Rapid Identification of Sequences for Orphan Enzymes to Power Accurate Protein Annotation

The power of genome sequencing depends on the ability to understand what those genes and their proteins products actually do. The automated methods used to assign functions to putative proteins in newly sequenced organisms are limited by the size of our library of proteins with both known function and sequence. Unfortunately this library grows slowly, lagging well behind the rapid increase in novel protein sequences produced by modern genome sequencing methods. One potential source for rapidly expanding this functional library is the “back catalog” of enzymology – “orphan enzymes,” those enzymes that have been characterized and yet lack any associated sequence. There are hundreds of orphan enzymes in the Enzyme Commission (EC) database alone. In this study, we demonstrate how this orphan enzyme “back catalog” is a fertile source for rapidly advancing the state of protein annotation. Starting from three orphan enzyme samples, we applied mass-spectrometry based analysis and computational methods (including sequence similarity networks, sequence and structural alignments, and operon context analysis) to rapidly identify the specific sequence for each orphan while avoiding the most time- and labor-intensive aspects of typical sequence identifications. We then used these three new sequences to more accurately predict the catalytic function of 385 previously uncharacterized or misannotated proteins. We expect that this kind of rapid sequence identification could be efficiently applied on a larger scale to make enzymology’s “back catalog” another powerful tool to drive accurate genome annotation.     

Understanding the Folding-Function Tradeoff in Proteins

When an amino-acid sequence cannot be optimized for both folding and function, folding can get compromised in favor of function. To understand this tradeoff better, we devise a novel method for extracting the “function-less” folding-motif of a protein fold from a set of structurally similar but functionally diverse proteins. We then obtain the β-trefoil folding-motif, and study its folding using structure-based models and molecular dynamics simulations. CompariA protein sequence serves two purpson with the folding of wild-type β-trefoil proteins shows that function affects folding in two ways: In the slower folding interleukin-1β, binding sites make the fold more complex, increase contact order and slow folding. In the faster folding hisactophilin, residues which could have been part of the folding-motif are used for function. This reduces the density of native contacts in functional regions and increases folding rate. The folding-motif helps identify subtle structural deviations which perturb folding. These may then be used for functional annotation. Further, the folding-motif could potentially be used as a first step in the sequence design of function-less scaffold proteins. Desired function can then be engineered into these scaffolds.     

Assessing the accuracy of ancestral protein reconstruction methods

The phylogenetic inference of ancestral protein sequences is a powerful technique for the study of molecular evolution, but any conclusions drawn from such studies are only as good as the accuracy of the reconstruction method. Every inference method leads to errors in the ancestral protein sequence, resulting in potentially misleading estimates of the ancestral protein's properties. To assess the accuracy of ancestral protein reconstruction methods, we performed computational population evolution simulations featuring near-neutral evolution under purifying selection, speciation, and divergence using an off-lattice protein model where fitness depends on the ability to be stable in a specified target structure. We were thus able to compare the thermodynamic properties of the true ancestral sequences with the properties of “ancestral sequences” inferred by maximum parsimony, maximum likelihood, and Bayesian methods. Surprisingly, we found that methods such as maximum parsimony and maximum likelihood that reconstruct a “best guess” amino acid at each position overestimate thermostability, while a Bayesian method that sometimes chooses less-probable residues from the posterior probability distribution does not. Maximum likelihood and maximum parsimony apparently tend to eliminate variants at a position that are slightly detrimental to structural stability simply because such detrimental variants are less frequent. Other properties of ancestral proteins might be similarly overestimated. This suggests that ancestral reconstruction studies require greater care to come to credible conclusions regarding functional evolution. Inferred functional patterns that mimic reconstruction bias should be reevaluated.     

