Update documentation

cumc · Aug 11, 2023 · ef5f867 · ef5f867
1 parent 8d26c42
commit ef5f867
Show file tree

Hide file tree

Showing 8 changed files with 373 additions and 187 deletions.
diff --git a/_sources/code/data_preprocessing/genotype/GWAS_QC.ipynb b/_sources/code/data_preprocessing/genotype/GWAS_QC.ipynb
diff --git a/_sources/code/data_preprocessing/genotype/VCF_QC.ipynb b/_sources/code/data_preprocessing/genotype/VCF_QC.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "damaged-trunk",
+   "id": "scientific-inspiration",
    "metadata": {
     "kernel": "SoS",
     "tags": []
@@ -13,7 +13,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "handmade-loading",
+   "id": "northern-primary",
    "metadata": {
     "kernel": "SoS"
    },
@@ -23,7 +23,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "detailed-specialist",
+   "id": "competitive-enemy",
    "metadata": {
     "kernel": "SoS"
    },
@@ -46,7 +46,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "auburn-formation",
+   "id": "dress-influence",
    "metadata": {
     "kernel": "SoS"
    },
@@ -69,7 +69,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "presidential-hello",
+   "id": "banner-portrait",
    "metadata": {
     "kernel": "SoS",
     "tags": []
@@ -94,7 +94,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "internal-thomson",
+   "id": "patient-catering",
    "metadata": {
     "kernel": "SoS"
    },
@@ -112,7 +112,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "noticed-entry",
+   "id": "inclusive-reconstruction",
    "metadata": {
     "kernel": "SoS"
    },
@@ -134,28 +134,28 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ignored-journalism",
+   "id": "wicked-teens",
    "metadata": {
     "kernel": "SoS"
    },
    "source": [
     "The MWE was used as follows:\n",
     "\n",
     "```\n",
-    "sos run pipeline/VCF_QC.ipynb rename_chrs \\\n",
+    "sos run VCF_QC.ipynb rename_chrs \\\n",
     "    --genoFile reference_data/00-All.vcf.gz \\\n",
     "    --cwd reference_data --container bioinfo.sif\n",
     "```\n",
     "\n",
     "```\n",
-    "sos run pipeline/VCF_QC.ipynb dbsnp_annotate \\\n",
+    "sos run VCF_QC.ipynb dbsnp_annotate \\\n",
     "    --genoFile reference_data/00-All.add_chr.vcf.gz \\\n",
     "    --cwd reference_data --container bioinfo.sif\n",
     "```\n",
     "\n",
     "\n",
     "```\n",
-    "sos run pipeline/VCF_QC.ipynb qc    \\\n",
+    "sos run VCF_QC.ipynb qc    \\\n",
     "    --genoFile data/MWE/MWE_genotype.vcf     \\\n",
     "    --dbsnp-variants data/reference_data/00-All.add_chr.variants.gz  \\\n",
     "    --reference-genome data/reference_data/GRCh38_full_analysis_set_plus_decoy_hla.noALT_noHLA_noDecoy_ERCC.fasta   \\\n",
@@ -165,7 +165,7 @@
     "To run in parallel for all genotype data listed in `mwe_genotype_list`,\n",
     "\n",
     "```\n",
-    "sos run pipeline/VCF_QC.ipynb qc    \\\n",
+    "sos run VCF_QC.ipynb qc    \\\n",
     "    --genoFile data/mwe/mwe_genotype_list    \\\n",
     "    --dbsnp-variants data/reference_data/00-All.add_chr.variants.gz  \\\n",
     "    --reference-genome data/reference_data/GRCh38_full_analysis_set_plus_decoy_hla.noALT_noHLA_noDecoy_ERCC.fasta   \\\n",
@@ -177,7 +177,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "fluid-ivory",
+   "id": "ranging-kansas",
    "metadata": {
     "kernel": "SoS"
    },
@@ -192,7 +192,7 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "floppy-aluminum",
+   "id": "commercial-wagon",
    "metadata": {
     "kernel": "SoS"
    },
@@ -211,7 +211,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "choice-round",
+   "id": "otherwise-gnome",
    "metadata": {
     "kernel": "SoS"
    },
