biopipen 0.7.0__py3-none-any.whl → 0.8.0__py3-none-any.whl

biopipen/ns/tcgamaf.py

@@ -0,0 +1,52 @@
+"""Processes for TCGA MAF files."""
+from ..core.proc import Proc
+from ..core.config import config
+
+
+class Maf2Vcf(Proc):
+    """Converts a MAF file to a VCF file.
+
+    This is a wrapper around the `maf2vcf` script from the `maf2vcf` package.
+
+    Input:
+        infile: The input MAF file
+
+    Output:
+        outfile: Output multi-sample VCF containing all TN-pairs
+        outdir: Path to output directory where VCFs will be stored,
+            one per TN-pair
+
+    Envs:
+        perl: Path to perl to run `maf2vcf.pl`
+        samtools: Path to samtools to be used in `maf2vcf.pl`
+        args: Other arguments to pass to the script
+    """
+    input = "infile:file"
+    output = [
+        'outfile:file:{{in.infile | stem}}.vcfs/'
+        '{{in.infile | stem}}.multisample.vcf',
+        'outdir:dir:{{in.infile | stem}}.vcfs'
+    ]
+    lang = config.lang.python
+    envs = {
+        "perl": config.lang.perl,
+        "samtools": config.exe.samtools,
+        "ref": config.ref.reffa,
+        "args": {"per-tn-vcfs": True},
+    }
+    script = "file://../scripts/tcgamaf/Maf2Vcf.py"
+
+
+class MafAddChr(Proc):
+    """Adds the `chr` prefix to chromosome names in a MAF file if not present.
+
+    Input:
+        infile: The input MAF file
+
+    Output:
+        outfile: The output MAF file
+    """
+    input = "infile:file"
+    output = "outfile:file:{{in.infile | stem}}.maf"
+    lang = config.lang.python
+    script = "file://../scripts/tcgamaf/MafAddChr.py"

biopipen/ns/tcr.py

@@ -116,7 +116,6 @@ class ImmunarchFilter(Proc):
             Placeholders like `{Sample}_` can be used to from the meta data
         metacols: The extra columns to be exported to the group file.
     """
-
     input = "immdata:file, filterfile:file"
     output = """
         outfile:file:{{in.immdata | stem}}.RDS,
@@ -209,7 +208,6 @@ class Immunarch(Proc):
             If you do want multiple parameter sets for the same K, You can use
             a float number as the K. For example: `5.1` for K `5`.
     """
-
     input = "immdata:file"
     output = "outdir:dir:{{in.immdata | stem}}.immunarch"
     lang = config.lang.rscript
@@ -341,7 +339,6 @@ class CloneResidency(Proc):
         sample_groups: How the samples aligned in the report.
             Useful for cohort with large number of samples.
     """
-
     input = "immdata:file"
     output = "outdir:dir:{{in.immdata | stem}}.cloneov"
     lang = config.lang.rscript
@@ -366,7 +363,6 @@ class Immunarch2VDJtools(Proc):
         outdir: The output directory containing the vdjtools input for each
             sample
     """
-
     input = "immdata:file"
     output = "outdir:dir:{{in.immdata | stem}}.vdjtools_input"
     lang = config.lang.rscript
@@ -451,7 +447,6 @@ class Attach2Seurat(Proc):
             `{Sample}_` to use the meta data from the immunarch object
         metacols: Which meta columns to attach
     """
-
     input = "immfile:file, sobjfile:file"
     output = "outfile:file:{{in.sobjfile | basename}}"
     lang = config.lang.rscript
@@ -505,12 +500,10 @@ class TCRClustering(Proc):
             For ClusTCR, they will be passed to `clustcr.Clustering(...)`
 
     Requires:
-        - name: clusTCR
-          if: {{ proc.envs.tool == 'ClusTCR' }}
-          check: |
-            {{ proc.envs.python }} -c "import clustcr"
+        clusTCR:
+            - if: {{ proc.envs.tool == 'ClusTCR' }}
+            - check: {{ proc.envs.python }} -c "import clustcr"
     """
-
     input = "immfile:file"
     output = [
         "immfile:file:{{in.immfile | basename}}",
@@ -549,11 +542,9 @@ class TCRClusteringStats(Proc):
             the diversities by groups
 
