DoBo: Protein domain boundary prediction by integrating evolutionary signals and machine learning

Background  

Accurate identification of protein domain boundaries is useful for protein structure determination and prediction. However, predicting protein domain boundaries from a sequence is still very challenging and largely unsolved.     

ANGLOR: a composite machine-learning algorithm for protein backbone torsion angle prediction

We developed a composite machine-learning based algorithm, called ANGLOR, to predict real-value protein backbone torsion angles from amino acid sequences. The input features of ANGLOR include sequence profiles, predicted secondary structure and solvent accessibility. In a large-scale benchmarking test, the mean absolute error (MAE) of the phi/psi prediction is 28 degrees/46 degrees , which is approximately 10% lower than that generated by software in literature. The prediction is statistically different from a random predictor (or a purely secondary-structure-based predictor) with p-value <1.0 x 10(-300) (or <1.0 x 10(-148)) by Wilcoxon signed rank test. For some residues (ILE, LEU, PRO and VAL) and especially the residues in helix and buried regions, the MAE of phi angles is much smaller (10-20 degrees ) than that in other environments. Thus, although the average accuracy of the ANGLOR prediction is still low, the portion of the accurately predicted dihedral angles may be useful in assisting protein fold recognition and ab initio 3D structure modeling.     

Protein subcellular localization based on PSI-BLAST and machine learning

Subcellular location is an important functional annotation of proteins. An automatic, reliable and efficient prediction system for protein subcellular localization is necessary for large-scale genome analysis. This paper describes a protein subcellular localization method which extracts features from protein profiles rather than from amino acid sequences. The protein profile represents a protein family, discards part of the sequence information that is not conserved throughout the family and therefore is more sensitive than the amino acid sequence. The amino acid compositions of whole profile and the N-terminus of the profile are extracted, respectively, to train and test the probabilistic neural network classifiers. On two benchmark datasets, the overall accuracies of the proposed method reach 89.1% and 68.9%, respectively. The prediction results show that the proposed method perform better than those methods based on amino acid sequences. The prediction results of the proposed method are also compared with Subloc on two redundance-reduced datasets.     

Evaluating machine learning approaches for aiding probe selection for gene-expression arrays

MOTIVATION: Microarrays are a fast and cost-effective method of performing thousands of DNA hybridization experiments simultaneously. DNA probes are typically used to measure the expression level of specific genes. Because probes greatly vary in the quality of their hybridizations, choosing good probes is a difficult task. If one could accurately choose probes that are likely to hybridize well, then fewer probes would be needed to represent each gene in a gene-expression microarray, and, hence, more genes could be placed on an array of a given physical size. Our goal is to empirically evaluate how successfully three standard machine-learning algorithms-na?ve Bayes, decision trees, and artificial neural networks-can be applied to the task of predicting good probes. Fortunately it is relatively easy to get training examples for such a learning task: place various probes on a gene chip, add a sample where the corresponding genes are highly expressed, and then record how well each probe measures the presence of its corresponding gene. With such training examples, it is possible that an accurate predictor of probe quality can be learned. RESULTS: Two of the learning algorithms we investigate-na?ve Bayes and neural networks-learn to predict probe quality surprisingly well. For example, in the top ten predicted probes for a given gene not used for training, on average about five rank in the top 2.5% of that gene's hundreds of possible probes. Decision-tree induction and the simple approach of using predicted melting temperature to rank probes perform significantly worse than these two algorithms. The features we use to represent probes are very easily computed and the time taken to score each candidate probe after training is minor. Training the na?ve Bayes algorithm takes very little time, and while it takes over 10 times as long to train a neural network, that time is still not very substantial (on the order of a few hours on a desktop workstation). We also report the information contained in the features we use to describe the probes. We find the fraction of cytosine in the probe to be the most informative feature. We also find, not surprisingly, that the nucleotides in the middle of the probes sequence are more informative than those at the ends of the sequence.     

An examination of on-line machine learning approaches for pseudo-random generated data

A pseudo-random generator is an algorithm to generate a sequence of objects determined by a truly random seed which is not truly random. It has been widely used in many applications, such as cryptography and simulations. In this article, we examine current popular machine learning algorithms with various on-line algorithms for pseudo-random generated data in order to find out which machine learning approach is more suitable for this kind of data for prediction based on on-line algorithms. To further improve the prediction performance, we propose a novel sample weighted algorithm that takes generalization errors in each iteration into account. We perform intensive evaluation on real Baccarat data generated by Casino machines and random number generated by a popular Java program, which are two typical examples of pseudo-random generated data. The experimental results show that support vector machine and k-nearest neighbors have better performance than others with and without sample weighted algorithm in the evaluation data set.     