@@ -222,7 +222,7 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "finite-gauge",
+   "id": "tribal-product",
    "metadata": {
     "kernel": "SoS"
    },
@@ -241,7 +241,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "conventional-communications",
+   "id": "wrapped-indie",
    "metadata": {
     "kernel": "SoS"
    },
@@ -252,7 +252,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "chronic-scholar",
+   "id": "thorough-microwave",
    "metadata": {
     "kernel": "SoS"
    },
@@ -264,7 +264,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "frozen-commercial",
+   "id": "approximate-patient",
    "metadata": {
     "kernel": "SoS"
    },
@@ -275,7 +275,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "digital-member",
+   "id": "coupled-pipeline",
    "metadata": {
     "kernel": "Bash",
     "tags": []
@@ -372,7 +372,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "statistical-berkeley",
+   "id": "square-smoke",
    "metadata": {
     "kernel": "Bash"
    },
@@ -383,7 +383,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "meaningful-marketplace",
+   "id": "thrown-wheat",
    "metadata": {
     "kernel": "SoS"
    },
@@ -463,7 +463,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "psychological-correction",
+   "id": "paperback-requirement",
    "metadata": {
     "kernel": "SoS",
     "tags": []
@@ -479,15 +479,15 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "electrical-breeding",
+   "id": "brown-national",
    "metadata": {
     "kernel": "SoS"
    },
    "outputs": [],
    "source": [
     "[rename_chrs: provides = '{filename}.add_chr.vcf.gz']\n",
     "parameter: walltime = '24h'\n",
-    "# This file can be downloaded from https://ftp.ncbi.nlm.nih.gov/snp/organisms//human_9606_b150_GRCh38p7/VCF/00-All.vcf.gz.\n",
+    "# This file can be downloaded from https://ftp.ncbi.nlm.nih.gov/snp/organisms/human_9606_b150_GRCh38p7/VCF/00-All.vcf.gz.\n",
     "input: f'{filename}.vcf.gz'\n",
     "output: f'{_input:nn}.add_chr.vcf.gz'\n",
     "task: trunk_workers = 1, trunk_size = job_size, walltime = walltime, mem = mem, cores = numThreads, tags = f'{step_name}_{_output:bn}'\n",
@@ -501,7 +501,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "hydraulic-robert",
+   "id": "scenic-chart",
    "metadata": {
     "kernel": "SoS"
    },
@@ -532,7 +532,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "above-thunder",
+   "id": "increased-complaint",
    "metadata": {
     "kernel": "SoS"
    },
@@ -545,7 +545,7 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "integral-equity",
+   "id": "neither-liberty",
    "metadata": {
     "kernel": "SoS"
    },
@@ -594,7 +594,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "after-pendant",
+   "id": "needed-mitchell",
    "metadata": {
     "kernel": "SoS"
    },
@@ -605,7 +605,7 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "infrared-composition",
+   "id": "southeast-garlic",
    "metadata": {
     "kernel": "SoS"
    },
@@ -671,7 +671,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "scheduled-alcohol",
+   "id": "driven-mills",
    "metadata": {
     "kernel": "SoS"
    },
@@ -686,7 +686,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "vocal-legislature",
+   "id": "quick-windsor",
    "metadata": {
     "kernel": "SoS"
    },
@@ -715,7 +715,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "professional-brunswick",
+   "id": "still-basketball",
    "metadata": {
     "kernel": "SoS"
    },

diff --git a/_sources/code/data_preprocessing/phenotype/gene_annotation.ipynb b/_sources/code/data_preprocessing/phenotype/gene_annotation.ipynb
@@ -914,7 +914,7 @@
      "sos"
     ]
    ],
-   "version": "0.24.1"
+   "version": "0.24.0"
   }
  },
  "nbformat": 4,