     Requires:
-        - name: r-immunarch
-          check: |
-            {{proc.lang}} -e "library(immunarch)"
+        r-immunarch:
+            - check: {{proc.lang}} -e "library(immunarch)"
     """
-
     input = "immfile:file"
     output = "outdir:dir:{{in.immfile | stem}}.tcrclusters_stats"
     lang = config.lang.rscript
@@ -602,7 +593,6 @@ class CloneSizeQQPlot(Proc):
         on: The key of the metadata to use for the QQ plot. One/Both of
             `["Clones", "Proportion"]`
     """
-
     input = "immdata:file"
     output = "outdir:dir:{{in.immdata | stem}}.qqplots"
     lang = config.lang.rscript

biopipen/ns/vcf.py

@@ -18,7 +18,6 @@ class VcfLiftOver(Proc):
         tmpdir: Directory for temporary storage of working files
         args: Other CLI arguments for `gatk LiftoverVcf`
     """
-
     input = "invcf:file"
     output = "outvcf:file:{{in.invcf | basename}}"
     envs = {
@@ -61,7 +60,6 @@ class VcfFilter(Proc):
         helper: Some helper code for the filters
         keep: Keep the variants not passing the filters?
     """  # noqa: E501
-
     input = "invcf:file"
     output = "outfile:file:{{in.invcf | basename}}"
     lang = config.lang.python
@@ -87,7 +85,6 @@ class VcfIndex(Proc):
     Envs:
         tabix: Path to tabix
     """
-
     input = "infile:file"
     output = """
         {%- if in.infile.endswith(".gz") %}
@@ -120,11 +117,9 @@ class Vcf2Bed(Proc):
         outbase: The coordinate base of the base file
 
     Requires:
-        - name: cyvcf2
-          check: |
-            {{proc.lang}} -c "import cyvcf2"
+        cyvcf2:
+            - check: {{proc.lang}} -c "import cyvcf2"
     """
-
     input = "infile:file"
     output = "outfile:file:{{in.infile | stem0}}.bed"
     lang = config.lang.python
@@ -147,10 +142,10 @@ class VcfDownSample(Proc):
             If `n > 1`, it is the number.
             If `n <= 1`, it is the fraction.
     """
-
     input = "infile:file"
     output = "outfile:file:{{in.infile | basename}}"
     envs = {"n": 0}
+    lang = config.lang.bash
     script = "file://../scripts/vcf/VcfDownSample.sh"
 
 
@@ -290,14 +285,7 @@ class VcfFix(Proc):
         helpers: raw code the provide some helpers for the fixes
             The code will automatically dedented if given as a string. A list
             of strings is also supported and will be joined with newlines.
-
-    Requires:
-        - name: biopipen
-          check: |
-            {{proc.lang}} -c "import biopipen"
-
     """
-
     input = "infile:file"
     output = "outfile:file:{{in.infile | basename}}"
     lang = config.lang.python
@@ -305,6 +293,44 @@ class VcfFix(Proc):
     script = "file://../scripts/vcf/VcfFix.py"
 
 
+class VcfAnno(Proc):
+    """Annotate a VCF file using vcfanno
+
+    https://github.com/brentp/vcfanno
+
+    Input:
+        infile: The input VCF file
+        conffile: The configuration file for vcfanno or configuration dict
+            itself
+
+    Output:
+        outfile: The output VCF file
+
+    Envs:
+        vcfanno: Path to vcfanno
+        ncores: Number of cores to use
+        conffile: configuration file for vcfanno or configuration dict itself
+            This is ignored when `conffile` is given as input
+        args: Additional arguments to pass to vcfanno
+
+    Requires:
+        - name: vcfanno
+          check: |
+            {{proc.envs.vcfanno}} --help
+    """
+
+    input = "infile:file, conffile"
+    output = "outfile:file:{{in.infile | stem0}}.{{envs.tool}}.vcf"
+    lang = config.lang.python
+    envs = {
+        "vcfanno": config.exe.vcfanno,
+        "ncores": config.misc.ncores,
+        "conffile": {},
+        "args": {"permissive-overlap": True},
+    }
+    script = "file://../scripts/vcf/VcfAnno.py"
+
+
 class TruvariBench(Proc):
     """Run `truvari bench` to compare a VCF with CNV calls and
     base CNV standards
@@ -323,11 +349,9 @@ class TruvariBench(Proc):
         `<other>`: Ohter `truvari bench` arguments
 
