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

ENH: allow FeatureData[MAG] as input to evaluate_busco action #151

Closed
wants to merge 11 commits into from
Closed

ENH: allow FeatureData[MAG] as input to evaluate_busco action #151

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
44027d6
Add new type and if clause in _run_busco
Sann5 Apr 5, 2024
b7812d5
typo
Sann5 Apr 5, 2024
dc7a995
Dynamically assign title to rendered graph.
Sann5 Apr 5, 2024
ea82d57
same as before
Sann5 Apr 5, 2024
a0fe60d
Typo un index.
Sann5 Apr 8, 2024
742da65
Fix zip file for feature data input
Sann5 Apr 8, 2024
f615a81
Fix old test becasue onf new header
Sann5 Apr 8, 2024
20e0271
Added test for rendered plot with FeatureData
Sann5 Apr 8, 2024
32bef30
Added test for adjustments in _run_busco
Sann5 Apr 8, 2024
eb15f2f
adjust test for the zipfile
Sann5 Apr 8, 2024
9364ea8
Merge branch 'main' into busco_w_feature_data_iss_111
Sann5 Apr 8, 2024
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
2 changes: 1 addition & 1 deletion q2_moshpit/assets/busco/index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ <h5 class="card-header">Plot description</h5>
>
<a
class="btn btn-outline-secondary"
href="all_batch_summeries.csv"
href="all_batch_summaries.csv"
>BUSCO batch summary for all samples (csv)</a
>
<a class="btn btn-outline-secondary" href="BUSCO_plots.zip"
Expand Down
4 changes: 3 additions & 1 deletion q2_moshpit/busco/busco.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,17 +10,19 @@
import os
import tempfile
import q2_moshpit.busco.utils
from typing import Union
from q2_moshpit.busco.utils import (
_parse_busco_params,
_render_html,
)
from q2_moshpit._utils import _process_common_input_params
from q2_types.per_sample_sequences._format import MultiMAGSequencesDirFmt
from q2_types.feature_data_mag import MAGSequencesDirFmt


