Explaining how mutations affect AlphaFold predictions
Clore, M. F.; Thole, J. F.; Dontha, S.; Sharma, P.; Jensen, D.; Volkman, B.; Coudron, M.; Porter, L.
Show abstract
Transformer models, neural networks that learn context by identifying relationships in sequential data, underpin many recent advances in artificial intelligence. Nevertheless, their inner workings are difficult to explain. Here, we find that a transformer model within the AlphaFold architecture uses simple, sparse patterns of amino acids to select protein conformations. To identify these patterns, we developed a straightforward algorithm called Conformational Attention Analysis Tool (CAAT). CAAT identifies amino acid positions that affect AlphaFolds predictions substantially when modified. These effects are corroborated by experiments in several cases. By contrast, modifying amino acids ignored by CAAT affects AlphaFold predictions less, regardless of experimental ground truth. Our results demonstrate that CAAT successfully identifies the positions of some amino acids important for protein structure prediction, narrowing the search space required to predict effective mutations and suggesting a framework that can be applied to other transformer-based neural networks.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Structural basis of the activation of the CC chemokine receptor 5 by a chemokine agonist 96%
- A disease resistance protein triggers oligomerization of its NLR helper into a hexameric resistosome to mediate innate immunity 95%
- The mechanisms of catalysis and ligand binding for the SARS-CoV-2 NSP3 macrodomain from neutron and X-ray diffraction at room temperature 95%
Similar papers in this journal
- An evolutionarily conserved tryptophan cage promotes folding of the extended RNA recognition motif in the hnRNPR-like protein family 96%
- Architecture and self-assembly of the SARS-CoV-2 nucleocapsid protein 95%
- Crystal structure and molecular dynamics of human POLDIP2, a multifaceted adaptor protein in metabolism and genome stability 94%
Similar papers in this journal
Similar papers in this journal
- Deep mutational scanning and machine learning reveal structural and molecular rules governing allosteric hotspots in homologous proteins 96%
- Mechanistic and evolutionary insights into isoform-specific 'supercharging' in DCLK family kinases 96%
- Integrative modeling reveals the molecular architecture of the Intraflagellar Transport A (IFT-A) complex 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.