Word Decoding of Protein Amino Acid Sequences with Availability Analysis: A Linguistic Approach

The amino acid sequences of proteins determine their three-dimensional structures and functions. However, how sequence information is related to structures and functions is still enigmatic. In this study, we show that at least a part of the sequence information can be extracted by treating amino acid sequences of proteins as a collection of English words, based on a working hypothesis that amino acid sequences of proteins are composed of short constituent amino acid sequences (SCSs) or “words”. We first confirmed that the English language highly likely follows Zipf''s law, a special case of power law. We found that the rank-frequency plot of SCSs in proteins exhibits a similar distribution when low-rank tails are excluded. In comparison with natural English and “compressed” English without spaces between words, amino acid sequences of proteins show larger linear ranges and smaller exponents with heavier low-rank tails, demonstrating that the SCS distribution in proteins is largely scale-free. A distribution pattern of SCSs in proteins is similar among species, but species-specific features are also present. Based on the availability scores of SCSs, we found that sequence motifs are enriched in high-availability sites (i.e., “key words”) and vice versa. In fact, the highest availability peak within a given protein sequence often directly corresponds to a sequence motif. The amino acid composition of high-availability sites within motifs is different from that of entire motifs and all protein sequences, suggesting the possible functional importance of specific SCSs and their compositional amino acids within motifs. We anticipate that our availability-based word decoding approach is complementary to sequence alignment approaches in predicting functionally important sites of unknown proteins from their amino acid sequences.     

Inferring functional constraints and divergence in protein families using 3D mapping of phylogenetic information

Comparative sequence analysis has been used to study specific questions about the structure and function of proteins for many years. Here we propose a knowledge-based framework in which the maximum likelihood rate of evolution is used to quantify the level of constraint on the identity of a site. We demonstrate that site-rate mapping on 3D structures using datasets of rhodopsin-like G-protein receptors and alpha- and beta-tubulins provides an excellent tool for pinpointing the functional features shared between orthologous and paralogous proteins. In addition, functional divergence within protein families can be inferred by examining the differences in the site rates, the differences in the chemical properties of the side chains or amino acid usage between aligned sites. Two novel analytical methods are introduced to characterize rate- independent functional divergence. These are tested using a dataset of two classes of HMG-CoA reductases for which only one class can perform both the forward and reverse reaction. We show that functionally divergent sites occur in a cluster of sites interacting with the catalytic residues and that this information should facilitate the design of experimental strategies to directly test functional properties of residues.     

Rheostat functional outcomes occur when substitutions are introduced at nonconserved positions that diverge with speciation

When amino acids vary during evolution, the outcome can be functionally neutral or biologically‐important. We previously found that substituting a subset of nonconserved positions, “rheostat” positions, can have surprising effects on protein function. Since changes at rheostat positions can facilitate functional evolution or cause disease, more examples are needed to understand their unique biophysical characteristics. Here, we explored whether “phylogenetic” patterns of change in multiple sequence alignments (such as positions with subfamily specific conservation) predict the locations of functional rheostat positions. To that end, we experimentally tested eight phylogenetic positions in human liver pyruvate kinase (hLPYK), using 10–15 substitutions per position and biochemical assays that yielded five functional parameters. Five positions were strongly rheostatic and three were non‐neutral. To test the corollary that positions with low phylogenetic scores were not rheostat positions, we combined these phylogenetic positions with previously‐identified hLPYK rheostat, “toggle” (most substitution abolished function), and “neutral” (all substitutions were like wild‐type) positions. Despite representing 428 variants, this set of 33 positions was poorly statistically powered. Thus, we turned to the in vivo phenotypic dataset for E. coli lactose repressor protein (LacI), which comprised 12–13 substitutions at 329 positions and could be used to identify rheostat, toggle, and neutral positions. Combined hLPYK and LacI results show that positions with strong phylogenetic patterns of change are more likely to exhibit rheostat substitution outcomes than neutral or toggle outcomes. Furthermore, phylogenetic patterns were more successful at identifying rheostat positions than were co‐evolutionary or eigenvector centrality measures of evolutionary change.     

Widespread Genomic Signatures of Natural Selection in Hominid Evolution

Selection acting on genomic functional elements can be detected by its indirect effects on population diversity at linked neutral sites. To illuminate the selective forces that shaped hominid evolution, we analyzed the genomic distributions of human polymorphisms and sequence differences among five primate species relative to the locations of conserved sequence features. Neutral sequence diversity in human and ancestral hominid populations is substantially reduced near such features, resulting in a surprisingly large genome average diversity reduction due to selection of 19–26% on the autosomes and 12–40% on the X chromosome. The overall trends are broadly consistent with “background selection” or hitchhiking in ancestral populations acting to remove deleterious variants. Average selection is much stronger on exonic (both protein-coding and untranslated) conserved features than non-exonic features. Long term selection, rather than complex speciation scenarios, explains the large intragenomic variation in human/chimpanzee divergence. Our analyses reveal a dominant role for selection in shaping genomic diversity and divergence patterns, clarify hominid evolution, and provide a baseline for investigating specific selective events.     

Rheostats and Toggle Switches for Modulating Protein Function

The millions of protein sequences generated by genomics are expected to transform protein engineering and personalized medicine. To achieve these goals, tools for predicting outcomes of amino acid changes must be improved. Currently, advances are hampered by insufficient experimental data about nonconserved amino acid positions. Since the property “nonconserved” is identified using a sequence alignment, we designed experiments to recapitulate that context: Mutagenesis and functional characterization was carried out in 15 LacI/GalR homologs (rows) at 12 nonconserved positions (columns). Multiple substitutions were made at each position, to reveal how various amino acids of a nonconserved column were tolerated in each protein row. Results showed that amino acid preferences of nonconserved positions were highly context-dependent, had few correlations with physico-chemical similarities, and were not predictable from their occurrence in natural LacI/GalR sequences. Further, unlike the “toggle switch” behaviors of conserved positions, substitutions at nonconserved positions could be rank-ordered to show a “rheostatic”, progressive effect on function that spanned several orders of magnitude. Comparisons to various sequence analyses suggested that conserved and strongly co-evolving positions act as functional toggles, whereas other important, nonconserved positions serve as rheostats for modifying protein function. Both the presence of rheostat positions and the sequence analysis strategy appear to be generalizable to other protein families and should be considered when engineering protein modifications or predicting the impact of protein polymorphisms.     

A Pareto-Optimal Refinement Method for Protein Design Scaffolds

Computational design of protein function involves a search for amino acids with the lowest energy subject to a set of constraints specifying function. In many cases a set of natural protein backbone structures, or “scaffolds”, are searched to find regions where functional sites (an enzyme active site, ligand binding pocket, protein – protein interaction region, etc.) can be placed, and the identities of the surrounding amino acids are optimized to satisfy functional constraints. Input native protein structures almost invariably have regions that score very poorly with the design force field, and any design based on these unmodified structures may result in mutations away from the native sequence solely as a result of the energetic strain. Because the input structure is already a stable protein, it is desirable to keep the total number of mutations to a minimum and to avoid mutations resulting from poorly-scoring input structures. Here we describe a protocol using cycles of minimization with combined backbone/sidechain restraints that is Pareto-optimal with respect to RMSD to the native structure and energetic strain reduction. The protocol should be broadly useful in the preparation of scaffold libraries for functional site design.     

Origin and Evolution of a New Gene Descended from Alcohol Dehydrogenase in Drosophila

Drosophila alcohol dehydrogenase (Adh) is highly conserved in size, organization, and amino acid sequence. Adh-ψ was hypothesized to be a pseudogene derived from an Adh duplication in the repleta group of Drosophila; however, several results from molecular analyses of this gene conflict with currently held notions of molecular evolution. Perhaps the most difficult observations to reconcile with the pseudogene hypothesis are that the hypothetical replacement sites of Adh-ψ evolve only slightly more quickly than replacement sites of closely related, functional Adh genes, and that the replacement sites of the pseudogenes evolve considerably more slowly than neighboring silent sites. The data have been presented as a paradox that challenges our understanding of the mechanisms underlying DNA sequence divergence. Here I show that Adh-ψ is actually a new, functional gene recently descended from an Adh duplication. This descendant recruited ~60 new N-terminal amino acids, is considerably more basic than ADH, and is evolving at a faster rate than Adh. Furthermore, though the descendant is clearly functional, as inferred from molecular evolution and population genetic data, it retains no obvious ADH activity. This probably reflects functional divergence from its Adh ancestor.     