def evaluate_busco(
output_dir: str,
bins: MultiMAGSequencesDirFmt,
bins: Union[MultiMAGSequencesDirFmt, MAGSequencesDirFmt],
mode: str = "genome",
lineage_dataset: str = None,
augustus: bool = False,
Expand Down
4 changes: 4 additions & 0 deletions q2_moshpit/busco/tests/data/all_batch_summaries_FeatureData.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
Input_file,Dataset,Complete,Single,Duplicated,Fragmented,Missing,n_markers,Scaffold N50,Contigs N50,Percent gaps,Number of scaffolds,sample_id
67392c6c-9f45-4c84-85f5-ae0bfc668892.fasta,bacteria_odb10,97.6,96.8,0.8,0.8,1.6,124,170295,170295,0.000%,27,data
67123d05-b5ae-4a53-873b-727952881899.fasta,bacteria_odb10,97.6,96.0,1.6,1.6,0.8,124,109922,109922,0.000%,65,data
311112c9-7f8b-460c-9cad-3864af3148c2.fasta,bacteria_odb10,97.6,96.0,1.6,1.6,0.8,124,111744,111744,0.000%,127,data
0 ...ta/busco_output/sample1/batch_summary.txt → ...output_FeatureData/data/batch_summary.txt
View file
Open in desktop
File renamed without changes.
0 ...ta/busco_output/sample2/batch_summary.txt → ...tput_SampleData/sample1/batch_summary.txt
View file
Open in desktop
File renamed without changes.
0 ...ta/busco_output/sample3/batch_summary.txt → ...tput_SampleData/sample2/batch_summary.txt
View file
Open in desktop
File renamed without changes.
Empty file added q2_moshpit/busco/tests/data/busco_output_SampleData/sample3/batch_summary.txt
View file
Open in desktop
Empty file.
3 changes: 2 additions & 1 deletion q2_moshpit/busco/tests/data/plot_as_dict.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -463,7 +463,8 @@
"facet": {
"row": {
"field": "sample_id",
"title": "Sample ID / MAG ID",
"header": {"labelFontSize": 15},
"title": "Sample ID and MAG ID",
"type": "nominal"
}
},
Expand Down
350 changes: 350 additions & 0 deletions q2_moshpit/busco/tests/data/plot_as_dict_FeatureData.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,350 @@
{
"config": {
"axis": {
"labelFontSize": 17,
"titleFontSize": 20
},
"header": {
"labelFontSize": 17,
"titleFontSize": 20
},
"legend": {
"labelFontSize": 17,
"titleFontSize": 20
},
"view": {
"continuousHeight": 300,
"continuousWidth": 300
}
},
"datasets": {
"data-8eeb27a58f5796f75448a5d3d8f81d69": [
{
"contigs_n50": 170295,
"mag_id": "67392c6c-9f45-4c84-85f5-ae0bfc668892",
"number_of_scaffolds": 27,
"percent_gaps": 0.0,
"sample_id": "data",
"scaffold_n50": 170295
},
{
"contigs_n50": 109922,
"mag_id": "67123d05-b5ae-4a53-873b-727952881899",
"number_of_scaffolds": 65,
"percent_gaps": 0.0,
"sample_id": "data",
"scaffold_n50": 109922
},
{
"contigs_n50": 111744,
"mag_id": "311112c9-7f8b-460c-9cad-3864af3148c2",
"number_of_scaffolds": 127,
"percent_gaps": 0.0,
"sample_id": "data",
"scaffold_n50": 111744
}
],
"data-aa27db16b89ba99bd435a50e28f5712a": [
{
"BUSCO_percentage": 96.8,
"category": "single",
"dataset": "bacteria_odb10",
"fracc_markers": "~120/124",
"mag_id": "67392c6c-9f45-4c84-85f5-ae0bfc668892",
"n_markers": 124,
"order": 1,
"sample_id": "data"
},
{
"BUSCO_percentage": 96.0,
"category": "single",
"dataset": "bacteria_odb10",
"fracc_markers": "~119/124",
"mag_id": "67123d05-b5ae-4a53-873b-727952881899",
"n_markers": 124,
"order": 1,
"sample_id": "data"
},
{
"BUSCO_percentage": 96.0,
"category": "single",
"dataset": "bacteria_odb10",
"fracc_markers": "~119/124",
"mag_id": "311112c9-7f8b-460c-9cad-3864af3148c2",
"n_markers": 124,
"order": 1,
"sample_id": "data"
},
{
"BUSCO_percentage": 0.8,
"category": "duplicated",
"dataset": "bacteria_odb10",
"fracc_markers": "~1/124",
"mag_id": "67392c6c-9f45-4c84-85f5-ae0bfc668892",
"n_markers": 124,
"order": 2,
"sample_id": "data"
},
{
"BUSCO_percentage": 1.6,
"category": "duplicated",
"dataset": "bacteria_odb10",
"fracc_markers": "~2/124",
"mag_id": "67123d05-b5ae-4a53-873b-727952881899",
