How is structural divergence related to evolutionary information?

AbstractConservation and covariation measures, as other evolutionary analysis, require a high number of distant homologous sequences, therefore a lot of structural divergence can be expected in such divergent alignments. However, most works linking evolutionary and structural information use a single structure ignoring the structural variability inside a protein family. That common practice seems unrealistic to the light of this work.In this work we studied how structural divergence affects conservation and covariation estimations. We uncover that, within a protein family, ~51% of multiple sequence alignment columns change their exposed/buried status between structures. Also, ~53% of residue pairs that are in contact in one structure are not in contact in another structure from the same family. We found out that residue conservation is not directly related to the relative solvent accessible surface area of a single protein structure. Using information from all the available structures rather than from a single representative structure gives more confidence in the structural interpretation of the evolutionary signals. That is particularly important for diverse multiple sequence alignments, where structures can drastically differ. High covariation scores tend to indicate residue contacts that are conserved in the family, therefore, are not suitable to find protein/conformer specific contacts.Our results suggest that structural divergence should be considered for a better understanding of protein function, to transfer annotation by homology and to model protein evolution.

Download Full-text

Embeddings from protein language models predict conservation and variant effects

10.21203/rs.3.rs-584804/v1 ◽

2021 ◽

Author(s):

Céline Marquet ◽

Michael Heinzinger ◽

Tobias Olenyi ◽

Christian Dallago ◽

Michael Bernhofer ◽

...

Keyword(s):

Protein Function ◽

Language Models ◽

Single Amino Acid ◽

Sequence Alignments ◽

Multiple Sequence ◽

Multiple Sequence Alignments ◽

Human Proteins ◽

Entire Sequence ◽

Embedding Methods ◽

Better Than

Abstract The emergence of SARS-CoV-2 variants stressed the demand for tools allowing to interpret the effect of single amino acid variants (SAVs) on protein function. While Deep Mutational Scanning (DMS) sets continue to expand our understanding of the mutational landscape of single proteins, the results continue to challenge analyses. Protein Language Models (LMs) use the latest deep learning (DL) algorithms to leverage growing databases of protein sequences. These methods learn to predict missing or marked amino acids from the context of entire sequence regions. Here, we explored how to benefit from learned protein LM representations (embeddings) to predict SAV effects. Although we have failed so far to predict SAV effects directly from embeddings, this input alone predicted residue conservation almost as accurately from single sequences as using multiple sequence alignments (MSAs) with a two-state per-residue accuracy (conserved/not) of Q2=80% (embeddings) vs. 81% (ConSeq). Considering all SAVs at all residue positions predicted as conserved to affect function reached 68.6% (Q2: effect/neutral; for PMD) without optimization, compared to an expert solution such as SNAP2 (Q2=69.8). Combining predicted conservation with BLOSUM62 to obtain variant-specific binary predictions, DMS experiments of four human proteins were predicted better than by SNAP2, and better than by applying the same simplistic approach to conservation taken from ConSeq. Thus, embedding methods have become competitive with methods relying on MSAs for SAV effect prediction at a fraction of the costs in computing/energy. This allowed prediction of SAV effects for the entire human proteome (~20k proteins) within 17 minutes on a single GPU.

Download Full-text

Embeddings from protein language models predict conservation and variant effects

Human Genetics ◽

10.1007/s00439-021-02411-y ◽

2021 ◽

Author(s):

Céline Marquet ◽

Michael Heinzinger ◽

Tobias Olenyi ◽

Christian Dallago ◽

Kyra Erckert ◽

...

Keyword(s):