     Requires:
-        - name: truvari
-          check: |
-            {{proc.envs.truvari}} version
+        truvari:
+            - check: {{proc.envs.truvari}} version
     """
-
     input = "compvcf:file, basevcf:file"
     output = "outdir:dir:{{in.compvcf | stem0 | append: '.truvari_bench'}}"
     envs = {
@@ -340,6 +364,7 @@ class TruvariBench(Proc):
         "typeignore": False,
         "multimatch": False,
     }
+    lang = config.lang.bash
     script = "file://../scripts/vcf/TruvariBench.sh"
 
 
@@ -363,21 +388,15 @@ class TruvariBenchSummary(Proc):
         devpars: The parameters to use for the plots.
 
     Requires:
-        - name: r-ggprism
-          check: |
-            {{proc.lang}} -e "library(ggprism)"
-        - name: r-rjson
-          check: |
-            {{proc.lang}} -e "library(rjson)"
-        - name: r-dplyr
-          check: |
-            {{proc.lang}} -e "library(dplyr)"
-        - name: r-ggplot2
-          check: |
-            {{proc.lang}} -e "library(ggplot2)"
-
+        r-ggprism:
+            - check: {{proc.lang}} -e "library(ggprism)"
+        r-rjson:
+            - check: {{proc.lang}} -e "library(rjson)"
+        r-dplyr:
+            - check: {{proc.lang}} -e "library(dplyr)"
+        r-ggplot2:
+            - check: {{proc.lang}} -e "library(ggplot2)"
     """
-
     input = "indirs:files"
     input_data = lambda ch: [list(ch.iloc[:, 0])]
     output = "outdir:dir:truvari_bench.summary"
@@ -411,7 +430,6 @@ class TruvariConsistency(Proc):
             annotations will be added as row annotations.
             Other options see also `biopipen.ns.plot.Heatmap`.
     """
-
     input = "vcfs:files"
     output = (
         "outdir:dir:"

biopipen/ns/web.py

@@ -1,5 +1,4 @@
 """Get data from the web"""
-
 from ..core.proc import Proc
 from ..core.config import config
 
@@ -22,16 +21,11 @@ class Download(Proc):
         ncores: The number of cores to use
 
     Requires:
-        - name: wget
-          message: Only required when envs.tool == "wget"
-          check: |
-            {{proc.envs.wget}} --version
-        - name: aria2c
-          message: Only required when envs.tool == "aria2c"
-          check: |
-            {{proc.envs.aria2c}} --version
+        wget: Only required when envs.tool == "wget"
+            - check: {{proc.envs.wget}} --version
+        aria2c: Only required when envs.tool == "aria2c"
+            - check: {{proc.envs.aria2c}} --version
     """
-
     input = "url"
     output = (
         "outfile:file:"
@@ -66,16 +60,11 @@ class DownloadList(Proc):
         ncores: The number of cores to use
 
     Requires:
-        - name: wget
-          message: Only required when envs.tool == "wget"
-          check: |
-            {{proc.envs.wget}} --version
-        - name: aria2c
-          message: Only required when envs.tool == "aria2c"
-          check: |
-            {{proc.envs.aria2c}} --version
+        wget: Only required when envs.tool == "wget"
+            - check: {{proc.envs.wget}} --version
+        aria2c: Only required when envs.tool == "aria2c"
+            - check: {{proc.envs.aria2c}} --version
     """
-
     input = "urlfile:file"
     output = "outdir:dir:{{in.urlfile | stem}}.downloaded"
     lang = config.lang.python

biopipen/reports/bam/CNAClinic.svelte

@@ -1,5 +1,5 @@
 <script>
-    import { Image } from "@@";
+    import { Image } from "$lib";
 </script>
 
