Predrag Radivojac

Automated inference of molecular mechanisms of disease from amino acid substitutions

MOTIVATION Advances in high-throughput genotyping and next generation sequencing have generated a vast amount of human genetic variation data. Single nucleotide substitutions within protein coding regions are of particular importance owing to their potential to give rise to amino acid substitutions that affect protein structure and function which may ultimately lead to a disease state. Over the last decade, a number of computational methods have been developed to predict whether such amino acid substitutions result in an altered phenotype. Although these methods are useful in practice, and accurate for their intended purpose, they are not well suited for providing probabilistic estimates of the underlying disease mechanism. RESULTS We have developed a new computational model, MutPred, that is based upon protein sequence, and which models changes of structural features and functional sites between wild-type and mutant sequences. These changes, expressed as probabilities of gain or loss of structure and function, can provide insight into the specific molecular mechanism responsible for the disease state. MutPred also builds on the established SIFT method but offers improved classification accuracy with respect to human disease mutations. Given conservative thresholds on the predicted disruption of molecular function, we propose that MutPred can generate accurate and reliable hypotheses on the molecular basis of disease for approximately 11% of known inherited disease-causing mutations. We also note that the proportion of changes of functionally relevant residues in the sets of cancer-associated somatic mutations is higher than for the inherited lesions in the Human Gene Mutation Database which are instead predicted to be characterized by disruptions of protein structure. AVAILABILITY http://mutdb.org/mutpred CONTACT predrag@indiana.edu; smooney@buckinstitute.org.

Length-dependent prediction of protein intrinsic disorder

BackgroundDue to the functional importance of intrinsically disordered proteins or protein regions, prediction of intrinsic protein disorder from amino acid sequence has become an area of active research as witnessed in the 6th experiment on Critical Assessment of Techniques for Protein Structure Prediction (CASP6). Since the initial work by Romero et al. (Identifying disordered regions in proteins from amino acid sequences, IEEE Int. Conf. Neural Netw., 1997), our group has developed several predictors optimized for long disordered regions (>30 residues) with prediction accuracy exceeding 85%. However, these predictors are less successful on short disordered regions (≤30 residues). A probable cause is a length-dependent amino acid compositions and sequence properties of disordered regions.ResultsWe proposed two new predictor models, VSL2-M1 and VSL2-M2, to address this length-dependency problem in prediction of intrinsic protein disorder. These two predictors are similar to the original VSL1 predictor used in the CASP6 experiment. In both models, two specialized predictors were first built and optimized for short (≤30 residues) and long disordered regions (>30 residues), respectively. A meta predictor was then trained to integrate the specialized predictors into the final predictor model. As the 10-fold cross-validation results showed, the VSL2 predictors achieved well-balanced prediction accuracies of 81% on both short and long disordered regions. Comparisons over the VSL2 training dataset via 10-fold cross-validation and a blind-test set of unrelated recent PDB chains indicated that VSL2 predictors were significantly more accurate than several existing predictors of intrinsic protein disorder.ConclusionThe VSL2 predictors are applicable to disordered regions of any length and can accurately identify the short disordered regions that are often misclassified by our previous disorder predictors. The success of the VSL2 predictors further confirmed the previously observed differences in amino acid compositions and sequence properties between short and long disordered regions, and justified our approaches for modelling short and long disordered regions separately. The VSL2 predictors are freely accessible for non-commercial use at http://www.ist.temple.edu/disprot/predictorVSL2.php

Intrinsic disorder is a common feature of hub proteins from four eukaryotic interactomes.

Recent proteome-wide screening approaches have provided a wealth of information about interacting proteins in various organisms. To test for a potential association between protein connectivity and the amount of predicted structural disorder, the disorder propensities of proteins with various numbers of interacting partners from four eukaryotic organisms (Caenorhabditis elegans, Saccharomyces cerevisiae, Drosophila melanogaster, and Homo sapiens) were investigated. The results of PONDR VL-XT disorder analysis show that for all four studied organisms, hub proteins, defined here as those that interact with ≥10 partners, are significantly more disordered than end proteins, defined here as those that interact with just one partner. The proportion of predicted disordered residues, the average disorder score, and the number of predicted disordered regions of various lengths were higher overall in hubs than in ends. A binary classification of hubs and ends into ordered and disordered subclasses using the consensus prediction method showed a significant enrichment of wholly disordered proteins and a significant depletion of wholly ordered proteins in hubs relative to ends in worm, fly, and human. The functional annotation of yeast hubs and ends using GO categories and the correlation of these annotations with disorder predictions demonstrate that proteins with regulation, transcription, and development annotations are enriched in disorder, whereas proteins with catalytic activity, transport, and membrane localization annotations are depleted in disorder. The results of this study demonstrate that intrinsic structural disorder is a distinctive and common characteristic of eukaryotic hub proteins, and that disorder may serve as a determinant of protein interactivity.

