03: Expression plot with metadata

Create an RNA isoform structure plot with an RNA isoform expression plot with dodged groups beside it

[9]:

import RNApysoforms as RNApy

[10]:

## Path to your ENSEMBL GTF file, counts matrix file, and metadata file
ensembl_gtf_path = "../dash_apps/RNApysoforms/tests/test_data/Homo_sapiens_chr21_and_Y.GRCh38.110.gtf"
counts_matrix_path = "../dash_apps/RNApysoforms/tests/test_data/counts_matrix_chr21_and_Y.tsv"
metadata_path = "../dash_apps/RNApysoforms/tests/test_data/sample_metadata.tsv"



## Read ENSEMBL gtf and counts matrix with metadata
annotation = RNApy.read_ensembl_gtf(ensembl_gtf_path)
counts_matrix = RNApy.read_expression_matrix(expression_matrix_path=counts_matrix_path,
                                          metadata_path=metadata_path)

[11]:

## Filter gene name in annotation and counts matrix.
sod1_annotation, sod1_counts_matrix = RNApy.gene_filtering(annotation=annotation, expression_matrix=counts_matrix, target_gene="SOD1")

## Notice how now the counts matrix has the metadata integrated.
sod1_counts_matrix.head()

[11]:

shape: (5, 7)

transcript_id	gene_id	sample_id	counts	AD status	Sex	AD status and sex
str	str	str	f64	str	str	str
"ENST00000476106"	"ENSG00000142168"	"sample_1"	0.0	"AD"	"Female"	"AD Female"
"ENST00000476106"	"ENSG00000142168"	"sample_4"	0.0	"Control"	"Male"	"Control Male"
"ENST00000476106"	"ENSG00000142168"	"sample_7"	0.0	"AD"	"Male"	"AD Male"
"ENST00000476106"	"ENSG00000142168"	"sample_2"	0.0	"Control"	"Female"	"Control Female"
"ENST00000476106"	"ENSG00000142168"	"sample_6"	0.0	"Control"	"Female"	"Control Female"

[12]:

## Rescale introns
sod1_annotation = RNApy.shorten_gaps(sod1_annotation)


"""
Create traces now using the `expression_hue` parameter
set to the AD status metadata column that was added to the
expression matrix.
"""
traces = RNApy.make_traces(annotation=sod1_annotation,  expression_matrix=sod1_counts_matrix,
                        x_start="rescaled_start", x_end="rescaled_end",
                         y='transcript_id', annotation_hue="transcript_biotype",
                         hover_start="start", hover_end="end",
                         expression_columns=["counts"],
                         expression_hue="AD status")

## Put traces into figure
fig = RNApy.make_plot(traces = traces, subplot_titles = ["Transcript Structure", "Counts"], width=1200, height=500)

## Show figure
fig.show()