Protein Function ◽

Pearson Correlation ◽

Performance Measure ◽

Language Models ◽

Single Amino Acid ◽

Data Sets ◽

Sequence Alignments ◽

Multiple Sequence ◽

Multiple Sequence Alignments ◽

Human Proteins

AbstractThe emergence of SARS-CoV-2 variants stressed the demand for tools allowing to interpret the effect of single amino acid variants (SAVs) on protein function. While Deep Mutational Scanning (DMS) sets continue to expand our understanding of the mutational landscape of single proteins, the results continue to challenge analyses. Protein Language Models (pLMs) use the latest deep learning (DL) algorithms to leverage growing databases of protein sequences. These methods learn to predict missing or masked amino acids from the context of entire sequence regions. Here, we used pLM representations (embeddings) to predict sequence conservation and SAV effects without multiple sequence alignments (MSAs). Embeddings alone predicted residue conservation almost as accurately from single sequences as ConSeq using MSAs (two-state Matthews Correlation Coefficient—MCC—for ProtT5 embeddings of 0.596 ± 0.006 vs. 0.608 ± 0.006 for ConSeq). Inputting the conservation prediction along with BLOSUM62 substitution scores and pLM mask reconstruction probabilities into a simplistic logistic regression (LR) ensemble for Variant Effect Score Prediction without Alignments (VESPA) predicted SAV effect magnitude without any optimization on DMS data. Comparing predictions for a standard set of 39 DMS experiments to other methods (incl. ESM-1v, DeepSequence, and GEMME) revealed our approach as competitive with the state-of-the-art (SOTA) methods using MSA input. No method outperformed all others, neither consistently nor statistically significantly, independently of the performance measure applied (Spearman and Pearson correlation). Finally, we investigated binary effect predictions on DMS experiments for four human proteins. Overall, embedding-based methods have become competitive with methods relying on MSAs for SAV effect prediction at a fraction of the costs in computing/energy. Our method predicted SAV effects for the entire human proteome (~ 20 k proteins) within 40 min on one Nvidia Quadro RTX 8000. All methods and data sets are freely available for local and online execution through bioembeddings.com, https://github.com/Rostlab/VESPA, and PredictProtein.

Download Full-text

Epistatic contributions promote the unification of incompatible models of neutral molecular evolution

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.1913071117 ◽

2020 ◽

Vol 117 (11) ◽

pp. 5873-5882 ◽

Cited By ~ 1

Author(s):

Jose Alberto de la Paz ◽

Charisse M. Nartey ◽

Monisha Yuvaraj ◽

Faruck Morcos

Keyword(s):

Structural Information ◽

Stokes Shift ◽

Neutral Evolution ◽

Emergent Properties ◽

Sequence Evolution ◽

Sequence Alignments ◽

Multiple Sequence ◽

Multiple Sequence Alignments ◽

Analysis Methodology ◽

The Relationship

We introduce a model of amino acid sequence evolution that accounts for the statistical behavior of real sequences induced by epistatic interactions. We base the model dynamics on parameters derived from multiple sequence alignments analyzed by using direct coupling analysis methodology. Known statistical properties such as overdispersion, heterotachy, and gamma-distributed rate-across-sites are shown to be emergent properties of this model while being consistent with neutral evolution theory, thereby unifying observations from previously disjointed evolutionary models of sequences. The relationship between site restriction and heterotachy is characterized by tracking the effective alphabet dynamics of sites. We also observe an evolutionary Stokes shift in the fitness of sequences that have undergone evolution under our simulation. By analyzing the structural information of some proteins, we corroborate that the strongest Stokes shifts derive from sites that physically interact in networks near biochemically important regions. Perspectives on the implementation of our model in the context of the molecular clock are discussed.

Download Full-text

Entropy, Fluctuations, and Disordered Proteins

Entropy ◽

10.3390/e21080764 ◽

2019 ◽

Vol 21 (8) ◽

pp. 764 ◽

Cited By ~ 2

Author(s):

Eshel Faraggi ◽

A. Keith Dunker ◽

Robert L. Jernigan ◽

Andrzej Kloczkowski

Keyword(s):

Protein Function ◽

Accessible Surface Area ◽

Disordered Proteins ◽

Dihedral Angles ◽

Residue Type ◽

Sequence Structure ◽

Multiple Sequence ◽

Accessible Surface ◽

Positive Correlations ◽

Related Proteins

Entropy should directly reflect the extent of disorder in proteins. By clustering structurally related proteins and studying the multiple-sequence-alignment of the sequences of these clusters, we were able to link between sequence, structure, and disorder information. We introduced several parameters as measures of fluctuations at a given MSA site and used these as representative of the sequence and structure entropy at that site. In general, we found a tendency for negative correlations between disorder and structure, and significant positive correlations between disorder and the fluctuations in the system. We also found evidence for residue-type conservation for those residues proximate to potentially disordered sites. Mutation at the disorder site itself appear to be allowed. In addition, we found positive correlation for disorder and accessible surface area, validating that disordered residues occur in exposed regions of proteins. Finally, we also found that fluctuations in the dihedral angles at the original mutated residue and disorder are positively correlated while dihedral angle fluctuations in spatially proximal residues are negatively correlated with disorder. Our results seem to indicate permissible variability in the disordered site, but greater rigidity in the parts of the protein with which the disordered site interacts. This is another indication that disordered residues are involved in protein function.

