diff --git a/workflows/benchmark/benchmark_helpers/benchmark_helpers/harvest.py b/workflows/benchmark/benchmark_helpers/benchmark_helpers/harvest.py index 257e0530e..9b7e21c67 100644 --- a/workflows/benchmark/benchmark_helpers/benchmark_helpers/harvest.py +++ b/workflows/benchmark/benchmark_helpers/benchmark_helpers/harvest.py @@ -59,6 +59,9 @@ def load_contig_lengths(contig_fasta): lines = cleanup.enter_context(open(contig_fasta)) cur = None for line in lines: + if "ASSEMBLY FAILED" in line: + return {} + if line.startswith(">"): if cur is not None: lengths[cur[0]] = cur[1] diff --git a/workflows/benchmark/notebooks/long-read-mngs-benchmarks.ipynb b/workflows/benchmark/notebooks/long-read-mngs-benchmarks.ipynb index 37746eb8e..517beae3f 100644 --- a/workflows/benchmark/notebooks/long-read-mngs-benchmarks.ipynb +++ b/workflows/benchmark/notebooks/long-read-mngs-benchmarks.ipynb @@ -1,17 +1,10 @@ { "cells": [ { - "attachments": { - "IDseq_logo_mono.png": { - "image/png": "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" - } - }, "cell_type": "markdown", "metadata": {}, "source": [ - "![IDseq_logo_mono.png](attachment:IDseq_logo_mono.png)\n", - "\n", - "# long-read-mngs benchmark" + "# CZ ID long-read-mngs benchmark" ] }, { diff --git a/workflows/benchmark/notebooks/short-read-mngs-benchmarks.ipynb b/workflows/benchmark/notebooks/short-read-mngs-benchmarks.ipynb index 2201b2440..1f4d11868 100644 --- a/workflows/benchmark/notebooks/short-read-mngs-benchmarks.ipynb +++ b/workflows/benchmark/notebooks/short-read-mngs-benchmarks.ipynb @@ -1,17 +1,10 @@ { "cells": [ { - "attachments": { - "IDseq_logo_mono.png": { - "image/png": "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" - } - }, "cell_type": "markdown", "metadata": {}, "source": [ - "![IDseq_logo_mono.png](attachment:IDseq_logo_mono.png)\n", - "\n", - "# short-read-mngs benchmark" + "# CZ ID short-read-mngs benchmark" ] }, { @@ -57,6 +50,7 @@ "import seaborn as sns\n", "import pandas as pd\n", "import matplotlib.pyplot as plt\n", + "import scipy\n", "from IPython.display import display, HTML" ] }, @@ -243,27 +237,23 @@ "metadata": {}, "outputs": [], "source": [ - "import scipy\n", - "correlations = joined[joined[\"max_rPM\"] >= min_rPM].fillna(0)\n", - "res = scipy.stats.spearmanr(correlations[\"max_rPM\"], correlations[\"max_rPM.REF\"])" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "fig, ax = plt.subplots(1, 2, figsize=(12,6))\n", - "fig.suptitle(f\"Correlation plots: Spearman's R {round(res.correlation, 2)}\")\n", - "sns.scatterplot(ax=ax[0], data=correlations, x=\"max_rPM\", y=\"max_rPM.REF\")\n", - "ax[0].set_title(\"Raw scatterplot\")\n", + "if ref_data: \n", + " correlations = joined[joined[\"max_rPM\"] >= min_rPM].fillna(0)\n", + " res = scipy.stats.spearmanr(correlations[\"max_rPM\"], correlations[\"max_rPM.REF\"])\n", + " correlation = round(res.correlation, 2)\n", + " with open(\"correlation.txt\", \"w\") as f:\n", + " f.write(str(correlation))\n", + "\n", + " fig, ax = plt.subplots(1, 2, figsize=(12,6))\n", + " fig.suptitle(f\"Correlation plots: Spearman's R {correlation}\")\n", + " sns.scatterplot(ax=ax[0], data=correlations, x=\"max_rPM\", y=\"max_rPM.REF\")\n", + " ax[0].set_title(\"Raw scatterplot\")\n", "\n", - "sns.scatterplot(ax=ax[1], data=correlations[[\"max_rPM\", \"max_rPM.REF\"]]+1, x=\"max_rPM\", y=\"max_rPM.REF\") # here the logged values must be +1 to avoid breaking 0 values\n", - "ax[1].set_title(\"Logged scatterplot\")\n", - "ax[1].set_xscale('log')\n", - "ax[1].set_yscale('log')\n", - "plt.show()" + " sns.scatterplot(ax=ax[1], data=correlations[[\"max_rPM\", \"max_rPM.REF\"]]+1, x=\"max_rPM\", y=\"max_rPM.REF\") # here the logged values must be +1 to avoid breaking 0 values\n", + " ax[1].set_title(\"Logged scatterplot\")\n", + " ax[1].set_xscale('log')\n", + " ax[1].set_yscale('log')\n", + " plt.show()" ] }, { diff --git a/workflows/benchmark/short-read-mngs-benchmark.wdl b/workflows/benchmark/short-read-mngs-benchmark.wdl index 0fa5ee206..3dd03d5ca 100644 --- a/workflows/benchmark/short-read-mngs-benchmark.wdl +++ b/workflows/benchmark/short-read-mngs-benchmark.wdl @@ -130,6 +130,7 @@ workflow short_read_mngs_benchmark { File preprocessed_nr = preprocess_taxa_nr.preprocessed_taxa File benchmark_notebook = test_notebook.benchmark_notebook File benchmark_html = test_notebook.benchmark_html + File? correlation = test_notebook.correlation File? step_counts_run_1_json = read_step_counts_run_1.step_counts File? step_counts_run_2_json = read_step_counts_run_2.step_counts File? step_count_tsv = merge_step_counts.step_count_tsv @@ -224,6 +225,7 @@ task notebook { File combined = "combined_taxa.json" File benchmark_notebook = "short-read-mngs-benchmarks.ipynb" File benchmark_html = "short-read-mngs-benchmarks.html" + File? correlation = "correlation.txt" } runtime { docker: docker_image_id