From f5e4693bd88005d53135b3479d36a1b9f97710b6 Mon Sep 17 00:00:00 2001
From: Lukas Heumos <lukas.heumos@posteo.net>
Date: Wed, 9 Aug 2023 03:40:52 -0700
Subject: [PATCH] New API (#6)

* :sparkles: Cache pipeline execution

* :art: Don't run pipeline from NB

* :art: Run pipeline from NB

* :art: Remove non-NB run again

* :art: Add late tree

* :art: Cache different folder

* :art: Half timeout

* :art: Cache attempt

* :art: Timeout

* :art: Refactor

* :art: Remove storage root

Signed-off-by: zethson <lukas.heumos@posteo.net>

---------

Signed-off-by: zethson <lukas.heumos@posteo.net>
---
 .github/workflows/build.yml   |  6 ++---
 docs/guide/bulk_rna_seq.ipynb | 49 ++++++++++++++++++-----------------
 2 files changed, 28 insertions(+), 27 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index d4f2924..a96077b 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -16,7 +16,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.9"]
-    timeout-minutes: 90
+    timeout-minutes: 50
 
     steps:
       - name: Checkout main
@@ -46,8 +46,8 @@ jobs:
       - name: Cache Nextflow output
         uses: actions/cache@v2
         with:
-          path: rna-seq-results
-          key: ${{ runner.os }}-nextflow
+          path: docs/guide/nextflow_rna_seq/rna-seq-results
+          key: ${{ runner.os }}-nextflow-rna-seq-results
 
       - uses: actions/cache@v3
         with:
diff --git a/docs/guide/bulk_rna_seq.ipynb b/docs/guide/bulk_rna_seq.ipynb
index 82ebb91..79d249d 100644
--- a/docs/guide/bulk_rna_seq.ipynb
+++ b/docs/guide/bulk_rna_seq.ipynb
@@ -79,7 +79,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "lb.settings.species = \"human\""
+    "lb.settings.species = \"saccharomyces cerevisiae\""
    ]
   },
   {
@@ -150,9 +150,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "input_fastqs_file = ln.File.from_dir(\n",
-    "    \"test-datasets/testdata/GSE110004/\", storage_root=Path(\".\")\n",
-    ")\n",
+    "input_fastqs_file = ln.File.from_dir(\"test-datasets/testdata/GSE110004/\")\n",
     "sample_sheet_file = ln.File(\"test-datasets/samplesheet/v3.10/samplesheet_test.csv\")\n",
     "ln.save(input_fastqs_file)\n",
     "ln.save(sample_sheet_file)"
@@ -173,7 +171,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "run = ln.Run.select(created_by_id=\"DzTjkKse\").one()\n",
+    "run = ln.Run.filter(created_by_id=\"DzTjkKse\").one()\n",
     "run"
    ]
   },
@@ -218,7 +216,11 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "2219c55e",
-   "metadata": {},
+   "metadata": {
+    "jupyter": {
+     "outputs_hidden": true
+    }
+   },
    "outputs": [],
    "source": [
     "!nextflow run nf-core/rnaseq -r 3.11.2 -profile test,docker --outdir rna-seq-results -name $LAMINDB_RUN_ID -resume"
@@ -239,9 +241,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "multiqc_results = ln.File.from_dir(\n",
-    "    \"rna-seq-results/multiqc/\", storage_root=Path(\".\"), run=run\n",
-    ")\n",
+    "multiqc_results = ln.File.from_dir(\"rna-seq-results/multiqc/\", run=run)\n",
     "ln.save(multiqc_results)"
    ]
   },
@@ -290,24 +290,24 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c1a58047-0c25-4632-b355-69610c6176f3",
+   "id": "b8ed9118-1fd1-47a7-a825-736f78a7d111",
    "metadata": {},
    "outputs": [],
    "source": [
-    "salmon_gene_counts_table = ln.File(\n",
-    "    \"rna-seq-results/salmon/salmon.merged.gene_counts.tsv\", run=run\n",
-    ")\n",
-    "ln.save(salmon_gene_counts_table)"
+    "salmon_gene_counts_table_df = pd.read_csv(\n",
+    "    \"rna-seq-results/salmon/salmon.merged.gene_counts.tsv\", sep=\"\\t\"\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4f8680e2-7c58-4822-94dd-f3ee0caeb5bc",
+   "id": "c1a58047-0c25-4632-b355-69610c6176f3",
    "metadata": {},
    "outputs": [],
    "source": [
-    "gene_counts_df = pd.read_csv(salmon_gene_counts_table.stage(), sep=\"\\t\")"
+    "salmon_gene_counts_table = ln.File.from_df(salmon_gene_counts_table_df, run=run)\n",
+    "ln.save(salmon_gene_counts_table)"
    ]
   },
   {
@@ -321,23 +321,24 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "0dad135a-4b32-4902-95ff-4585c2ab99dc",
+   "id": "e655b46d-2bee-404e-9ecc-0d219e97d976",
    "metadata": {},
    "outputs": [],
    "source": [
-    "feature_set_genes = ln.FeatureSet.from_values(\n",
-    "    gene_counts_df[\"gene_name\"], lb.Gene.symbol\n",
+    "genes = ln.FeatureSet.from_values(\n",
+    "    salmon_gene_counts_table_df[\"gene_name\"], lb.Gene.symbol\n",
     ")\n",
-    "feature_set_genes.save()\n",
-    "salmon_gene_counts_table.feature_sets.add(feature_set_genes)"
+    "salmon_gene_counts_table.features.add_feature_set(genes, slot=\"rna\")"
    ]
   },
   {
-   "cell_type": "markdown",
-   "id": "b0bfe4f5-5566-423d-9a1e-6796c8f98a77",
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ba83bfee-5cb8-4520-9a32-0deccd47ff34",
    "metadata": {},
+   "outputs": [],
    "source": [
-    "The dataset contains yeast samples and our species is set to human. Hence, a lot of gene records are being created. Bionty will soon also support yeast genes."
+    "salmon_gene_counts_table.describe()"
    ]
   },
   {