SGP-1: prediction and validation of homologous genes based on sequence alignments

Conventional methods of gene prediction rely on the recognition of DNA-sequence signals, the coding potential or the comparison of a genomic sequence with a cDNA, EST, or protein database. Reasons for limited accuracy in many circumstances are species-specific training and the incompleteness of reference databases. Lately, comparative genome analysis has attracted increasing attention. Several analysis tools that are based on human/mouse comparisons are already available. Here, we present a program for the prediction of protein-coding genes, termed SGP-1 (Syntenic Gene Prediction), which is based on the similarity of homologous genomic sequences. In contrast to most existing tools, the accuracy of SGP-1 depends little on species-specific properties such as codon usage or the nucleotide distribution. SGP-1 may therefore be applied to nonstandard model organisms in vertebrates as well as in plants, without the need for extensive parameter training. In addition to predicting genes in large-scale genomic sequences, the program may be useful to validate gene structure annotations from databases. To this end, SGP-1 output also contains comparisons between predicted and annotated gene structures in HTML format. The program can be accessed via a Web server at http://soft.ice.mpg.de/sgp-1. The source code, written in ANSI C, is available on request from the authors.

An assessment of gene prediction accuracy in large DNA sequences

One of the first useful products from the human genome will be a set of predicted genes. Besides its intrinsic scientific interest, the accuracy and completeness of this data set is of considerable importance for human health and medicine. Though progress has been made on computational gene identification in terms of both methods and accuracy evaluation measures, most of the sequence sets in which the programs are tested are short genomic sequences, and there is concern that these accuracy measures may not extrapolate well to larger, more challenging data sets. Given the absence of experimentally verified large genomic data sets, we constructed a semiartificial test set comprising a number of short single-gene genomic sequences with randomly generated intergenic regions. This test set, which should still present an easier problem than real human genomic sequence, mimics the approximately 200kb long BACs being sequenced. In our experiments with these longer genomic sequences, the accuracy of GENSCAN, one of the most accurate ab initio gene prediction programs, dropped significantly, although its sensitivity remained high. Conversely, the accuracy of similarity-based programs, such as GENEWISE, PROCRUSTES, and BLASTX was not affected significantly by the presence of random intergenic sequence, but depended on the strength of the similarity to the protein homolog. As expected, the accuracy dropped if the models were built using more distant homologs, and we were able to quantitatively estimate this decline. However, the specificities of these techniques are still rather good even when the similarity is weak, which is a desirable characteristic for driving expensive follow-up experiments. Our experiments suggest that though gene prediction will improve with every new protein that is discovered and through improvements in the current set of tools, we still have a long way to go before we can decipher the precise exonic structure of every gene in the human genome using purely computational methodology.

Comparative gene prediction in human and mouse

The completion of the sequencing of the mouse genome promises to help predict human genes with greater accuracy. While current ab initio gene prediction programs are remarkably sensitive (i.e., they predict at least a fragment of most genes), their specificity is often low, predicting a large number of false-positive genes in the human genome. Sequence conservation at the protein level with the mouse genome can help eliminate some of those false positives. Here we describe SGP2, a gene prediction program that combines ab initio gene prediction with TBLASTX searches between two genome sequences to provide both sensitive and specific gene predictions. The accuracy of SGP2 when used to predict genes by comparing the human and mouse genomes is assessed on a number of data sets, including single-gene data sets, the highly curated human chromosome 22 predictions, and entire genome predictions from ENSEMBL. Results indicate that SGP2 outperforms purely ab initio gene prediction methods. Results also indicate that SGP2 works about as well with 3x shotgun data as it does with fully assembled genomes. SGP2 provides a high enough specificity that its predictions can be experimentally verified at a reasonable cost. SGP2 was used to generate a complete set of gene predictions on both the human and mouse by comparing the genomes of these two species. Our results suggest that another few thousand human and mouse genes currently not in ENSEMBL are worth verifying experimentally.

