File formats

Initialize SeQuiLaSession and download sample data (check Initialize section for details)

[1]:

%run initialize.ipynb

BAM

[2]:

ss.sql(f'''CREATE TABLE IF NOT EXISTS {table_name} \
         USING org.biodatageeks.sequila.datasources.BAM.BAMDataSource \
         OPTIONS(path "{bam_path}")''')

[2]:

DataFrame[]

[3]:

ss.sql(f'''SELECT distinct cigar,tag_MD FROM {table_name} LIMIT 5''').toPandas()

[3]:

	cigar	tag_MD
0	101M	26G26G47
1	76M	19C56
2	101M	53A47
3	95M6S	95
4	76M	18A23A33

CRAM

[4]:

ss.sql(f'''CREATE TABLE IF NOT EXISTS {table_name}_cram \
         USING org.biodatageeks.sequila.datasources.BAM.CRAMDataSource \
         OPTIONS(path "{cram_path}", refPath "{ref_path}")''')

[4]:

DataFrame[]

[5]:

ss.sql(f'''SELECT distinct cigar,tag_MD FROM {table_name}_cram LIMIT 5''').toPandas()

[5]:

	cigar	tag_MD
0	101M	26G26G47
1	76M	19C56
2	101M	53A47
3	95M6S	95
4	76M	18A23A33

VCF

[6]:

ss.sql(f'''CREATE TABLE IF NOT EXISTS variants \
         USING org.biodatageeks.sequila.datasources.VCF.VCFDataSource \
         OPTIONS(path "{vcf_path}" )''')

[6]:

DataFrame[]

[7]:

ss.sql(f'''SELECT contig, pos_start, pos_end, ref, alt FROM variants LIMIT 5''').toPandas()

[7]:

	contig	pos_start	pos_end	ref	alt
0	20	14369	14370	G	[A]
1	20	17329	17330	T	[A]
2	20	1110695	1110696	A	[G, T]
3	20	1230236	1230237	T	None
4	20	1234566	1234569	GTC	[G, GTCT]

BED

[8]:

ss.sql(f'''
    CREATE TABLE IF NOT EXISTS targets(contig String,pos_start Integer,pos_end Integer) \
    USING csv \
    OPTIONS (path "{bed_path}", delimiter "\t")''')

[8]:

DataFrame[]

[9]:

ss.sql(f'''SELECT replace(targets.contig,"chr","") as contig, pos_start, pos_end FROM targets LIMIT 5''').toPandas()

[9]:

	contig	pos_start	pos_end
0	1	4505	4745
1	1	4806	4926
2	1	5614	5853
3	1	6462	6582
4	1	6697	6937

[ ]: