May 2024
·
11 Reads
Current Opinion in Structural Biology
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
May 2024
·
11 Reads
Current Opinion in Structural Biology
February 2024
·
63 Reads
·
7 Citations
Nature Methods
Deep learning models, such as AlphaFold2 and RosettaFold, enable high-accuracy protein structure prediction. However, large protein complexes are still challenging to predict due to their size and the complexity of interactions between multiple subunits. Here we present CombFold, a combinatorial and hierarchical assembly algorithm for predicting structures of large protein complexes utilizing pairwise interactions between subunits predicted by AlphaFold2. CombFold accurately predicted (TM-score >0.7) 72% of the complexes among the top-10 predictions in two datasets of 60 large, asymmetric assemblies. Moreover, the structural coverage of predicted complexes was 20% higher compared to corresponding Protein Data Bank entries. We applied the method on complexes from Complex Portal with known stoichiometry but without known structure and obtained high-confidence predictions. CombFold supports the integration of distance restraints based on crosslinking mass spectrometry and fast enumeration of possible complex stoichiometries. CombFold’s high accuracy makes it a promising tool for expanding structural coverage beyond monomeric proteins.
October 2023
·
194 Reads
·
23 Citations
Proteins Structure Function and Bioinformatics
We present the results for CAPRI Round 54, the 5th joint CASP‐CAPRI protein assembly prediction challenge. The Round offered 37 targets, including 14 homodimers, 3 homo‐trimers, 13 heterodimers including 3 antibody–antigen complexes, and 7 large assemblies. On average ~70 CASP and CAPRI predictor groups, including more than 20 automatics servers, submitted models for each target. A total of 21 941 models submitted by these groups and by 15 CAPRI scorer groups were evaluated using the CAPRI model quality measures and the DockQ score consolidating these measures. The prediction performance was quantified by a weighted score based on the number of models of acceptable quality or higher submitted by each group among their five best models. Results show substantial progress achieved across a significant fraction of the 60+ participating groups. High‐quality models were produced for about 40% of the targets compared to 8% two years earlier. This remarkable improvement is due to the wide use of the AlphaFold2 and AlphaFold2‐Multimer software and the confidence metrics they provide. Notably, expanded sampling of candidate solutions by manipulating these deep learning inference engines, enriching multiple sequence alignments, or integration of advanced modeling tools, enabled top performing groups to exceed the performance of a standard AlphaFold2‐Multimer version used as a yard stick. This notwithstanding, performance remained poor for complexes with antibodies and nanobodies, where evolutionary relationships between the binding partners are lacking, and for complexes featuring conformational flexibility, clearly indicating that the prediction of protein complexes remains a challenging problem.
July 2023
·
219 Reads
·
2 Citations
We present the results for CAPRI Round 54, the 5th joint CASP-CAPRI protein assembly prediction challenge. The Round offered 37 targets, including 14 homo-dimers, 3 homo-trimers, 13 hetero-dimers including 3 antibody-antigen complexes, and 7 large assemblies. On average ~70 CASP and CAPRI predictor groups, including more than 20 automatics servers, submitted models for each target. A total of 21941 models submitted by these groups and by 15 CAPRI scorer groups were evaluated using the CAPRI model quality measures and the DockQ score consolidating these measures. The prediction performance was quantified by a weighted score based on the number of models of acceptable quality or higher submitted by each group among their 5 best models. Results show substantial progress achieved across a significant fraction of the 60+ participating groups. High-quality models were produced for about 40% for the targets compared to 8% two years earlier, a remarkable improvement resulting from the wide use of the AlphaFold2 and AlphaFold-Multimer software. Creative use was made of the deep learning inference engines affording the sampling of a much larger number of models and enriching the multiple sequence alignments with sequences from various sources. Wide use was also made of the AlphaFold confidence metrics to rank models, permitting top performing groups to exceed the results of the public AlphaFold-Multimer version used as a yard stick. This notwithstanding, performance remained poor for complexes with antibodies and nanobodies, where evolutionary relationships between the binding partners are lacking, and for complexes featuring conformational flexibility, clearly indicating that the prediction of protein complexes remains a challenging problem.
May 2023
·
77 Reads
·
2 Citations
Deep learning models, such as AlphaFold2 and RosettaFold, enable high-accuracy protein structure prediction. However, large protein complexes are still challenging to predict due to their size and the complexity of interactions between multiple subunits. Here we present CombFold, a combinatorial and hierarchical assembly algorithm for predicting structures of large protein complexes utilizing pairwise interactions between subunits predicted by AlphaFold2. CombFold accurately predicted (TM-score > 0.7) 72% of the complexes among the Top-10 predictions in two datasets of 60 large, asymmetric assemblies. Moreover, the structural coverage of predicted complexes was 20% higher compared to corresponding PDB entries. We applied the method on complexes from Complex Portal with known stoichiometry but without known structure and obtained high-confidence predictions. CombFold supports the integration of distance restraints based on crosslinking mass spectrometry and fast enumeration of possible complex stoichiometries. CombFold’s high accuracy makes it a promising tool for expanding structural coverage beyond monomeric proteins.
... Two monomer protein structures with a TM-score> 0.5 are considered to have the same topology [71]. For complex models, they are considered acceptable quality if the TM-score is above 0.7 and high quality if the TM-score is above 0.8 [72]. When the reference structure is unknown, the predicted TM-score (pTM) [27] derived from AF2 assumes the existence of a distribution of probable structures and uses the pairwise error matrix to find the expected value of the TM-score for the predicted structure. ...
February 2024
Nature Methods
... CASP (Critical Assessment of Techniques for Protein Structure Prediction) and CAPRI (Critical Assessment of PRedicted Interactions) are two worldwide experiments that rigorously test computational methods of predicting protein complex structures and estimate their accuracy. The latest competitions [33] offer widely accepted measures for assessing the overall (global) structural quality, interface quality, and local structural quality of predicted complex structures with respect to their true structures, as well as for evaluating the performance of EMA methods of estimating/predicting the accuracy of predicted complex structures, as discussed below. ...
October 2023
Proteins Structure Function and Bioinformatics
... Complexes with weak evolutionary signals, lacking structural templates, or assembled from many heterogeneous subunits and containing over 1800 residues proved particularly challenging (Akdel et al., 2022, Ozden et al., 2023. These shortcomings were in part alleviated by optimizing MSA construction (Ozden et al., 2023), such as done in AFProfile (Bryant and Noé, 2023) and ESMPair ; increasing the number and diversity of predicted complex structures, for example, by increasing the number of iterations through the AF2-Multimer network (recycles) or randomly disabling neurons (dropout) (Johansson-Akhe and Wallner, 2022, Wallner, 2023); and assembling higher order complexes from smaller interacting subcomponents individually predicted by AF2-Multimer, such as done in MolPC , CombFold (Shor and Schneidman-Duhovny, 2023), and the method developed by Jeppesen and André. However, none of these strategies individually yielded acceptable structures for all test complexes. ...
May 2023