+        for line in fin:
+            # type, coor, length, rd, p1, p2, p3, p4, q0, pe = line.strip("\n").split()
+            items = line.strip("\n").split()
+            type, coor, length = items[:3]
+            rd = float(items[3]) if len(items) > 3 else False
+            p1 = items[4] if len(items) > 4 else ""
+            p2 = items[5] if len(items) > 5 else ""
+            p3 = items[6] if len(items) > 6 else ""
+            p4 = items[7] if len(items) > 7 else ""
+            q0 = items[8] if len(items) > 8 else ""
+            pe = items[9] if len(items) > 9 else ""
+            chrom, pos = coor.split(":")
+            start, end = pos.split("-")
+            start, end = int(start), int(end)
+            is_del = type == "deletion"
+            is_dup = type == "duplication"
+
+            if not is_del and not is_dup:
+                warnings.warn(f"Skipping unrecognized CNV type: {type}")
+                continue
 
-        fix_vcffile(unfixedfile, outfile, fixes)
-    else:
-        outfile.write_text(stdout)
+            if chrom != prev_chrom:
+                chrom_seq = parse_chrom(chrom, refdir)
+                prev_chrom = chrom
+
+            count += 1
+            info = f"END={end}"
+            info += f";SVTYPE=DEL;SVLEN=-{length}" if is_del else f";SVTYPE=DUP;SVLEN={length}"
+            info += ";IMPRECISE"
+            info += f";natorRD={rd}" if rd is not False else ""
+            info += f";natorP1={p1}" if p1 else ""
+            info += f";natorP2={p2}" if p2 else ""
+            info += f";natorP3={p3}" if p3 else ""
+            info += f";natorP4={p4}" if p4 else ""
+            info += f";natorQ0={q0}" if q0 else ""
+            info += f";natorPE={pe}" if pe else ""
+
+            gt = "GT"
+            if rd is not False:
+                gt += ":CN"
+                gt += ":PE" if pe else ""
+                gt += "\t"
+                if is_del and rd < 0.25:
+                    gt += "1/1:0"
+                elif is_del and rd >= 0.25:
+                    gt += "0/1:1"
+                elif rd <= 1.75:
+                    gt += "0/1:2"
+                elif rd > 1.75 and rd <= 2.25:
+                    gt += "1/1:2"
+                elif rd > 2.25:
+                    gt += f"./2:{rd:.0f}"
+                else:
+                    gt = "GT:PE\t./." if pe else "GT\t./."
+
+                gt += f":{pe}" if pe else ""
+            else:
+                gt += "\t./."
+
+            fout.write("\t".join(
+                [
+                    chrom,
+                    str(start),
+                    f"CNVpytor_{'del_' if is_del else 'dup_'}{count}",
+                    chrom_seq[start - 1] if start < len(chrom_seq) else "N",
+                    "<DEL>" if is_del else "<DUP>",
+                    ".",
+                    "PASS",
+                    info,
+                    gt,
+                ]
+            ) + "\n")
 
 
 def do_case():
@@ -290,7 +380,7 @@ def do_case():
     rootfile = outdir / "file.pytor"
     case["j"] = case.get("j", ncores)
 
-    # read depth signal
+    logger.info("Reading depth signals ...")
     run_command(
         dict_to_cli_args(
             {
@@ -305,7 +395,7 @@ def do_case():
         fg=True,
     )
 
-    # predicting cnv
+    logger.info("Predicting CNVs ...")
     run_command(
         dict_to_cli_args(
             {
@@ -314,6 +404,7 @@ def do_case():
                 "his": binsizes,
             },
             prefix="-",
+            dup_key=False,
         ),
         fg=True,
     )
@@ -326,6 +417,7 @@ def do_case():
                 "partition": binsizes,
             },
             prefix="-",
+            dup_key=False,
         ),
         fg=True,
     )
@@ -336,6 +428,7 @@ def do_case():
         mask_snps = snp.pop("mask_snps", True)
         baf_nomask = snp.pop("baf_nomask", False)
 
+        logger.info("Importing SNP data ...")
         run_command(
             dict_to_cli_args(
                 {
@@ -350,6 +443,7 @@ def do_case():
         )
 
         if mask_snps:
+            logger.info("Masking 1000 Genome SNPs ...")
             run_command(
                 dict_to_cli_args(
                     {
@@ -362,6 +456,7 @@ def do_case():
                 fg=True,
             )
 