"n_markers": 124,
"order": 2,
"sample_id": "data"
},
{
"BUSCO_percentage": 1.6,
"category": "duplicated",
"dataset": "bacteria_odb10",
"fracc_markers": "~2/124",
"mag_id": "311112c9-7f8b-460c-9cad-3864af3148c2",
"n_markers": 124,
"order": 2,
"sample_id": "data"
},
{
"BUSCO_percentage": 0.8,
"category": "fragmented",
"dataset": "bacteria_odb10",
"fracc_markers": "~1/124",
"mag_id": "67392c6c-9f45-4c84-85f5-ae0bfc668892",
"n_markers": 124,
"order": 3,
"sample_id": "data"
},
{
"BUSCO_percentage": 1.6,
"category": "fragmented",
"dataset": "bacteria_odb10",
"fracc_markers": "~2/124",
"mag_id": "67123d05-b5ae-4a53-873b-727952881899",
"n_markers": 124,
"order": 3,
"sample_id": "data"
},
{
"BUSCO_percentage": 1.6,
"category": "fragmented",
"dataset": "bacteria_odb10",
"fracc_markers": "~2/124",
"mag_id": "311112c9-7f8b-460c-9cad-3864af3148c2",
"n_markers": 124,
"order": 3,
"sample_id": "data"
},
{
"BUSCO_percentage": 1.6,
"category": "missing",
"dataset": "bacteria_odb10",
"fracc_markers": "~2/124",
"mag_id": "67392c6c-9f45-4c84-85f5-ae0bfc668892",
"n_markers": 124,
"order": 4,
"sample_id": "data"
},
{
"BUSCO_percentage": 0.8,
"category": "missing",
"dataset": "bacteria_odb10",
"fracc_markers": "~1/124",
"mag_id": "67123d05-b5ae-4a53-873b-727952881899",
"n_markers": 124,
"order": 4,
"sample_id": "data"
},
{
"BUSCO_percentage": 0.8,
"category": "missing",
"dataset": "bacteria_odb10",
"fracc_markers": "~1/124",
"mag_id": "311112c9-7f8b-460c-9cad-3864af3148c2",
"n_markers": 124,
"order": 4,
"sample_id": "data"
}
]
},
"hconcat": [
{
"data": {
"name": "data-aa27db16b89ba99bd435a50e28f5712a"
},
"facet": {
"row": {
"field": "sample_id",
"header": {
"labelFontSize": 0
},
"title": "MAG ID",
"type": "nominal"
}
},
"resolve": {
"scale": {
"y": "independent"
}
},
"spacing": 20,
"spec": {
"encoding": {
"color": {
"field": "category",
"legend": {
"orient": "top",
"title": "BUSCO Category"
},
"scale": {
"domain": [
"single",
"duplicated",
"fragmented",
"missing"
],
"range": [
"#1E90FF",
"#87CEFA",
"#FFA500",
"#FF7F50"
]
},
"type": "nominal"
},
"opacity": {
"value": 0.85
},
"order": {
"field": "order",
"sort": "ascending",
"type": "quantitative"
},
"tooltip": [
{
"field": "sample_id",
"title": "Sample ID",
"type": "nominal"
},
{
"field": "mag_id",
"title": "MAG ID",
"type": "nominal"
},
{
"field": "dataset",
"title": "Lineage dataset",
"type": "nominal"
},
{
"field": "fracc_markers",
"title": "Aprox. number of markers in this category",
"type": "nominal"
},
{
"field": "BUSCO_percentage",
"title": "% BUSCOs",
"type": "quantitative"
}
],
"x": {
"aggregate": "sum",
"field": "BUSCO_percentage",
"stack": "normalize",
"title": "BUSCO fraction",
"type": "quantitative"
},
"y": {
"axis": {
"titleFontSize": 0
},
"field": "mag_id",
"type": "nominal"
}
},
"height": {
"step": 30
},
"mark": {
"type": "bar"
},
"width": 500
}
},
{
"data": {
"name": "data-8eeb27a58f5796f75448a5d3d8f81d69"
},
"facet": {
"row": {
"field": "sample_id",
"header": {
"labelFontSize": 0
},
"title": null,
"type": "nominal"
}
},
"resolve": {
"scale": {
"y": "independent"
}
},
"spacing": 20,
"spec": {
"encoding": {
"opacity": {
"value": 0.85
},
"tooltip": [
{
"field": "x",
"title": "value",
"type": "quantitative"
}
],
"x": {
"field": "x",
"title": "Assembly Statistic",
"type": "quantitative"
},
"y": {
"axis": null,
"field": "mag_id",
"type": "nominal"
}
},
"height": {
"step": 30
},
"mark": {
"type": "bar"
},
"transform": [
{
"as": "x",
"calculate": "datum[param_i]"
}
],
"width": 500
}
}
],
"params": [
{
"bind": {
"input": "select",
"name": "Assembly Statistics: ",
"options": [
"scaffold_n50",
"contigs_n50",
"percent_gaps",
"number_of_scaffolds"
]
},
"name": "param_i",
"value": "scaffold_n50"
}
],
"spacing": 3
}
Loading
Loading