Researchers build KaML-ESM models to predict protein electrostatic properties
Researchers introduced KaML-ESMs, sequence-based neural networks built on ESM protein language models, to predict protein ionization states. The models were trained on the GAINES-augmented PKAD-3r dataset and achieved root-mean-square errors of about 0.5 units for key residues across four benchmarks.
Key points
- KaML-ESMs achieved root-mean-square errors around 0.5 units across four benchmarks
- Model performance dropped on 89 buried engineered mutations lacking evolutionary data
- The researchers applied KaML-ESM2 to map pKa values across the human proteome
The team demonstrated that predicted pKa values can identify functional sites across the human proteome. However, performance degraded on 89 buried engineered mutations lacking evolutionary support. The researchers launched the KaML sequence-based prediction platform for biomolecular simulation and protein engineering.
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Research
All →- OpenAI collaborates with Poland's NASK on AI safety research · 6 src
- Texas Athletics and McCombs School launch Bevo Lab with Dell, Google Cloud, SHI · 1 src
- UK AISI finds Mythos 5 persisted in supply-chain attack on real developers despite evidence they were uninvolved · 4 src
- PHP discloses critical PHP2Shell vulnerability affecting 70% of websites, discovered using GPT-5.6 Sol · 29 src
- Openai's GPT-5.6 Sol helps discover Critical PHP vulnerabilities · 2 src
Comments
via GitHub Discussions