Skip to content

Ek/initial experimentation#49

Draft
ekiefl wants to merge 20 commits intoCAODH:masterfrom
Arcadia-Science:ek/initial-experimentation
Draft

Ek/initial experimentation#49
ekiefl wants to merge 20 commits intoCAODH:masterfrom
Arcadia-Science:ek/initial-experimentation

Conversation

@ekiefl
Copy link
Copy Markdown

@ekiefl ekiefl commented Mar 19, 2026

No description provided.

ekiefl added 20 commits March 17, 2026 15:20
…search

Remove tqdm progress bars, loguru logging, gc.collect calls, EMA,
tensorboard, and checkpoint saving from the training loop. Output is
now just epoch summaries + structured results block for agent parsing.
Replace brute-force bridge detection (deepcopy + is_connected per edge)
with nx.bridges() which runs a single O(V+E) DFS.

Also fixes a bug for disconnected molecules (e.g. 1esz, which has a
106-atom component + 1 isolated atom). The old code checked
nx.is_connected(G2) after removing each edge, but if the graph was
already disconnected, *every* edge removal produced a disconnected G2,
so the code never hit `continue`. Then the smallest connected component
was always the pre-existing isolated atom (size 1), so every edge was
filtered by the `len(l) < 2` guard, returning [] even though the large
component had 37 valid bridge torsions. nx.bridges() correctly
identifies bridge edges within each connected component regardless of
the overall graph connectivity.

Verified equivalent output on 500 PDBbind ligands (499/500 match; the
1 difference is the bug fix above).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant