Support vector machines for learning to identify the critical positions of a protein

Prediction of parathyroid hormone signalling potency using SVMs

Parathyroid hormone is the most important endocrine regulator of calcium concentration. Its N-terminal fragment (1-34) has sufficient activity for biological function. Recently, site-directed mutagenesis studies demonstrated that substitutions at several positions within shorter analogues (1-14) can enhance the bioactivity to greater than that of PTH (1-34). However, designing the optimal sequence combination is not simple due to complex combinatorial problems. In this study, support vector machines were introduced to predict the biological activity of modified PTH (1-14) analogues using mono-substituted experimental data and to analyze the key physicochemical properties at each position that correlated with bioactivity. This systematic approach can reduce the time and effort needed to obtain desirable molecules by bench experiments and provide useful information in the design of simpler activating molecules.

Better library design: data-driven protein engineering

Data-driven protein engineering is increasingly used as an alternative to rational design and combinatorial engineering because it uses available knowledge to limit library size, while still allowing for the identification of unpredictable substitutions that lead to large effects. Recent advances in computational modeling and bioinformatics, as well as an increasing databank of experiments on functional variants, have led to new strategies to choose particular amino acid residues to vary in order to increase the chances of obtaining a variant protein with the desired property. Strategies for limiting diversity at each position, design of small sub-libraries, and the performance of scouting experiments, have also been developed or even automated, further reducing the library size.

Recent progress in engineering alpha/beta hydrolase-fold family members

The members of the alpha/beta hydrolase-fold family represent a functionally versatile group of enzymes with many important applications in biocatalysis. Given the technical significance of alpha/beta hydrolases in processes ranging from the kinetic resolution of enantiomeric precursors for pharmaceutical compounds to bulk products such as laundry detergent, optimizing and tailoring enzymes for these applications presents an ongoing challenge to chemists, biochemists, and engineers alike. A review of the recent literature on alpha/beta hydrolase engineering suggests that the early successes of "random processes" such as directed evolution are now being slowly replaced by more hypothesis-driven, focused library approaches. These developments reflect a better understanding of the enzymes' structure-function relationship and improved computational resources, which allow for more sophisticated search and prediction algorithms, as well as, in a very practical sense, the realization that bigger is not always better.

Exploiting residue-level and profile-level interface propensities for usage in binding sites prediction of proteins

Background

Recognition of binding sites in proteins is a direct computational approach to the characterization of proteins in terms of biological and biochemical function. Residue preferences have been widely used in many studies but the results are often not satisfactory. Although different amino acid compositions among the interaction sites of different complexes have been observed, such differences have not been integrated into the prediction process. Furthermore, the evolution information has not been exploited to achieve a more powerful propensity.

Result

In this study, the residue interface propensities of four kinds of complexes (homo-permanent complexes, homo-transient complexes, hetero-permanent complexes and hetero-transient complexes) are investigated. These propensities, combined with sequence profiles and accessible surface areas, are inputted to the support vector machine for the prediction of protein binding sites. Such propensities are further improved by taking evolutional information into consideration, which results in a class of novel propensities at the profile level, i.e. the binary profiles interface propensities. Experiment is performed on the 1139 non-redundant protein chains. Although different residue interface propensities among different complexes are observed, the improvement of the classifier with residue interface propensities can be negligible in comparison with that without propensities. The binary profile interface propensities can significantly improve the performance of binding sites prediction by about ten percent in term of both precision and recall.

Conclusion

Although there are minor differences among the four kinds of complexes, the residue interface propensities cannot provide efficient discrimination for the complicated interfaces of proteins. The binary profile interface propensities can significantly improve the performance of binding sites prediction of protein, which indicates that the propensities at the profile level are more accurate than those at the residue level.

Identifying the interacting positions of a protein using Boolean learning and support vector machines

It is known that in the three-dimensional structure of a protein, certain amino acids can interact with each other in order to provide structural integrity or aid in its catalytic function. If these positions are mutated the loss of this interaction usually leads to a non-functional protein. Directed evolution experiments, which probe the sequence space of a protein through mutations in search for an improved variant, frequently result in such inactive sequences. In this work, we address the use of machine learning algorithms, Boolean learning and support vector machines (SVMs), to find such pairs of amino acid positions. The recombination method of imparting mutations was simulated to create in silico sequences that were used as training data for the algorithms. The two algorithms were combined together to develop an approach that weighs the structural risk as well as the empirical risk to solve the problem. This strategy was adapted to a multi-round framework of experiments where the data generated in the present round is used to design experiments for the next round to improve the generated library, as well as the estimation of the interacting positions. It is observed that this strategy can greatly improve the number of functional variants that are generated as well as the average number of mutations that can be made in the library.