gene

here is some examples of trackc’s gene track

convert GTF to BED13

Download the GTF version of the genome corresponding to the multi-group data. And convert it to bed13 using trackc gtf2bed

# download
wget https://ftp.ensembl.org/pub/release-105/gtf/homo_sapiens/Homo_sapiens.GRCh38.105.chr.gtf.gz
gunzip Homo_sapiens.GRCh38.105.chr.gtf.gz
# convert
trackc gtf2bed -g Homo_sapiens.GRCh38.105.chr.gtf -o Homo_sapiens.GRCh38.105.chr.bed13 --biotype2bed13

import pandas as pd

import trackc as tc

gene_bed12_file = "../../trackc_data/tutorials/4C/Homo_sapiens.GRCh38.105.chr.bed13"
gene_bed12 = pd.read_table(gene_bed12_file, header=None)
display(gene_bed12[12].unique())
# only show the protein_coding type gene
gene_bed12 = gene_bed12[gene_bed12[12] == "protein_coding"]

array(['protein_coding', 'lncRNA', 'unprocessed_pseudogene',
       'processed_pseudogene', 'transcribed_processed_pseudogene',
       'transcribed_unitary_pseudogene',
       'transcribed_unprocessed_pseudogene', 'TEC', 'unitary_pseudogene',
       'snRNA', 'miRNA', 'misc_RNA', 'snoRNA', 'scaRNA',
       'rRNA_pseudogene', 'pseudogene', 'rRNA', 'polymorphic_pseudogene',
       'IG_V_pseudogene', 'scRNA', 'IG_V_gene', 'IG_C_gene', 'IG_J_gene',
       'sRNA', 'ribozyme', 'translated_processed_pseudogene', 'vault_RNA',
       'TR_V_gene', 'TR_C_gene', 'TR_J_gene', 'TR_V_pseudogene',
       'TR_D_gene', 'translated_unprocessed_pseudogene',
       'IG_C_pseudogene', 'TR_J_pseudogene', 'IG_J_pseudogene',
       'IG_D_gene', 'IG_pseudogene', 'Mt_tRNA', 'Mt_rRNA'], dtype=object)

trackc.pl.scale_track

Trackc supports trackc.pl.scale_track methods for gene track visualization

show_label

Default value is True, means show all the gene names of the regions

• False, do not show all the gene names of the regions

• one single gene string, example “KMT2C”, means only show KMT2C gene name, if the gene position is in the regions

• gene list, example [“KMT2C”, “ACTR3B”], means show gene names in the given gene list

regions = ["7:153000000-151000000", "11:118500000-116500000"]

ten = tc.tenon(figsize=(8, 1))
ten.add(pos="bottom", height=1.2)
ten.add(pos="bottom", height=0.4, hspace=0.1)
ten.add(pos="bottom", height=0.6, hspace=0.1)

tc.pl.gene_track(
    ax=ten.axs(0),
    bed12=gene_bed12,
    regions=regions,
    line=7,
    show_label=["KMT2C"],
    ax_on=True,
    gene_fontsize=12,
)
tc.pl.multi_scale_track(
    ten.axs(1),
    regions=regions,
    scale_adjust="Mb",
    intervals=1,
    tick_rotation=0,
    tick_fontsize=10,
)
tc.pl.multi_scale_track(
    ten.axs(2), regions=regions, scale_adjust="Mb", intervals=2, tick_rotation=0
)

# tc.savefig('gene_track.pdf')

ten = tc.tenon(figsize=(8, 1))
ten.add(pos="bottom", height=1)

region = "7:153000000-152000000"
tc.pl.gene_track(
    ax=ten.axs(0), bed12=gene_bed12, regions=region, line=3, gene_fontsize=10
)
tc.pl.scale_track(
    ax=ten.axs(0), region=region, scale_adjust="Mb", tick_pos="bottom", ratio2ax=0.6
)