Skip to content

works with variable length sequences #46

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
akmorrow13 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

works with variable length sequences #46

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion modisco
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,7 +185,7 @@ if args.cmd == "motifs":

if sequences.shape[1] < args.window:
raise ValueError("Window ({}) cannot be ".format(args.window) +
"longer than the sequences".format(sequences.shape))
"longer than the sequences {}".format(sequences.shape[1]))

sequences = sequences.astype('float32')
attributions = attributions.astype('float32')
Expand Down
13 changes: 6 additions & 7 deletions modiscolite/aggregator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,6 @@ def polish_pattern(pattern, min_frac, min_num, track_set, flank, window_size, bg

def _expand_seqlets_to_fill_pattern(pattern, track_set, left_flank_to_add,
right_flank_to_add):

new_seqlets = []
for seqlet in pattern.seqlets:
left_expansion = left_flank_to_add
Expand All @@ -55,11 +54,11 @@ def _expand_seqlets_to_fill_pattern(pattern, track_set, left_flank_to_add,
end = seqlet.end + left_expansion

if start >= 0 and end <= track_set.length:
seqlet = track_set.create_seqlets(
seqlets = track_set.create_seqlets(
seqlets=[core.Seqlet(example_idx=seqlet.example_idx,
start=start, end=end, is_revcomp=seqlet.is_revcomp)])[0]

new_seqlets.append(seqlet)
start=start, end=end, is_revcomp=seqlet.is_revcomp)])
if len(seqlets) > 0:
new_seqlets.append(seqlets[0])

if len(new_seqlets) > 0:
return core.SeqletSet(seqlets=new_seqlets)
Expand Down Expand Up @@ -299,7 +298,7 @@ def SimilarPatternsCollapser(patterns, track_set,

within_pattern1_sims = affinitymat.jaccard(
flat_pattern1_fwdseqdata[:, :, None],
flat_pattern1_fwdseqdata[:, :, None])[:, :, 0].flatten()
flat_pattern1_fwdseqdata[:, :, None])[:, :, 0].flatten()

auroc = roc_auc_score(
y_true=[0 for x in between_pattern_sims]
Expand Down Expand Up @@ -502,4 +501,4 @@ def SimilarPatternsCollapser(patterns, track_set,
current_level_nodes = next_level_nodes

return patterns, PatternMergeHierarchy(root_nodes=current_level_nodes)


10 changes: 7 additions & 3 deletions modiscolite/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,8 @@ def __init__(self, one_hot, contrib_scores, hypothetical_contribs):
self.length = len(one_hot[0])

def create_seqlets(self, seqlets):
for seqlet in seqlets:
out_seqlets = []
for i,seqlet in enumerate(seqlets):
idx = seqlet.example_idx
s, e = seqlet.start, seqlet.end

Expand All @@ -33,8 +34,11 @@ def create_seqlets(self, seqlets):
seqlet.sequence = self.one_hot[idx][s:e]
seqlet.contrib_scores = self.contrib_scores[idx][s:e]
seqlet.hypothetical_contribs = self.hypothetical_contribs[idx][s:e]

return seqlets

# verify that seqlet is not at the end of the sequence and has some bp set
if seqlet.sequence.sum()>0:
out_seqlets.append(seqlet)
return out_seqlets

class Seqlet(object):
def __init__(self, example_idx, start, end, is_revcomp):
Expand Down