Splitting statistical potentials into meaningful scoring functions: testing the prediction of near-native structures from decoy conformations

Background: Recent advances on high-throughput technologies have produced a vast amount of protein sequences, while the number of high-resolution structures has seen a limited increase. This has impelled the production of many strategies to built protein structures from its sequence, generating a considerable amount of alternative models. The selection of the closest model to the native conformation has thus become crucial for structure prediction. Several methods have been developed to score protein models by energies, knowledge-based potentials and combination of both.Results: Here, we present and demonstrate a theory to split the knowledge-based potentials in scoring terms biologically meaningful and to combine them in new scores to predict near-native structures. Our strategy allows circumventing the problem of defining the reference state. In this approach we give the proof for a simple and linear application that can be further improved by optimizing the combination of Zscores. Using the simplest composite score () we obtained predictions similar to state-of-the-art methods. Besides, our approach has the advantage of identifying the most relevant terms involved in the stability of the protein structure. Finally, we also use the composite Zscores to assess the conformation of models and to detect local errors.Conclusion: We have introduced a method to split knowledge-based potentials and to solve the problem of defining a reference state. The new scores have detected near-native structures as accurately as state-of-art methods and have been successful to identify wrongly modeled regions of many near-native conformations.

Prediction of enzyme function by combining sequence similarity and protein interactions

Background: A number of studies have used protein interaction data alone for protein function prediction. Here, we introduce a computational approach for annotation of enzymes, based on the observation that similar protein sequences are more likely to perform the same function if they share similar interacting partners. Results: The method has been tested against the PSI-BLAST program using a set of 3,890 protein sequences from which interaction data was available. For protein sequences that align with at least 40% sequence identity to a known enzyme, the specificity of our method in predicting the first three EC digits increased from 80% to 90% at 80% coverage when compared to PSI-BLAST. Conclusion: Our method can also be used in proteins for which homologous sequences with known interacting partners can be detected. Thus, our method could increase 10% the specificity of genome-wide enzyme predictions based on sequence matching by PSI-BLAST alone.

Chroma binary similarity and local alignment applied to cover song identification

We present a new technique for audio signal comparison based on tonal subsequence alignment and its application to detect cover versions (i.e., different performances of the same underlying musical piece). Cover song identification is a task whose popularity has increased in the Music Information Retrieval (MIR) community along in the past, as it provides a direct and objective way to evaluate music similarity algorithms.This article first presents a series of experiments carried outwith two state-of-the-art methods for cover song identification.We have studied several components of these (such as chroma resolution and similarity, transposition, beat tracking or Dynamic Time Warping constraints), in order to discover which characteristics would be desirable for a competitive cover song identifier. After analyzing many cross-validated results, the importance of these characteristics is discussed, and the best-performing ones are finally applied to the newly proposed method. Multipleevaluations of this one confirm a large increase in identificationaccuracy when comparing it with alternative state-of-the-artapproaches.

Personalized modeling for drug concentration prediction using Support Vector Machine

Building a personalized model to describe the drug concentration inside the human body for each patient is highly important to the clinical practice and demanding to the modeling tools. Instead of using traditional explicit methods, in this paper we propose a machine learning approach to describe the relation between the drug concentration and patients' features. Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. We focus mainly on the prediction of the drug concentrations as well as the analysis of different features' influence. Models are built based on Support Vector Machine and the prediction results are compared with the traditional analytical models.

The role of the New Trauma and Injury Severity Score (NTRISS) for survival prediction

The objective of this study was to verify if replacing the Injury Severity Score (ISS) by the New Injury Severity Score (NISS) in the original Trauma and Injury Severity Score (TRISS) form would improve the survival rate estimation. This retrospective study was performed in a level I trauma center during one year. ROC curve was used to identify the best indicator (TRISS or NTRISS) for survival probability prediction. Participants were 533 victims, with a mean age of 38±16 years. There was predominance of motor vehicle accidents (61.9%). External injuries were more frequent (63.0%), followed by head/neck injuries (55.5%). Survival rate was 76.9%. There is predominance of ISS scores ranging from 9-15 (40.0%), and NISS scores ranging from 16-24 (25.5%). Survival probability equal to or greater than 75.0% was obtained for 83.4% of the victims according to TRISS, and for 78.4% according to NTRISS. The new version (NTRISS) is better than TRISS for survival prediction in trauma patients.

