Knowledge acquisition and development of accurate rules for predicting protein stability changes

Convolution Neural Network-Based Prediction of Protein Thermostability

Most natural proteins exhibit poor thermostability, which limits their industrial application. Computer-aided rational design is an efficient purpose-oriented method that can improve protein thermostability. Numerous machine-learning-based methods have been designed to predict the changes in protein thermostability induced by mutations. However, all of these methods have certain limitations due to existing mutation coding methods that overlook protein sequence features. Here we propose a method to predict protein thermostability using convolutional neural networks based on an in-depth study of thermostability-related protein properties. This method comprises a three-dimensional coding algorithm, including protein mutation information and a strategy to extract neighboring features at protein mutation sites based on multiscale convolution. The accuracies on the S1615 and S388 data sets, which are widely used for protein thermostability predictions, reached 86.4 and 87%, respectively. The Matthews correlation coefficient was nearly double those produced using other methods. Furthermore, a model was constructed to predict the thermostability of Rhizomucor miehei lipase mutants based on the S3661 data set, a single amino acid mutation data set screened from the ProTherm protein thermodynamics database. Compared with the RIF strategy, which consists of three algorithms, i.e., Rosetta ddg monomer, I Mutant 3.0, and FoldX, the accuracy of the proposed method was higher (75.0 vs 66.7%), and the negative sample resolution was simultaneously enhanced. These results indicate that our prediction method more effectively assessed the protein thermostability and distinguished its features, making it a powerful tool to devise mutations that enhance the thermostability of proteins, particularly enzymes.

Understanding the undelaying mechanism of HA-subtyping in the level of physic-chemical characteristics of protein

The evolution of the influenza A virus to increase its host range is a major concern worldwide. Molecular mechanisms of increasing host range are largely unknown. Influenza surface proteins play determining roles in reorganization of host-sialic acid receptors and host range. In an attempt to uncover the physic-chemical attributes which govern HA subtyping, we performed a large scale functional analysis of over 7000 sequences of 16 different HA subtypes. Large number (896) of physic-chemical protein characteristics were calculated for each HA sequence. Then, 10 different attribute weighting algorithms were used to find the key characteristics distinguishing HA subtypes. Furthermore, to discover machine leaning models which can predict HA subtypes, various Decision Tree, Support Vector Machine, Naïve Bayes, and Neural Network models were trained on calculated protein characteristics dataset as well as 10 trimmed datasets generated by attribute weighting algorithms. The prediction accuracies of the machine learning methods were evaluated by 10-fold cross validation. The results highlighted the frequency of Gln (selected by 80% of attribute weighting algorithms), percentage/frequency of Tyr, percentage of Cys, and frequencies of Try and Glu (selected by 70% of attribute weighting algorithms) as the key features that are associated with HA subtyping. Random Forest tree induction algorithm and RBF kernel function of SVM (scaled by grid search) showed high accuracy of 98% in clustering and predicting HA subtypes based on protein attributes. Decision tree models were successful in monitoring the short mutation/reassortment paths by which influenza virus can gain the key protein structure of another HA subtype and increase its host range in a short period of time with less energy consumption. Extracting and mining a large number of amino acid attributes of HA subtypes of influenza A virus through supervised algorithms represent a new avenue for understanding and predicting possible future structure of influenza pandemics.

Sequence-only evolutionary and predicted structural features for the prediction of stability changes in protein mutants

Background

Even a single amino acid substitution in a protein sequence may result in significant changes in protein stability, structure, and therefore in protein function as well. In the post-genomic era, computational methods for predicting stability changes from only the sequence of a protein are of importance. While evolutionary relationships of protein mutations can be extracted from large protein databases holding millions of protein sequences, relevant evolutionary features for the prediction of stability changes have not been proposed. Also, the use of predicted structural features in situations when a protein structure is not available has not been explored.

Results

We proposed a number of evolutionary and predicted structural features for the prediction of stability changes and analysed which of them capture the determinants of protein stability the best. We trained and evaluated our machine learning method on a non-redundant data set of experimentally measured stability changes. When only the direction of the stability change was predicted, we found that the best performance improvement can be achieved by the combination of the evolutionary features mutation likelihood and SIFTscore in conjunction with the predicted structural feature secondary structure. The same two evolutionary features in the combination with the predicted structural feature accessible surface area achieved the lowest error when the prediction of actual values of stability changes was assessed. Compared to similar studies, our method achieved improvements in prediction performance.

