Fold recognition by concurrent use of solvent accessibility and residue depth

CRFalign: A Sequence-Structure Alignment of Proteins Based on a Combination of HMM-HMM Comparison and Conditional Random Fields

Sequence–structure alignment for protein sequences is an important task for the template-based modeling of 3D structures of proteins. Building a reliable sequence–structure alignment is a challenging problem, especially for remote homologue target proteins. We built a method of sequence–structure alignment called CRFalign, which improves upon a base alignment model based on HMM-HMM comparison by employing pairwise conditional random fields in combination with nonlinear scoring functions of structural and sequence features. Nonlinear scoring part is implemented by a set of gradient boosted regression trees. In addition to sequence profile features, various position-dependent structural features are employed including secondary structures and solvent accessibilities. Training is performed on reference alignments at superfamily levels or twilight zone chosen from the SABmark benchmark set. We found that CRFalign method produces relative improvement in terms of average alignment accuracies for validation sets of SABmark benchmark. We also tested CRFalign on 51 sequence–structure pairs involving 15 FM target domains of CASP14, where we could see that CRFalign leads to an improvement in average modeling accuracies in these hard targets (TM-CRFalign ≃42.94%) compared with that of HHalign (TM-HHalign ≃39.05%) and also that of MRFalign (TM-MRFalign ≃36.93%). CRFalign was incorporated to our template search framework called CRFpred and was tested for a random target set of 300 target proteins consisting of Easy, Medium and Hard sets which showed a reasonable template search performance.

SelfAT-Fold: Protein Fold Recognition Based on Residue-Based and Motif-Based Self-Attention Networks

The protein fold recognition is a fundamental and crucial step of tertiary structure determination. In this regard, several computational predictors have been proposed. Recently, the predictive performance has been obviously improved by the fold-specific features generated by deep learning techniques. However, these methods failed to measure the global associations among residues or motifs along the protein sequences. Furthermore, these deep learning techniques are often treated as black boxes without interpretability. Inspired by the similarities between protein sequences and natural language sentences, we applied the self-attention mechanism derived from natural language processing (NLP) field to protein fold recognition. The motif-based self-attention network (MSAN) and the residue-based self-attention network (RSAN) were constructed based on a training set to capture the global associations among the structure motifs and residues along the protein sequences, respectively. The fold-specific attention features trained and generated from the training set were then combined with Support Vector Machines (SVMs) to predict the samples in the widely used LE benchmark dataset, which is fully independent from the training set. Experimental results showed that the proposed two SelfAT-Fold predictors outperformed 34 existing state-of-the-art computational predictors. The two SelfAT-Fold predictors were further tested on an independent dataset SCOP_TEST, and they can achieve stable performance. Furthermore, the fold-specific attention features can be used to analyse the characteristics of protein folds. The trained models and data of SelfAT-Fold can be downloaded from http://bliulab.net/selfAT_fold/.

Improving protein fold recognition using triplet network and ensemble deep learning

Protein fold recognition is a critical step toward protein structure and function prediction, aiming at providing the most likely fold type of the query protein. In recent years, the development of deep learning (DL) technique has led to massive advances in this important field, and accordingly, the sensitivity of protein fold recognition has been dramatically improved. Most DL-based methods take an intermediate bottleneck layer as the feature representation of proteins with new fold types. However, this strategy is indirect, inefficient and conditional on the hypothesis that the bottleneck layer's representation is assumed as a good representation of proteins with new fold types. To address the above problem, in this work, we develop a new computational framework by combining triplet network and ensemble DL. We first train a DL-based model, termed FoldNet, which employs triplet loss to train the deep convolutional network. FoldNet directly optimizes the protein fold embedding itself, making the proteins with the same fold types be closer to each other than those with different fold types in the new protein embedding space. Subsequently, using the trained FoldNet, we implement a new residue-residue contact-assisted predictor, termed FoldTR, which improves protein fold recognition. Furthermore, we propose a new ensemble DL method, termed FSD_XGBoost, which combines protein fold embedding with the other two discriminative fold-specific features extracted by two DL-based methods SSAfold and DeepFR. The Top 1 sensitivity of FSD_XGBoost increases to 74.8% at the fold level, which is ~9% higher than that of the state-of-the-art method. Together, the results suggest that fold-specific features extracted by different DL methods complement with each other, and their combination can further improve fold recognition at the fold level. The implemented web server of FoldTR and benchmark datasets are publicly available at http://csbio.njust.edu.cn/bioinf/foldtr/.

FoldRec-C2C: protein fold recognition by combining cluster-to-cluster model and protein similarity network

As a key for studying the protein structures, protein fold recognition is playing an important role in predicting the protein structures associated with COVID-19 and other important structures. However, the existing computational predictors only focus on the protein pairwise similarity or the similarity between two groups of proteins from 2-folds. However, the homology relationship among proteins is in a hierarchical structure. The global protein similarity network will contribute to the performance improvement. In this study, we proposed a predictor called FoldRec-C2C to globally incorporate the interactions among proteins into the prediction. For the FoldRec-C2C predictor, protein fold recognition problem is treated as an information retrieval task in nature language processing. The initial ranking results were generated by a surprised ranking algorithm Learning to Rank, and then three re-ranking algorithms were performed on the ranking lists to adjust the results globally based on the protein similarity network, including seq-to-seq model, seq-to-cluster model and cluster-to-cluster model (C2C). When tested on a widely used and rigorous benchmark dataset LINDAHL dataset, FoldRec-C2C outperforms other 34 state-of-the-art methods in this field. The source code and data of FoldRec-C2C can be downloaded from http://bliulab.net/FoldRec-C2C/download.

