Conversation
…d packed structures
1 task
There was a problem hiding this comment.
Pull request overview
Implements a new dreid-pack-bench CLI for benchmarking packing accuracy on structure datasets and restructures the repo into a Cargo workspace to separate core packing code from benchmarking infrastructure.
Changes:
- Converted the repository into a Cargo workspace with
crates/dreid-packandcrates/dreid-pack-bench. - Added a new
dreid-pack-benchcrate withdpack-benchbinary and CLI feature-gating. - Introduced a GitHub Actions workflow to build and run the benchmark and publish results into the job summary.
Reviewed changes
Copilot reviewed 4 out of 430 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
| crates/dreid-pack-bench/data/db379/1YZM.cif | Adds a benchmark dataset structure file used by the new bench pipeline. |
| crates/dreid-pack-bench/Cargo.toml | Defines the new bench crate, its dependencies, and a feature-gated dpack-bench binary. |
| Cargo.toml | Converts the repo root manifest into a workspace manifest and centralizes package metadata. |
| .github/workflows/bench.yml | Adds CI job to build/run the benchmark and publish a markdown summary. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary:
Introduced the
dpack-benchCLI utility to rigorously evaluate sidechain packing accuracy against crystal structures (e.g., the DB379 dataset). To support this, the repository was restructured into a Cargo workspace, isolating the coredreid-packlibrary/CLI from benchmark-specific infrastructure. Added a CI workflow for automated benchmark reporting.Changes:
Workspace Reorganization: Converted the repository into a Cargo workspace containing
crates/dreid-pack(core engine/CLI) andcrates/dreid-pack-bench(evaluation tools).Benchmark Pipeline (
dreid-pack-bench): Developed a multi-threaded evaluation pipeline that automatically packs structure directories, compares against crystal references, and outputs aggregated tabular or CSV metrics.Accuracy Metrics (
chi,rmsd.rs):B-factor Filtering (
bfactor.rs): Built zero-allocation PDB/mmCIF B-factor parsers to exclude highly flexible (unreliable) crystal residues from accuracy statistics based on configurable percentile cutoffs.Structural Pairing (
format.rs): Integratedbio-forgeto handle reference and packed structure loading, cleaning, and exact atom-to-atom coordinate mapping.CI Integration: Added
.github/workflows/bench.ymlto executedpack-benchon the 379-structure dataset and inject markdown reports into GitHub Actions summaries.