Protein backbone chemical shifts predicted from searching a database for torsion angle and sequence homology

Chemical shifts of nuclei in or attached to a protein backbone are exquisitely sensitive to their local environment. A computer program, SPARTA, is described that uses this correlation with local structure to predict protein backbone chemical shifts, given an input three-dimensional structure, by searching a newly generated database for triplets of adjacent residues that provide the best match in phi/psi/chi(1 )torsion angles and sequence similarity to the query triplet of interest. The database contains (15)N, (1)H(N), (1)H(alpha), (13)C(alpha), (13)C(beta) and (13)C' chemical shifts for 200 proteins for which a high resolution X-ray (< or =2.4 A) structure is available. The relative importance of the weighting factors for the phi/psi/chi(1) angles and sequence similarity was optimized empirically. The weighted, average secondary shifts of the central residues in the 20 best-matching triplets, after inclusion of nearest neighbor, ring current, and hydrogen bonding effects, are used to predict chemical shifts for the protein of known structure. Validation shows good agreement between the SPARTA-predicted and experimental shifts, with standard deviations of 2.52, 0.51, 0.27, 0.98, 1.07 and 1.08 ppm for (15)N, (1)H(N), (1)H(alpha), (13)C(alpha), (13)C(beta) and (13)C', respectively, including outliers.     

TANGLE: two-level support vector regression approach for protein backbone torsion angle prediction from primary sequences

Protein backbone torsion angles (Phi) and (Psi) involve two rotation angles rotating around the C(α)-N bond (Phi) and the C(α)-C bond (Psi). Due to the planarity of the linked rigid peptide bonds, these two angles can essentially determine the backbone geometry of proteins. Accordingly, the accurate prediction of protein backbone torsion angle from sequence information can assist the prediction of protein structures. In this study, we develop a new approach called TANGLE (Torsion ANGLE predictor) to predict the protein backbone torsion angles from amino acid sequences. TANGLE uses a two-level support vector regression approach to perform real-value torsion angle prediction using a variety of features derived from amino acid sequences, including the evolutionary profiles in the form of position-specific scoring matrices, predicted secondary structure, solvent accessibility and natively disordered region as well as other global sequence features. When evaluated based on a large benchmark dataset of 1,526 non-homologous proteins, the mean absolute errors (MAEs) of the Phi and Psi angle prediction are 27.8° and 44.6°, respectively, which are 1% and 3% respectively lower than that using one of the state-of-the-art prediction tools ANGLOR. Moreover, the prediction of TANGLE is significantly better than a random predictor that was built on the amino acid-specific basis, with the p-value<1.46e-147 and 7.97e-150, respectively by the Wilcoxon signed rank test. As a complementary approach to the current torsion angle prediction algorithms, TANGLE should prove useful in predicting protein structural properties and assisting protein fold recognition by applying the predicted torsion angles as useful restraints. TANGLE is freely accessible at http://sunflower.kuicr.kyoto-u.ac.jp/~sjn/TANGLE/.     

TargetSpy: a supervised machine learning approach for microRNA target prediction

Background  

Virtually all currently available microRNA target site prediction algorithms require the presence of a (conserved) seed match to the 5' end of the microRNA. Recently however, it has been shown that this requirement might be too stringent, leading to a substantial number of missed target sites.     

Local backbone structure prediction of proteins

A statistical analysis of the PDB structures has led us to define a new set of small 3D structural prototypes called Protein Blocks (PBs). This structural alphabet includes 16 PBs, each one is defined by the (phi, psi) dihedral angles of 5 consecutive residues. The amino acid distributions observed in sequence windows encompassing these PBs are used to predict by a Bayesian approach the local 3D structure of proteins from the sole knowledge of their sequences. LocPred is a software which allows the users to submit a protein sequence and performs a prediction in terms of PBs. The prediction results are given both textually and graphically.     

High-dimensional pharmacogenetic prediction of a continuous trait using machine learning techniques with application to warfarin dose prediction in African Americans

MOTIVATION: With complex traits and diseases having potential genetic contributions of thousands of genetic factors, and with current genotyping arrays consisting of millions of single nucleotide polymorphisms (SNPs), powerful high-dimensional statistical techniques are needed to comprehensively model the genetic variance. Machine learning techniques have many advantages including lack of parametric assumptions, and high power and flexibility. RESULTS: We have applied three machine learning approaches: Random Forest Regression (RFR), Boosted Regression Tree (BRT) and Support Vector Regression (SVR) to the prediction of warfarin maintenance dose in a cohort of African Americans. We have developed a multi-step approach that selects SNPs, builds prediction models with different subsets of selected SNPs along with known associated genetic and environmental variables and tests the discovered models in a cross-validation framework. Preliminary results indicate that our modeling approach gives much higher accuracy than previous models for warfarin dose prediction. A model size of 200 SNPs (in addition to the known genetic and environmental variables) gives the best accuracy. The R(2) between the predicted and actual square root of warfarin dose in this model was on average 66.4% for RFR, 57.8% for SVR and 56.9% for BRT. Thus RFR had the best accuracy, but all three techniques achieved better performance than the current published R(2) of 43% in a sample of mixed ethnicity, and 27% in an African American sample. In summary, machine learning approaches for high-dimensional pharmacogenetic prediction, and for prediction of clinical continuous traits of interest, hold great promise and warrant further research.     