Prediction of infant drug exposure through breastfeeding: population PK modeling and simulation of fluoxetine

BACKGROUND: Risks of significant infant drug exposurethrough breastmilk are poorly defined for many drugs, and largescalepopulation data are lacking. We used population pharmacokinetics(PK) modeling to predict fluoxetine exposure levels ofinfants via mother's milk in a simulated population of 1000 motherinfantpairs.METHODS: Using our original data on fluoxetine PK of 25breastfeeding women, a population PK model was developed withNONMEM and parameters, including milk concentrations, wereestimated. An exponential distribution model was used to account forindividual variation. Simulation random and distribution-constrainedassignment of doses, dosing time, feeding intervals and milk volumewas conducted to generate 1000 mother-infant pairs with characteristicssuch as the steady-state serum concentrations (Css) and infantdose relative to the maternal weight-adjusted dose (relative infantdose: RID). Full bioavailability and a conservative point estimate of1-month-old infant CYP2D6 activity to be 20% of the adult value(adjusted by weigth) according to a recent study, were assumed forinfant Css calculations.RESULTS: A linear 2-compartment model was selected as thebest model. Derived parameters, including milk-to-plasma ratios(mean: 0.66; SD: 0.34; range, 0 - 1.1) were consistent with the valuesreported in the literature. The estimated RID was below 10% in >95%of infants. The model predicted median infant-mother Css ratio was0.096 (range 0.035 - 0.25); literature reported mean was 0.07 (range0-0.59). Moreover, the predicted incidence of infant-mother Css ratioof >0.2 was less than 1%.CONCLUSION: Our in silico model prediction is consistent withclinical observations, suggesting that substantial systemic fluoxetineexposure in infants through human milk is rare, but further analysisshould include active metabolites. Our approach may be valid forother drugs. [supported by CIHR and Swiss National Science Foundation(SNSF)]

IL28B expression depends on a novel TT/-G polymorphism which improves HCV clearance prediction.

Approximately 3% of the world population is chronically infected with the hepatitis C virus (HCV), with potential development of cirrhosis and hepatocellular carcinoma. Despite the availability of new antiviral agents, treatment remains suboptimal. Genome-wide association studies (GWAS) identified rs12979860, a polymorphism nearby IL28B, as an important predictor of HCV clearance. We report the identification of a novel TT/-G polymorphism in the CpG region upstream of IL28B, which is a better predictor of HCV clearance than rs12979860. By using peripheral blood mononuclear cells (PBMCs) from individuals carrying different allelic combinations of the TT/-G and rs12979860 polymorphisms, we show that induction of IL28B and IFN-γ-inducible protein 10 (IP-10) mRNA relies on TT/-G, but not rs12979860, making TT/-G the only functional variant identified so far. This novel step in understanding the genetic regulation of IL28B may have important implications for clinical practice, as the use of TT/G genotyping instead of rs12979860 would improve patient management.

Prediction of clinical response after renal angioplasty: respective value of renal Doppler sonography and scintigraphy.