+        logger.info("Calculating BAF histograms ...")
         run_command(
             dict_to_cli_args(
                 {
@@ -375,8 +470,9 @@ def do_case():
             fg=True,
         )
 
-    # call
+    logger.info("Predicting CNV regions using joint caller ...")
     for binsize in binsizes:
+        logger.info(f"- binsize: {binsize}")
         outfile = outdir / f"calls{'.combined' if snp is not False else ''}.{binsize}.tsv"
         outfile_filtered = outdir / f"calls{'.combined' if snp is not False else ''}.{binsize}.filtered.tsv"
         run_command(
@@ -392,6 +488,7 @@ def do_case():
             stdout=outfile,
         )
 
+        logger.info("  Converting to other formats ...")
         cnvpytor2other(outfile, bool(snp), "gff")
         cnvpytor2other(outfile, bool(snp), "bed")
         cnvpytor2vcf(outfile, bool(snp))
@@ -424,6 +521,7 @@ def do_case():
         cnvpytor2vcf(outfile_filtered, bool(snp))
 
         # plots
+        logger.info("  Plotting ...")
         manplot = outdir / f"manhattan.{binsize}.png"
         run_command(
             dict_to_cli_args(

biopipen/scripts/bed/BedtoolsIntersect.py

@@ -0,0 +1,54 @@
+from pathlib import Path
+from biopipen.utils.misc import run_command, dict_to_cli_args, logger
+
+afile = Path({{in.afile | repr}})  # pyright: ignore # noqa: #999
+bfile = Path({{in.bfile | repr}})  # pyright: ignore
+outfile = {{out.outfile | repr}}  # pyright: ignore
+envs = {{envs | repr}}  # pyright: ignore
+
+bedtools = envs.pop("bedtools")
+sort = envs.pop("sort")
+chrsize = envs.pop("chrsize")
+postcmd = envs.pop("postcmd", None)
+outdir = Path(outfile).parent
+
+if chrsize and "g" in envs:
+    logger.warning("Ignoring envs.g because envs.chrsize is provided.")
+    envs["g"] = Path(chrsize).expanduser()
+elif chrsize:
+    envs["g"] = Path(chrsize).expanduser()
+
+if sort:
+    afile_sorted = outdir / f"{afile.stem}_sorted{afile.suffix}"
+    bfile_sorted = outdir / f"{bfile.stem}_sorted{bfile.suffix}"
+    run_command(
+        [bedtools, "sort", "-g", envs["g"], "-i", afile],
+        stdout=afile_sorted,
+    )
+    run_command(
+        [bedtools, "sort", "-g", envs["g"], "-i", bfile],
+        stdout=bfile_sorted,
+    )
+    afile = afile_sorted
+    bfile = bfile_sorted
+
+envs[""] = [bedtools, "intersect"]
+envs["a"] = afile
+envs["b"] = bfile
+envs.setdefault("sorted", True)
+
+if envs["sorted"] and not "g" in envs:
+    raise ValueError("envs.g is required or manullay set envs.sorted to False.")
+
+if postcmd:
+    ofile = Path(outfile).with_suffix(".prior.bt")
+    run_command(dict_to_cli_args(envs, prefix="-"), stdout=ofile)
+    postcmd_file = outdir / "_postcmd.sh"
+    postcmd_file.write_text(postcmd)
+    run_command(
+        ["bash", postcmd_file],
+        env={"infile": ofile, "outfile": outfile, "outdir": outdir},
+        fg=True,
+    )
+else:
+    run_command(dict_to_cli_args(envs, prefix="-"), stdout=outfile)

biopipen/scripts/bed/BedtoolsMerge.py

@@ -1,6 +1,6 @@
 from biopipen.utils import run_command, dict_to_cli_args
 
-inbed = {{in.inbed | repr}}  # pyright: ignore
+inbed = {{in.inbed | repr}}  # pyright: ignore # noqa: #999
 outbed = {{out.outbed | repr}}  # pyright: ignore
 envs = {{envs | repr}}  # pyright: ignore
 bedtools = envs.pop("bedtools", "bedtools")

biopipen/scripts/cnv/AneuploidyScore.R

@@ -127,13 +127,32 @@ getCAA <- function(segf, cytoarm, tcn_col,
   return(as(seg_cyto_chr, "GRangesList"))
 }
 
-segments = read.table(segfile, header=T, row.names=NULL, sep="\t", stringsAsFactors=F)
-seg = data.frame(
-    seqnames = segments[, chrom_col],
-    start = segments[, start_col],
-    end = segments[, end_col],
-    seg.mean = segments[, seg_col]
-)
+if (endsWith(segfile, ".vcf") || endsWith(segfile, ".vcf.gz")) {
+  library(VariantAnnotation)
+  vcf = readVcf(segfile)
+  seg = data.frame(
+      seqnames = as.character(seqnames(vcf)),
+      start = start(vcf),
+      end = vcf@info[[end_col]],
+      seg.mean = vcf@info[[seg_col]]
+  )
+} else if (endsWith(segfile, ".bed")) {
+  segments = read.table(segfile, header=F, row.names=NULL, sep="\t", stringsAsFactors=F)
+  seg = data.frame(
+      seqnames = segments[, 1],
+      start = segments[, 2],
+      end = segments[, 3],
+      seg.mean = segments[, 5]
+  )
+} else {
+  segments = read.table(segfile, header=T, row.names=NULL, sep="\t", stringsAsFactors=F)
+  seg = data.frame(
+      seqnames = segments[, chrom_col],
+      start = segments[, start_col],
+      end = segments[, end_col],
+      seg.mean = segments[, seg_col]
+  )
+}
 
 {% if envs.segmean_transform %}
 segmean_transform = {{envs.segmean_transform}}
@@ -168,6 +187,10 @@ if (is.character(cn_transform)) {
 }
 {% endif %}
 
+seg <- seg[
+  !is.na(seg$seg.mean) & !is.na(seg$TCN) & !is.infinite(seg$seg.mean) & !is.infinite(seg$TCN),,
+  drop=FALSE]
+
 write.table(seg, file.path(outdir, "seg.txt"), sep="\t", quote=F, row.names=F, col.names=T)
 
 wgd_ploidy = checkIfWGD(

biopipen/scripts/cnv/AneuploidyScoreSummary.R

@@ -52,8 +52,11 @@ if (!is.null(group_cols)) {
 
 if (!is.null(metafile)) {
     metadf = read.table(metafile, header=T, row.names=NULL, sep="\t", stringsAsFactors=F)
-    sample_col = colnames(metadf)[1]
-    colnames(metadf)[1] = "Sample"
+    if (!is.null(metadf$Sample)) {
+        metadf$Sample = as.character(metadf$Sample)
+    } else {
+        colnames(metadf)[1] = "Sample"
+    }
     metadf = metadf[metadf$Sample %in% sams, c("Sample", meta_cols), drop=FALSE]
     if (nrow(metadf) != length(sams)) {
         stop(paste("Not all samples in metafile:", paste(setdiff(sams, metadf$Sample), collapse=", ")))

biopipen/scripts/cnv/TMADScore.R

@@ -11,11 +11,27 @@ if (is.character(segmean_transform)) {
     segmean_transform = eval(parse(text=segmean_transform))
 } # otherwise NULL
 
-segments = read.table(segfile, header=T, row.names=NULL, sep="\t", stringsAsFactors=F)
-seg = data.frame(
-    chrom = segments[, chrom_col],
-    log2 = segments[, seg_col]
-)
+
+if (endsWith(segfile, ".vcf") || endsWith(segfile, ".vcf.gz")) {
+  library(VariantAnnotation)
+  segments = readVcf(segfile)
+  seg = data.frame(
+      chrom = as.character(seqnames(segments)),
+      log2 = segments@info[[seg_col]]
+  )
+} else if (endsWith(segfile, ".bed")) {
+  segments = read.table(segfile, header=F, row.names=NULL, sep="\t", stringsAsFactors=F)
+  seg = data.frame(
+      chrom = segments[, 1],
+      log2 = segments[, 5]
+  )
+} else {
+  segments = read.table(segfile, header=T, row.names=NULL, sep="\t", stringsAsFactors=F)
+  seg = data.frame(
+      chrom = segments[, chrom_col],
+      log2 = segments[, seg_col]
+  )
+}
 rm(segments)
 
