v2.0.0: Protenix-v2 Model Released

What's changed

🚀 Key Highlights

• Protenix-v2 Model Released: Introduced protenix-v2, an enhanced-capacity model (464M parameters). It delivers significant accuracy improvements in predicting challenging antibody-antigen complex structures and updates ligand-related plausibility.
• Training-Free Guidance (TFG) Module: Introduced a powerful new guidance module enforcing geometric and physical constraints (Steric, Torsion, Bond, etc.) during diffusion sampling without the need for retraining.

✨ New Features & Enhancements

• Inference Efficiency Breakthrough: protenix-v2 shows remarkable efficiency gains. Utilizing only 5 sampling seeds, it successfully
outperforms protenix-v1 at 1000 seeds.
• Configurable TFG Capabilities: Exposed via the --use_tfg_guidance CLI flag. Supported geometries include VinaStericPotential,
ExperimentalTorsionPotential, and PairwiseDistancePotential.

📖 Documentation & Assets

• Bumped protenix version to 2.0.0.
• Published the new Protenix-v2 Technical Report (docs/PX2.pdf).
• Updated README.md and docs/supported_models.md with the latest Protenix-v2 benchmarks, showcasing a 9 to 13 percentage points absolute success rate gain over Protenix-v1 at the DockQ > 0.23 threshold.

v1.1.0: Support fallback to torch cache dir for layer_norm

What's changed

• Check if current directory is writable before compiling layer_norm cuda extension
• Fallback to torch cache directory if not writable

v1.0.9: Add a include_discont_poly_poly_bonds switch for 'protenix json' command

What's changed

• Add a include_discont_poly_poly_bonds switch for protenix json command

v1.0.8: Disable triton fused ops by default

What's Changed

• Triton fused ops for dropout residual are now disabled by default as they cause a slight drop in foldbench performance. They can be enabled via the FUSED_DROPOUT_RESIDUAL environment variable.

v1.0.7: Refactor: consolidate version management and bump to 1.0.7

What's Changed

• Add protenix/version.py to store version string
• Update setup.py to read version dynamically
• Update runner/batch_inference.py to use shared version
• Expose version in protenix/init.py

v1.0.6: Support custom id field in input json

What's Changed

• Auto-detect CUDA architectures for layer norm kernel compilation by @longleo17 in #252
• Featurizer: zero-copy tensor creation + numpy vectorization by @longleo17 in #246
• MSA encoding: vectorized sequence parsing by @longleo17 in #247
• Dataset: vectorize pandas/numpy operations by @longleo17 in #248
• Attention precision fix + LDDT fused thresholds + loss caching by @longleo17 in #249
• Fused Triton dropout+residual-add kernel (v2, cueq fix) by @longleo17 in #256
• Fix/blackwell gpu compatibility by @giulioisac in #257
• chain reindexing by @giulioisac in #260
• fix return identity matrix in eye_mask when opposite is False by @mrzzmrzz in #261
• Remove invalid AdamW arg and handle None param_names by @mrzzmrzz in #262
• Support custom id field in input json

Full Changelog: v1.0.5...v1.0.6

v1.0.5: Add need_atom_confidence option in protenix cli

What's Changed

• inference: fix MSA assertion and harden input/model-name validation by @ullahsamee in #235
• On-demand remote fetching of mmCIF template files by @giulioisac in #243
• Add need_atom_confidence option in protenix cli

New Contributors

• @giulioisac made their first contribution in #243

Full Changelog: v1.0.4...v1.0.5

v1.0.4: Raise if use template and kalign is not found

What's Changed

• fix: Add proper file handle management in colab_request_utils.py by @hobostay in #228
• triangular: Fix PyTorch 2.9 tensor indexing deprecation warnings by @ullahsamee in #229
• Raise if use template and kalign is not found

New Contributors

• @hobostay made their first contribution in #228
• @ullahsamee made their first contribution in #229

Full Changelog: v1.0.3...v1.0.4

v1.0.3: Fix edge case inference for mini_esm models

What's changed

• Fix edge case inference for mini_esm models

Full Changelog: v1.0.2...v1.0.3

v1.0.2: Release RNA MSA data and change back chain ID format

What's changed

• Release RNA MSA data and corresponding configuration documentation.
• Minior change for chain ID in final output cif.