Conclusion

Although the strongest feature for the prediction of stability changes appears to be the vector of amino acid identities in the sequential neighbourhood of the mutation, the most relevant combination of evolutionary and predicted structural features further improves prediction performance. Even the predicted structural features, which did not perform well on their own, turn out to be beneficial when appropriately combined with evolutionary features. We conclude that a high prediction accuracy can be achieved knowing only the sequence of a protein when the right combination of both structural and evolutionary features is used.

Grading amino acid properties increased accuracies of single point mutation on protein stability prediction

Background

Protein stabilities can be affected sometimes by point mutations introduced to the protein. Current sequence-information-based protein stability prediction encoding schemes of machine learning approaches include sparse encoding and amino acid property encoding. Property encoding schemes employ physical-chemical information of the mutated protein environments, however, they produce complexity in the mean time when many properties joined in the scheme. The complexity introduces noises that affect machine learning algorithm accuracies. In order to overcome the problem we described a new encoding scheme that graded twenty amino acids into groups according to their specific property values.

Results

We employed three predefined values, 0.1, 0.5, and 0.9 to represent 'weak', 'middle', and 'strong' groups for each amino acid property, and introduced two thresholds for each property to split twenty amino acids into one of the three groups according to their property values. Each amino acid can take only one out of three predefined values rather than twenty different values for each property. The complexity and noises in the encoding schemes were reduced in this way. More than 7% average accuracy improvement was found in the graded amino acid property encoding schemes by 20-fold cross validation. The overall accuracy of our method is more than 72% when performed on the independent test sets starting from sequence information with three-state prediction definitions.

Conclusions

Grading numeric values of amino acid property can reduce the noises and complexity of input information. It is in accordance with biochemical concepts for amino acid properties and makes the input data simplified in the mean time. The idea of graded property encoding schemes may be applied to protein related predictions with machine learning approaches.

Toward better understanding of protein secondary structure: extracting prediction rules

Although numerous computational techniques have been applied to predict protein secondary structure (PSS), only limited studies have dealt with discovery of logic rules underlying the prediction itself. Such rules offer interesting links between the prediction model and the underlying biology. In addition, they enhance interpretability of PSS prediction by providing a degree of transparency to the predicting model usually regarded as a black box. In this paper, we explore the generation and use of C4.5 decision trees to extract relevant rules from PSS predictions modeled with two-stage support vector machines (TS-SVM). The proposed rules were derived on the RS126 data set of 126 nonhomologous globular proteins and on the PSIPRED data set of 1,923 protein sequences. Our approach has produced sets of comprehensible, and often interpretable, rules underlying the PSS predictions. Moreover, many of the rules seem to be strongly supported by biological evidence. Further, our approach resulted in good prediction accuracy, few and usually compact rules, and rules that are generally of higher confidence levels than those generated by other rule extraction techniques.

Machine learning integration for predicting the effect of single amino acid substitutions on protein stability

BACKGROUND

Computational prediction of protein stability change due to single-site amino acid substitutions is of interest in protein design and analysis. We consider the following four ways to improve the performance of the currently available predictors: (1) We include additional sequence- and structure-based features, namely, the amino acid substitution likelihoods, the equilibrium fluctuations of the alpha- and beta-carbon atoms, and the packing density. (2) By implementing different machine learning integration approaches, we combine information from different features or representations. (3) We compare classification vs. regression methods to predict the sign vs. the output of stability change. (4) We allow a reject option for doubtful cases where the risk of misclassification is high.

RESULTS

We investigate three different approaches: early, intermediate and late integration, which respectively combine features, kernels over feature subsets, and decisions. We perform simulations on two data sets: (1) S1615 is used in previous studies, (2) S2783 is the updated version (as of July 2, 2009) extracted also from ProTherm. For S1615 data set, our highest accuracy using both sequence and structure information is 0.842 on cross-validation and 0.904 on testing using early integration. Newly added features, namely, local compositional packing and the mobility extent of the mutated residues, improve accuracy significantly with intermediate integration. For S2783 data set, we also train regression methods to estimate not only the sign but also the amount of stability change and apply risk-based classification to reject when the learner has low confidence and the loss of misclassification is high. The highest accuracy is 0.835 on cross-validation and 0.832 on testing using only sequence information. The percentage of false positives can be decreased to less than 0.005 by rejecting 10 per cent using late integration.

