Quartz 4

❯

Rosetta

Created Apr 10, 2026

rosetta

Rosetta is a multi-purpose macromolecular modeling program written in C++. It relies on force fields and Monte Carlo sampling, and does not use any deep learning.

Graph View

Backlinks

Adding noise sometimes leads to greater diversity during inverse folding inference
CUMAb
Conformational entropy in antibodies decreases during affinity maturation
Diffusion-based protein structure prediction methods double as energy methods comparable to traditional force fields
Interleukins
Inverse folding sequence perplexities correlate with Rosetta energies, forward folding TM-scores, and sequence recovery
ML-based protein design methods outperform physics-based methods at identifying deleterious sequences but not top sequences
Most ML quality metrics cannot effectively predict enzyme activity after controlling for similarity to native
Most possible alpha-beta topologies unexplored by nature
Normal mode analysis
Protein structure prediction and design confidence metrics do not correlate with binding affinity
ProteinMPNN
PyRosetta convert mAb structure numbering
Structural tokens improve zero-shot variant effect prediction in ESM3, but only when structures are not computationally derived
Structure prediction with AlphaFold improved when starting from an initial guess, rather than default initialization
Structure-based methods outperform sequence-based methods on protein stability prediction of point mutants, but not full sequences
Variable regions can adopt multiple interchain orientations, and these are difficult to predict

GitHub
Discord Community

Quartz 4

Explorer

Rosetta

Graph View

Backlinks