On interactive spatial visualisation of pathogenicity predictions
Xu, J.; Kovacs, A. S.; Portelli, S.; Malik, A. J.; Ascher, D. B.
Show abstract
The past few years have revolutionised the utility of protein structural information in assessing disease risk. Such efforts have been pioneered by the DeepMind and Meta teams, who initially developed accurate protein prediction tools AlphaFold and ESMFold, respectively. More recently, both have been readapted to create AlphaMissene and ESM1b, through which, the pathogenicity potential of all possible missense mutations within the human proteome has been predicted. Similarly, VESPA was created as an alignment-agnostic predictor, which infers conservation from protein-language model embeddings to assign an effect for each variant. To facilitate their utility, we present a unified dashboard, MissenseViewer, which permits direct predictor comparison, and visualisation within the protein 3-dimensional structural context. Our interactive resource is freely available at: https://biosig.lab.uq.edu.au/missenseviewer/.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- CICLOP: A Robust, Faster, and Accurate Computational Framework for Protein Inner Cavity Detection 95%
- Rhapsody: Pathogenicity prediction of human missense variants based on protein sequence, structure and dynamics 94%
- MutaFrame - an interpretative visualization framework for deleteriousness prediction of missense variants in the human exome 93%
Similar papers in this journal
- LYRUS: A Machine Learning Model for Predicting the Pathogenicity of Missense Variants 94%
- TITINdb2 - Expanding Annotation and Structural Information for Protein Variants in the Giant Sarcomeric Protein Titin 92%
- Challenges in predicting PROTAC-mediated Protein-Protein Interfaces with AlphaFold reveal a General Limitation on Small Interfaces 92%
Similar papers in this journal
"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.