Why can deep convolutional neural networks improve protein fold recognition? A visual explanation by interpretation

As an essential task in protein structure and function prediction, protein fold recognition has attracted increasing attention. The majority of the existing machine learning-based protein fold recognition approaches strongly rely on handcrafted features, which depict the characteristics of different protein folds; however, effective feature extraction methods still represent the bottleneck for further performance improvement of protein fold recognition. As a powerful feature extractor, deep convolutional neural network (DCNN) can automatically extract discriminative features for fold recognition without human intervention, which has demonstrated an impressive performance on protein fold recognition. Despite the encouraging progress, DCNN often acts as a black box, and as such, it is challenging for users to understand what really happens in DCNN and why it works well for protein fold recognition. In this study, we explore the intrinsic mechanism of DCNN and explain why it works for protein fold recognition using a visual explanation technique. More specifically, we first trained a VGGNet-based DCNN model, termed VGGNet-FE, which can extract fold-specific features from the predicted protein residue-residue contact map for protein fold recognition. Subsequently, based on the trained VGGNet-FE, we implemented a new contact-assisted predictor, termed VGGfold, for protein fold recognition; we then visualized what features were extracted by each of the convolutional layers in VGGNet-FE using a deconvolution technique. Furthermore, we visualized the high-level semantic information, termed fold-discriminative region, of a predicted contact map from the localization map obtained from the last convolutional layer of VGGNet-FE. It is visually confirmed that VGGNet-FE could effectively extract distinct fold-discriminative regions for different types of protein folds, thereby accounting for the improved performance of VGGfold for protein fold recognition. In summary, this study is of great significance for both understanding the working principle of DCNNs in protein fold recognition and exploring the relationship between the predicted protein contact map and protein tertiary structure. This proposed visualization method is flexible and applicable to address other DCNN-based bioinformatics and computational biology questions. The online web server of VGGfold is freely available at http://csbio.njust.edu.cn/bioinf/vggfold/.

ProtFold-DFG: protein fold recognition by combining Directed Fusion Graph and PageRank algorithm

As one of the most important tasks in protein structure prediction, protein fold recognition has attracted more and more attention. In this regard, some computational predictors have been proposed with the development of machine learning and artificial intelligence techniques. However, these existing computational methods are still suffering from some disadvantages. In this regard, we propose a new network-based predictor called ProtFold-DFG for protein fold recognition. We propose the Directed Fusion Graph (DFG) to fuse the ranking lists generated by different methods, which employs the transitive closure to incorporate more relationships among proteins and uses the KL divergence to calculate the relationship between two proteins so as to improve its generalization ability. Finally, the PageRank algorithm is performed on the DFG to accurately recognize the protein folds by considering the global interactions among proteins in the DFG. Tested on a widely used and rigorous benchmark data set, LINDAHL dataset, experimental results show that the ProtFold-DFG outperforms the other 35 competing methods, indicating that ProtFold-DFG will be a useful method for protein fold recognition. The source code and data of ProtFold-DFG can be downloaded from http://bliulab.net/ProtFold-DFG/download.

iStable 2.0: Predicting protein thermal stability changes by integrating various characteristic modules

Protein mutations can lead to structural changes that affect protein function and result in disease occurrence. In protein engineering, drug design or and optimization industries, mutations are often used to improve protein stability or to change protein properties while maintaining stability. To provide possible candidates for novel protein design, several computational tools for predicting protein stability changes have been developed. Although many prediction tools are available, each tool employs different algorithms and features. This can produce conflicting prediction results that make it difficult for users to decide upon the correct protein design. Therefore, this study proposes an integrated prediction tool, iStable 2.0, which integrates 11 sequence-based and structure-based prediction tools by machine learning and adds protein sequence information as features. Three coding modules are designed for the system, an Online Server Module, a Stand-alone Module and a Sequence Coding Module, to improve the prediction performance of the previous version of the system. The final integrated structure-based classification model has a higher Matthews correlation coefficient than that of the single prediction tool (0.708 vs 0.547, respectively), and the Pearson correlation coefficient of the regression model likewise improves from 0.669 to 0.714. The sequence-based model not only successfully integrates off-the-shelf predictors but also improves the Matthews correlation coefficient of the best single prediction tool by at least 0.161, which is better than the individual structure-based prediction tools. In addition, both the Sequence Coding Module and the Stand-alone Module maintain performance with only a 5% decrease of the Matthews correlation coefficient when the integrated online tools are unavailable. iStable 2.0 is available at http://ncblab.nchu.edu.tw/iStable2.

Evaluating the significance of contact maps in low-homology protein modeling using contact-assisted threading

The development of improved threading algorithms for remote homology modeling is a critical step forward in template-based protein structure prediction. We have recently demonstrated the utility of contact information to boost protein threading by developing a new contact-assisted threading method. However, the nature and extent to which the quality of a predicted contact map impacts the performance of contact-assisted threading remains elusive. Here, we systematically analyze and explore this interdependence by employing our newly-developed contact-assisted threading method over a large-scale benchmark dataset using predicted contact maps from four complementary methods including direct coupling analysis (mfDCA), sparse inverse covariance estimation (PSICOV), classical neural network-based meta approach (MetaPSICOV), and state-of-the-art ultra-deep learning model (RaptorX). Experimental results demonstrate that contact-assisted threading using high-quality contacts having the Matthews Correlation Coefficient (MCC) ≥ 0.5 improves threading performance in nearly 30% cases, while low-quality contacts with MCC <0.35 degrades the performance for 50% cases. This holds true even in CASP13 dataset, where threading using high-quality contacts (MCC ≥ 0.5) significantly improves the performance of 22 instances out of 29. Collectively, our study uncovers the mutual association between the quality of predicted contacts and its possible utility in boosting threading performance for improving low-homology protein modeling.

Rational molecular design for improving digestive enzyme resistance of beta-glucosidase from Trichoderma viride based on inhibition of bound state formation

Beta-glucosidase (BGL1) is widely used in animal feed industries. However, degradation caused by digestive enzymes in the intestine hampers its application. Improving the resistance of feed enzymes against proteases is crucial in livestock farming. To improve the resistance of beta-glucosidase against pepsin and trypsin, a rational molecular design based on the inhibition of bound-state formation and secondary design was developed. The strategy includes: (1) prediction of the interaction surface of the pepsin-BGL1 complex structure, (2) prediction of key amino acids affecting the formation of the complex, (3) optimization of pepsin-resistant mutants by structural evaluation, (4) secondary molecular design based on pepsin-resistant mutants, and optimization of pepsin and trypsin-resistant mutants. Two BGL1 protein mutants (BGL1^Q627C and BGL1^{Q627C/R543H/R646W}) were constructed, and then mutated and wild-type BGL1s were expressed in Pichia pastoris. The half-life of BGL1^Q627C and BGL1^{Q627C/R543H/R646W} were 1.36 and 1.51 times that of the wild type upon pepsin exposure, respectively. For trypsin resistance, the half-life were 0.93 and 1.53 times that of the wild type, respectively. Compare to those of the wild type, most of the basic enzymatic properties of both mutants were not significantly changed except for increased Michaelis constants. The rational design method can be used as a guide for modifying other feed enzymes.

