From eac69c497fdb1d135ad2e5258dbb05f352eb7a5b Mon Sep 17 00:00:00 2001 From: Sanjay C Nagi Date: Mon, 24 Jul 2023 11:56:44 +0100 Subject: [PATCH] edits --- docs/rna-seq-pop-docs/notebooks/installation.ipynb | 6 ++++++ workflow/envs/pythonGenomics.yaml | 1 + workflow/notebooks/counts-qc.ipynb | 8 ++++---- workflow/notebooks/windowed-selection.ipynb | 4 ++-- 4 files changed, 13 insertions(+), 6 deletions(-) diff --git a/docs/rna-seq-pop-docs/notebooks/installation.ipynb b/docs/rna-seq-pop-docs/notebooks/installation.ipynb index 26d2630..8a5a270 100644 --- a/docs/rna-seq-pop-docs/notebooks/installation.ipynb +++ b/docs/rna-seq-pop-docs/notebooks/installation.ipynb @@ -42,6 +42,12 @@ "\n", "When we run RNA-Seq-Pop, it is important to use the `--use-conda` directive - this will automatically install all necessary packages into isolated software environments, so we do not have to install any other dependencies.\n", "\n", + "Please also ensure your conda has channel priorities set to 'flexible', otherwise, conda may throw up errors when installing packages. You can do this with the following command:\n", + "\n", + "```\n", + "conda config --set channel_priority flexible\n", + "```\n", + "\n", "#### Testing the setup\n", "\n", "To test whether RNA-Seq-Pop is configured correctly, from the root directory you can perform a dry-run on the test dataset, with the following command:\n", diff --git a/workflow/envs/pythonGenomics.yaml b/workflow/envs/pythonGenomics.yaml index 128e2f0..b5c4d1c 100644 --- a/workflow/envs/pythonGenomics.yaml +++ b/workflow/envs/pythonGenomics.yaml @@ -259,5 +259,6 @@ dependencies: - zstd=1.5.2=hfc55251_7 - papermill - ipykernel + - plotly - pip: - wand diff --git a/workflow/notebooks/counts-qc.ipynb b/workflow/notebooks/counts-qc.ipynb index f8431de..e065aff 100644 --- a/workflow/notebooks/counts-qc.ipynb +++ b/workflow/notebooks/counts-qc.ipynb @@ -57,7 +57,7 @@ "import pandas as pd \n", "import plotly.express as px\n", "\n", - "total_counts = pd.read_csv(\"results/quant/countStatistics.tsv\", sep=\"\\t\").rename(columns={'Sample':'sampleID'})\n", + "total_counts = pd.read_csv(\"results/counts/countStatistics.tsv\", sep=\"\\t\").rename(columns={'Sample':'sampleID'})\n", "metadata = pd.read_csv(metadata_path, sep=\"\\t\")\n", "\n", "total_counts = total_counts.merge(metadata, how='left')" @@ -2885,7 +2885,7 @@ } ], "source": [ - "map_df = pd.read_csv(\"results/quant/KallistoQuantSummary.tsv\", sep=\"\\t\").rename(columns={'sample':'sampleID'})\n", + "map_df = pd.read_csv(\"results/counts/KallistoQuantSummary.tsv\", sep=\"\\t\").rename(columns={'sample':'sampleID'})\n", "map_df = map_df.merge(metadata)\n", "px.bar(map_df,\n", " x='sampleID', \n", @@ -2927,7 +2927,7 @@ ], "source": [ "from wand.image import Image as WImage\n", - "img = WImage(filename='results/plots/heatmap_correlations.pdf')\n", + "img = WImage(filename='results/counts/heatmap_correlations.pdf')\n", "img" ] }, @@ -2963,7 +2963,7 @@ ], "source": [ "from wand.image import Image as WImage\n", - "img = WImage(filename='results/plots/PCA.pdf')\n", + "img = WImage(filename='results/counts/PCA.pdf')\n", "img" ] } diff --git a/workflow/notebooks/windowed-selection.ipynb b/workflow/notebooks/windowed-selection.ipynb index 767424a..72ab15b 100644 --- a/workflow/notebooks/windowed-selection.ipynb +++ b/workflow/notebooks/windowed-selection.ipynb @@ -122,7 +122,7 @@ " ylim=1, \n", " save=True)\n", " \n", - " fig = px.express(x=FstArray, y=midpoint, title=f'Fst {cohortNoSpaceText} | {contig}')\n", + " fig = px.line(x=FstArray, y=midpoint, title=f'Fst {cohortNoSpaceText} | {contig}')\n", " fig.show()\n", " \n", " #### Population Branch Statistic (PBS) in windows ####\n", @@ -157,7 +157,7 @@ " ylim=0.5, \n", " save=True)\n", " \n", - " fig = px.express(x=pbsArray, y=midpoint, title=f'PBS {cohortNoSpaceText} | {contig}')\n", + " fig = px.line(x=pbsArray, y=midpoint, title=f'PBS {cohortNoSpaceText} | {contig}')\n", " fig.show()" ] }