Computational prediction of inter-species relationships through omics data analysis and machine learning

Background

Antibiotic resistance and its rapid dissemination around the world threaten the efficacy of currently-used medical treatments and call for novel, innovative approaches to manage multi-drug resistant infections. Phage therapy, i.e., the use of viruses (phages) to specifically infect and kill bacteria during their life cycle, is one of the most promising alternatives to antibiotics. It is based on the correct matching between a target pathogenic bacteria and the therapeutic phage. Nevertheless, correctly matching them is a major challenge. Currently, there is no systematic method to efficiently predict whether phage-bacterium interactions exist and these pairs must be empirically tested in laboratory. Herein, we present our approach for developing a computational model able to predict whether a given phage-bacterium pair can interact based on their genome.

Results

Based on public data from GenBank and phagesDB.org, we collected more than a thousand positive phage-bacterium interactions with their complete genomes. In addition, we generated putative negative (i.e., non-interacting) pairs. We extracted, from the collected genomes, a set of informative features based on the distribution of predictive protein-protein interactions and on their primary structure (e.g. amino-acid frequency, molecular weight and chemical composition of each protein). With these features, we generated multiple candidate datasets to train our algorithms. On this base, we built predictive models exhibiting predictive performance of around 90% in terms of F1-score, sensitivity, specificity, and accuracy, obtained on the test set with 10-fold cross-validation.

Conclusion

These promising results reinforce the hypothesis that machine learning techniques may produce highly-predictive models accelerating the search of interacting phage-bacteria pairs.

     

Biochemical,machine learning and molecular approaches for the differential diagnosis of Mucopolysaccharidoses

This study was aimed to construct classification and regression tree (CART) model of glycosaminoglycans (GAGs) for the differential diagnosis of Mucopolysaccharidoses (MPS). Two-dimensional electrophoresis and liquid chromatography–tandem mass spectrometry (LC–MS/MS) were used for the qualitative and quantitative analysis of GAGs. Specific enzyme assays and targeted gene sequencing were performed to confirm the diagnosis. Machine learning tools were used to develop CART model based on GAG profile. Qualitative and quantitative CART models showed 96.3% and 98.3% accuracy, respectively, in the differential diagnosis of MPS. The thresholds of different GAGs diagnostic of specific MPS types were established. In 60 MPS positive cases, 46 different mutations were identified in six specific genes. Among 31 different mutations identified in IDUA, nine were nonsense mutations and two were gross deletions while the remaining were missense mutations. In IDS gene, four missense, two frameshift, and one deletion were identified. In NAGLU gene, c.1693C?>?T and c.1914_1914insT were the most common mutations. Two ARSB, one case each of SGSH and GALNS mutations were observed. LC–MS/MS-based GAG pattern showed higher accuracy in the differential diagnosis of MPS. The mutation spectrum of MPS, specifically in IDUA and IDS genes, is highly heterogeneous among the cases studied.

     

Candidate gene prioritization by network analysis of differential expression using machine learning approaches

Background  

Discovering novel disease genes is still challenging for diseases for which no prior knowledge - such as known disease genes or disease-related pathways - is available. Performing genetic studies frequently results in large lists of candidate genes of which only few can be followed up for further investigation. We have recently developed a computational method for constitutional genetic disorders that identifies the most promising candidate genes by replacing prior knowledge by experimental data of differential gene expression between affected and healthy individuals.     

Improved classification of mass spectrometry database search results using newer machine learning approaches

Manual analysis of mass spectrometry data is a current bottleneck in high throughput proteomics. In particular, the need to manually validate the results of mass spectrometry database searching algorithms can be prohibitively time-consuming. Development of software tools that attempt to quantify the confidence in the assignment of a protein or peptide identity to a mass spectrum is an area of active interest. We sought to extend work in this area by investigating the potential of recent machine learning algorithms to improve the accuracy of these approaches and as a flexible framework for accommodating new data features. Specifically we demonstrated the ability of boosting and random forest approaches to improve the discrimination of true hits from false positive identifications in the results of mass spectrometry database search engines compared with thresholding and other machine learning approaches. We accommodated additional attributes obtainable from database search results, including a factor addressing proton mobility. Performance was evaluated using publically available electrospray data and a new collection of MALDI data generated from purified human reference proteins.