Fold-LTR-TCP: protein fold recognition based on triadic closure principle

As an important task in protein structure and function studies, protein fold recognition has attracted more and more attention. The existing computational predictors in this field treat this task as a multi-classification problem, ignoring the relationship among proteins in the dataset. However, previous studies showed that their relationship is critical for protein homology analysis. In this study, the protein fold recognition is treated as an information retrieval task. The Learning to Rank model (LTR) was employed to retrieve the query protein against the template proteins to find the template proteins in the same fold with the query protein in a supervised manner. The triadic closure principle (TCP) was performed on the ranking list generated by the LTR to improve its accuracy by considering the relationship among the query protein and the template proteins in the ranking list. Finally, a predictor called Fold-LTR-TCP was proposed. The rigorous test on the LE benchmark dataset showed that the Fold-LTR-TCP predictor achieved an accuracy of 73.2%, outperforming all the other competing methods.

MotifCNN-fold: protein fold recognition based on fold-specific features extracted by motif-based convolutional neural networks

Protein fold recognition is one of the most critical tasks to explore the structures and functions of the proteins based on their primary sequence information. The existing protein fold recognition approaches rely on features reflecting the characteristics of protein folds. However, the feature extraction methods are still the bottleneck of the performance improvement of these methods. In this paper, we proposed two new feature extraction methods called MotifCNN and MotifDCNN to extract more discriminative fold-specific features based on structural motif kernels to construct the motif-based convolutional neural networks (CNNs). The pairwise sequence similarity scores calculated based on fold-specific features are then fed into support vector machines to construct the predictor for fold recognition, and a predictor called MotifCNN-fold has been proposed. Experimental results on the benchmark dataset showed that MotifCNN-fold obviously outperformed all the other competing methods. In particular, the fold-specific features extracted by MotifCNN and MotifDCNN are more discriminative than the fold-specific features extracted by other deep learning techniques, indicating that incorporating the structural motifs into the CNN is able to capture the characteristics of protein folds.

DeepSVM-fold: protein fold recognition by combining support vector machines and pairwise sequence similarity scores generated by deep learning networks

Protein fold recognition is critical for studying the structures and functions of proteins. The existing protein fold recognition approaches failed to efficiently calculate the pairwise sequence similarity scores of the proteins in the same fold sharing low sequence similarities. Furthermore, the existing feature vectorization strategies are not able to measure the global relationships among proteins from different protein folds. In this article, we proposed a new computational predictor called DeepSVM-fold for protein fold recognition by introducing a new feature vector based on the pairwise sequence similarity scores calculated from the fold-specific features extracted by deep learning networks. The feature vectors are then fed into a support vector machine to construct the predictor. Experimental results on the benchmark dataset (LE) show that DeepSVM-fold obviously outperforms all the other competing methods.

Protein Solvent-Accessibility Prediction by a Stacked Deep Bidirectional Recurrent Neural Network

Residue solvent accessibility is closely related to the spatial arrangement and packing of residues. Predicting the solvent accessibility of a protein is an important step to understand its structure and function. In this work, we present a deep learning method to predict residue solvent accessibility, which is based on a stacked deep bidirectional recurrent neural network applied to sequence profiles. To capture more long-range sequence information, a merging operator was proposed when bidirectional information from hidden nodes was merged for outputs. Three types of merging operators were used in our improved model, with a long short-term memory network performing as a hidden computing node. The trained database was constructed from 7361 proteins extracted from the PISCES server using a cut-off of 25% sequence identity. Sequence-derived features including position-specific scoring matrix, physical properties, physicochemical characteristics, conservation score and protein coding were used to represent a residue. Using this method, predictive values of continuous relative solvent-accessible area were obtained, and then, these values were transformed into binary states with predefined thresholds. Our experimental results showed that our deep learning method improved prediction quality relative to current methods, with mean absolute error and Pearson’s correlation coefficient values of 8.8% and 74.8%, respectively, on the CB502 dataset and 8.2% and 78%, respectively, on the Manesh215 dataset.

A Sequential Segment Based Alpha-Helical Transmembrane Protein Alignment Method

Alpha-helical transmembrane protein (αTMP) is one of the two major categories of transmembrane protein (TMP). They are abundant existing in eukaryotic cells and involved in many biological processes. The special physicochemical properties, the structures of αTMP are hard to be experimentally solved, but αTMP's sequential segments are important to determine their conformations, so that TM-specific alignment is necessary to benefit their structure prediction. We used segment information extracted from topology structure and evolutionary information as features to implement a αTMP Segment Alignment method (TMSA). The method was trained using one non-redundant dataset and tested using another non-redundant dataset. Comparing the results to a general alignment method HHalign, TMSA achieved higher alignment accuracy, and easier to recognize the fold of αTMPs.

RBSURFpred: Modeling protein accessible surface area in real and binary space using regularized and optimized regression

Accessible surface area (ASA) of a protein residue is an effective feature for protein structure prediction, binding region identification, fold recognition problems etc. Improving the prediction of ASA by the application of effective feature variables is a challenging but explorable task to consider, specially in the field of machine learning. Among the existing predictors of ASA, REGAd³p is a highly accurate ASA predictor which is based on regularized exact regression with polynomial kernel of degree 3. In this work, we present a new predictor RBSURFpred, which extends REGAd³p on several dimensions by incorporating 58 physicochemical, evolutionary and structural properties into 9-tuple peptides via Chou's general PseAAC, which allowed us to obtain higher accuracies in predicting both real-valued and binary ASA. We have compared RBSURFpred for both real and binary space predictions with state-of-the-art predictors, such as REGAd³p and SPIDER2. We also have carried out a rigorous analysis of the performance of RBSURFpred in terms of different amino acids and their properties, and also with biologically relevant case-studies. The performance of RBSURFpred establishes itself as a useful tool for the community.

Accurate prediction of protein relative solvent accessibility using a balanced model

BACKGROUND

Protein relative solvent accessibility provides insight into understanding protein structure and function. Prediction of protein relative solvent accessibility is often the first stage of predicting other protein properties. Recent predictors of relative solvent accessibility discriminate against exposed regions as compared with buried regions, resulting in higher prediction accuracy associated with buried regions relative to exposed regions.

METHODS

Here, we propose a more accurate and balanced predictor of protein relative solvent accessibility. First, we collected known proteins in three subsets according to sequence length and constructed a balanced dataset after reducing redundancy within each subset. Next, we measured the performance associated with different variables and variable combinations to determine the best variable combination. Finally, a predictor called BMRSA was constructed for modelling and prediction, which used the balanced set as the training set, the position- specific scoring matrix, predicted secondary structure, buried-exposed profile, and length of a query sequence as variables, and the conditional random field as the machine-learning method.

