Abstract Motivation The success of genome sequencing techniques has resulted in rapid explosion of protein sequences. Collections of multiple homologous sequences can provide critical information to the modeling of structure and function of unknown proteins. There are however no standard and efficient pipeline available for sensitive multiple sequence alignment (MSA) collection. This is particularly challenging when large whole-genome and metagenome databases are involved. Results We developed DeepMSA, a new open-source method for sensitive MSA construction, which has homologous sequences and alignments created from multi-sources of whole-genome and metagenome databases through complementary hidden Markov model algorithms. The practical usefulness of the pipeline was examined in three large-scale benchmark experiments based on 614 non-redundant proteins. First, DeepMSA was utilized to generate MSAs for residue-level contact prediction by six coevolution and deep learning-based programs, which resulted in an accuracy increase in long-range contacts by up to 24.4% compared to the default programs. Next, multiple threading programs are performed for homologous structure identification, where the average TM-score of the template alignments has over 7.5% increases with the use of the new DeepMSA profiles. Finally, DeepMSA was used for secondary structure prediction and resulted in statistically significant improvements in the Q3 accuracy. It is noted that all these improvements were achieved without re-training the parameters and neural-network models, demonstrating the robustness and general usefulness of the DeepMSA in protein structural bioinformatics applications, especially for targets without homologous templates in the PDB library. Availability and implementation https://zhanglab.ccmb.med.umich.edu/DeepMSA/. Supplementary information Supplementary data are available at Bioinformatics online.
more »
« less
End-to-end learning of multiple sequence alignments with differentiable Smith–Waterman
Multiple sequence alignments (MSAs) of homologous sequences contain information on structural and functional constraints and their evolutionary histories. Despite their importance for many downstream tasks, such as structure prediction, MSA generation is often treated as a separate pre-processing step, without any guidance from the application it will be used for.
Here, we implement a smooth and differentiable version of the Smith–Waterman pairwise alignment algorithm that enables jointly learning an MSA and a downstream machine learning system in an end-to-end fashion. To demonstrate its utility, we introduce SMURF (Smooth Markov Unaligned Random Field), a new method that jointly learns an alignment and the parameters of a Markov Random Field for unsupervised contact prediction. We find that SMURF learns MSAs that mildly improve contact prediction on a diverse set of protein and RNA families. As a proof of concept, we demonstrate that by connecting our differentiable alignment module to AlphaFold2 and maximizing predicted confidence, we can learn MSAs that improve structure predictions over the initial MSAs. Interestingly, the alignments that improve AlphaFold predictions are self-inconsistent and can be viewed as adversarial. This work highlights the potential of differentiable dynamic programming to improve neural network pipelines that rely on an alignment and the potential dangers of optimizing predictions of protein sequences with methods that are not fully understood.
Our code and examples are available at: https://github.com/spetti/SMURF.
Supplementary data are available at Bioinformatics online.
- Award ID(s):
- 2032259
- NSF-PAR ID:
- 10388948
- Publisher / Repository:
- Oxford University Press
- Date Published:
- Journal Name:
- Bioinformatics
- Volume:
- 39
- Issue:
- 1
- ISSN:
- 1367-4811
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract We report the results of residue‐residue contact prediction of a new pipeline built purely on the learning of coevolutionary features in the CASP13 experiment. For a query sequence, the pipeline starts with the collection of multiple sequence alignments (MSAs) from multiple genome and metagenome sequence databases using two complementary Hidden Markov Model (HMM)‐based searching tools. Three profile matrices, built on covariance, precision, and pseudolikelihood maximization respectively, are then created from the MSAs, which are used as the input features of a deep residual convolutional neural network architecture for contact‐map training and prediction. Two ensembling strategies have been proposed to integrate the matrix features through end‐to‐end training and stacking, resulting in two complementary programs called TripletRes and ResTriplet, respectively. For the 31 free‐modeling domains that do not have homologous templates in the PDB, TripletRes and ResTriplet generated comparable results with an average accuracy of 0.640 and 0.646, respectively, for the top
L /5 long‐range predictions, where 71% and 74% of the cases have an accuracy above 0.5. Detailed data analyses showed that the strength of the pipeline is due to the sensitive MSA construction and the advanced strategies for coevolutionary feature ensembling. Domain splitting was also found to help enhance the contact prediction performance. Nevertheless, contact models for tail regions, which often involve a high number of alignment gaps, and for targets with few homologous sequences are still suboptimal. Development of new approaches where the model is specifically trained on these regions and targets might help address these problems. -
more » « less
Abstract Motivation The analysis of sequence conservation patterns has been widely utilized to identify functionally important (catalytic and ligand-binding) protein residues for over a half-century. Despite decades of development, on average state-of-the-art non-template-based functional residue prediction methods must predict ∼25% of a protein’s total residues to correctly identify half of the protein’s functional site residues. The overwhelming proportion of false positives results in reported ‘F-Scores’ of ∼0.3. We investigated the limits of current approaches, focusing on the so-far neglected impact of the specific choice of homologs included in multiple sequence alignments (MSAs).