 {% for gwpng in job.out.outdir | glob: "*/*.png" %}

biopipen/reports/bam/CNVpytor.svelte

@@ -1,7 +1,7 @@
 {% from "utils/misc.liq" import table_of_images -%}
 <script>
-    import { Image } from "@@";
-    import { Tabs, Tab, TabContent } from "carbon-components-svelte";
+    import { Image } from "$lib";
+    import { Tabs, Tab, TabContent } from "$ccs";
 </script>
 
 {% for case in envs.cases %}

biopipen/reports/bam/ControlFREEC.svelte

@@ -1,6 +1,6 @@
 {% from "utils/misc.liq" import report_jobs, table_of_images -%}
 <script>
-    import { Image, DataTable } from "@@";
+    import { Image, DataTable } from "$lib";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/cnv/AneuploidyScore.svelte

@@ -1,8 +1,8 @@
 {% from "utils/misc.liq" import report_jobs -%}
 
 <script>
-    import { Image, DataTable } from "@@";
-    import { Tabs, Tab, TabContent, Tile } from "carbon-components-svelte";
+    import { Image, DataTable } from "$lib";
+    import { Tabs, Tab, TabContent, Tile } from "$ccs";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/cnv/AneuploidyScoreSummary.svelte

@@ -1,5 +1,5 @@
 <script>
-    import { Image, DataTable } from "@@";
+    import { Image, DataTable } from "$lib";
 </script>
 
 <h1>Total number of arm-level gains/losses</h1>

biopipen/reports/cnvkit/CNVkitDiagram.svelte

@@ -1,6 +1,6 @@
 {% from "utils/misc.liq" import report_jobs -%}
 <script>
-    import { Image } from "@@";
+    import { Image } from "$lib";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/cnvkit/CNVkitHeatmap.svelte

@@ -1,6 +1,6 @@
 {% from "utils/misc.liq" import report_jobs -%}
 <script>
-    import { Image } from "@@";
+    import { Image } from "$lib";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/cnvkit/CNVkitScatter.svelte

@@ -1,6 +1,6 @@
 {% from "utils/misc.liq" import report_jobs -%}
 <script>
-    import { Image } from "@@";
+    import { Image } from "$lib";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/gsea/FGSEA.svelte

@@ -1,7 +1,7 @@
 {% from "utils/gsea.liq" import fgsea_report -%}
 {% from "utils/misc.liq" import report_jobs -%}
 <script>
-    import { Image, DataTable } from "@@";
+    import { Image, DataTable } from "$lib";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/gsea/GSEA.svelte

@@ -1,8 +1,8 @@
 {% from "utils/misc.liq" import report_jobs -%}
 {% from "utils/gsea.liq" import gsea_report -%}
 <script>
-    import { Image, DataTable } from "@@";
-    import { Tile } from "carbon-components-svelte";
+    import { Image, DataTable } from "$lib";
+    import { Tile } from "$ccs";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/scrna/CellsDistribution.svelte

@@ -1,6 +1,6 @@
 {% from "utils/misc.liq" import report_jobs -%}
 <script>
-    import { Image } from "@@";
+    import { Image } from "$lib";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/scrna/DimPlots.svelte

@@ -1,6 +1,6 @@
 {% from "utils/misc.liq" import table_of_images, report_jobs -%}
 <script>
-    import { Image } from "@@";
+    import { Image } from "$lib";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/scrna/GeneExpressionInvistigation.svelte

@@ -2,7 +2,7 @@
 {% from "utils/misc.liq" import report_jobs, table_of_images -%}
 
 <script>
-    import { Image } from "@@";
+    import { Image } from "$lib";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/scrna/MarkersFinder.svelte