RESULTS

BMRSA performance on test sets confirmed that our approach improved prediction accuracy relative to state-of-the-art approaches and was balanced in its comparison of buried and exposed regions. Our method is valuable when higher levels of accuracy in predicting exposed-residue states are required. The BMRSA is available at: http://cheminfo.tongji.edu.cn:8080/BMRSA/.

Accurate Prediction of One-Dimensional Protein Structure Features Using SPINE-X

Accurate prediction of protein secondary structure and other one-dimensional structure features is essential for accurate sequence alignment, three-dimensional structure modeling, and function prediction. SPINE-X is a software package to predict secondary structure as well as accessible surface area and dihedral angles ϕ and ψ. For secondary structure SPINE-X achieves an accuracy of between 81 and 84 % depending on the dataset and choice of tests. The Pearson correlation coefficient for accessible surface area prediction is 0.75 and the mean absolute error from the ϕ and ψ dihedral angles are 20^∘ and 33^∘, respectively. The source code and a Linux executables for SPINE-X are available from Research and Information Systems at http://mamiris.com .

Dataset of eye disease-related proteins analyzed using the unfolding mutation screen

A number of genetic diseases are a result of missense mutations in protein structure. These mutations can lead to severe protein destabilization and misfolding. The unfolding mutation screen (UMS) is a computational method that calculates unfolding propensities for every possible missense mutation in a protein structure. The UMS validation demonstrated a good agreement with experimental and phenotypical data. 15 protein structures (a combination of homology models and crystal structures) were analyzed using UMS. The standard and clustered heat maps, and patterned protein structure from the analysis were stored in a UMS library. The library is currently composed of 15 protein structures from 14 inherited eye diseases including retina degenerations, glaucoma, and cataracts, and contains data for 181,110 mutations. The UMS protein library introduces 13 new human models of eye disease related proteins and is the first collection of the consistently calculated unfolding propensities, which could be used as a tool for the express analysis of novel mutations in clinical practice, next generation sequencing, and genotype-to-phenotype relationships in inherited eye disease.

OMPcontact: An Outer Membrane Protein Inter-Barrel Residue Contact Prediction Method

In the two transmembrane protein types, outer membrane proteins (OMPs) perform diverse important biochemical functions, including substrate transport and passive nutrient uptake and intake. Hence their 3D structures are expected to reveal these functions. Because experimental structures are scarce, predicted 3D structures are more adapted to OMP research instead, and the inter-barrel residue contact is becoming one of the most remarkable features, improving prediction accuracy by describing the structural information of OMPs. To predict OMP structures accurately, we explored an OMP inter-barrel residue contact prediction method: OMPcontact. Multiple OMP-specific features were integrated in the method, including residue evolutionary covariation, topology-based transmembrane segment relative residue position, OMP lipid layer accessibility, and residue evolution conservation. These features describe the properties of a residue pair in different respects: sequential, structural, evolutionary, and biochemical. Within a 3-residues slide window, a Support Vector Machine (SVM) could accurately determinate the inter-barrel contact residue pair using above features. A 5-fold cross-valuation process was applied in testing the OMPcontact performance against a non-redundant OMP set with 75 samples inside. The tests compared four evolutionary covariation methods and screen analyzed the adaptive ones for inter-barrel contact prediction. The results showed our method not only efficiently realized the prediction, but also scored the possibility for residue pairs reliably. This is expected to improve OMP tertiary structure prediction. Therefore, OMPcontact will be helpful in compiling a structural census of outer membrane protein.

PredRSA: a gradient boosted regression trees approach for predicting protein solvent accessibility

Background

Protein solvent accessibility prediction is a pivotal intermediate step towards modeling protein tertiary structures directly from one-dimensional sequences. It also plays an important part in identifying protein folds and domains. Although some methods have been presented to the protein solvent accessibility prediction in recent years, the performance is far from satisfactory. In this work, we propose PredRSA, a computational method that can accurately predict relative solvent accessible surface area (RSA) of residues by exploring various local and global sequence features which have been observed to be associated with solvent accessibility. Based on these features, a novel and efficient approach, Gradient Boosted Regression Trees (GBRT), is first adopted to predict RSA.

Results

Experimental results obtained from 5-fold cross-validation based on the Manesh-215 dataset show that the mean absolute error (MAE) and the Pearson correlation coefficient (PCC) of PredRSA are 9.0 % and 0.75, respectively, which are better than that of the existing methods. Moreover, we evaluate the performance of PredRSA using an independent test set of 68 proteins. Compared with the state-of-the-art approaches (SPINE-X and ASAquick), PredRSA achieves a significant improvement on the prediction quality.

Conclusions

Our experimental results show that the Gradient Boosted Regression Trees algorithm and the novel feature combination are quite effective in relative solvent accessibility prediction. The proposed PredRSA method could be useful in assisting the prediction of protein structures by applying the predicted RSA as useful restraints.

Improving Protein Fold Recognition by Deep Learning Networks

For accurate recognition of protein folds, a deep learning network method (DN-Fold) was developed to predict if a given query-template protein pair belongs to the same structural fold. The input used stemmed from the protein sequence and structural features extracted from the protein pair. We evaluated the performance of DN-Fold along with 18 different methods on Lindahl’s benchmark dataset and on a large benchmark set extracted from SCOP 1.75 consisting of about one million protein pairs, at three different levels of fold recognition (i.e., protein family, superfamily, and fold) depending on the evolutionary distance between protein sequences. The correct recognition rate of ensembled DN-Fold for Top 1 predictions is 84.5%, 61.5%, and 33.6% and for Top 5 is 91.2%, 76.5%, and 60.7% at family, superfamily, and fold levels, respectively. We also evaluated the performance of single DN-Fold (DN-FoldS), which showed the comparable results at the level of family and superfamily, compared to ensemble DN-Fold. Finally, we extended the binary classification problem of fold recognition to real-value regression task, which also show a promising performance. DN-Fold is freely available through a web server at http://iris.rnet.missouri.edu/dnfold.

Detecting local residue environment similarity for recognizing near-native structure models

We developed a new representation of local amino acid environments in protein structures called the Side-chain Depth Environment (SDE). An SDE defines a local structural environment of a residue considering the coordinates and the depth of amino acids that locate in the vicinity of the side-chain centroid of the residue. SDEs are general enough that similar SDEs are found in protein structures with globally different folds. Using SDEs, we developed a procedure called PRESCO (Protein Residue Environment SCOre) for selecting native or near-native models from a pool of computational models. The procedure searches similar residue environments observed in a query model against a set of representative native protein structures to quantify how native-like SDEs in the model are. When benchmarked on commonly used computational model datasets, our PRESCO compared favorably with the other existing scoring functions in selecting native and near-native models.

