Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

update reporting notebook #34

Open
wants to merge 1 commit into
base: latest
Choose a base branch
from
Open

update reporting notebook #34

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
79 changes: 77 additions & 2 deletions genome_grist/notebooks/report-sample.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@
},
"outputs": [],
"source": [
"sample_id='SRR606249'\n",
"sample_id='SRR1976948'\n",
"#sample_id = 'p8808mo9'\n",
"#sample_id = 'p8808mo11'\n",
"outdir = 'outputs'\n"
Expand Down Expand Up @@ -321,7 +321,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## fig 8: correlation between hashes and mapping rates"
"## fig 8: correlation between hash abundance and mapping rates"
]
},
{
Expand All @@ -340,6 +340,81 @@
"pylab.title(f'{sample_id}: gather f_match vs leftover mapping bp covered')\n",
"pylab.legend(loc='lower right')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## fig 9: fraction of genome covered by mapping"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pylab.figure(num=None, figsize=(10, 10))\n",
"\n",
"pylab.plot(left_df.covered_bp / left_df[\"genome bp\"] * 100, left_df.iloc[::-1].index, 'bo', label='mapped bp to this genome')\n",
"pylab.plot(all_df.covered_bp / all_df[\"genome bp\"] * 100, left_df.iloc[::-1].index, 'r.', label='mapped bp to this genome')\n",
"\n",
"pylab.plot(((all_df.covered_bp - left_df.covered_bp) / all_df[\"genome bp\"]) * 100, left_df.iloc[::-1].index, 'b-', label='diff')\n",
"\n",
"#pylab.plot(gather_df.intersect_bp / left_df[\"genome bp\"] * 100, gather_df.iloc[::-1].index, 'gx', label='hashes classified to this species')\n",
"#pylab.plot(gather_df.unique_intersect_bp / left_df[\"genome bp\"] * 100, gather_df.iloc[::-1].index, 'ro', label='hashes classified for this genome')\n",
"\n",
"positions = list(gather_df.index)\n",
"labels = list(reversed(names_df.ncbi_tax_name))\n",
"pylab.yticks(positions, labels, fontsize='small')\n",
"\n",
"pylab.xlabel('percent genome covered by reads')\n",
"pylab.legend(loc='lower right')\n",
"pylab.title(f'{sample_id}: mapped bp, all & leftover')\n",
"pylab.tight_layout()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## fig 10: fraction of genome covered by hashes"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"pylab.figure(num=None, figsize=(10, 10))\n",
"\n",
"#pylab.plot(left_df.covered_bp / left_df[\"genome bp\"] * 100, left_df.iloc[::-1].index, 'bo') #, label='mapped bp to this genome')\n",
"#pylab.plot(all_df.covered_bp / all_df[\"genome bp\"] * 100, left_df.iloc[::-1].index, 'r.') #, label='mapped bp to this genome')\n",
"\n",
"pylab.plot(gather_df.intersect_bp / left_df[\"genome bp\"] * 100, gather_df.iloc[::-1].index, 'bo', label='hashes classified to this species')\n",
"pylab.plot(gather_df.unique_intersect_bp / left_df[\"genome bp\"] * 100, gather_df.iloc[::-1].index, 'r.', label='hashes classified for this genome')\n",
"\n",
"pylab.plot((gather_df.intersect_bp - gather_df.unique_intersect_bp) / left_df[\"genome bp\"] * 100, gather_df.iloc[::-1].index, 'b-', label='hashes classified for this genome')\n",
"\n",
"positions = list(gather_df.index)\n",
"labels = list(reversed(names_df.ncbi_tax_name))\n",
"pylab.yticks(positions, labels, fontsize='small')\n",
"\n",
"pylab.xlabel('percent genome covered by reads')\n",
"pylab.legend(loc='lower right')\n",
"pylab.title(f'{sample_id}: unique vs all hashes')\n",
"pylab.tight_layout()\n",
"\n",
"pylab.savefig(f'/tmp/gather-{sample_id}.pdf')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
Expand Down