Logistic regression models to predict solvent accessible residues using sequence- and homology-based qualitative and quantitative descriptors applied to a domain-complete X-ray structure learning set

A working example of relative solvent accessibility (RSA) prediction for proteins is presented. Novel logistic regression models with various qualitative descriptors that include amino acid type and quantitative descriptors that include 20- and six-term sequence entropy have been built and validated. A domain-complete learning set of over 1300 proteins is used to fit initial models with various sequence homology descriptors as well as query residue qualitative descriptors. Homology descriptors are derived from BLASTp sequence alignments, whereas the RSA values are determined directly from the crystal structure. The logistic regression models are fitted using dichotomous responses indicating buried or accessible solvent, with binary classifications obtained from the RSA values. The fitted models determine binary predictions of residue solvent accessibility with accuracies comparable to other less computationally intensive methods using the standard RSA threshold criteria 20 and 25% as solvent accessible. When an additional non-homology descriptor describing Lobanov-Galzitskaya residue disorder propensity is included, incremental improvements in accuracy are achieved with 25% threshold accuracies of 76.12 and 74.79% for the Manesh-215 and CASP(8+9) test sets, respectively. Moreover, the described software and the accompanying learning and validation sets allow students and researchers to explore the utility of RSA prediction with simple, physically intuitive models in any number of related applications.

Bayesian model of protein primary sequence for secondary structure prediction

Determining the primary structure (i.e., amino acid sequence) of a protein has become cheaper, faster, and more accurate. Higher order protein structure provides insight into a protein's function in the cell. Understanding a protein's secondary structure is a first step towards this goal. Therefore, a number of computational prediction methods have been developed to predict secondary structure from just the primary amino acid sequence. The most successful methods use machine learning approaches that are quite accurate, but do not directly incorporate structural information. As a step towards improving secondary structure reduction given the primary structure, we propose a Bayesian model based on the knob-socket model of protein packing in secondary structure. The method considers the packing influence of residues on the secondary structure determination, including those packed close in space but distant in sequence. By performing an assessment of our method on 2 test sets we show how incorporation of multiple sequence alignment data, similarly to PSIPRED, provides balance and improves the accuracy of the predictions. Software implementing the methods is provided as a web application and a stand-alone implementation.

Generating thermal stable variants of protein domains through phage display

Often in protein design research, one desires to generate thermally stable variants of a protein or domain. One route to identifying mutations that yield domains that remain folded and active at a higher temperature is through the use of directed evolution. A library of protein domain variants can be generated by mutagenic PCR, expressed on the surface of bacteriophage M13, and subjected to heat, such that the unfolded forms of the domain, showing reduced or no binding activity, are lost during subsequent affinity selection, whereas variants that still retain binding to their target are selected and enriched with each subsequent round of affinity selection. This approach takes advantage of the fact that bacteriophage M13 particles are heat stable and resistant to many proteases and protein denaturants. We present the application of this general approach to generating thermally stable variants of a eukaryotic peptide-binding domain. The benefits of producing such variants are that they typically express at high levels in Escherichia coli (30-60 mg/L shake flask) and remain soluble in solution at higher concentrations for longer periods of time than the wild-type form of the domain. The process of library generation and screening generally requires about one month of effort, and yields variants with >10 °C increase in thermal stability, as measured in a simple fluorescence-based thermal shift assay. It is anticipated that thermally stable variants will serve as excellent scaffolds for generating affinity reagents to a variety of targets of interest.