Context similarity scoring improves protein sequence alignments in the midnight zone

MOTIVATION

High-quality protein sequence alignments are essential for a number of downstream applications such as template-based protein structure prediction. In addition to the similarity score between sequence profile columns, many current profile-profile alignment tools use extra terms that compare 1D-structural properties such as secondary structure and solvent accessibility, which are predicted from short profile windows around each sequence position. Such scores add non-redundant information by evaluating the conservation of local patterns of hydrophobicity and other amino acid properties and thus exploiting correlations between profile columns.

RESULTS

Here, instead of predicting and comparing known 1D properties, we follow an agnostic approach. We learn in an unsupervised fashion a set of maximally conserved patterns represented by 13-residue sequence profiles, without the need to know the cause of the conservation of these patterns. We use a maximum likelihood approach to train a set of 32 such profiles that can best represent patterns conserved within pairs of remotely homologs, structurally aligned training profiles. We include the new context score into our Hmm-Hmm alignment tool hhsearch and improve especially the quality of difficult alignments significantly.

CONCLUSION

The context similarity score improves the quality of homology models and other methods that depend on accurate pairwise alignments.

Improving protein fold recognition by random forest

BACKGROUND

Recognizing the correct structural fold among known template protein structures for a target protein (i.e. fold recognition) is essential for template-based protein structure modeling. Since the fold recognition problem can be defined as a binary classification problem of predicting whether or not the unknown fold of a target protein is similar to an already known template protein structure in a library, machine learning methods have been effectively applied to tackle this problem. In our work, we developed RF-Fold that uses random forest - one of the most powerful and scalable machine learning classification methods - to recognize protein folds.

RESULTS

RF-Fold consists of hundreds of decision trees that can be trained efficiently on very large datasets to make accurate predictions on a highly imbalanced dataset. We evaluated RF-Fold on the standard Lindahl's benchmark dataset comprised of 976 × 975 target-template protein pairs through cross-validation. Compared with 17 different fold recognition methods, the performance of RF-Fold is generally comparable to the best performance in fold recognition of different difficulty ranging from the easiest family level, the medium-hard superfamily level, and to the hardest fold level. Based on the top-one template protein ranked by RF-Fold, the correct recognition rate is 84.5%, 63.4%, and 40.8% at family, superfamily, and fold levels, respectively. Based on the top-five template protein folds ranked by RF-Fold, the correct recognition rate increases to 91.5%, 79.3% and 58.3% at family, superfamily, and fold levels.

CONCLUSIONS

The good performance achieved by the RF-Fold demonstrates the random forest's effectiveness for protein fold recognition.

Conservation of inter-residue interactions and prediction of folding rates of domain repeats

Domains are the main structural and functional units of larger proteins. They tend to be contiguous in primary structure and can fold and function independently. It has been observed that 10-20% of all encoded proteins contain duplicated domains and the average pairwise sequence identity between them is usually low. In the present study, we have analyzed the structural similarity between domain repeats of proteins with known structures available in the Protein Data Bank using structure-based inter-residue interaction measures such as the number of long-range contacts, surrounding hydrophobicity, and pairwise interaction energy. We used RADAR program for detecting the repeats in a protein sequence which were further validated using Pfam domain assignments. The sequence identity between the repeats in domains ranges from 20 to 40% and their secondary structural elements are well conserved. The number of long-range contacts, surrounding hydrophobicity calculations and pairwise interaction energy of the domain repeats clearly reveal the conservation of 3-D structure environment in the repeats of domains. The proportions of mainchain-mainchain hydrogen bonds and hydrophobic interactions are also highly conserved between the repeats. The present study has suggested that the computation of these structure-based parameters will give better clues about the tertiary environment of the repeats in domains. The folding rates of individual domains in the repeats predicted using the long-range order parameter indicate that the predicted folding rates correlate well with most of the experimentally observed folding rates for the analyzed independently folded domains.

SPOT-Seq-RNA: predicting protein-RNA complex structure and RNA-binding function by fold recognition and binding affinity prediction

RNA-binding proteins (RBPs) play key roles in RNA metabolism and post-transcriptional regulation. Computational methods have been developed separately for prediction of RBPs and RNA-binding residues by machine-learning techniques and prediction of protein-RNA complex structures by rigid or semiflexible structure-to-structure docking. Here, we describe a template-based technique called SPOT-Seq-RNA that integrates prediction of RBPs, RNA-binding residues, and protein-RNA complex structures into a single package. This integration is achieved by combining template-based structure-prediction software, SPARKS X, with binding affinity prediction software, DRNA. This tool yields reasonable sensitivity (46 %) and high precision (84 %) for an independent test set of 215 RBPs and 5,766 non-RBPs. SPOT-Seq-RNA is computationally efficient for genome-scale prediction of RBPs and protein-RNA complex structures. Its application to human genome study has revealed a similar sensitivity and ability to uncover hundreds of novel RBPs beyond simple homology. The online server and downloadable version of SPOT-Seq-RNA are available at http://sparks-lab.org/server/SPOT-Seq-RNA/.

Protein depth calculation and the use for improving accuracy of protein fold recognition

Protein structure and function are largely specified by the distribution of different atoms and residues relative to the core and surface of the molecule. Relative depths of atoms therefore are key attributions that have been widely used in protein structure modeling and function annotation. However, accurate calculation of depth is time consuming. Here, we developed an algorithm which uses Euclidean distance transform (EDT) to convert the target protein structure into a 3D gray-scale image, where depths of atoms in the protein can be conveniently and precisely derived from the minimum distance of the pixels to the surface of the protein. We tested the proposed EDT-based method on a set of 261 non-redundant protein structures, which shows that the method is 2.6 times faster than the widely used method proposed by Chakravarty and Varadarajan. Depth values by EDT method are highly accurate with a Pearson's correlation coefficient ≈1 compared to the calculations from exhaustive search. To explore the usefulness of the method in protein structure prediction, we add the calculated residue depth to the scoring function of the state of the art, profile-profile alignment based fold-recognition program, which shows an additional 3% improvement in the TM-score of the alignments. The data demonstrate that the EDT-based depth calculation program can be used as an efficient tool to assist protein structure analysis and structure-based function annotation.