Results The limits of conservation-based functional residue prediction were explored by surveying the binding sites of 1023 proteins. A straightforward conservation analysis of MSAs composed of randomly selected homologs sampled from a PSI-BLAST search achieves average F-Scores of ∼0.3, a performance matching that reported by state-of-the-art methods, which often consider additional features for the prediction in a machine learning setting. Interestingly, we found that a simple combinatorial MSA sampling algorithm will in almost every case produce an MSA with an optimal set of homologs whose conservation analysis reaches average F-Scores of ∼0.6, doubling state-of-the-art performance. We also show that this is nearly at the theoretical limit of possible performance given the agreement between different binding site definitions. Additionally, we showcase the progress in this direction made by Selection of Alignment by Maximal Mutual Information (SAMMI), an information-theory-based approach to identifying biologically informative MSAs. This work highlights the importance and the unused potential of optimally composed MSAs for conservation analysis.
Supplementary information Supplementary data are available at Bioinformatics online.
-
Abstract Motivation Deep learning has become the dominant technology for protein contact prediction. However, the factors that affect the performance of deep learning in contact prediction have not been systematically investigated. Results We analyzed the results of our three deep learning-based contact prediction methods (MULTICOM-CLUSTER, MULTICOM-CONSTRUCT and MULTICOM-NOVEL) in the CASP13 experiment and identified several key factors [i.e. deep learning technique, multiple sequence alignment (MSA), distance distribution prediction and domain-based contact integration] that influenced the contact prediction accuracy. We compared our convolutional neural network (CNN)-based contact prediction methods with three coevolution-based methods on 75 CASP13 targets consisting of 108 domains. We demonstrated that the CNN-based multi-distance approach was able to leverage global coevolutionary coupling patterns comprised of multiple correlated contacts for more accurate contact prediction than the local coevolution-based methods, leading to a substantial increase of precision by 19.2 percentage points. We also tested different alignment methods and domain-based contact prediction with the deep learning contact predictors. The comparison of the three methods showed deeper sequence alignments and the integration of domain-based contact prediction with the full-length contact prediction improved the performance of contact prediction. Moreover, we demonstrated that the domain-based contact prediction based on a novel ab initio approach of parsing domains from MSAs alone without using known protein structures was a simple, fast approach to improve contact prediction. Finally, we showed that predicting the distribution of inter-residue distances in multiple distance intervals could capture more structural information and improve binary contact prediction. Availability and implementation https://github.com/multicom-toolbox/DNCON2/. Supplementary information Supplementary data are available at Bioinformatics online.more » « less
-
more » « less
Abstract Motivation Protein structure prediction has been greatly improved by deep learning, but the contribution of different information is yet to be fully understood. This article studies the impacts of two kinds of information for structure prediction: template and multiple sequence alignment (MSA) embedding. Templates have been used by some methods before, such as AlphaFold2, RoseTTAFold and RaptorX. AlphaFold2 and RosetTTAFold only used templates detected by HHsearch, which may not perform very well on some targets. In addition, sequence embedding generated by pre-trained protein language models has not been fully explored for structure prediction. In this article, we study the impact of templates (including the number of templates, the template quality and how the templates are generated) on protein structure prediction accuracy, especially when the templates are detected by methods other than HHsearch. We also study the impact of sequence embedding (generated by MSATransformer and ESM-1b) on structure prediction.
Results We have implemented a deep learning method for protein structure prediction that may take templates and MSA embedding as extra inputs. We study the contribution of templates and MSA embedding to structure prediction accuracy. Our experimental results show that templates can improve structure prediction on 71 of 110 CASP13 (13th Critical Assessment of Structure Prediction) targets and 47 of 91 CASP14 targets, and templates are particularly useful for targets with similar templates. MSA embedding can improve structure prediction on 63 of 91 CASP14 (14th Critical Assessment of Structure Prediction) targets and 87 of 183 CAMEO targets and is particularly useful for proteins with shallow MSAs. When both templates and MSA embedding are used, our method can predict correct folds (TMscore > 0.5) for 16 of 23 CASP14 FM targets and 14 of 18 Continuous Automated Model Evaluation (CAMEO) targets, outperforming RoseTTAFold by 5% and 7%, respectively.
Availability and implementation Available at https://github.com/xluo233/RaptorXFold.
Supplementary information Supplementary data are available at Bioinformatics online.
