browser

Contains the GenomeBrowser class

---

source

GenomeBrowser

 GenomeBrowser (gff_path:str, genome_path:str=None, seq_id:str=None,
                init_pos:int=None, init_win:int=10000, bounds:tuple=None,
                max_interval:int=100000, show_seq:bool=True,
                search:bool=True, attributes:list=['gene', 'locus_tag',
                'product'], feature_name:str='gene',
                feature_types:list=['CDS', 'repeat_region', 'ncRNA',
                'rRNA', 'tRNA'], glyphs:dict=None, height:int=150,
                width:int=600, label_angle:int=45,
                label_font_size:str='10pt', feature_height:float=0.15,
                output_backend:str='webgl', **kwargs)

Initialize a GenomeBrowser object.

	Type	Default	Details
gff_path	str		path to the gff3 file of the annotations (also accepts gzip files)
genome_path	str	None	path to the fasta file of the genome sequence
seq_id	str	None	id of the sequence to show for genomes with multiple contigs
init_pos	int	None	initial position to display
init_win	int	10000	initial window size (max=20000)
bounds	tuple	None	bounds can be specified. This helps preserve memory by not loading the whole genome if not needed.
max_interval	int	100000	maximum size of the field of view in bp
show_seq	bool	True	shows the sequence when zooming in
search	bool	True	enables a search bar
attributes	list	[‘gene’, ‘locus_tag’, ‘product’]	list of attribute names from the GFF attributes column to be extracted
feature_name	str	gene	attribute to be displayed as the feature name
feature_types	list	[‘CDS’, ‘repeat_region’, ‘ncRNA’, ‘rRNA’, ‘tRNA’]	list of feature types to display
glyphs	dict	None	dictionnary defining the type and color of glyphs to display for each feature type
height	int	150	height of the annotation track
width	int	600	width of the inner frame of the browser
label_angle	int	45	angle of the feature names displayed on top of the features
label_font_size	str	10pt	font size fo the feature names
feature_height	float	0.15	fraction of the annotation track height occupied by the features
output_backend	str	webgl	can be “webgl” or “svg”. webgl is more efficient but svg is a vectorial format that can be conveniently modified using other software
kwargs

Additional keyword arguments are passed as is to bokeh.plotting.figure

from genomenotebook.data import get_example_data_dir
import os

data_path = get_example_data_dir()
genome_path = os.path.join(data_path, "MG1655_U00096.fasta")
gff_path = os.path.join(data_path, "MG1655_U00096.gff3")

g=GenomeBrowser(genome_path=genome_path, gff_path=gff_path, bounds=(0,50000),width=600)
g.show()

#Providing GFF file as only input
g=GenomeBrowser(gff_path)
g.show()

#List available attributes
from genomenotebook.utils import available_attributes, available_feature_types

available_attributes(gff_path)

Index(['seq_id', 'source', 'type', 'start', 'end', 'score', 'strand', 'phase',
       'attributes', 'Name', 'mobile_element_type', 'Is_circular',
       'recombination_class', 'gbkey', 'protein_id', 'exception', 'pseudo',
       'gene_synonym', 'orig_transcript_id', 'strain', 'part', 'gene',
       'mol_type', 'transl_except', 'ID', 'substrain', 'genome', 'rpt_type',
       'Note', 'Dbxref', 'product', 'transl_table', 'orig_protein_id',
       'locus_tag', 'Parent', 'gene_biotype', 'left', 'right', 'middle'],
      dtype='object')

#Showing different attributes from the GFF file
g=GenomeBrowser(gff_path, attributes=["locus_tag","protein_id",'gene','product'],feature_name="protein_id")
g.show()

---

source

GenomeBrowser.add_track

 GenomeBrowser.add_track (height:int=200, tools:str='xwheel_zoom,
                          ywheel_zoom, pan, box_zoom, save, reset',
                          **kwargs)

Adds a track to the GenomeBrowser. Ensures that the x_range are shared and figure widths are identical.

	Type	Default	Details
height	int	200	size of the track
tools	str	xwheel_zoom, ywheel_zoom, pan, box_zoom, save, reset	comma separated list of Bokeh tools that can be used to navigate the plot
kwargs
Returns	Track

data_path = get_example_data_dir()
genome_path = os.path.join(data_path, "MG1655_U00096.fasta")
gff_path = os.path.join(data_path, "MG1655_U00096.gff3")

data=pd.DataFrame(dict(x=np.arange(0,50000,100),
                       y=np.sin(np.arange(0,50000,100))))

g=GenomeBrowser(genome_path=genome_path, gff_path=gff_path, bounds=(0,5000), search=False, show_seq=False)

track = g.add_track(height=100)
track.scatter(data=data,pos="x",y="y")
g.show()

---

source

GenomeBrowser.highlight

 GenomeBrowser.highlight (data:pandas.core.frame.DataFrame,
                          left:str='left', right:str='right',
                          color:str='color', alpha:str=0.2,
                          hover_data:list=[], highlight_tracks:bool=False,
                          **kwargs)

	Type	Default	Details
data	DataFrame		pandas DataFrame containing the data
left	str	left	name of the column containing the start positions of the regions
right	str	right	name of the column containing the end positions of the regions
color	str	color	color of the regions
alpha	str	0.2	transparency
hover_data	list	[]	list of additional column names to be shown when hovering over the data
highlight_tracks	bool	False	whether to highlight just the annotation track or also the other tracks
kwargs

import pandas as pd

g=GenomeBrowser(gff_path=gff_path, genome_path=genome_path, bounds=(0,10000))
highlight_regions=pd.DataFrame({"start": [5000, 8000], "stop": [6000, 8500], "color": ["red","green"], "y":[23, 45]})
g.highlight(data=highlight_regions, left="start", right="stop", hover_data=["y"])
g.show()

data=pd.DataFrame(dict(x=np.arange(0,50000,100),
                       y=np.sin(np.arange(0,50000,100))))

g=GenomeBrowser(genome_path=genome_path, gff_path=gff_path, bounds=(0,5000), search=False, show_seq=False)
track = g.add_track(height=100)
track.scatter(data=data,pos="x",y="y")

highlight_regions=pd.DataFrame({"start": [2000, 4000], "stop": [3000, 4500], "color": ["red","green"], "y":[23, 45]})
g.highlight(data=highlight_regions, left="start", right="stop", hover_data=["y"], highlight_tracks=True)

g.show()

---

source

GenomeBrowser.save

 GenomeBrowser.save (fname:str)

This function saves the initial plot that is generated and not the current view of the browser. To save in svg format you must initialise your GenomeBrowser using output_backend="svg"

	Type	Details
fname	str	path to file or a simple name (extensions are automatically added)

Saving to svg

Plots can only be saved to svg if you initialise your GenomeBrowser using output_backend="svg"

g=GenomeBrowser(gff_path=gff_path, 
                bounds=(0,5000),
                output_backend="svg",
                search=False)
track = g.add_track(height=100)
track.fig.scatter(x=np.arange(0,5000,100),y=np.sin(np.arange(0,5000,100)))
g.show()
g.save("test.svg")

Saving to png

g=GenomeBrowser(genome_path=genome_path, 
                gff_path=gff_path,
                bounds=(0,5000),
                search=False,
                height=200,
                width=2000,
                label_font_size="20pt")
g.save("test.png")