RESUMEN
In a protein, interactions exist between amino acid residues that influence the protein's structural integrity or stability and thus affect its catalytic function. The loss of this interaction due to mutations in these amino acids usually leads to a non-functional protein. Probing the sequence space of a protein through mutations or recombinations, as performed in directed evolution to search for an improved variant, frequently results in such inactive sequences. In this work, we demonstrate the use of machine learning to identify such interacting residues and the use of template engineering strategies to increase the fraction of active variants in a library. We show that using the sequences from recombination of monomeric red fluorescent protein (mRFP) and Discosoma red fluorescent protein (DsRed), we were able to identify a pair of interacting residues using an algorithm based on Boolean Learning and Support Vector Machines. The interaction between the identified residues was verified through point mutations on the mRFP and DsRed genes. We also show that it is possible to use such results to alter the parental genes such that the probability of disrupting the important interactions is minimized. This will result in a larger fraction of active variants in the recombinant library and allow us to access more functional space. We demonstrate this effect by comparing the recombinant library of wild-type (WT) DsRed, mRFP and an altered sequence of DsRed with mRFP WT genes.
Asunto(s)
Algoritmos , Inteligencia Artificial , Proteínas Luminiscentes/química , Modelos Químicos , Secuencia de Aminoácidos , Sitios de Unión , Simulación por Computador , Datos de Secuencia Molecular , Unión Proteica , Análisis de Secuencia de Proteína , Proteína Fluorescente RojaRESUMEN
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.
Asunto(s)
Algoritmos , Inteligencia Artificial , Simulación por Computador , Proteínas/química , Sitios de Unión/fisiología , Biología ComputacionalRESUMEN
Pooling in directed-evolution experiments will greatly increase the throughput of screening systems, but important parameters such as the number of good mutants created and the activity level increase of the good mutants will depend highly on the protein being engineered. The authors developed and validated a Monte Carlo simulation model of pooling that allows the testing of various scenarios in silico before starting experimentation. Using a simplified test system of 2 enzymes, betagalactosidase (supermutant, or greatly improved enzyme) and beta-glucuronidase (dud, or enzyme with ancestral level of activity), the model accurately predicted the number of supermutants detected in experiments within a factor of 2. Additional simulations using more complex activity distributions show the versatility of the model. Pooling is most suited to cases such as the directed evolution of new function in a protein, where the background level of activity is minimized, making it easier to detect small increases in activity level. Pooling is most successful when a sensitive assay is employed. Using the model will increase the throughput of screening procedures for directed-evolution experiments and thus lead to speedier engineering of proteins.
Asunto(s)
Simulación por Computador , Evolución Molecular Dirigida , Evaluación Preclínica de Medicamentos/métodos , Método de Montecarlo , Ingeniería de Proteínas , Células Cultivadas , Modelos Biológicos , Programas Informáticos , Análisis de Matrices TisularesRESUMEN
A method for identifying the positions in the amino acid sequence, which are critical for the catalytic activity of a protein using support vector machines (SVMs) is introduced and analysed. SVMs are supported by an efficient learning algorithm and can utilize some prior knowledge about the structure of the problem. The amino acid sequences of the variants of a protein, created by inducing mutations, along with their fitness are required as input data by the method to predict its critical positions. To investigate the performance of this algorithm, variants of the beta-lactamase enzyme were created in silico using simulations of both mutagenesis and recombination protocols. Results from literature on beta-lactamase were used to test the accuracy of this method. It was also compared with the results from a simple search algorithm. The algorithm was also shown to be able to predict critical positions that can tolerate two different amino acids and retain function.