AlphaFold2 and ESMFold: A large-scale pairwise model comparison of human enzymes upon Pfam functional annotation
AlphaFold2 predicts protein structures from structural and functional knowledge. Alternatively, ESMFold does the same adopting protein language models. Here, we map available Pfam domains on pairs of models of the human reference proteome computed with both procedures and we compare the mapped regio...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Computational and Structural Biotechnology Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S200103702500008X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586266618626048 |
|---|---|
| author | Matteo Manfredi Gabriele Vazzana Castrense Savojardo Pier Luigi Martelli Rita Casadio |
| author_facet | Matteo Manfredi Gabriele Vazzana Castrense Savojardo Pier Luigi Martelli Rita Casadio |
| author_sort | Matteo Manfredi |
| collection | DOAJ |
| description | AlphaFold2 predicts protein structures from structural and functional knowledge. Alternatively, ESMFold does the same adopting protein language models. Here, we map available Pfam domains on pairs of models of the human reference proteome computed with both procedures and we compare the mapped regions relevant for functional annotation. We find that, rather irrespectively of the global superimposition of the pairwise models, Pfam-containing regions overlap with a TM-score above 0.8 and a predicted local distance difference test (pLDDT) which is higher than the rest of the modeled sequence. This indicates that both methods are similarly performing in modeled regions that overlap Pfam domains, carrying structural and functional information, with pLDDT values slightly higher for AlphaFold2. The mapping of 9834 Pfam domains also allows the location of 2578 active sites in 3382 enzymes of the human proteome, including 807 proteins for which the active site is not reported in UniProt. |
| format | Article |
| id | doaj-art-681092a4356842a79e11855a5b1b9e9b |
| institution | Kabale University |
| issn | 2001-0370 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computational and Structural Biotechnology Journal |
| spelling | doaj-art-681092a4356842a79e11855a5b1b9e9b2025-01-26T05:03:42ZengElsevierComputational and Structural Biotechnology Journal2001-03702025-01-0127461466AlphaFold2 and ESMFold: A large-scale pairwise model comparison of human enzymes upon Pfam functional annotationMatteo Manfredi0Gabriele Vazzana1Castrense Savojardo2Pier Luigi Martelli3Rita Casadio4Biocomputing Group, University of Bologna, Italy; Dept. of Pharmacy and Biotechnology, University of Bologna, ItalyBiocomputing Group, University of Bologna, Italy; Dept. of Pharmacy and Biotechnology, University of Bologna, ItalyBiocomputing Group, University of Bologna, Italy; Dept. of Pharmacy and Biotechnology, University of Bologna, ItalyBiocomputing Group, University of Bologna, Italy; Dept. of Pharmacy and Biotechnology, University of Bologna, Italy; Corresponding authors at: Biocomputing Group, University of Bologna, Italy.Biocomputing Group, University of Bologna, Italy; the Alma Climate Institute, University of Bologna, Italy; Corresponding authors at: Biocomputing Group, University of Bologna, Italy.AlphaFold2 predicts protein structures from structural and functional knowledge. Alternatively, ESMFold does the same adopting protein language models. Here, we map available Pfam domains on pairs of models of the human reference proteome computed with both procedures and we compare the mapped regions relevant for functional annotation. We find that, rather irrespectively of the global superimposition of the pairwise models, Pfam-containing regions overlap with a TM-score above 0.8 and a predicted local distance difference test (pLDDT) which is higher than the rest of the modeled sequence. This indicates that both methods are similarly performing in modeled regions that overlap Pfam domains, carrying structural and functional information, with pLDDT values slightly higher for AlphaFold2. The mapping of 9834 Pfam domains also allows the location of 2578 active sites in 3382 enzymes of the human proteome, including 807 proteins for which the active site is not reported in UniProt.http://www.sciencedirect.com/science/article/pii/S200103702500008XHuman enzyme structural and functional annotationPfam domainsEnzyme Active siteAlphaFold2ESMFoldHuman Reference Proteome |
| spellingShingle | Matteo Manfredi Gabriele Vazzana Castrense Savojardo Pier Luigi Martelli Rita Casadio AlphaFold2 and ESMFold: A large-scale pairwise model comparison of human enzymes upon Pfam functional annotation Computational and Structural Biotechnology Journal Human enzyme structural and functional annotation Pfam domains Enzyme Active site AlphaFold2 ESMFold Human Reference Proteome |
| title | AlphaFold2 and ESMFold: A large-scale pairwise model comparison of human enzymes upon Pfam functional annotation |
| title_full | AlphaFold2 and ESMFold: A large-scale pairwise model comparison of human enzymes upon Pfam functional annotation |
| title_fullStr | AlphaFold2 and ESMFold: A large-scale pairwise model comparison of human enzymes upon Pfam functional annotation |
| title_full_unstemmed | AlphaFold2 and ESMFold: A large-scale pairwise model comparison of human enzymes upon Pfam functional annotation |
| title_short | AlphaFold2 and ESMFold: A large-scale pairwise model comparison of human enzymes upon Pfam functional annotation |
| title_sort | alphafold2 and esmfold a large scale pairwise model comparison of human enzymes upon pfam functional annotation |
| topic | Human enzyme structural and functional annotation Pfam domains Enzyme Active site AlphaFold2 ESMFold Human Reference Proteome |
| url | http://www.sciencedirect.com/science/article/pii/S200103702500008X |
| work_keys_str_mv | AT matteomanfredi alphafold2andesmfoldalargescalepairwisemodelcomparisonofhumanenzymesuponpfamfunctionalannotation AT gabrielevazzana alphafold2andesmfoldalargescalepairwisemodelcomparisonofhumanenzymesuponpfamfunctionalannotation AT castrensesavojardo alphafold2andesmfoldalargescalepairwisemodelcomparisonofhumanenzymesuponpfamfunctionalannotation AT pierluigimartelli alphafold2andesmfoldalargescalepairwisemodelcomparisonofhumanenzymesuponpfamfunctionalannotation AT ritacasadio alphafold2andesmfoldalargescalepairwisemodelcomparisonofhumanenzymesuponpfamfunctionalannotation |