Skip to content

update bases2fastq MultiQC module #7

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

Draft
MSamman wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

update bases2fastq MultiQC module #7

Show file tree
Hide file tree
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
5 changes: 2 additions & 3 deletions multiqc/modules/bases2fastq/plot_project_runs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,11 +22,10 @@ def tabulate_project_run_stats(run_data, color_dict):

headers = {}
headers["num_polonies_run"] = {
"title": f"# Polonies ({config.base_count_prefix})",
"description": f"The total number of polonies that are calculated for the run ({config.base_count_desc})",
"title": "# Polonies",
"description": "The total number of polonies that are calculated for the run",
"min": 0,
"scale": "RdYlGn",
"shared_key": "base_count",
}
headers["percent_assigned_run"] = {
"title": "% Assigned Reads",
Expand Down
13 changes: 6 additions & 7 deletions multiqc/modules/bases2fastq/plot_runs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ def plot_run_stats(run_data, color_dict):
pconfig = {
"data_labels": [
{"name": "Number of Polonies", "ylab": "Number of Polonies", "format": "{d}"},
{"name": "Yield (Gb)", "ylab": "Gb"},
{"name": "Yield (Gb)", "ylab": "Yield"},
],
"cpswitch": True,
"stacking": "normal",
Expand Down Expand Up @@ -99,11 +99,10 @@ def tabulate_run_stats(run_data, color_dict):

headers = {}
headers["num_polonies_run"] = {
"title": f"# Polonies ({config.base_count_prefix})",
"description": f"The total number of polonies that are calculated for the run. ({config.base_count_desc})",
"title": "# Polonies",
"description": "The total number of polonies that are calculated for the run.",
"min": 0,
"scale": "RdYlGn",
"shared_key": "base_count",
}
headers["percent_assigned_run"] = {
"title": "% Assigned Reads",
Expand Down Expand Up @@ -221,6 +220,7 @@ def plot_base_quality_hist(run_data, color_dict):
"id": "per_run_bq_hist",
"title": "bases2fastq: Quality Histograms",
"ylab": "Percentage",
"xlab": "Q score",
}
plot_html = linegraph.plot(plot_content, pconfig=pconfig)
plot_name = "Run Base Quality Histogram"
Expand Down Expand Up @@ -347,10 +347,9 @@ def plot_base_quality_by_cycle(run_data, color_dict):
plot_html = linegraph.plot(plot_content, pconfig=pconfig)
plot_name = "Quality Metrics By Cycle"
anchor = "per_cycle_quality"
description = "Per run base qualities by cycle"
description = "Per run base qualities by cycle. Read 1 and Read 2 are separated by a red dashed line."
helptext = """
This section plots the base qualities by each instrument cycle.\n
Choose between Median Quality, Mean Quality, Percent Q30 or Percentage Q40 per cycle.\n
Read 1 and Read 2 are separated by a red dashed line.
Choose between Median Quality, Mean Quality, Percent Q30 or Percentage Q40 per cycle.
"""
return plot_html, plot_name, anchor, description, helptext, plot_content
34 changes: 23 additions & 11 deletions multiqc/modules/bases2fastq/plot_samples.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ def tabulate_sample_stats(sample_data, group_lookup_dict, project_lookup_dict, s
general_stats.update({"mean_base_quality_sample": sample_data[s_name]["QualityScoreMean"]})
general_stats.update({"percent_q30_sample": sample_data[s_name]["PercentQ30"]})
general_stats.update({"percent_q40_sample": sample_data[s_name]["PercentQ40"]})
general_stats.update({"percent_mismatch": sample_data[s_name]["PercentMismatch"]})
plot_content.update({s_name: general_stats})

headers = {}
Expand All @@ -37,11 +38,10 @@ def tabulate_sample_stats(sample_data, group_lookup_dict, project_lookup_dict, s
"scale": False,
}
headers["num_polonies_sample"] = {
"title": f"# Polonies ({config.base_count_prefix})",
"description": f"The total number of polonies that are calculated for the run. ({config.base_count_desc})",
"title": "# Polonies",
"description": "The total number of polonies that are calculated for the run.",
"min": 0,
"scale": "Blues",
"shared_key": "base_count",
}
headers["yield_sample"] = {
"title": "Yield (Gb)",
Expand Down Expand Up @@ -70,6 +70,14 @@ def tabulate_sample_stats(sample_data, group_lookup_dict, project_lookup_dict, s
"scale": "RdYlGn",
"suffix": "%",
}
headers["percent_mismatch"] = {
"title": "Percent Mismatch",
"description": "The percentage of mismatching reads for the sample.",
"max": 100,
"min": 0,
"scale": "RdYlGn",
"suffix": "%",
}

pconfig = {"id": "sample_qc_metric_table", "title": "Sample QC Metrics Table", "no_violin": True}

Expand Down Expand Up @@ -100,14 +108,15 @@ def sequence_content_plot(sample_data, group_lookup_dict, project_lookup_dict, c

r1r2_split = 0
for s_name in sorted(sample_data.keys()):
paired_end = True if len(sample_data[s_name]["Reads"]) > 1 else False
for base in "ACTG":
base_s_name = "__".join([s_name, base])
data[base_s_name] = {}
R1 = sample_data[s_name]["Reads"][0]["Cycles"]
r1r2_split = max(r1r2_split, len(R1))

for s_name in sorted(sample_data.keys()):
paired_end = True if len(sample_data[s_name]["Reads"]) > 1 else False

R1 = sample_data[s_name]["Reads"][0]["Cycles"]
for cycle in range(len(R1)):
base_no = cycle + 1
Expand Down Expand Up @@ -135,8 +144,8 @@ def sequence_content_plot(sample_data, group_lookup_dict, project_lookup_dict, c
plot_content = data

pconfig = {
"xlab": "cycle",
"ylab": "Percentage",
"xlab": "Cycle",
"ylab": "Percentage of total reads",
"x_lines": [{"color": "#FF0000", "width": 2, "value": r1r2_split, "dashStyle": "dash"}],
"colors": color_dict,
"ymin": 0,
Expand All @@ -147,8 +156,8 @@ def sequence_content_plot(sample_data, group_lookup_dict, project_lookup_dict, c
plot_name = "Per Cycle Base Content"
anchor = "base_content"
description = """
Percentage of unidentified bases ("N" bases) by each sequencing cycle.
Read 1 and Read 2 are separated by a red dashed line
Base composition per sample per cycle.
Read 1 and Read 2 are separated by a red dashed line.
"""
helptext = """
If a sequencer is unable to make a base call with sufficient confidence then it will
Expand Down Expand Up @@ -252,8 +261,8 @@ def plot_per_read_gc_hist(sample_data, group_lookup_dict, project_lookup_dict, s
plot_content = gc_hist_dict

pconfig = {
"xlab": "% GC",
"ylab": "Percentage",
"xlab": "Percentage of total reads",
"ylab": "Percentage of reads that are GC",
"colors": sample_color,
"id": "gc_hist",
"title": "bases2fastq: Per Sample GC Content Histogram",
Expand Down Expand Up @@ -323,7 +332,10 @@ def plot_adapter_content(sample_data, group_lookup_dict, project_lookup_dict, sa
pconfig.update({"colors": sample_color})
plot_html = linegraph.plot(plot_content, pconfig=pconfig)
anchor = "adapter_content"
description = "Adapter content per cycle"
description = """
Adapter content per cycle.
Read 1 and Read 2 are separated by a red dashed line.
"""
helptext = """
The plot shows a cumulative percentage count of the proportion
of your library which has seen each of the adapter sequences at each cycle.
Expand Down