def compute(self):
# TODO: this will at some point have to be a state machine
running = True
paused = False
while running:
# TODO: figure out what to do with framerates
self.clock.tick(60)
# TODO: unfuck calculation, draw, and update
# react to user input
single_frame = False
for e in pygame.event.get():
if e.type == pygame.QUIT:
running = False
if e.type == pygame.KEYDOWN:
if e.key == pygame.K_ESCAPE:
running = False
elif e.key == pygame.K_SPACE:
self.players[0].act()
elif e.key == pygame.K_LEFT:
paused = not paused
elif e.key == pygame.K_RIGHT:
single_frame = True
if paused:
if single_frame:
single_frame = False
else:
continue
# check collisions
for player in self.players:
player.check_wall_collisions()
player.update()
pairs = combinations(range(len(self.players)), 2)
for i, j in pairs:
if utils.overlaps(self.players[i], self.players[j]):
utils.change_velocities(self.players[i], self.players[j])
# move players and Orbs
for orb in chain(self.players, self.orbs):
orb.move()
# Draw the scene
self.screen.fill((0, 0, 0))
for game_object in chain(self.walls, self.orbits, self.orbs,
self.players):
game_object.draw(self.screen)
pygame.display.flip()
def parse_head_row(head_row, gene_group, outfile):
parse_head_row.last_args = head_row, gene_group, outfile
for _, gene_row in gene_group.iterrows():
if overlaps((gene_row.start, gene_row.end),
(head_row.start, head_row.end)):
flag = 'olap'
chosen_gene_id = gene_row.id
distance = 0
break
# if none overlaps
else:
# b f de forward ou backfill
distance = 9e99 # create Inf() class for that?
for meth in ['b', 'f']:
fill_back = meth == 'b'
gene_pos = ['end', 'start'][fill_back]
head_pos = ['end', 'start'][not fill_back]
if gene_group[gene_pos].duplicated().sum():
raise pd.core.indexes.base.InvalidIndexError(
'You appear to have duplicated gene positions. '
'Indexes won\'t work properly.')
indexed_group = gene_group.sort_values(gene_pos).set_index(
gene_pos)
try:
near_gene_index = indexed_group.index.get_loc(
head_row[head_pos], meth + 'fill')
gene_row = gene_group.iloc[near_gene_index]
new_distance = abs(gene_row[gene_pos] - head_row[head_pos])
if new_distance < distance:
chosen_gene_id = gene_row.id
flag = ["gh", "hg"][fill_back]
distance = new_distance
except KeyError as e:
prinf(
f'\nNão há gene {meth.upper()} de {head_row.id}. (B=atrás, F=à frente)\n'
)
outfile.write('\t'.join([head_row.id, chosen_gene_id, flag,
str(distance)]) + '\n')
near_gene_index = indexed_group.index.get_loc(
head_row.start, meth + 'fill')
gene_row = gene_group.iloc[near_gene_index]
relation_dic[head_row.id] = dict({flag: gene_row.id},
**relation_dic.get(
head_row.id, {}))
outfile.write('\t'.join([head_row.id, gene_row.id, flag]) +
'\n')
except KeyError:
if verbose:
print(f'Não há gene à {flag} de {head_row.id}.')
for _, gene_row in gene_group.iterrows():
if overlaps((gene_row.start, gene_row.end),
(head_row.start, head_row.end)):
flag = 'olap'
relation_dic[head_row.id] = dict({flag: gene_row.id},
**relation_dic.get(
head_row.id, {}))
outfile.write(
'\t'.join([head_row.id, gene_row.id, flag]) + '\n')
print(relation_dic)
print(f"Guardando dicionário em '{str(outpath)}'...")
with outdicpath.open('wb') as outdicfile:
dump(relation_dic, outdicfile)
print('Concluído.')