Exploiting heterogeneous sequence properties improves prediction of protein disorder

During the past few years we have investigated methods to improve predictors of intrinsically disordered regions longer than 30 consecutive residues. Experimental evidence, however, showed that these predictors were less successful on short disordered regions, as observed two years ago during the fifth Critical Assessment of Techniques for Protein Structure Prediction (CASP5). To address this shortcoming, we developed a two‐level model called VSL1 (CASP6 id: 193‐1). At the first level, VSL1 consists of two specialized predictors, one of which was optimized for long disordered regions (>30 residues) and the other for short disordered regions (≤30 residues). At the second level, a meta‐predictor was built to assign weights for combining the two first‐level predictors. As the results of the CASP6 experiment showed, this new predictor has achieved the highest accuracy yet and significantly improved performance on short disordered regions, while maintaining high performance on long disordered regions. Proteins 2005;Suppl 7:176–182.

Predicting intrinsic disorder from amino acid sequence

Blind predictions of intrinsic order and disorder were made on 42 proteins subsequently revealed to contain 9,044 ordered residues, 284 disordered residues in 26 segments of length 30 residues or less, and 281 disordered residues in 2 disordered segments of length greater than 30 residues. The accuracies of the six predictors used in this experiment ranged from 77% to 91% for the ordered regions and from 56% to 78% for the disordered segments. The average of the order and disorder predictions ranged from 73% to 77%. The prediction of disorder in the shorter segments was poor, from 25% to 66% correct, while the prediction of disorder in the longer segments was better, from 75% to 95% correct. Four of the predictors were composed of ensembles of neural networks. This enabled them to deal more efficiently with the large asymmetry in the training data through diversified sampling from the significantly larger ordered set and achieve better accuracy on ordered and long disordered regions. The exclusive use of long disordered regions for predictor training likely contributed to the disparity of the predictions on long versus short disordered regions, while averaging the output values over 61‐residue windows to eliminate short predictions of order or disorder probably contributed to the even greater disparity for three of the predictors. This experiment supports the predictability of intrinsic disorder from amino acid sequence. Proteins 2003;53:566–572.

Identification, analysis, and prediction of protein ubiquitination sites

Ubiquitination plays an important role in many cellular processes and is implicated in many diseases. Experimental identification of ubiquitination sites is challenging due to rapid turnover of ubiquitinated proteins and the large size of the ubiquitin modifier. We identified 141 new ubiquitination sites using a combination of liquid chromatography, mass spectrometry, and mutant yeast strains. Investigation of the sequence biases and structural preferences around known ubiquitination sites indicated that their properties were similar to those of intrinsically disordered protein regions. Using a combined set of new and previously known ubiquitination sites, we developed a random forest predictor of ubiquitination sites, UbPred. The class‐balanced accuracy of UbPred reached 72%, with the area under the ROC curve at 80%. The application of UbPred showed that high confidence Rsp5 ubiquitin ligase substrates and proteins with very short half‐lives were significantly enriched in the number of predicted ubiquitination sites. Proteome‐wide prediction of ubiquitination sites in Saccharomyces cerevisiae indicated that highly ubiquitinated substrates were prevalent among transcription/enzyme regulators and proteins involved in cell cycle control. In the human proteome, cytoskeletal, cell cycle, regulatory, and cancer‐associated proteins display higher extent of ubiquitination than proteins from other functional categories. We show that gain and loss of predicted ubiquitination sites may likely represent a molecular mechanism behind a number of disease‐associatedmutations. UbPred is available at http://www.ubpred.org. Proteins 2010.