Coupling Protein Side-Chain and Backbone Flexibility Improves the Re-design of Protein-Ligand Specificity

Interactions between small molecules and proteins play critical roles in regulating and facilitating diverse biological functions, yet our ability to accurately re-engineer the specificity of these interactions using computational approaches has been limited. One main difficulty, in addition to inaccuracies in energy functions, is the exquisite sensitivity of protein–ligand interactions to subtle conformational changes, coupled with the computational problem of sampling the large conformational search space of degrees of freedom of ligands, amino acid side chains, and the protein backbone. Here, we describe two benchmarks for evaluating the accuracy of computational approaches for re-engineering protein-ligand interactions: (i) prediction of enzyme specificity altering mutations and (ii) prediction of sequence tolerance in ligand binding sites. After finding that current state-of-the-art “fixed backbone” design methods perform poorly on these tests, we develop a new “coupled moves” design method in the program Rosetta that couples changes to protein sequence with alterations in both protein side-chain and protein backbone conformations, and allows for changes in ligand rigid-body and torsion degrees of freedom. We show significantly increased accuracy in both predicting ligand specificity altering mutations and binding site sequences. These methodological improvements should be useful for many applications of protein – ligand design. The approach also provides insights into the role of subtle conformational adjustments that enable functional changes not only in engineering applications but also in natural protein evolution.     

Testing the ortholog conjecture with comparative functional genomic data from mammals

A common assumption in comparative genomics is that orthologous genes share greater functional similarity than do paralogous genes (the "ortholog conjecture"). Many methods used to computationally predict protein function are based on this assumption, even though it is largely untested. Here we present the first large-scale test of the ortholog conjecture using comparative functional genomic data from human and mouse. We use the experimentally derived functions of more than 8,900 genes, as well as an independent microarray dataset, to directly assess our ability to predict function using both orthologs and paralogs. Both datasets show that paralogs are often a much better predictor of function than are orthologs, even at lower sequence identities. Among paralogs, those found within the same species are consistently more functionally similar than those found in a different species. We also find that paralogous pairs residing on the same chromosome are more functionally similar than those on different chromosomes, perhaps due to higher levels of interlocus gene conversion between these pairs. In addition to offering implications for the computational prediction of protein function, our results shed light on the relationship between sequence divergence and functional divergence. We conclude that the most important factor in the evolution of function is not amino acid sequence, but rather the cellular context in which proteins act.     

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Protein alignments are commonly used to evaluate the similarity of protein residues, and the derived consensus sequence used for identifying functional units (e.g., domains). Traditional consensus-building models fail to account for interpositional dependencies – functionally required covariation of residues that tend to appear simultaneously throughout evolution and across the phylogentic tree. These relationships can reveal important clues about the processes of protein folding, thermostability, and the formation of functional sites, which in turn can be used to inform the engineering of synthetic proteins. Unfortunately, these relationships essentially form sub-motifs which cannot be predicted by simple “majority rule” or even HMM-based consensus models, and the result can be a biologically invalid “consensus” which is not only never seen in nature but is less viable than any extant protein. We have developed a visual analytics tool, StickWRLD, which creates an interactive 3D representation of a protein alignment and clearly displays covarying residues. The user has the ability to pan and zoom, as well as dynamically change the statistical threshold underlying the identification of covariants. StickWRLD has previously been successfully used to identify functionally-required covarying residues in proteins such as Adenylate Kinase and in DNA sequences such as endonuclease target sites.     

