LIVIA Launches as Browser Tool to Score Protein-Protein Interface Predictions
sokrypton · x · 2026-09-21
Researcher ahramkim1128 released LIVIA (Local Interaction Visualization and Analysis), a browser-based tool for assessing predicted protein-protein interactions. It accepts outputs from AlphaFold-Multimer, AF3, ColabFold, Boltz-1/2, Chai-1, and OpenFold3 (ZIP or folder, auto-detected) and answers two key questions: do these proteins interact, and which residues form the interface. Outputs include confidence scores (iLIS, ipSAE, actifpTM, ipTM), interface heatmaps (PAE, LIS, cLIS), sequence viewers, linear and circular contact maps highlighting LIR/cLIR residues, and an embedded Mol 3D viewer. New LIpDockQ/LIpDockQ2 metrics score full-length predictions without the dilution ipTM suffers on proteins with IDRs or multiple domains, and don't filter by PAE.
More from Research
- Researchers formally verify the Kubernetes control plane with a compositional CORE spec — tianyin_xu · 2026-09-21
- Astra shows any 3D/4D prior can be distilled into VLMs, a new embodied AI paradigm — mariyaivasileva · 2026-09-21
- ReCouPLe: Reason-Augmented Preference Learning Boosts Reward Accuracy 1.5x Under Shift — burny_tech · 2026-09-21
- kalomaze rethinks 'cribbing SSL backbone features' after peers hit multimodal walls — kalomaze · 2026-09-21
- Closed-loop spatial understanding from just two wrist cameras, no gripper feedback — ChongZzZhang · 2026-09-21
- DeepMind's weather model ingests raw satellite radiances hourly, ending the 6-12h analysis lag — burny_tech · 2026-09-21