OPTIMIZING LONG INTRINSIC DISORDER PREDICTORS WITH PROTEIN EVOLUTIONARY INFORMATION

Protein existing as an ensemble of structures, called intrinsically disordered, has been shown to be responsible for a wide variety of biological functions and to be common in nature. Here we focus on improving sequence-based predictions of long (>30 amino acid residues) regions lacking specific 3-D structure by means of four new neural-network-based Predictors Of Natural Disordered Regions (PONDRs): VL3, VL3H, VL3P, and VL3E. PONDR VL3 used several features from a previously introduced PONDR VL2, but benefitted from optimized predictor models and a slightly larger (152 vs. 145) set of disordered proteins that were cleaned of mislabeling errors found in the smaller set. PONDR VL3H utilized homologues of the disordered proteins in the training stage, while PONDR VL3P used attributes derived from sequence profiles obtained by PSI-BLAST searches. The measure of accuracy was the average between accuracies on disordered and ordered protein regions. By this measure, the 30-fold cross-validation accuracies of VL3, VL3H, and VL3P were, respectively, 83.6 +/- 1.4%, 85.3 +/- 1.4%, and 85.2 +/- 1.5%. By combining VL3H and VL3P, the resulting PONDR VL3E achieved an accuracy of 86.7 +/- 1.4%. This is a significant improvement over our previous PONDRs VLXT (71.6 +/- 1.3%) and VL2 (80.9 +/- 1.4%). The new disorder predictors with the corresponding datasets are freely accessible through the web server at http://www.ist.temple.edu/disprot.

Protein flexibility and intrinsic disorder

Comparisons were made among four categories of protein flexibility: (1) low‐B‐factor ordered regions, (2) high‐B‐factor ordered regions, (3) short disordered regions, and (4) long disordered regions. Amino acid compositions of the four categories were found to be significantly different from each other, with high‐B‐factor ordered and short disordered regions being the most similar pair. The high‐B‐factor (flexible) ordered regions are characterized by a higher average flexibility index, higher average hydrophilicity, higher average absolute net charge, and higher total charge than disordered regions. The low‐B‐factor regions are significantly enriched in hydrophobic residues and depleted in the total number of charged residues compared to the other three categories. We examined the predictability of the high‐B‐factor regions and developed a predictor that discriminates between regions of low and high B‐factors. This predictor achieved an accuracy of 70% and a correlation of 0.43 with experimental data, outperforming the 64% accuracy and 0.32 correlation of predictors based solely on flexibility indices. To further clarify the differences between short disordered regions and ordered regions, a predictor of short disordered regions was developed. Its relatively high accuracy of 81% indicates considerable differences between ordered and disordered regions. The distinctive amino acid biases of high‐B‐factor ordered regions, short disordered regions, and long disordered regions indicate that the sequence determinants for these flexibility categories differ from one another, whereas the significantly‐greater‐than‐chance predictability of these categories from sequence suggest that flexible ordered regions, short disorder, and long disorder are, to a significant degree, encoded at the primary structure level.

Two Sample Logo: a graphical representation of the differences between two sets of sequence alignments

SUMMARY Two Sample Logo is a web-based tool that detects and displays statistically significant differences in position-specific symbol compositions between two sets of multiple sequence alignments. In a typical scenario, two groups of aligned sequences will share a common motif but will differ in their functional annotation. The inclusion of the background alignment provides an appropriate underlying amino acid or nucleotide distribution and addresses intersite symbol correlations. In addition, the difference detection process is sensitive to the sizes of the aligned groups. Two Sample Logo extends WebLogo, a widely-used sequence logo generator. The source code is distributed under the MIT Open Source license agreement and is available for download free of charge.

An integrated approach to inferring gene-disease associations in humans.

One of the most important tasks of modern bioinformatics is the development of computational tools that can be used to understand and treat human disease. To date, a variety of methods have been explored and algorithms for candidate gene prioritization are gaining in their usefulness. Here, we propose an algorithm for detecting gene–disease associations based on the human protein–protein interaction network, known gene–disease associations, protein sequence, and protein functional information at the molecular level. Our method, PhenoPred, is supervised: first, we mapped each gene/protein onto the spaces of disease and functional terms based on distance to all annotated proteins in the protein interaction network. We also encoded sequence, function, physicochemical, and predicted structural properties, such as secondary structure and flexibility. We then trained support vector machines to detect gene–disease associations for a number of terms in Disease Ontology and provided evidence that, despite the noise/incompleteness of experimental data and unfinished ontology of diseases, identification of candidate genes can be successful even when a large number of candidate disease terms are predicted on simultaneously. Availability: www.phenopred.org. Proteins 2008.