Download Full-text

CAUSA 2.0: accurate and consistent evolutionary analysis of proteins using codon and amino acid unified sequence alignments

10.7287/peerj.preprints.1214v1 ◽

2015 ◽

Author(s):

Xiaolong Wang ◽

Chao Yang

Keyword(s):

Amino Acid ◽

Sequence Alignment ◽

Novel Mutation ◽

Genetic Diseases ◽

Amino Acid Level ◽

Evolutionary Analysis ◽

Sequence Alignments ◽

Multiple Sequence ◽

Coding Sequences ◽

Functional Changes

Multiple sequence alignment (MSA) is widely used to reveal structural and functional changes leading to genetic differences among species, and to reconstruct evolutionary histories of related genes, proteins and genomes. Traditionally, proteins and their coding sequences (CDSs) are aligned and analyzed separately, but often drastically different conclusions were drawn on a same set of data. Here we present a new alignment strategy, Codon and Amino Acid Unified Sequence Alignment (CAUSA) 2.0, which aligns proteins and their coding sequences simultaneously. CAUSA 2.0 optimizes the alignment of CDSs at both codon and amino acid level efficiently. Theoretical analysis showed that CAUSA 2.0 enhances the entropy information content of MSA. Empirical data analysis demonstrated that CAUSA 2.0 is more accurate and consistent than nucleotide, protein or codon level alignments. CAUSA 2.0 locates in-frame indels more accurately, makes the alignment of coding sequences biologically more significant, and reveals several novel mutation mechanisms that relate to some genetic diseases. CAUSA 2.0 is available in website www.DNAPlusPro.com .

Download Full-text

AttentiveDist: Protein Inter-Residue Distance Prediction Using Deep Learning with Attention on Quadruple Multiple Sequence Alignments

10.1101/2020.11.24.396770 ◽

2020 ◽

Author(s):

Aashish Jain ◽

Genki Terashi ◽

Yuki Kagaya ◽

Sai Raghavendra Maddhuri Venkata Subramaniya ◽

Charles Christoffer ◽

...

Keyword(s):

Deep Learning ◽

Structure Prediction ◽

Prediction Models ◽

3D Structure ◽

Evolutionary Information ◽

Sequence Alignments ◽

Multiple Sequence ◽

Contact Prediction ◽

Multiple Sequence Alignments ◽

Distance Prediction

ABSTRACTProtein 3D structure prediction has advanced significantly in recent years due to improving contact prediction accuracy. This improvement has been largely due to deep learning approaches that predict inter-residue contacts and, more recently, distances using multiple sequence alignments (MSAs). In this work we present AttentiveDist, a novel approach that uses different MSAs generated with different E-values in a single model to increase the co-evolutionary information provided to the model. To determine the importance of each MSA’s feature at the inter-residue level, we added an attention layer to the deep neural network. The model is trained in a multi-task fashion to also predict backbone and orientation angles further improving the inter-residue distance prediction. We show that AttentiveDist outperforms the top methods for contact prediction in the CASP13 structure prediction competition. To aid in structure modeling we also developed two new deep learning-based sidechain center distance and peptide-bond nitrogen-oxygen distance prediction models. Together these led to a 12% increase in TM-score from the best server method in CASP13 for structure prediction.

Download Full-text

Rosetta design with co-evolutionary information retains protein function

PLoS Computational Biology ◽

10.1371/journal.pcbi.1008568 ◽

2021 ◽

Vol 17 (1) ◽

pp. e1008568

Author(s):

Samuel Schmitz ◽

Moritz Ertelt ◽

Rainer Merkl ◽

Jens Meiler

Keyword(s):

Protein Design ◽

Protein Function ◽

Complex Function ◽

Evolutionary Information ◽

Homologous Proteins ◽

Multiple Sequence ◽

Novel Proteins ◽

Negative Effect ◽

Correlated Mutations ◽

A Minor

Computational protein design has the ambitious goal of crafting novel proteins that address challenges in biology and medicine. To overcome these challenges, the computational protein modeling suite Rosetta has been tailored to address various protein design tasks. Recently, statistical methods have been developed that identify correlated mutations between residues in a multiple sequence alignment of homologous proteins. These subtle inter-dependencies in the occupancy of residue positions throughout evolution are crucial for protein function, but we found that three current Rosetta design approaches fail to recover these co-evolutionary couplings. Thus, we developed the Rosetta method ResCue (residue-coupling enhanced) that leverages co-evolutionary information to favor sequences which recapitulate correlated mutations, as observed in nature. To assess the protocols via recapitulation designs, we compiled a benchmark of ten proteins each represented by two, structurally diverse states. We could demonstrate that ResCue designed sequences with an average sequence recovery rate of 70%, whereas three other protocols reached not more than 50%, on average. Our approach had higher recovery rates also for functionally important residues, which were studied in detail. This improvement has only a minor negative effect on the fitness of the designed sequences as assessed by Rosetta energy. In conclusion, our findings support the idea that informing protocols with co-evolutionary signals helps to design stable and native-like proteins that are compatible with the different conformational states required for a complex function.