def test_overlap():
x1, x2 = 2005, 2008
y1, y2 = 2003, 2007
assert overlaps(x1, x2, y1, y2) == True
def test_no_overlap():
x1, x2 = 2005, 2008
y1, y2 = 2003, 2004
assert overlaps(x1, x2, y1, y2) == False
sr3_scaffold_groups = sr3_vs_genoma.groupby(['saccver'])
start_time = time()
count = 0
discarded = []
pos = 0
for i, p in tqdm(list(perere3_vs_genoma.iterrows())):
count += 1
if p['saccver'] in sr3_scaffold_groups.groups:
for j, s in sr3_scaffold_groups.get_group(
p['saccver']).loc[pos:].iterrows():
if overlaps((p['sstart'], p['send']), (s['sstart'], s['send'])):
# print('Alinhamentos coincidentes encontrados:')
# print(f"{p['sstart']}-{p['send']}\n{s['sstart']}-{s['send']}")
if s['bitscore'] > p['bitscore']:
# print('SR3 tem mais bitscore:')
# print(f"SR3 = {s['bitscore']}\nPer = {p['bitscore']}")
pos = j
filtered_perere3_vs_genoma.drop(i, inplace=True)
# print(f'Alinhamento {i} descartado.\n')
discarded.append(str(i))
break
sam_row = sam_row.iloc[0, :]
if sam_row.chrom == '*':
continue
try:
head_group = head_groups.get_group(sam_row.chrom)
except KeyError:
if verbose:
print(f'\nNão há heads no cromossomo {sam_row.chrom}.')
continue
for _, head_row in head_group.iterrows():
if overlaps((sam_row.start,
sam_row.start + len_from_cigar(sam_row.cigar)),
(head_row.start, head_row.end)):
outfile.write('\t'.join([
head_row.chrom, head_row.id,
str(head_row.start),
str(head_row.end),
str(sam_row.start), sam_row.cigar
]) + '\n')
outfile.close()
log(f"O SAM '{sam_path.stem}' acabou de ser filtrado.", __file__)
print('Concluído.')
def main():
heads = pd.read_table(head_annotations_path,
names=GFF3_COLUMNS,
usecols=GFF_COLS_SUBSET)
genes = pd.read_table(gene_annotations_path,
names=GFF3_COLUMNS,
usecols=GFF_COLS_SUBSET)
heads['id'] = parse_gff_attributes(heads.attributes).index
genes['id'] = parse_gff_attributes(genes.attributes).index
head_groups = heads.groupby(COLS_TO_GROUP)
gene_groups = genes.groupby(COLS_TO_GROUP)
outfile = safe_open(outpath, exist_ok=False)
# write header
outfile.write('\t'.join(['head_id', 'gene_id', 'flag', 'distance']) + '\n')
print('Iterate for each contig and for each head in contig.')
for head_group_name, head_group in tqdm(head_groups):
try:
gene_group = gene_groups.get_group(head_group_name)
except KeyError:
prinf(
'Não há nenhum gene no cromossomo. As heads abaixo são "desgenadas".'
)
prinf(head_group)
continue
for _, head_row in tqdm(list(head_group.iterrows())):
for _, gene_row in gene_group.iterrows():
if overlaps((gene_row.start, gene_row.end),
(head_row.start, head_row.end)):
flag = 'olap'
chosen_gene_id = gene_row.id
distance = 0
break
# if none overlaps
else:
# b f de forward ou backfill
distance = 9e99 # create Inf() class for that?
for meth in ['b', 'f']:
fill_back = meth == 'b'
gene_pos = ['end', 'start'][fill_back]
head_pos = ['end', 'start'][not fill_back]
if gene_group[gene_pos].duplicated().sum():
raise pd.core.indexes.base.InvalidIndexError(
'You appear to have duplicated gene positions.'
'Indexes won\'t work properly.')
indexed_group = gene_group.sort_values(gene_pos).set_index(
gene_pos)
try:
near_gene_index = indexed_group.index.get_loc(
head_row[head_pos], meth + 'fill')
gene_row = gene_group.iloc[near_gene_index]
new_distance = abs(gene_row[gene_pos] -
head_row[head_pos])
if new_distance < distance:
chosen_gene_id = gene_row.id
flag = ["gh", "hg"][fill_back]
distance = new_distance
except KeyError:
prinf(f'Não há gene à {flag} de {head_row.id}.')
outfile.write(
'\t'.join([head_row.id, chosen_gene_id, flag,
str(distance)]) + '\n')
print(f'\nConcluído. Relações salvas em {str(outpath)}.')
outfile.close()
