Better prediction of protein contact number using a support vector regression analysis of amino acid sequence

Background: Protein tertiary structure can be partly characterized via each amino acid's contact number measuring how residues are spatially arranged. The contact number of a residue in a folded protein is a measure of its exposure to the local environment, and is defined as the number of C-beta atoms in other residues within a sphere around the C-beta atom of the residue of interest. Contact number is partly conserved between protein folds and thus is useful for protein fold and structure prediction. In turn, each residue's contact number can be partially predicted from primary amino acid sequence, assisting tertiary fold analysis from sequence data. In this study, we provide a more accurate contact number prediction method from protein primary sequence. Results: We predict contact number from protein sequence using a novel support vector regression algorithm. Using protein local sequences with multiple sequence alignments (PSI-BLAST profiles), we demonstrate a correlation coefficient between predicted and observed contact numbers of 0.70, which outperforms previously achieved accuracies. Including additional information about sequence weight and amino acid composition further improves prediction accuracies significantly with the correlation coefficient reaching 0.73. If residues are classified as being either contacted or non-contacted, the prediction accuracies are all greater than 77%, regardless of the choice of classification thresholds. Conclusion: The successful application of support vector regression to the prediction of protein contact number reported here, together with previous applications of this approach to the prediction of protein accessible surface area and B-factor profile, suggests that a support vector regression approach may be very useful for determining the structure-function relation between primary sequence and higher order consecutive protein structural and functional properties.

Prediction of protein B-factor profiles

The polypeptide backbones and side chains of proteins are constantly moving due to thermal motion and the kinetic energy of the atoms. The B-factors of protein crystal structures reflect the fluctuation of atoms about their average positions and provide important information about protein dynamics. Computational approaches to predict thermal motion are useful for analyzing the dynamic properties of proteins with unknown structures. In this article, we utilize a novel support vector regression (SVR) approach to predict the B-factor distribution (B-factor profile) of a protein from its sequence. We explore schemes for encoding sequences and various settings for the parameters used in SVR. Based on a large dataset of high-resolution proteins, our method predicts the B-factor distribution with a Pearson correlation coefficient (CC) of 0.53. In addition, our method predicts the B-factor profile with a CC of at least 0.56 for more than half of the proteins. Our method also performs well for classifying residues (rigid vs. flexible). For almost all predicted B-factor thresholds, prediction accuracies (percent of correctly predicted residues) are greater than 70%. These results exceed the best results of other sequence-based prediction methods. (C) 2005 Wiley-Liss, Inc.

Effect of disrupted SOX18 transcription factor function on tumor growth, vascularization, and endothelial development

Background. The growth of solid tumors depends on establishing blood supply; thus, inhibiting tumor angiogenesis has been a long-term goal in cancer therapy. The SOX18 transcription factor is a key regulator of murine and human blood vessel formation. Methods: We established allograft melanoma tumors in wild-type mice, Sox18-null mice, and mice expressing a dominant-negative form of Sox18 (Sox18RaOp) (n = 4 per group) and measured tumor growth and microvessel density by immunohistochemical analysis with antibodies to the endothelial marker CD31 and the pericyte marker NG2. We also assessed the affects of disrupted SOX18 function on MCF-7 human breast cancer and human umbilical vein endothelial cell (HUVEC) proliferation by measuring BrdU incorporation and by MTS assay, cell migration using Boyden chamber assay, and capillary tube formation in vitro. All statistical tests were two-sided. Results: Allograft tumors in Sox18-null and Sox18RaOp mice grew more slowly than those in wild-type mice (tumor volume at day 14, Sox18 null, mean = 486 mm(3), 95% confidence interval [CI] = 345 mm(3) to 627 mm(3), p = .004; Sox18RaOp, mean = 233 mm(3), 95% CI = 73 mm(3) to 119 mm(3), p < .001; versus wild-type, mean = 817 mm(3), 95% CI = 643 mm(3) to 1001 mm(3)) and had fewer CD31- and NG2-expressing vessels. Expression of dominant-negative Sox18 reduced the proliferation of MCF-7 cells (BrdU incorporation: MCF-7(Ra) = 20%, 95% CI = 15% to 25% versus MCF-7 = 41%, 95% CI = 35% to 45%; P = .013) and HUVECs (optical density at 490 nm, empty vector, mean = 0.46 versus SOX18 mean = 0.29; difference = 0.17, 95% CI = 0.14 to 0.19; P = .001) compared with control subjects. Overexpression of wild-type SOX18 promoted capillary tube formation of HUVECs in vitro, whereas expression of dominant-negative SOX18 impaired tube formation of HUVECs and the migration of MCF-7 cells via the disruption of the actin cytoskeleton. Conclusions: SOX18 is a potential target for antiangiogenic therapy of human cancers.

Predicting residue-wise contact orders in proteins by support vector regression

Background: The residue-wise contact order (RWCO) describes the sequence separations between the residues of interest and its contacting residues in a protein sequence. It is a new kind of one-dimensional protein structure that represents the extent of long-range contacts and is considered as a generalization of contact order. Together with secondary structure, accessible surface area, the B factor, and contact number, RWCO provides comprehensive and indispensable important information to reconstructing the protein three-dimensional structure from a set of one-dimensional structural properties. Accurately predicting RWCO values could have many important applications in protein three-dimensional structure prediction and protein folding rate prediction, and give deep insights into protein sequence-structure relationships. Results: We developed a novel approach to predict residue-wise contact order values in proteins based on support vector regression (SVR), starting from primary amino acid sequences. We explored seven different sequence encoding schemes to examine their effects on the prediction performance, including local sequence in the form of PSI-BLAST profiles, local sequence plus amino acid composition, local sequence plus molecular weight, local sequence plus secondary structure predicted by PSIPRED, local sequence plus molecular weight and amino acid composition, local sequence plus molecular weight and predicted secondary structure, and local sequence plus molecular weight, amino acid composition and predicted secondary structure. When using local sequences with multiple sequence alignments in the form of PSI-BLAST profiles, we could predict the RWCO distribution with a Pearson correlation coefficient (CC) between the predicted and observed RWCO values of 0.55, and root mean square error (RMSE) of 0.82, based on a well-defined dataset with 680 protein sequences. Moreover, by incorporating global features such as molecular weight and amino acid composition we could further improve the prediction performance with the CC to 0.57 and an RMSE of 0.79. In addition, combining the predicted secondary structure by PSIPRED was found to significantly improve the prediction performance and could yield the best prediction accuracy with a CC of 0.60 and RMSE of 0.78, which provided at least comparable performance compared with the other existing methods. Conclusion: The SVR method shows a prediction performance competitive with or at least comparable to the previously developed linear regression-based methods for predicting RWCO values. In contrast to support vector classification (SVC), SVR is very good at estimating the raw value profiles of the samples. The successful application of the SVR approach in this study reinforces the fact that support vector regression is a powerful tool in extracting the protein sequence-structure relationship and in estimating the protein structural profiles from amino acid sequences.