RFCRYS: sequence-based protein crystallization propensity prediction by means of random forest

Benchmarking protein language models for protein crystallization

The problem of protein structure determination is usually solved by X-ray crystallography. Several in silico deep learning methods have been developed to overcome the high attrition rate, cost of experiments and extensive trial-and-error settings, for predicting the crystallization propensities of proteins based on their sequences. In this work, we benchmark the power of open protein language models (PLMs) through the TRILL platform, a be-spoke framework democratizing the usage of PLMs for the task of predicting crystallization propensities of proteins. By comparing LightGBM / XGBoost classifiers built on the average embedding representations of proteins learned by different PLMs, such as ESM2, Ankh, ProtT5-XL, ProstT5, xTrimoPGLM, SaProt with the performance of state-of-the-art sequence-based methods like DeepCrystal, ATTCrys and CLPred, we identify the most effective methods for predicting crystallization outcomes. The LightGBM classifiers utilizing embeddings from ESM2 model with 30 and 36 transformer layers and 150 and 3000 million parameters respectively have performance gains by 3-[Formula: see text] than all compared models for various evaluation metrics, including AUPR (Area Under Precision-Recall Curve), AUC (Area Under the Receiver Operating Characteristic Curve), and F1 on independent test sets. Furthermore, we fine-tune the ProtGPT2 model available via TRILL to generate crystallizable proteins. Starting with 3000 generated proteins and through a step of filtration processes including consensus of all open PLM-based classifiers, sequence identity through CD-HIT, secondary structure compatibility, aggregation screening, homology search and foldability evaluation, we identified a set of 5 novel proteins as potentially crystallizable.

Machine learning model of the catalytic efficiency and substrate specificity of acyl-ACP thioesterase variants generated from natural and in vitro directed evolution

Modulating the catalytic activity of acyl-ACP thioesterase (TE) is an important biotechnological target for effectively increasing flux and diversifying products of the fatty acid biosynthesis pathway. In this study, a directed evolution approach was developed to improve the fatty acid titer and fatty acid diversity produced by E. coli strains expressing variant acyl-ACP TEs. A single round of in vitro directed evolution, coupled with a high-throughput colorimetric screen, identified 26 novel acyl-ACP TE variants that convey up to a 10-fold increase in fatty acid titer, and generate altered fatty acid profiles when expressed in a bacterial host strain. These in vitro-generated variant acyl-ACP TEs, in combination with 31 previously characterized natural variants isolated from diverse phylogenetic origins, were analyzed with a random forest classifier machine learning tool. The resulting quantitative model identified 22 amino acid residues, which define important structural features that determine the catalytic efficiency and substrate specificity of acyl-ACP TE.

GCmapCrys: Integrating graph attention network with predicted contact map for multi-stage protein crystallization propensity prediction

X-ray crystallography is the major approach for atomic-level protein structure determination. Since not all proteins can be easily crystallized, accurate prediction of protein crystallization propensity is critical to guiding the experimental design and improving the success rate of X-ray crystallography experiments. In this work, we proposed a new deep learning pipeline, GCmapCrys, for multi-stage crystallization propensity prediction through integrating graph attention network with predicted protein contact map. Experimental results on 1548 proteins with known crystallization records demonstrated that GCmapCrys increased the value of Matthew's correlation coefficient by 37.0% in average compared to state-of-the-art protein crystallization propensity predictors. Detailed analyses show that the major advantages of GCmapCrys lie in the efficiency of the graph attention network with predicted contact map, which effectively associates the residue-interaction knowledge with crystallization pattern. Meanwhile, the designed four sequence-based features can be complementary to further enhance crystallization propensity proprediction.

Protein Crystallization Identification via Fuzzy Model on Linear Neighborhood Representation

X-ray crystallography is the most popular approach for analyzing protein 3D structure. However, the success rate of protein crystallization is very low (2-10 percent). To reduce the cost of time and resources, lots of computation-based methods are developed to detect the protein crystallization. Improving the accuracy of predicting protein crystallization is very important for the determination of protein structure by X-ray crystallography. At present, many machine learning methods are used to predict protein crystallization. In this article, we propose a Fuzzy Support Vector Machine based on Linear Neighborhood Representation (FSVM-LNR) to predict the crystallization propensity of proteins. Proteins are represented by three types of features (PsePSSM, PSSM-DWT, MMI-PS), and these features are serially combined and fed into FSVM-LNR. FSVM-LNR can filter outliers by membership score, which is calculated via reconstruction residuals of k nearest samples. To evaluate the performance of our predictive model, we test FSVM-LNR on the datasets of TRAIN3587, TEST3585 and TEST500. Our method achieves better Mathew's correlation coefficient (MCC) on TRAIN3587 (MCC: 0.56) and TEST3585 (MCC: 0.58). Although the performance of independent test is not the best on TEST500, FSVM-LNR also has a certain predictability (MCC: 0.70) in the identification of protein crystallization. The good performance on the datasets proves the effectiveness of our method and the better performance on large datasets further demonstrates the stability and superiority of our method.

Sequence-Based Prediction of Transmembrane Protein Crystallization Propensity

Transmembrane proteins play a vital role in cell life activities. There are several techniques to determine transmembrane protein structures and X-ray crystallography is the primary methodology. However, due to the special properties of transmembrane proteins, it is still hard to determine their structures by X-ray crystallography technique. To reduce experimental consumption and improve experimental efficiency, it is of great significance to develop computational methods for predicting the crystallization propensity of transmembrane proteins. In this work, we proposed a sequence-based machine learning method, namely Prediction of TransMembrane protein Crystallization propensity (PTMC), to predict the propensity of transmembrane protein crystallization. First, we obtained several general sequence features and the specific encoded features of relative solvent accessibility and hydrophobicity. Second, feature selection was employed to filter out redundant and irrelevant features, and the optimal feature subset is composed of hydrophobicity, amino acid composition and relative solvent accessibility. Finally, we chose extreme gradient boosting by comparing with other several machine learning methods. Comparative results on the independent test set indicate that PTMC outperforms state-of-the-art sequence-based methods in terms of sensitivity, specificity, accuracy, Matthew's Correlation Coefficient (MCC) and Area Under the receiver operating characteristic Curve (AUC). In comparison with two competitors, Bcrystal and TMCrys, PTMC achieves an improvement by 0.132 and 0.179 for sensitivity, 0.014 and 0.127 for specificity, 0.037 and 0.192 for accuracy, 0.128 and 0.362 for MCC, and 0.027 and 0.125 for AUC, respectively.

CrystalM: A Multi-View Fusion Approach for Protein Crystallization Prediction

Improving the accuracy of predicting protein crystallization is very important for protein crystallization projects, which is a critical step for the determination of protein structure by X-ray crystallography. At present, many machine learning methods are used to predict protein crystallization. Here, we use a novel feature combination to construct a SVM model in the prediction of protein crystallization, called as CrystalM. In this work, we extract six features to represent protein sequences, namely Average Block-Position specific scoring matrix (AVBlock-PSSM), Average Block-Secondary Structure (AVBlock-SS), Global Encoding (GE), Pseudo-Position specific scoring matrix (PsePSSM), Protscale, and Discrete Wavelet Transform-Position specific scoring matrix (DWT-PSSM). Moreover, we employ two training datasets (TRAIN3587 and TRAIN1500) and their corresponding independent test datasets (TEST3585 and TEST500) to evaluate CrystalM by feeding multi-view features into Support Vector Machine (SVM) classifier. Two training datasets are employed for five-fold cross validation, and two test datasets are separately used to test the corresponding datasets. Finally, we compare CrystalM with other existing methods in the performance. For the datasets of TRAIN3587 and TEST3585, CrystalM achieves best Accuracy (ACC), best Specificity (SP), and the same Mathew's correlation coefficient (MCC) as the previous outperforming methods in the five-fold cross validation. In particular, ACC, SP, and MCC have surpassed the existing methods in independent test, which proves the effectiveness of CrystalM. Meanwhile, ACC, SP, and MCC are higher than existing methods in the five-fold cross validation for TRAIN1500. Although the performance of independent test for TEST500 is not the best, CrystalM also has a certain predictability in the prediction of protein crystallization. In addition, we find that only choosing the first four features can improve the performance of prediction for TRAIN1500 and TEST500, not only in independent tests but also in five-fold cross validation. This phenomenon indicates that the latter two features can not effectively represent proteins of TRAIN1500 and TEST500. CrystalM is a sequence-based protein crystallization prediction method. The good performance on the datasets proves the effectiveness of CrystalM and the better performance on large datasets further demonstrates the stability and superiority of CrystalM.

