Skip to content

feat: add bond length distribution benchmark#666

Draft
lwalew wants to merge 1 commit into
ddmms:mainfrom
lwalew:feat/add-bond-length-distribution
Draft

feat: add bond length distribution benchmark#666
lwalew wants to merge 1 commit into
ddmms:mainfrom
lwalew:feat/add-bond-length-distribution

Conversation

@lwalew

@lwalew lwalew commented Jul 3, 2026

Copy link
Copy Markdown

Pre-review checklist for PR author

PR author must check the checkboxes below when creating the PR.

Summary

Migrates the bond length distribution benchmark from the MLIP Audit suite. For each of a set of small organic molecules — covering the C-C, C=C, C#C, C-N, C-O, C=O and C-F bond types — an NVT molecular dynamics simulation is run at 300 K starting from a QM-optimised reference geometry (selected from QM9), and the deviation of a tracked covalent bond from its reference length is measured over the trajectory. A well behaved potential keeps bonds close to their reference length, so a lower average deviation is better.

The analysis reports the average bond length deviation per model in the metrics table and shows the distribution of sampled deviations as a histogram.

Linked issue

Resolves #671

Progress

  • Calculations
  • Analysis
  • Application
  • Documentation

Testing

Not yet run end-to-end: the benchmark input data still needs to be uploaded to the ML-PEG S3 bucket at inputs/molecular_dynamics/bond_length_distribution/bond_length_distribution.zip (layout bond_length_distribution/bond_length_distribution.json). Kept as a draft until the data is available. Style checks (pre-commit) pass locally.

New decorators/callbacks

No new callbacks required; uses the existing plot_hist and build_table decorators and the plot_from_table_column callback.

Note for reviewers

Migrate the bond length distribution benchmark from the MLIP Audit suite.
An NVT molecular dynamics simulation is run for each of a set of small organic
molecules, and the deviation of a tracked covalent bond from its QM-optimised
reference length is measured over the trajectory. Lower average deviation is
better.

Adds the calculation, analysis (histogram of deviations plus a metrics table),
Dash app, documentation, and the mlipaudit dependency wiring (optional extra,
git source and MLIP Audit framework badge).
@lwalew lwalew mentioned this pull request Jul 8, 2026
5 tasks
@ElliottKasoar ElliottKasoar added the new benchmark Proposals and suggestions for new benchmarks label Jul 8, 2026
Computational cost
------------------

High: one MD simulation per molecule, each 1,000,000 steps. Faster inference can be achieved

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

gpu estimate?

@joehart2001

Copy link
Copy Markdown
Collaborator

Thanks for the pr! same as #658 could you send the data + have a look at the element filtering?

docs: https://ddmms.github.io/ml-peg/developer_guide/filter.html

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

new benchmark Proposals and suggestions for new benchmarks

Projects

None yet

Development

Successfully merging this pull request may close these issues.

New benchmark Bond Length Distribution

3 participants