@@ -1,52 +1,55 @@
 {% from "utils/misc.liq" import report_jobs -%}
 <script>
-    import { Image, DataTable } from "@@";
-    import { Tabs, Tab, TabContent } from "carbon-components-svelte";
+    import { Image, DataTable } from "$lib";
+    import { Tabs, Tab, TabContent, InlineNotification } from "$ccs";
 </script>
 
 
 {%- macro report_job(job, h=1) -%}
-{% for casedir in job.out.outdir | glob: "*" %}
-{%  set case = casedir | basename %}
-<h{{h}}>{{case}}</h{{h}}>
-
-<h{{h+1}}>Markers</h{{h+1}}>
-<DataTable
-    src={{ casedir | joinpaths: "markers.txt" | quote }}
-    data={ {{ casedir | joinpaths: "markers.txt" | datatable: sep="\t", nrows=100 }} }
-    />
-
-<h{{h+1}}>Enrichment analysis</h{{h+1}}>
-<Tabs>
-    {% for enrtxt in casedir | as_path | attr: "glob" | call: "Enrichr-*.txt"  %}
-    {%  set db = enrtxt | stem | replace: "Enrichr-", "" %}
-    <Tab label="{{db}}" title="{{db}}" />
-    {% endfor %}
-    <div slot="content">
-        {% for enrtxt in casedir | as_path | attr: "glob" | call: "Enrichr-*.txt" %}
-        {%  set db = enrtxt | stem | replace: "Enrichr-", "" %}
-        <TabContent>
-            <Image src={{casedir | joinpaths: "Enrichr-" + db + ".png" | quote}} />
-            <DataTable
-                src={{ enrtxt | quote }}
-                data={ {{ enrtxt | datatable: sep="\t", nrows=100 }} }
-                />
-        </TabContent>
-        {% endfor %}
-    </div>
-</Tabs>
-
-{% endfor %}
+  {% for casedir in job.out.outdir | glob: "*" %}
+    {% set case = casedir | basename %}
+    <h{{h}}>{{case}}</h{{h}}>
+
+    {% if casedir | joinpaths: "error.txt" | exists %}
+      <InlineNotification
+        hideCloseButton
+        lowContrast
+        kind="warning"
+        subtitle={{ casedir | joinpaths: "error.txt" | read | quote }}
+        />
+    {% else %}
+      <h{{h+1}}>Markers</h{{h+1}}>
+      <DataTable
+          src={{ casedir | joinpaths: "markers.txt" | quote }}
+          data={ {{ casedir | joinpaths: "markers.txt" | datatable: sep="\t", nrows=100 }} }
+          />
+
+      <h{{h+1}}>Enrichment analysis</h{{h+1}}>
+      <Tabs>
+          {% for enrtxt in casedir | glob: "Enrichr-*.txt"  %}
+          {%  set db = enrtxt | stem | replace: "Enrichr-", "" %}
+          <Tab label="{{db}}" title="{{db}}" />
+          {% endfor %}
+          <div slot="content">
+              {% for enrtxt in casedir | glob: "Enrichr-*.txt" %}
+              {%  set db = enrtxt | stem | replace: "Enrichr-", "" %}
+              <TabContent>
+                  <Image src={{casedir | joinpaths: "Enrichr-" + db + ".png" | quote}} />
+                  <DataTable
+                      src={{ enrtxt | quote }}
+                      data={ {{ enrtxt | datatable: sep="\t", nrows=100 }} }
+                      />
+              </TabContent>
+              {% endfor %}
+          </div>
+      </Tabs>
+    {% endif %}
+  {% endfor %}
 {%- endmacro -%}
 
 
 {%- macro head_job(job) -%}
-{% if in.casefile %}
-{%  set name = in.casefile | config: "toml" | attr: "name" %}
-{% else %}
-{%  set name = envs | attr: "name" %}
-{% endif %}
-<h1>{{name | escape}}</h1>
+  <h1>{{job.in.srtobj | stem | escape}}</h1>
 {%- endmacro -%}
 