OBJECTIVE: The goal of our study was to compare Doppler sonography and renal scintigraphy as tools for predicting the therapeutic response in patients after undergoing renal angioplasty. SUBJECTS AND METHODS. Seventy-four hypertensive patients underwent clinical examination, Doppler sonography, and renal scintigraphy before and after receiving captopril in preparation for renal revascularization. The patients were evaluated for the status of hypertension 3 months after the procedure. The predictive values of the findings of clinical examination, Doppler sonography, renal scintigraphy, and angiography were assessed. RESULTS: For prediction of a favorable therapeutic outcome, abnormal results from renal scintigraphy before and after captopril administration had a sensitivity of 58% and specificity of 57%. Findings of Doppler sonography had a sensitivity of 68% and specificity of 50% before captopril administration and a sensitivity of 81% and specificity of 32% after captopril administration. Significant predictors of a cure or reduction of hypertension after revascularization were low unilateral (p = 0.014) and bilateral resistive (p = 0.016) indexes on Doppler sonography before (p = 0.009) and after (p = 0.028) captopril administration. On multivariate analysis, the best predictors were a unilateral resistive index of less than 0.65 (odds ratio [OR] = 3.7) after captopril administration and a kidney longer than 93 mm (OR = 7.8). The two best combined criteria to predict the favorable therapeutic outcome were a bilateral resistive index of less than 0.75 before captopril administration combined with a unilateral resistive index of less than 0.70 after captopril administration (sensitivity, 76%; specificity, 58%) or a bilateral resistive index of less than 0.75 before captopril administration and a kidney measuring longer than 90 mm (sensitivity, 81%; specificity, 50%). CONCLUSION: Measurements of kidney length and unilateral and bilateral resistive indexes before and after captopril administration were useful in predicting the outcome after renal angioplasty. Renal scintigraphy had no significant predictive value.

Response Prediction in Chronic Hepatitis C by Assessment of IP-10 and IL28B-Related Single Nucleotide Polymorphisms.

BACKGROUND: High baseline levels of IP-10 predict a slower first phase decline in HCV RNA and a poor outcome following interferon/ribavirin therapy in patients with chronic hepatitis C. Several recent studies report that single nucleotide polymorphisms (SNPs) adjacent to IL28B predict spontaneous resolution of HCV infection and outcome of treatment among HCV genotype 1 infected patients. METHODS AND FINDINGS: In the present study, we correlated the occurrence of variants at three such SNPs (rs12979860, rs12980275, and rs8099917) with pretreatment plasma IP-10 and HCV RNA throughout therapy within a phase III treatment trial (HCV-DITTO) involving 253 Caucasian patients. The favorable SNP variants (CC, AA, and TT, respectively) were associated with lower baseline IP-10 (P = 0.02, P = 0.01, P = 0.04) and were less common among HCV genotype 1 infected patients than genotype 2/3 (P<0.0001, P<0.0001, and P = 0.01). Patients carrying favorable SNP genotypes had higher baseline viral load than those carrying unfavorable variants (P = 0.0013, P = 0.029, P = 0.0004 respectively). Among HCV genotype 1 infected carriers of the favorable C, A, or T alleles, IP-10 below 150 pg/mL significantly predicted a more pronounced reduction of HCV RNA from day 0 to 4 (first phase decline), which translated into increased rates of RVR (62%, 53%, and 39%) and SVR (85%, 76%, and 75% respectively) among homozygous carriers with baseline IP-10 below 150 pg/mL. In multivariate analyses of genotype 1-infected patients, baseline IP-10 and C genotype at rs12979860 independently predicted the first phase viral decline and RVR, which in turn independently predicted SVR. CONCLUSIONS: Concomitant assessment of pretreatment IP-10 and IL28B-related SNPs augments the prediction of the first phase decline in HCV RNA, RVR, and final therapeutic outcome.

Urinary incontinence in the prediction of falls in hospitalized elderly

Objective Analyzing the effect of urinary incontinence as a predictor of the incidence of falls among hospitalized elderly. Method Concurrent cohort study where 221 elderly inpatients were followed from the date of admission until discharge, death or fall. The Kaplan-Meier methods, the incidence density and the Cox regression model were used for the survival analysis and the assessment of the association between the exposure variable and the other variables. Results Urinary incontinence was a strong predictor of falls in the surveyed elderly, and was associated with shorter time until the occurrence of event. Urinary incontinence, concomitant with gait and balance dysfunction and use of antipsychotics was associated with falls. Conclusion Measures to prevent the risk of falls specific to hospitalized elderly patients who have urinary incontinence are necessary.