def main():
args = parse_args()
from_gdb = genome.db.GenomeDB(assembly=args.from_assembly)
to_gdb = genome.db.GenomeDB(assembly=args.to_assembly)
chain_list = chain.read_chain_file(args.liftover_file, from_gdb, to_gdb)
sys.stderr.write("initializing tables\n")
track = create_tables(from_gdb, args.tabname)
sys.stderr.write("writing to tables\n")
for c in chain_list:
sys.stderr.write(" current chain: %s\n" % str(c))
tab = track.h5f.getNode("/%s" % c.from_coord.chrom.name)
to_chr_id = c.to_coord.chrom.idnum
for block in c.blocks:
# update table with mappings to new chromosomal locations
to_pos = np.arange(block.to_start, block.to_end+1)
block_size = block.to_end - block.to_start + 1
to_chr_id = np.repeat(c.to_coord.chrom.idnum, block_size)
ori = np.repeat(c.ori, block_size)
vals = np.transpose(np.vstack((to_chr_id, to_pos, ori)))
tab[block.from_start-1:block.from_end, :] = vals
def liftover_data(chain_file, from_gdb, to_gdb, from_track, rev_from_track,
to_track, rev_to_track):
sys.stderr.write("reading chain file\n")
chain_list = read_chain_file(chain_file, from_gdb, to_gdb)
sys.stderr.write("copying data\n")
for chain in chain_list:
sys.stderr.write(" current chain: %s\n" % str(chain))
for block in chain.blocks:
# liftover the data data for this block
copy_data(from_track, rev_from_track, chain.from_coord.chrom,
block.from_start, block.from_end, to_track, rev_to_track,
chain.to_coord.chrom, block.to_start, block.to_end,
chain.ori)
def liftover_data(chain_file, from_gdb, to_gdb, from_track, rev_from_track, to_track, rev_to_track):
sys.stderr.write("reading chain file\n")
chain_list = read_chain_file(chain_file, from_gdb, to_gdb)
sys.stderr.write("copying data\n")
for chain in chain_list:
sys.stderr.write(" current chain: %s\n" % str(chain))
for block in chain.blocks:
# liftover the data data for this block
copy_data(
from_track,
rev_from_track,
chain.from_coord.chrom,
block.from_start,
block.from_end,
to_track,
rev_to_track,
chain.to_coord.chrom,
block.to_start,
block.to_end,
chain.ori,
)