Critical evaluation of bioinformatics tools for the prediction of protein crystallization propensity

X-ray crystallography is the main tool for structural determination of proteins. Yet, the underlying crystallization process is costly, has a high attrition rate and involves a series of trial-and-error attempts to obtain diffraction-quality crystals. The Structural Genomics Consortium aims to systematically solve representative structures of major protein-fold classes using primarily high-throughput X-ray crystallography. The attrition rate of these efforts can be improved by selection of proteins that are potentially easier to be crystallized. In this context, bioinformatics approaches have been developed to predict crystallization propensities based on protein sequences. These approaches are used to facilitate prioritization of the most promising target proteins, search for alternative structural orthologues of the target proteins and suggest designs of constructs capable of potentially enhancing the likelihood of successful crystallization. We reviewed and compared nine predictors of protein crystallization propensity. Moreover, we demonstrated that integrating selected outputs from multiple predictors as candidate input features to build the predictive model results in a significantly higher predictive performance when compared to using these predictors individually. Furthermore, we also introduced a new and accurate predictor of protein crystallization propensity, Crysf, which uses functional features extracted from UniProt as inputs. This comprehensive review will assist structural biologists in selecting the most appropriate predictor, and is also beneficial for bioinformaticians to develop a new generation of predictive algorithms.

Survey of Predictors of Propensity for Protein Production and Crystallization with Application to Predict Resolution of Crystal Structures

Selection of proper targets for the X-ray crystallography will benefit biological research community immensely. Several computational models were proposed to predict propensity of successful protein production and diffraction quality crystallization from protein sequences. We reviewed a comprehensive collection of 22 such predictors that were developed in the last decade. We found that almost all of these models are easily accessible as webservers and/or standalone software and we demonstrated that some of them are widely used by the research community. We empirically evaluated and compared the predictive performance of seven representative methods. The analysis suggests that these methods produce quite accurate propensities for the diffraction-quality crystallization. We also summarized results of the first study of the relation between these predictive propensities and the resolution of the crystallizable proteins. We found that the propensities predicted by several methods are significantly higher for proteins that have high resolution structures compared to those with the low resolution structures. Moreover, we tested a new meta-predictor, MetaXXC, which averages the propensities generated by the three most accurate predictors of the diffraction-quality crystallization. MetaXXC generates putative values of resolution that have modest levels of correlation with the experimental resolutions and it offers the lowest mean absolute error when compared to the seven considered methods. We conclude that protein sequences can be used to fairly accurately predict whether their corresponding protein structures can be solved using X-ray crystallography. Moreover, we also ascertain that sequences can be used to reasonably well predict the resolution of the resulting protein crystals.

Crysalis: an integrated server for computational analysis and design of protein crystallization

The failure of multi-step experimental procedures to yield diffraction-quality crystals is a major bottleneck in protein structure determination. Accordingly, several bioinformatics methods have been successfully developed and employed to select crystallizable proteins. Unfortunately, the majority of existing in silico methods only allow the prediction of crystallization propensity, seldom enabling computational design of protein mutants that can be targeted for enhancing protein crystallizability. Here, we present Crysalis, an integrated crystallization analysis tool that builds on support-vector regression (SVR) models to facilitate computational protein crystallization prediction, analysis, and design. More specifically, the functionality of this new tool includes: (1) rapid selection of target crystallizable proteins at the proteome level, (2) identification of site non-optimality for protein crystallization and systematic analysis of all potential single-point mutations that might enhance protein crystallization propensity, and (3) annotation of target protein based on predicted structural properties. We applied the design mode of Crysalis to identify site non-optimality for protein crystallization on a proteome-scale, focusing on proteins currently classified as non-crystallizable. Our results revealed that site non-optimality is based on biases related to residues, predicted structures, physicochemical properties, and sequence loci, which provides in-depth understanding of the features influencing protein crystallization. Crysalis is freely available at http://nmrcen.xmu.edu.cn/crysalis/.

Protein stability: a crystallographer's perspective

Protein stability is a topic of major interest for the biotechnology, pharmaceutical and food industries, in addition to being a daily consideration for academic researchers studying proteins. An understanding of protein stability is essential for optimizing the expression, purification, formulation, storage and structural studies of proteins. In this review, discussion will focus on factors affecting protein stability, on a somewhat practical level, particularly from the view of a protein crystallographer. The differences between protein conformational stability and protein compositional stability will be discussed, along with a brief introduction to key methods useful for analyzing protein stability. Finally, tactics for addressing protein-stability issues during protein expression, purification and crystallization will be discussed.

Computational crystallization

Crystallization is a key step in macromolecular structure determination by crystallography. While a robust theoretical treatment of the process is available, due to the complexity of the system, the experimental process is still largely one of trial and error. In this article, efforts in the field are discussed together with a theoretical underpinning using a solubility phase diagram. Prior knowledge has been used to develop tools that computationally predict the crystallization outcome and define mutational approaches that enhance the likelihood of crystallization. For the most part these tools are based on binary outcomes (crystal or no crystal), and the full information contained in an assembly of crystallization screening experiments is lost. The potential of this additional information is illustrated by examples where new biological knowledge can be obtained and where a target can be sub-categorized to predict which class of reagents provides the crystallization driving force. Computational analysis of crystallization requires complete and correctly formatted data. While massive crystallization screening efforts are under way, the data available from many of these studies are sparse. The potential for this data and the steps needed to realize this potential are discussed.

Predicting Crystallization Propensity of Proteins from Arabidopsis Thaliana

Background

Many studies have correlated characteristics of amino acids with crystallization propensity, as part of the effort to determine the factors that affect the propensity of protein crystallization. However, these characteristics are constant; that is, the encoded amino acid sequences have the same value for each type of amino acid. To overcome this inflexibility, three dynamic characteristics of amino acids and protein were introduced to analyze the crystallization propensity of proteins. Both logistic regression and neural network models were used to correlate each of two dynamic characteristics with the crystallization propensity of 301 proteins from Arabidopsis thaliana, and their results were compared with those obtained from each of 531 constant amino acid characteristics, which served as the benchmark.

Results

The neural network model was more powerful for predicting the crystallization propensity of proteins than the logistic regression model. Compared with the benchmark, the dynamic characteristics of amino acids provided good prediction results for the crystallization propensity, and the distribution probability gave the highest sensitivity. Using 90 % accuracy as a cutoff point, the predictable portion of A. thaliana portions was ranked, and the statistical analysis showed that the larger the predictable portion, the better the prediction.

Conclusions

These results demonstrate that dynamic characteristics have a certain relationship with the crystallization propensity, and they could be helpful for the prediction of protein crystallization, which may provide a theoretical concept for certain proteins before conducting experimental crystallization.

Electronic supplementary material

The online version of this article (doi:10.1186/s12575-015-0029-3) contains supplementary material, which is available to authorized users.

Analysis of crystallization data in the Protein Data Bank

The Protein Data Bank (PDB) is the largest available repository of solved protein structures and contains a wealth of information on successful crystallization. Many centres have used their own experimental data to draw conclusions about proteins and the conditions in which they crystallize. Here, data from the PDB were used to reanalyse some of these results. The most successful crystallization reagents were identified, the link between solution pH and the isoelectric point of the protein was investigated and the possibility of predicting whether a protein will crystallize was explored.

TargetFreeze: Identifying Antifreeze Proteins via a Combination of Weights using Sequence Evolutionary Information and Pseudo Amino Acid Composition

Antifreeze proteins (AFPs) are indispensable for living organisms to survive in an extremely cold environment and have a variety of potential biotechnological applications. The accurate prediction of antifreeze proteins has become an important issue and is urgently needed. Although considerable progress has been made, AFP prediction is still a challenging problem due to the diversity of species. In this study, we proposed a new sequence-based AFP predictor, called TargetFreeze. TargetFreeze utilizes an enhanced feature representation method that weightedly combines multiple protein features and takes the powerful support vector machine as the prediction engine. Computer experiments on benchmark datasets demonstrate the superiority of the proposed TargetFreeze over most recently released AFP predictors. We also implemented a user-friendly web server, which is openly accessible for academic use and is available at http://csbio.njust.edu.cn/bioinf/TargetFreeze. TargetFreeze supplements existing AFP predictors and will have potential applications in AFP-related biotechnology fields.

Will it crystallise? Predicting crystallinity of molecular materials

Machine learning algorithms can be used to create models which separate molecular materials which will form good-quality crystals from those that will not, and predict how synthetic modifications will change the crystallinity.

PredPPCrys: accurate prediction of sequence cloning, protein production, purification and crystallization propensity from protein sequences using multi-step heterogeneous feature fusion and selection

