POODLE-L: a two-level SVM prediction system for reliably predicting long disordered regions

Predicting disordered regions in proteins using the profiles of amino acid indices

BACKGROUND

Intrinsically unstructured or disordered proteins are common and functionally important. Prediction of disordered regions in proteins can provide useful information for understanding protein function and for high-throughput determination of protein structures.

RESULTS

In this paper, algorithms are presented to predict long and short disordered regions in proteins, namely the long disordered region prediction algorithm DRaai-L and the short disordered region prediction algorithm DRaai-S. These algorithms are developed based on the Random Forest machine learning model and the profiles of amino acid indices representing various physiochemical and biochemical properties of the 20 amino acids.

CONCLUSION

Experiments on DisProt3.6 and CASP7 demonstrate that some sets of the amino acid indices have strong association with the ordered and disordered status of residues. Our algorithms based on the profiles of these amino acid indices as input features to predict disordered regions in proteins outperform that based on amino acid composition and reduced amino acid composition, and also outperform many existing algorithms. Our studies suggest that the profiles of amino acid indices combined with the Random Forest learning model is an important complementary method for pinpointing disordered regions in proteins.

Large-scale prediction of long disordered regions in proteins using random forests

Background

Many proteins contain disordered regions that lack fixed three-dimensional (3D) structure under physiological conditions but have important biological functions. Prediction of disordered regions in protein sequences is important for understanding protein function and in high-throughput determination of protein structures. Machine learning techniques, including neural networks and support vector machines have been widely used in such predictions. Predictors designed for long disordered regions are usually less successful in predicting short disordered regions. Combining prediction of short and long disordered regions will dramatically increase the complexity of the prediction algorithm and make the predictor unsuitable for large-scale applications. Efficient batch prediction of long disordered regions alone is of greater interest in large-scale proteome studies.

Results

A new algorithm, IUPforest-L, for predicting long disordered regions using the random forest learning model is proposed in this paper. IUPforest-L is based on the Moreau-Broto auto-correlation function of amino acid indices (AAIs) and other physicochemical features of the primary sequences. In 10-fold cross validation tests, IUPforest-L can achieve an area of 89.5% under the receiver operating characteristic (ROC) curve. Compared with existing disorder predictors, IUPforest-L has high prediction accuracy and is efficient for predicting long disordered regions in large-scale proteomes.

Conclusion

The random forest model based on the auto-correlation functions of the AAIs within a protein fragment and other physicochemical features could effectively detect long disordered regions in proteins. A new predictor, IUPforest-L, was developed to batch predict long disordered regions in proteins, and the server can be accessed from

Optimization of linear disorder predictors yields tight association between crystallographic disorder and hydrophobicity

X-ray crystallographic protein structures often contain disordered regions that are observed as missing electron density. Diffraction data may give little or no direct evidence as to the specific nature of disordered regions. We have developed a weighted window-based disorder predictor optimized using crystallographic data. Performance of a predictor is strongly influenced by chain termini. Optimized score adjustment values for amino- and carboxy-terminal positions demonstrate a simple, monotonic relationship between disorder and residue distance from termini. This optimized disorder predictor performs similarly to DISOPRED2 on crystallographically disordered regions. Data-optimized residue disorder propensities show strong linear correlation with experimentally determined amino acid transfer energies between water and hydrogen-bonding organic solvents, which primarily reflect residue hydrophobicity (exemplified by the Nozaki-Tanford hydrophobicity scale). Disorder propensities do not correlate as well with transfer energies between water and apolar solvents, which primarily reflect a different hydropathic property: residue hydrophilicity (also reflected by the Kyte-Doolittle hydropathy scale). Our results suggest that while hydrophobic side-chain interactions are primarily involved in determining stability of the folded conformation, hydrogen bonding, and similar polar interactions are primarily involved in conformational and interaction specificity.