Ankh-score produces better sequence alignments than AlphaFold3
Malec, J.; Rusen, K.; Golding, G. B.; Ilie, L.
Show abstract
Protein sequence alignment is one of the most fundamental procedures in bioinformatics. Due to its many downstream applications, improvements to this procedure are of great importance. We consider two revolutionary concepts that emerged recently as candidates for improving the state-of-the-art alignment methods: AlphaFold and protein embeddings. Alignment improvements can come from structural alignment of AlphaFold-predicted structures or scoring based on similarity of protein embedding vectors, resp. Thorough comparison on many domains from BAliBASE and CDD demonstrates that the Ankh-score method produces much better sequence alignments than structural alignments using US-align of AlphaFold3-predicted structures. Both are better than the traditional method using BLOSUM matrices. This suggests that Ankh embedding vectors may possess certain information that is not available in the AlphaFold3-predicted structures.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Estimating statistical significance of local protein profile-profile alignments 96%
- Struct2Graph: A graph attention network for structure based predictions of protein-protein interactions 95%
- Multi-Head Attention-based U-Nets for Predicting Protein Domain Boundaries Using 1D Sequence Features and 2D Distance Maps 95%
Similar papers in this journal
- A fully open-source framework for deep learning protein real-valued distances 96%
- Predicting interchain contacts for homodimeric and homomultimeric protein complexes using multiple sequence alignments of monomers and deep learning 96%
- Benchmarking Protein Language Models for Protein Crystallization 95%
Similar papers in this journal
- Navigating the Unstructured by Evaluating AlphaFold's Efficacy in Predicting Missing Residues and Structural Disorder in Proteins 95%
- Using AlphaFold to predict the impact of single mutations on protein stability and function 95%
- SARS-CoV-2 protein structure and sequence mutations: evolutionary analysis and effects on virus variants SARS-CoV-2 protein structure and sequence mutations: 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.