Download Full-text

Protein embeddings and deep learning predict binding residues for various ligand classes

10.1101/2021.09.03.458869 ◽

2021 ◽

Author(s):

Maria Littmann ◽

Michael Heinzinger ◽

Christian Dallago ◽

Konstantin Weissenow ◽

Burkhard Rost

Keyword(s):

Nucleic Acids ◽

Metal Ions ◽

Small Molecules ◽

Protein Function ◽

Language Model ◽

Data Sets ◽

Sequence Alignments ◽

Multiple Sequence ◽

Human Proteins ◽

Binding Residues

AbstractOne important aspect of protein function is the binding of proteins to ligands, including small molecules, metal ions, and macromolecules such as DNA or RNA. Despite decades of experimental progress many binding sites remain obscure. Here, we proposed bindEmbed21, a method predicting whether a protein residue binds to metal ions, nucleic acids, or small molecules. The Artificial Intelligence (AI)-based method exclusively uses embeddings from the Transformer-based protein Language Model (pLM) ProtT5 as input. Using only single sequences without creating multiple sequence alignments (MSAs), bindEmbed21DL outperformed existing MSA-based methods. Combination with homology-based inference increased performance to F1=48±3% (95% CI) and MCC=0.46±0.04 when merging all three ligand classes into one. All results were confirmed by three independent data sets. Focusing on very reliably predicted residues could complement experimental evidence: For the 25% most strongly predicted binding residues, at least 73% were correctly predicted even when ignoring the problem of missing experimental annotations. The new method bindEmbed21 is fast, simple, and broadly applicable - neither using structure nor MSAs. Thereby, it found binding residues in over 42% of all human proteins not otherwise implied in binding and predicted about 6% of all residues as binding to metal ions, nucleic acids, or small molecules.

Download Full-text

Analysis of several key factors influencing deep learning-based inter-residue contact prediction

Bioinformatics ◽

10.1093/bioinformatics/btz679 ◽

2019 ◽

Cited By ~ 1

Author(s):

Tianqi Wu ◽

Jie Hou ◽

Badri Adhikari ◽

Jianlin Cheng

Keyword(s):

Deep Learning ◽

Structural Information ◽

Protein Structures ◽

Supplementary Information ◽

Prediction Methods ◽

Key Factors ◽

Sequence Alignments ◽

Multiple Sequence ◽

Contact Prediction ◽

Ab Initio Approach

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.

Download Full-text

R-chie: a web server and R package for visualizing cis and trans RNA–RNA, RNA–DNA and DNA–DNA interactions

Nucleic Acids Research ◽

10.1093/nar/gkaa708 ◽

2020 ◽

Vol 48 (18) ◽

pp. e105-e105 ◽

Cited By ~ 1

Author(s):

Volodymyr Tsybulskyi ◽

Mohamed Mounir ◽

Irmtraud M Meyer

Keyword(s):

Web Server ◽

R Package ◽

Quantitative Information ◽

Evolutionary Information ◽

Dna Interactions ◽

Sequence Alignments ◽

Multiple Sequence ◽

Functional Roles ◽

Genome Interactions

Abstract Interactions between biological entities are key to understanding their potential functional roles. Three fields of research have recently made particular progress: the investigation of transRNA–RNA and RNA–DNA transcriptome interactions and of trans DNA–DNA genome interactions. We now have both experimental and computational methods for examining these interactions in vivo and on a transcriptome- and genome-wide scale, respectively. Often, key insights can be gained by visually inspecting figures that manage to combine different sources of evidence and quantitative information. We here present R-chie, a web server and R package for visualizing cis and transRNA–RNA, RNA–DNA and DNA–DNA interactions. For this, we have completely revised and significantly extended an earlier version of R-chie (1) which was initially introduced for visualizing RNA secondary structure features. The new R-chie offers a range of unique features for visualizing cis and transRNA–RNA, RNA–DNA and DNA–DNA interactions. Particularly note-worthy features include the ability to incorporate evolutionary information, e.g. multiple-sequence alignments, to compare two alternative sets of information and to incorporate detailed, quantitative information. R-chie is readily available via a web server as well as a corresponding R package called R4RNA which can be used to run the software locally.

Download Full-text