 if (!is.null(excl_chroms) && length(excl_chroms) > 0) {

biopipen/scripts/cnv/TMADScoreSummary.R

@@ -49,8 +49,12 @@ if (!is.null(group_cols)) {
 data = data.frame(Sample = sams, tMAD = tmads)
 if (file.exists(metafile) && length(meta_cols) > 0) {
     metadf = read.table(metafile, header=T, row.names=NULL, sep="\t", stringsAsFactors=F)
-    sample_col = colnames(metadf)[1]
-    meta = metadf[, c(sample_col, meta_cols), drop=FALSE]
+    if (!is.null(metadf$Sample)) {
+        metadf$Sample = as.character(metadf$Sample)
+    } else {
+        colnames(metadf)[1] = "Sample"
+    }
+    meta = metadf[, c("Sample", meta_cols), drop=FALSE]
     colnames(meta) = c("Sample", meta_cols)
     data = data %>% left_join(meta, by="Sample")
 }

biopipen/scripts/cnvkit/CNVkitAccess.py

@@ -1,3 +1,4 @@
+from pathlib import Path
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
 excfiles = {{in.excfiles | repr}}  # pyright: ignore
@@ -12,7 +13,7 @@ def main():
         "": [cnvkit, "access"],
         "s": min_gap_size,
         "o": outfile,
-        "_": reffile,
+        "_": Path(reffile).expanduser(),
     }
     if excfiles:
         other_args["exclude"] = excfiles

biopipen/scripts/cnvkit/CNVkitAutobin.py

@@ -1,3 +1,4 @@
+from pathlib import Path
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
 bamfiles = {{in.bamfiles | repr}}  # pyright: ignore
@@ -20,7 +21,7 @@ short_names = {{envs.short_names | repr}}  # pyright: ignore
 def main():
 
     args = dict(
-        f=reffile,
+        f=Path(reffile).expanduser(),
         m=method,
         g=accfile,
         t=baitfile,
@@ -29,7 +30,7 @@ def main():
         target_min_size=target_min_size,
         antitarget_max_size=antitarget_max_size,
         antitarget_min_size=antitarget_min_size,
-        annotate=annotate,
+        annotate=Path(annotate).expanduser(),
         short_names=short_names,
         target_output_bed=target_file,
         antitarget_output_bed=antitarget_file,

biopipen/scripts/cnvkit/CNVkitBatch.py

@@ -42,7 +42,7 @@ def gen_access():
         exclude=access_excludes or False,
         s=access_min_gap_size or False,
         o=accessfile,
-        _=ref,
+        _=Path(ref).expanduser(),
     )
     args[""] = [cnvkit, "access"]
     run_command(dict_to_cli_args(args, dashify=True), fg=True)

biopipen/scripts/cnvkit/CNVkitCoverage.py

@@ -1,3 +1,4 @@
+from pathlib import Path
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
 bamfile = {{in.bamfile | quote}}  # pyright: ignore
@@ -13,7 +14,7 @@ ncores = {{envs.ncores | repr}}  # pyright: ignore
 def main():
 
     args = dict(
-        f=reffile,
+        f=Path(reffile).expanduser(),
         c=count,
         q=min_mapq,
         p=ncores,

biopipen/scripts/cnvkit/CNVkitGuessBaits.py

@@ -60,7 +60,7 @@ params.update({
     "o": targetfile,
     "c": covfile,
     "p": ncores,
-    "f": ref,
+    "f": Path(ref).expanduser(),
     "s": samtools,
     "_": bamfiles,
 })

biopipen/scripts/cnvkit/CNVkitHeatmap.py

@@ -4,7 +4,7 @@ from diot import Diot
 
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
-segfiles = {{in.segfiles | repr}}  # pyright: ignore
+segfiles = {{in.segfiles | repr}}  # pyright: ignore # noqa
 sample_sex = {{in.sample_sex | repr}}  # pyright: ignore
 outdir = {{out.outdir | repr}}  # pyright: ignore
 cnvkit = {{envs.cnvkit | quote}}  # pyright: ignore

biopipen/scripts/cnvkit/CNVkitReference.py

@@ -1,3 +1,4 @@
+from pathlib import Path
 from biopipen.utils.misc import run_command, dict_to_cli_args
 