Transmembrane protein alignment and fold recognition based on predicted topology

BACKGROUND

Although Transmembrane Proteins (TMPs) are highly important in various biological processes and pharmaceutical developments, general prediction of TMP structures is still far from satisfactory. Because TMPs have significantly different physicochemical properties from soluble proteins, current protein structure prediction tools for soluble proteins may not work well for TMPs. With the increasing number of experimental TMP structures available, template-based methods have the potential to become broadly applicable for TMP structure prediction. However, the current fold recognition methods for TMPs are not as well developed as they are for soluble proteins.

METHODOLOGY

We developed a novel TMP Fold Recognition method, TMFR, to recognize TMP folds based on sequence-to-structure pairwise alignment. The method utilizes topology-based features in alignment together with sequence profile and solvent accessibility. It also incorporates a gap penalty that depends on predicted topology structure segments. Given the difference between α-helical transmembrane protein (αTMP) and β-strands transmembrane protein (βTMP), parameters of scoring functions are trained respectively for these two protein categories using 58 αTMPs and 17 βTMPs in a non-redundant training dataset.

RESULTS

We compared our method with HHalign, a leading alignment tool using a non-redundant testing dataset including 72 αTMPs and 30 βTMPs. Our method achieved 10% and 9% better accuracies than HHalign in αTMPs and βTMPs, respectively. The raw score generated by TMFR is negatively correlated with the structure similarity between the target and the template, which indicates its effectiveness for fold recognition. The result demonstrates TMFR provides an effective TMP-specific fold recognition and alignment method.

Adepth: New Representation and its implications for atomic depths of macromolecules

We applied the signed distance function (SDF) for representing the depths of atoms in a macromolecule. The calculations of SDF values were performed on grid points in a rectangular box that accommodates the macromolecule. The depth for an atom inside the molecule was then obtained as a result of tri-linear interpolation of SDF values at the nearest grid points surrounding the atom. For testing the performance of present program Adepth, we have constructed an artificial molecule whose atomic depths are known as the gold standard for accuracy assessments. On average, our results showed that Adepth reached an accuracy of 1.6% at 0.5 Å of grid spacing, whereas the current reference server DEPTH reached 7.5%. The Adepth program provides both depth and height representations; it is capable of computing iso-surfaces for atomic depths and presenting graphical view of macromolecular shape at some distance away from the surface. Web interface is available at http://biodev.cea.fr/adepth.

Fast and Accurate Calculation of Protein Depth by Euclidean Distance Transform

The depth of each atom/residue in a protein structure is a key attribution that has been widely used in protein structure modeling and function annotation. However, the accurate calculation of depth is time consuming. Here, we propose to use the Euclidean distance transform (EDT) to calculate the depth, which conveniently converts the protein structure to a 3D gray-scale image with each pixel labeling the minimum distance of the pixel to the surface of the molecule (i.e. the depth). We tested the proposed EDT method on a set of 261 non-redundant protein structures. The data show that the EDT method is 2.6 times faster than the widely used method by Chakravarty and Varadarajan. The depth value by EDT method is also highly accurate, which is almost identical to the depth calculated by exhaustive search (Pearson's correlation coefficient≈1). We believe the EDT-based depth calculation program can be used as an efficient tool to assist the studies of protein fold recognition and structure-based function annotation.

Effective inter-residue contact definitions for accurate protein fold recognition

BACKGROUND

Effective encoding of residue contact information is crucial for protein structure prediction since it has a unique role to capture long-range residue interactions compared to other commonly used scoring terms. The residue contact information can be incorporated in structure prediction in several different ways: It can be incorporated as statistical potentials or it can be also used as constraints in ab initio structure prediction. To seek the most effective definition of residue contacts for template-based protein structure prediction, we evaluated 45 different contact definitions, varying bases of contacts and distance cutoffs, in terms of their ability to identify proteins of the same fold.

RESULTS

We found that overall the residue contact pattern can distinguish protein folds best when contacts are defined for residue pairs whose Cβ atoms are at 7.0 Å or closer to each other. Lower fold recognition accuracy was observed when inaccurate threading alignments were used to identify common residue contacts between protein pairs. In the case of threading, alignment accuracy strongly influences the fraction of common contacts identified among proteins of the same fold, which eventually affects the fold recognition accuracy. The largest deterioration of the fold recognition was observed for β-class proteins when the threading methods were used because the average alignment accuracy was worst for this fold class. When results of fold recognition were examined for individual proteins, we found that the effective contact definition depends on the fold of the proteins. A larger distance cutoff is often advantageous for capturing spatial arrangement of the secondary structures which are not physically in contact. For capturing contacts between neighboring β strands, considering the distance between Cα atoms is better than the Cβ-based distance because the side-chain of interacting residues on β strands sometimes point to opposite directions.

CONCLUSION

Residue contacts defined by Cβ-Cβ distance of 7.0 Å work best overall among tested to identify proteins of the same fold. We also found that effective contact definitions differ from fold to fold, suggesting that using different residue contact definition specific for each template will lead to improvement of the performance of threading.

Template-based structure prediction and classification of transcription factors in Arabidopsis thaliana

Transcription factors (TFs) play important roles in plants. However, there is no systematic study of their structures and functions of most TFs in plants. Here, we performed template-based structure prediction for all TFs in Arabidopsis thaliana, with their full-length sequences as well as C-terminal and N-terminal regions. A total of 2918 model structures were obtained with a high confidence score. We find that TF families employ only a smaller number of templates for DNA-binding domains (DBD) but a diverse number of templates for transcription regulatory domains (TRD). Although TF families are classified according to DBD, their sizes have a significant correlation with the number of unique non-DNA-binding templates employed in the family (Pearson correlation coefficient of 0.74). That is, the size of TF family is related to its functional diversity. Network analysis reveals new connections between TF families based on shared TRD or DBD templates; 81% TF families share DBD and 67% share TRD templates. Two large fully connected family clusters in this network are observed along with 69 island families. In addition, 25 genes with unknown functions are found to be DNA-binding and/or TF factors according to predicted structures. This work provides a global view of the classification of TFs based on their DBD or TRD templates, and hence, a deeper understanding of DNA-binding and regulatory functions from structural perspective. All structural models of TFs are deposited in the online database for public usage at http://sysbio.unl.edu/AthTF.

Coarse-grain Protein Models

Coarse-graining is a powerful approach for modeling biomolecules that, over the last few decades, has been extensively applied to proteins. Coarse-grain models offer access to large systems and to slow processes without becoming computationally unmanageable. In addition, they are very versatile, enabling both the protein representation and the energy function to be adapted to the biological problem in hand. This review concentrates on modeling soluble proteins and their assemblies. It presents an overview of the coarse-grain representations, of the associated interaction potentials, and of the optimization procedures used to define them. It then shows how coarse-grain models have been used to understand processes involving proteins, from their initial folding to their functional properties, their binary interactions, and the assembly of large complexes.