Functional divergence after gene duplication and sequence-structure relationship: a case study of G-protein alpha subunits

In this article, we use animal G-protein alpha subunit family as an example to illustrate a comprehensive analytical pipeline for detecting different types of functional divergence of protein families, which is phylogeny-dependent, combined with ancestral sequence inference and available protein structure information. In particular, we focus on (i) Type-I functional divergence, or site-specific rate shift, as typically exemplified by amino acid residue highly conserved in a subset of homologous genes but highly variable in a different subset of homologous genes, and (ii) Type-II functional divergence, or the shift of cluster-specific amino acid property, as exemplified by a radical shift of amino acid property between duplicate genes, which is otherwise evolutionally conserved. We utilized the software DIVERGE2 to carry out these analyses. In the case of G-protein alpha subunit gene family, we have predicted amino acid residues that are related to either Type-I or Type-II functional divergence. The inferred ancestral sequences for these sites are helpful to explore the trends of functional divergence. Finally, these predicted residues are mapped to the protein structures to test whether these residues may have 3D structure or solvent accessibility preference.     

Resolving protein structure‐function‐binding site relationships from a binding site similarity network perspective

Functional annotation is seldom straightforward with complexities arising due to functional divergence in protein families or functional convergence between non‐homologous protein families, leading to mis‐annotations. An enzyme may contain multiple domains and not all domains may be involved in a given function, adding to the complexity in function annotation. To address this, we use binding site information from bound cognate ligands and catalytic residues, since it can help in resolving fold‐function relationships at a finer level and with higher confidence. A comprehensive database of 2,020 fold‐function‐binding site relationships has been systematically generated. A network‐based approach is employed to capture the complexity in these relationships, from which different types of associations are deciphered, that identify versatile protein folds performing diverse functions, same function associated with multiple folds and one‐to‐one relationships. Binding site similarity networks integrated with fold, function, and ligand similarity information are generated to understand the depth of these relationships. Apart from the observed continuity in the functional site space, network properties of these revealed versatile families with topologically different or dissimilar binding sites and structural families that perform very similar functions. As a case study, subtle changes in the active site of a set of evolutionarily related superfamilies are studied using these networks. Tracing of such similarities in evolutionarily related proteins provide clues into the transition and evolution of protein functions. Insights from this study will be helpful in accurate and reliable functional annotations of uncharacterized proteins, poly‐pharmacology, and designing enzymes with new functional capabilities. Proteins 2017; 85:1319–1335. © 2017 Wiley Periodicals, Inc.     

Dictionary-driven protein annotation

Computational methods seeking to automatically determine the properties (functional, structural, physicochemical, etc.) of a protein directly from the sequence have long been the focus of numerous research groups. With the advent of advanced sequencing methods and systems, the number of amino acid sequences that are being deposited in the public databases has been increasing steadily. This has in turn generated a renewed demand for automated approaches that can annotate individual sequences and complete genomes quickly, exhaustively and objectively. In this paper, we present one such approach that is centered around and exploits the Bio-Dictionary, a collection of amino acid patterns that completely covers the natural sequence space and can capture functional and structural signals that have been reused during evolution, within and across protein families. Our annotation approach also makes use of a weighted, position-specific scoring scheme that is unaffected by the over-representation of well-conserved proteins and protein fragments in the databases used. For a given query sequence, the method permits one to determine, in a single pass, the following: local and global similarities between the query and any protein already present in a public database; the likeness of the query to all available archaeal/ bacterial/eukaryotic/viral sequences in the database as a function of amino acid position within the query; the character of secondary structure of the query as a function of amino acid position within the query; the cytoplasmic, transmembrane or extracellular behavior of the query; the nature and position of binding domains, active sites, post-translationally modified sites, signal peptides, etc. In terms of performance, the proposed method is exhaustive, objective and allows for the rapid annotation of individual sequences and full genomes. Annotation examples are presented and discussed in Results, including individual queries and complete genomes that were released publicly after we built the Bio-Dictionary that is used in our experiments. Finally, we have computed the annotations of more than 70 complete genomes and made them available on the World Wide Web at http://cbcsrv.watson.ibm.com/Annotations/.