Reconstruct encoded sequence before evaluation in MCTS simulation#294
Merged
NennoMP merged 1 commit intoApr 8, 2026
Merged
Conversation
Signed-off-by: WHOIM1205 <rathourprateek8@gmail.com> Signed-off-by: WHOIM1205 <your-email@users.noreply.github.com>
Collaborator
|
@WHOIM1205 You are right. Thanks for spotting this! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fix incorrect sequence evaluation in MCTS simulation
What was happening
During simulation, we were passing encoded sequences (with
_markers) directly to the evaluator. These got converted into invalid sequences internally (full ofNs), so the scores driving the MCTS search were basically meaningless.What’s changed
We now reconstruct the sequence using
_reconstruct()before evaluation, so the model sees the actual nucleotide sequence.Why it matters
This ensures the search is guided by real scores instead of corrupted ones, making the generated candidates much more reliable.