CONTSOR--a new knowledge-based fold recognition potential, based on side chain orientation and contacts between residue terminal groups

Recognizing the structural similarity without significant sequence identity (fold recognition) is an effective method for protein structure prediction. Previously, we developed a fold recognition potential called SORDIS, which incorporated side chain orientation in relation to hydrophobic core centers, distance of the residues from the protein globule center and secondary structure terms. But this potential does not include terms, based on close contacts between residues. In this paper a new fold recognition potential CONTSOR was presented, which based on SORDIS terms and the term, based on contacts between amino acid terminal groups. The performance of this potential was evaluated on SABmark benchmark for alignment accuracy and on SABmark and Lindahl benchmarks for fold recognition. The results show that CONTSOR has the best performance among other potentials on SABmark benchmark both for alignment accuracy and fold recognition and one of the best performances on Lindahl benchmark. CONTSOR software package is available for download at http://www.lifescience.org.ge/downloads/contsor.zip.

Highly accurate and high-resolution function prediction of RNA binding proteins by fold recognition and binding affinity prediction

A full understanding of the mechanism of post- transcriptional regulation requires more than simple two- state prediction (binding or not binding) for RNA binding proteins. Here we report a sequence-based technique dedicated for predicting complex structures of protein and RNA by combining fold recognition with binding affinity prediction. The method not only provides a highly accurate complex structure prediction (77% of residues are within 4°A RMSD from native in average for the independent test set) but also achieves the best performing two-state binding or non-binding prediction with an accuracy of 98%, precision of 84%, and Mathews correlation coefficient (MCC) of 0.62. Moreover, it predicts binding residues with an accuracy of 84%, precision of 66% and MCC value of 0.51. In addition, it has a success rate of 77% in predicting RNA binding types (mRNA, tRNA or rRNA). We further demonstrate that it makes more than 10% improvement either in precision or sensitivity than PSI- BLAST, HHPRED and our previously developed structure- based technique. This method expects to be useful for highly accurate genome-scale, high-resolution prediction of RNA-binding proteins and their complex structures. A web server (SPOT) is freely available for academic users at http://sparks.informatics.iupui.edu.

Using structure to explore the sequence alignment space of remote homologs

Protein structure modeling by homology requires an accurate sequence alignment between the query protein and its structural template. However, sequence alignment methods based on dynamic programming (DP) are typically unable to generate accurate alignments for remote sequence homologs, thus limiting the applicability of modeling methods. A central problem is that the alignment that is “optimal” in terms of the DP score does not necessarily correspond to the alignment that produces the most accurate structural model. That is, the correct alignment based on structural superposition will generally have a lower score than the optimal alignment obtained from sequence. Variations of the DP algorithm have been developed that generate alternative alignments that are “suboptimal” in terms of the DP score, but these still encounter difficulties in detecting the correct structural alignment. We present here a new alternative sequence alignment method that relies heavily on the structure of the template. By initially aligning the query sequence to individual fragments in secondary structure elements and combining high-scoring fragments that pass basic tests for “modelability”, we can generate accurate alignments within a small ensemble. Our results suggest that the set of sequences that can currently be modeled by homology can be greatly extended.

It has been suggested that, for nearly every protein sequence, there is already a protein with a similar structure in current protein structure databases. However, with poor or undetectable sequence relationships, it is expected that accurate alignments and models cannot be generated. Here we show that this is not the case, and that whenever structural relationship exists, there are usually local sequence relationships that can be used to generate an accurate alignment, no matter what the global sequence identity. However, this requires an alternative to the traditional dynamic programming algorithm and the consideration of a small ensemble of alignments. We present an algorithm, S4, and demonstrate that it is capable of generating accurate alignments in nearly all cases where a structural relationship exists between two proteins. Our results thus constitute an important advance in the full exploitation of the information in structural databases. That is, the expectation of an accurate alignment suggests that a meaningful model can be generated for nearly every sequence for which a suitable template exists.

QSE: A new 3-D solvent exposure measure for the analysis of protein structure

Solvent exposure of amino acids measures how deep residues are buried in tertiary structure of proteins, and hence it provides important information for analyzing and predicting protein structure and functions. Existing methods of calculating solvent exposure such as accessible surface area, relative accessible surface area, residue depth, contact number, and half-sphere exposure still have some limitations. In this article, we propose a novel solvent exposure measure named quadrant-sphere exposure (QSE) based on eight quadrants derived from spherical neighborhood. The proposed measure forms a microenvironment around Cα atom as a sphere with a radius of 13 Å, and subdivides it into eight quadrants according to a rectangular coordinate system constructed based on geometric relationships of backbone atoms. The number of neighboring Cα atoms whose labels are the same is given as the QSE value of the center Cα atom at hand. As evidenced by histograms that show very different distributions for different structure configurations, the proposed measure captures local properties that are characteristic for a residue's eight-directional neighborhood within a sphere. Compared with other measures, QSE provides a different view of solvent exposure, and provides information that is specific for different tertiary structure. As the experimental results show, QSE measure can potentially be used in protein structure analysis and predictions.

Improving protein fold recognition and template-based modeling by employing probabilistic-based matching between predicted one-dimensional structural properties of query and corresponding native properties of templates

MOTIVATION

In recent years, development of a single-method fold-recognition server lags behind consensus and multiple template techniques. However, a good consensus prediction relies on the accuracy of individual methods. This article reports our efforts to further improve a single-method fold recognition technique called SPARKS by changing the alignment scoring function and incorporating the SPINE-X techniques that make improved prediction of secondary structure, backbone torsion angle and solvent accessible surface area.

RESULTS

The new method called SPARKS-X was tested with the SALIGN benchmark for alignment accuracy, Lindahl and SCOP benchmarks for fold recognition, and CASP 9 blind test for structure prediction. The method is compared to several state-of-the-art techniques such as HHPRED and BoostThreader. Results show that SPARKS-X is one of the best single-method fold recognition techniques. We further note that incorporating multiple templates and refinement in model building will likely further improve SPARKS-X.

