feat: add torsion net benchmark#659
Open
lwehrhan wants to merge 1 commit into
Open
Conversation
ellalbolland
pushed a commit
to ellalbolland/ml-peg
that referenced
this pull request
Jul 8, 2026
Renames the benchmark (directories, files, and all internal references) to TorsionNet500CCSDT to distinguish it from the existing barrier-height TorsionNet500 implementation in ddmms#642/ddmms#659, since this benchmark reports RMSE/MAE of the full relative energy profile against CCSD(T)/CBS reference data - a different metric and reference level of theory, not a duplicate.
ElliottKasoar
added
the
new benchmark
ellalbolland
pushed a commit
to ellalbolland/ml-peg
that referenced
this pull request
Jul 8, 2026
Adds per-fragment RMSE/MAE scatter plots and per-fragment torsion energy profile curves to the TorsionNet500CCSDT analysis, wired into the app via a table-cell -> scatter -> curve click-through. Renames the raw energy fields to ref_energy/model_energy (and ref_rel_energy/model_rel_energy for the mean-centered profiles) to match existing codebase conventions, and switches to the shared rmse/mae utilities instead of a local reimplementation. Named TorsionNet500CCSDT rather than TorsionNet500 to coexist alongside the existing barrier-height implementation in ddmms#642/ddmms#659, since this benchmark reports RMSE/MAE of the full relative energy profile against CCSD(T)/CBS reference data - a different metric and reference level of theory, not a duplicate.
5 tasks
joehart2001
reviewed
Jul 9, 2026
| Computational cost | ||
| ------------------ | ||
|
|
||
| Medium: 12,000 single point inference calls on small molecular systems. |
Collaborator
There was a problem hiding this comment.
same as before, cpu/gpu estimate?
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 |
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
3 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.
Pre-review checklist for PR author
PR author must check the checkboxes below when creating the PR.
Summary
The TorsionNet500 dataset consists of 500 drug-like organic molecules with systematically sampled dihedral angles. The target metric is the the barrier height of the dihedrals. The level of theory is ωB97M-D3(BJ)/def2-TZVPPD (re-computed by InstaDeep in-house).
Linked issue
Resolves #642
Progress
Testing
New decorators/callbacks