 covfiles = {{in.covfiles | repr}}  # pyright: ignore
@@ -18,7 +19,7 @@ no_rmask = {{envs.no_rmask | repr}}  # pyright: ignore
 def main():
 
     args = dict(
-        f=reffile,
+        f=Path(reffile).expanduser(),
         o=outfile,
         c=cluster,
         min_cluster_size=min_cluster_size,

biopipen/scripts/delim/SampleInfo.R

@@ -88,7 +88,11 @@ for (name in names(stats)) {
     group <- if (is.null(stat$group)) sym("..group") else sym(stat$group)
     count_on <- paste0("..count.", stat$on)
     if (!is_continuous) {
-        data <- data %>% add_count(!!group, name = count_on)
+        if (!is.null(stat$each)) {
+            data <- data %>% add_count(!!group, !!sym(stat$each), name = count_on)
+        } else {
+            data <- data %>% add_count(!!group, name = count_on)
+        }
     }
 
     if (is.null(stat$devpars)) {
@@ -141,18 +145,19 @@ for (name in names(stats)) {
         } else {
             data <- data %>%
                 distinct(!!group, !!sym(stat$each), .keep_all = TRUE) %>%
+                mutate(!!group := factor(!!group, levels = unique(!!group))) %>%
                 group_by(!!sym(stat$each))
         }
         p <- ggplot(
-            data %>% arrange(!!group),
-            aes(x = "", y = !!sym(count_on), fill = !!group, label = !!sym(count_on))
+            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", width=1, color="white", position = position_stack(reverse = TRUE)) +
+            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_stack(vjust = 0.5),
+                position = position_fill(reverse = TRUE,vjust = .5),
                 color="#333333",
                 fill="#EEEEEE",
                 size=4

biopipen/scripts/gene/GeneNameConversion.R

@@ -0,0 +1,65 @@
+source("{{biopipen_dir}}/utils/misc.R")
+source("{{biopipen_dir}}/utils/gene.R")
+
+infile <- {{in.infile | quote}}
+outfile <- {{out.outfile | quote}}
+notfound <- {{envs.notfound | r}}
+genecol <- {{envs.genecol | r}}
+output <- {{envs.output | r}}
+dup <- {{envs.dup | r}}
+infmt <- {{envs.infmt | r}}
+outfmt <- {{envs.outfmt | r}}
+species <- {{envs.species | r}}
+
+if (is.na(notfound)) {
+    notfound = "na"
+}
+
+df <- read.table(infile, header=TRUE, sep="\t", check.names=FALSE)
+
+if (genecol == 0) {
+    log_warn("envs.genecol should be 1-based, but 0 was given. Using 1 instead.")
+    genecol <- 1
+}
+
+if (is.numeric(genecol)) { genecol <- colnames(df)[genecol] }
+if (dup == "combine") { dup <- ";" }
+
+genes <- df[[genecol]]
+converted <- gene_name_conversion(
+    genes=genes,
+    species=species,
+    infmt=infmt,
+    outfmt=outfmt,
+    notfound=notfound,
+    dup=dup
+)
+#    <genecol> <outfmt>
+# 1  1255_g_at   GUCA1A
+# 2    1316_at     THRA
+# 3    1320_at   PTPN21
+# 4    1294_at  MIR5193
+
+# order the converted dataframe by the original gene column
+converted <- converted[order(match(converted$query, genes)), , drop=FALSE]
+outcol <- outfmt
+
+if (notfound == "skip" || notfound == "ignore") {
+    df <- df[df[[genecol]] %in% converted$query, , drop=FALSE]
+}
+
+if (output == "append") {
+    if (outfmt %in% colnames(df)) {
+        log_warn("The output column name already exists in the input dataframe. Appending with a suffix `_1`.")
+        outcol <- paste(outfmt, "_1", sep="")
+    }
+    df[[outcol]] <- converted[[outfmt]]
+} else if (output == "replace") {
+    df[[genecol]] <- converted[[outfmt]]
+} else if (output == "with-query") {
+    df <- converted
+} else {
+    df <- converted[, outfmt, drop=FALSE]
+}
+
+write.table(df, file=outfile, sep="\t", quote=FALSE, row.names=FALSE)