AVAILABILITY

The method is available as a SPARKS-X server at http://sparks.informatics.iupui.edu/

Protein sequence comparison and fold recognition: progress and good-practice benchmarking

Protein sequence comparison methods have grown increasingly sensitive during the last decade and can often identify distantly related proteins sharing a common ancestor some 3 billion years ago. Although cellular function is not conserved so long, molecular functions and structures of protein domains often are. In combination with a domain-centered approach to function and structure prediction, modern remote homology detection methods have a great and largely underexploited potential for elucidating protein functions and evolution. Advances during the last few years include nonlinear scoring functions combining various sequence features, the use of sequence context information, and powerful new software packages. Since progress depends on realistically assessing new and existing methods and published benchmarks are often hard to compare, we propose 10 rules of good-practice benchmarking.

TASSER_low-zsc: an approach to improve structure prediction using low z-score-ranked templates

In a variety of threading methods, often poorly ranked (low z-score) templates have good alignments. Here, a new method, TASSER_low-zsc that identifies these low z-score-ranked templates to improve protein structure prediction accuracy, is described. The approach consists of clustering of threading templates by affinity propagation on the basis of structural similarity (thread_cluster) followed by TASSER modeling, with final models selected by using a TASSER_QA variant. To establish the generality of the approach, templates provided by two threading methods, SP(3) and SPARKS(2), are examined. The SP(3) and SPARKS(2) benchmark datasets consist of 351 and 357 medium/hard proteins (those with moderate to poor quality templates and/or alignments) of length < or =250 residues, respectively. For SP(3) medium and hard targets, using thread_cluster, the TM-scores of the best template improve by approximately 4 and 9% over the original set (without low z-score templates) respectively; after TASSER modeling/refinement and ranking, the best model improves by approximately 7 and 9% over the best model generated with the original template set. Moreover, TASSER_low-zsc generates 22% (43%) more foldable medium (hard) targets. Similar improvements are observed with low-ranked templates from SPARKS(2). The template clustering approach could be applied to other modeling methods that utilize multiple templates to improve structure prediction.

Incorporation of local structural preference potential improves fold recognition

Fold recognition, or threading, is a popular protein structure modeling approach that uses known structure templates to build structures for those of unknown. The key to the success of fold recognition methods lies in the proper integration of sequence, physiochemical and structural information. Here we introduce another type of information, local structural preference potentials of 3-residue and 9-residue fragments, for fold recognition. By combining the two local structural preference potentials with the widely used sequence profile, secondary structure information and hydrophobic score, we have developed a new threading method called FR-t5 (fold recognition by use of 5 terms). In benchmark testings, we have found the consideration of local structural preference potentials in FR-t5 not only greatly enhances the alignment accuracy and recognition sensitivity, but also significantly improves the quality of prediction models.

Effect of using suboptimal alignments in template-based protein structure prediction

Computational protein structure prediction remains a challenging task in protein bioinformatics. In the recent years, the importance of template-based structure prediction is increasing because of the growing number of protein structures solved by the structural genomics projects. To capitalize the significant efforts and investments paid on the structural genomics projects, it is urgent to establish effective ways to use the solved structures as templates by developing methods for exploiting remotely related proteins that cannot be simply identified by homology. In this work, we examine the effect of using suboptimal alignments in template-based protein structure prediction. We showed that suboptimal alignments are often more accurate than the optimal one, and such accurate suboptimal alignments can occur even at a very low rank of the alignment score. Suboptimal alignments contain a significant number of correct amino acid residue contacts. Moreover, suboptimal alignments can improve template-based models when used as input to Modeller. Finally, we use suboptimal alignments for handling a contact potential in a probabilistic way in a threading program, SUPRB. The probabilistic contacts strategy outperforms the partly thawed approach, which only uses the optimal alignment in defining residue contacts, and also the re-ranking strategy, which uses the contact potential in re-ranking alignments. The comparison with existing methods in the template-recognition test shows that SUPRB is very competitive and outperforms existing methods.

Cpl-7, a lysozyme encoded by a pneumococcal bacteriophage with a novel cell wall-binding motif

Bacteriophage endolysins include a group of new antibacterials reluctant to development of resistance. We present here the first structural study of the Cpl-7 endolysin, encoded by pneumococcal bacteriophage Cp-7. It contains an N-terminal catalytic module (CM) belonging to the GH25 family of glycosyl hydrolases and a C-terminal region encompassing three identical repeats of 42 amino acids (CW_7 repeats). These repeats are unrelated to choline-targeting motifs present in other cell wall hydrolases produced by Streptococcus pneumoniae and its bacteriophages, and are responsible for the protein attachment to the cell wall. By combining different biophysical techniques and molecular modeling, a three-dimensional model of the overall protein structure is proposed, consistent with circular dichroism and sequence-based secondary structure prediction, small angle x-ray scattering data, and Cpl-7 hydrodynamic behavior. Cpl-7 is an ∼115-Å long molecule with two well differentiated regions, corresponding to the CM and the cell wall binding region (CWBR), arranged in a lateral disposition. The CM displays the (βα)(5)β(3) barrel topology characteristic of the GH25 family, and the impact of sequence differences with the CM of the Cpl-1 lysozyme in substrate binding is discussed. The CWBR is organized in three tandemly assembled three-helical bundles whose dispositions remind us of a super-helical structure. Its approximate dimensions are 60 × 20 × 20 Å and presents a concave face that might constitute the functional region involved in bacterial surface recognition. The distribution of CW_7 repeats in the sequences deposited in the Entrez Database have been examined, and the results drastically expanded the antimicrobial potential of the Cpl-7 endolysin.

Shape and evolution of thermostable protein structure

Organisms evolved at high temperatures must maintain their proteins' structures in the face of increased thermal disorder. This challenge results in differences in residue utilization and overall structure. Focusing on thermostable/mesostable pairs of homologous structures, we have examined these differences using novel geometric measures: specifically burial depth (distance from the molecular surface to each atom) and travel depth (distance from the convex hull to the molecular surface that avoids the protein interior). These along with common metrics like packing and Wadell Sphericity are used to gain insight into the constraints experienced by thermophiles. Mean travel depth of hyperthermostable proteins is significantly less than that of their mesostable counterparts, indicating smaller, less numerous and less deep pockets. The mean burial depth of hyperthermostable proteins is significantly higher than that of mesostable proteins indicating that they bury more atoms further from the surface. The burial depth can also be tracked on the individual residue level, adding a finer level of detail to the standard exposed surface area analysis. Hyperthermostable proteins for the first time are shown to be more spherical than their mesostable homologues, regardless of when and how they adapted to extreme temperature. Additionally, residue specific burial depth examinations reveal that charged residues stay unburied, most other residues are slightly more buried and Alanine is more significantly buried in hyperthermostable proteins.