X-ray crystallography is the primary approach to solve the three-dimensional structure of a protein. However, a major bottleneck of this method is the failure of multi-step experimental procedures to yield diffraction-quality crystals, including sequence cloning, protein material production, purification, crystallization and ultimately, structural determination. Accordingly, prediction of the propensity of a protein to successfully undergo these experimental procedures based on the protein sequence may help narrow down laborious experimental efforts and facilitate target selection. A number of bioinformatics methods based on protein sequence information have been developed for this purpose. However, our knowledge on the important determinants of propensity for a protein sequence to produce high diffraction-quality crystals remains largely incomplete. In practice, most of the existing methods display poorer performance when evaluated on larger and updated datasets. To address this problem, we constructed an up-to-date dataset as the benchmark, and subsequently developed a new approach termed ‘PredPPCrys’ using the support vector machine (SVM). Using a comprehensive set of multifaceted sequence-derived features in combination with a novel multi-step feature selection strategy, we identified and characterized the relative importance and contribution of each feature type to the prediction performance of five individual experimental steps required for successful crystallization. The resulting optimal candidate features were used as inputs to build the first-level SVM predictor (PredPPCrys I). Next, prediction outputs of PredPPCrys I were used as the input to build second-level SVM classifiers (PredPPCrys II), which led to significantly enhanced prediction performance. Benchmarking experiments indicated that our PredPPCrys method outperforms most existing procedures on both up-to-date and previous datasets. In addition, the predicted crystallization targets of currently non-crystallizable proteins were provided as compendium data, which are anticipated to facilitate target selection and design for the worldwide structural genomics consortium. PredPPCrys is freely available at http://www.structbioinfor.org/PredPPCrys.

Improving the chances of successful protein structure determination with a random forest classifier

Obtaining diffraction quality crystals remains one of the major bottlenecks in structural biology. The ability to predict the chances of crystallization from the amino-acid sequence of the protein can, at least partly, address this problem by allowing a crystallographer to select homologs that are more likely to succeed and/or to modify the sequence of the target to avoid features that are detrimental to successful crystallization. In 2007, the now widely used XtalPred algorithm [Slabinski et al. (2007), Protein Sci. 16, 2472-2482] was developed. XtalPred classifies proteins into five `crystallization classes' based on a simple statistical analysis of the physicochemical features of a protein. Here, towards the same goal, advanced machine-learning methods are applied and, in addition, the predictive potential of additional protein features such as predicted surface ruggedness, hydrophobicity, side-chain entropy of surface residues and amino-acid composition of the predicted protein surface are tested. The new XtalPred-RF (random forest) achieves significant improvement of the prediction of crystallization success over the original XtalPred. To illustrate this, XtalPred-RF was tested by revisiting target selection from 271 Pfam families targeted by the Joint Center for Structural Genomics (JCSG) in PSI-2, and it was estimated that the number of targets entered into the protein-production and crystallization pipeline could have been reduced by 30% without lowering the number of families for which the first structures were solved. The prediction improvement depends on the subset of targets used as a testing set and reaches 100% (i.e. twofold) for the top class of predicted targets.

SCMCRYS: predicting protein crystallization using an ensemble scoring card method with estimating propensity scores of P-collocated amino acid pairs

Existing methods for predicting protein crystallization obtain high accuracy using various types of complemented features and complex ensemble classifiers, such as support vector machine (SVM) and Random Forest classifiers. It is desirable to develop a simple and easily interpretable prediction method with informative sequence features to provide insights into protein crystallization. This study proposes an ensemble method, SCMCRYS, to predict protein crystallization, for which each classifier is built by using a scoring card method (SCM) with estimating propensity scores of p-collocated amino acid (AA) pairs (p = 0 for a dipeptide). The SCM classifier determines the crystallization of a sequence according to a weighted-sum score. The weights are the composition of the p-collocated AA pairs, and the propensity scores of these AA pairs are estimated using a statistic with optimization approach. SCMCRYS predicts the crystallization using a simple voting method from a number of SCM classifiers. The experimental results show that the single SCM classifier utilizing dipeptide composition with accuracy of 73.90% is comparable to the best previously-developed SVM-based classifier, SVM_POLY (74.6%), and our proposed SVM-based classifier utilizing the same dipeptide composition (77.55%). The SCMCRYS method with accuracy of 76.1% is comparable to the state-of-the-art ensemble methods PPCpred (76.8%) and RFCRYS (80.0%), which used the SVM and Random Forest classifiers, respectively. This study also investigates mutagenesis analysis based on SCM and the result reveals the hypothesis that the mutagenesis of surface residues Ala and Cys has large and small probabilities of enhancing protein crystallizability considering the estimated scores of crystallizability and solubility, melting point, molecular weight and conformational entropy of amino acids in a generalized condition. The propensity scores of amino acids and dipeptides for estimating the protein crystallizability can aid biologists in designing mutation of surface residues to enhance protein crystallizability. The source code of SCMCRYS is available at http://iclab.life.nctu.edu.tw/SCMCRYS/.