 {{ report_jobs(jobs, head_job, report_job) }}

biopipen/reports/scrna/ScFGSEA.svelte

@@ -1,15 +1,15 @@
 {% from "utils/gsea.liq" import fgsea_report -%}
 {% from "utils/misc.liq" import report_jobs -%}
 <script>
-    import { Image, DataTable } from "@@";
+    import { Image, DataTable } from "$lib";
 </script>
 
 {%- macro report_job(job, h=1) -%}
 {% for casedir in job.out.outdir | glob: "*" %}
     {%- set case = casedir | basename -%}
     <h{{h}}>{{case}}</h{{h}}>
-    {%- if casedir | joinpaths: "percluster" | as_path | attr: "is_file" | call -%}
-        {%- for cldir in casedir | as_path | attr: "glob" | call: "*" -%}
+    {%- if casedir | joinpaths: "percluster" | isfile -%}
+        {%- for cldir in casedir | glob: "*" -%}
             {%- if basename(cldir) == "percluster" -%}
                 {%- continue -%}
             {%- endif -%}

biopipen/reports/scrna/SeuratClusterStats.svelte

@@ -1,8 +1,8 @@
 {% from "utils/misc.liq" import report_jobs, table_of_images -%}
 {% from_ os import path %}
 <script>
-    import { DataTable, Image } from "@@";
-    import { Tabs, Tab, TabContent } from "carbon-components-svelte";
+    import { DataTable, Image } from "$lib";
+    import { Tabs, Tab, TabContent } from "$ccs";
 </script>
 
 {%- macro report_job(job, h=1) -%}
@@ -112,7 +112,7 @@
 {%- endif -%}
 
 
-{%- if job.out.outdir | joinpaths: "dimplots" | as_path | attr: "is_dir" | call -%}
+{%- if job.out.outdir | joinpaths: "dimplots" | isdir -%}
 <h{{h}}>Dimensional reduction plots</h{{h}}>
 {%-   set dpimgs = job.out.outdir | glob: "dimplots", "*.png" -%}
 {{ table_of_images(dpimgs, caps=[]) }}

biopipen/reports/scrna/SeuratPreparing.svelte

@@ -1,8 +1,8 @@
 {% from "utils/misc.liq" import report_jobs, table_of_images -%}
 {% from_ os import path %}
 <script>
-    import { Image } from "@@";
-    import { Tile } from "carbon-components-svelte";
+    import { Image } from "$lib";
+    import { Tile } from "$ccs";
 </script>
 
 {%- macro report_job(job, h=1) -%}

biopipen/reports/scrna_metabolic_landscape/MetabolicFeaturesIntraSubsets.svelte

@@ -2,7 +2,7 @@
 {% from "utils/gsea.liq" import fgsea_report, gsea_report -%}
 
 <script>
-  import { Image, DataTable } from "@@";
+  import { Image, DataTable } from "$lib";
 </script>
 
 {%- macro report_job(job, h=2) -%}
@@ -12,7 +12,7 @@
     {% for dsdir in groupdir | glob: "*" %}
         <h{{h+1}}>{{ dsdir | basename }}</h{{h+1}}>
         {% if envs.fgsea %}
-            {% if dsdir | joinpaths: "fgsea.txt" | as_path | attr: "is_file" | call %}
+            {% if dsdir | joinpaths: "fgsea.txt" | isfile %}
                 {{ fgsea_report(dsdir, h+2, envs, envs.top) }}
             {% else %}
                 <p>Not enough events.</p>

biopipen/reports/scrna_metabolic_landscape/MetabolicPathwayActivity.svelte

@@ -1,7 +1,7 @@
 {% from "utils/misc.liq" import report_jobs -%}
 
 <script>
-    import { Image } from "@@";
+    import { Image } from "$lib";
 </script>
 
 <h1>Introduction</h1>

biopipen/reports/scrna_metabolic_landscape/MetabolicPathwayHeterogeneity.svelte

@@ -1,7 +1,7 @@
 {% from "utils/misc.liq" import report_jobs, table_of_images -%}
 
 <script>
-    import { Image } from "@@";
+    import { Image } from "$lib";
 </script>
 
 {%- macro report_job(job, h=2) -%}