CONCLUSION

We find that in both early and late integration, combining inputs or decisions is useful in increasing accuracy. Intermediate integration allows assessing the contributions of individual features by looking at the assigned weights. Overall accuracy of regression is not better than that of classification but it has less false positives, especially when combined with the reject option. The server for stability prediction for three integration approaches and the data sets are available at http://www.prc.boun.edu.tr/appserv/prc/mlsta.

Reliable prediction of protein thermostability change upon double mutation from amino acid sequence

SUMMARY

The accurate prediction of protein stability change upon mutation is one of the important issues for protein design. In this work, we have focused on the stability change of double mutations and systematically analyzed the wild-type and mutant residues, patterns in amino acid sequence and locations of mutants. Based on the sequence information of wild-type, mutant and three neighboring residues, we have presented a weighted decision table method (WET) for predicting the stability changes of 180 double mutants obtained from thermal (DeltaDeltaG) denaturation. Using 10-fold cross-validation test, our method showed a correlation of 0.75 between experimental and predicted values of stability changes, and an accuracy of 82.2% for discriminating the stabilizing and destabilizing mutants.

An integrated method for cancer classification and rule extraction from microarray data

Different microarray techniques recently have been successfully used to investigate useful information for cancer diagnosis at the gene expression level due to their ability to measure thousands of gene expression levels in a massively parallel way. One important issue is to improve classification performance of microarray data. However, it would be ideal that influential genes and even interpretable rules can be explored at the same time to offer biological insight.

Introducing the concepts of system design in software engineering, this paper has presented an integrated and effective method (named X-AI) for accurate cancer classification and the acquisition of knowledge from DNA microarray data. This method included a feature selector to systematically extract the relative important genes so as to reduce the dimension and retain as much as possible of the class discriminatory information. Next, diagonal quadratic discriminant analysis (DQDA) was combined to classify tumors, and generalized rule induction (GRI) was integrated to establish association rules which can give an understanding of the relationships between cancer classes and related genes.

Two non-redundant datasets of acute leukemia were used to validate the proposed X-AI, showing significantly high accuracy for discriminating different classes. On the other hand, I have presented the abilities of X-AI to extract relevant genes, as well as to develop interpretable rules. Further, a web server has been established for cancer classification and it is freely available at .

Robust prediction of mutation-induced protein stability change by property encoding of amino acids

Current methods of predicting mutation-induced protein stability change are imprecise. Machine learning methods have been introduced for this prediction recently; however, the available experimental data used for training these predictors are biased. Abundant data are available for several frequently occurring amino acid substitutions, whereas only limited data have been accumulated for some other mutation types. Generally, current statistical models do not account for this bias toward the commoner amino acids during the encoding process and are thus less effective in making predictions on less frequently occurring mutations. In this paper, we propose a method based on support vector machines and property encoding of amino acids. The predictor we constructed outperforms other methods on the same data sets and is more robust with poor training data. The prediction accuracy for mutations with no training data exceeded 80%. This advantage is critical for practical application, where the prediction could be applied for any type of mutations. Further analysis demonstrates our model relies on biological significant features to make predictions. To overcome the drawbacks of classifying mutations into 'stabilizing' and 'destabilizing' ones, a three-class classification of mutations was also discussed, where our method obtained an overall accuracy of 79.1%.

Sequence analysis and rule development of predicting protein stability change upon mutation using decision tree model

Understanding the mechanism of the protein stability change is one of the most challenging tasks. Recently, the prediction of protein stability change affected by single point mutations has become an interesting topic in molecular biology. However, it is desirable to further acquire knowledge from large databases to provide new insights into the nature of them. This paper presents an interpretable prediction tree method (named iPTREE-2) that can accurately predict changes of protein stability upon mutations from sequence based information and analyze sequence characteristics from the viewpoint of composition and order. Therefore, iPTREE-2 based on a regression tree algorithm exhibits the ability of finding important factors and developing rules for the purpose of data mining. On a dataset of 1859 different single point mutations from thermodynamic database, ProTherm, iPTREE-2 yields a correlation coefficient of 0.70 between predicted and experimental values. In the task of data mining, detailed analysis of sequences reveals the possibility of the compositional specificity of residues in different ranges of stability change and implies the existence of certain patterns. As building rules, we found that the mutation residues in wild type and in mutant protein play an important role. The present study demonstrates that iPTREE-2 can serve the purpose of predicting protein stability change, especially when one requires more understandable knowledge.