SEARCH · PubMed Health

Results for “machine learning prediction”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 865 records · Page 48Linked to original sources

PubMed2026

From Variability to Consensus: Rescoring Harmonizes Peptide Identification across Diverse Search Engines and Data Sets.

Peptide-spectrum match (PSM) rescoring has become standard in proteomics workflows, improving peptide identification accuracy across diverse search engines. Despite the availability of multiple rescoring strategies, systematic comparisons spanning several search engines, data sets, and database configurations remain limited. Here, we benchmarked seven publicly available search engines, evaluating standard target-decoy-based false discovery rate (FDR) estimation alongside Percolator, MS2Rescore, and Oktoberfest across four data sets acquired on different mass spectrometry platforms in data-dependent mode and searched against protein databases of varying size and composition. Rescoring substantially increased identification consensus and reduced variability between search engines, with prediction-based approaches yielding the largest gains. While database size had limited impact for human data sets, it significantly affected identification rates on a metaproteomic data set. Entrapment-based evaluation indicated generally adequate FDR control across methods, although prediction-based rescoring exhibited a higher tendency toward FDR underestimation in specific configurations. Overall, advanced rescoring strategies harmonize peptide identification outcomes across search engines, thereby enhancing robustness and comparability in proteomics analyses. However, careful feature selection and appropriate database choice remain essential to ensure reliable FDR control and optimal performance across diverse experimental settings.

Search Engine↗

PubMed2004

Statistical evaluation of local alignment features predicting allergenicity using supervised classification algorithms.

BACKGROUND: Recently, two promising alignment-based features predicting food allergenicity using the k nearest neighbor (kNN) classifier were reported. These features are the alignment score and alignment length of the best local alignment obtained in a database of known allergen sequences. METHODS: In the work reported here a much more comprehensive statistical evaluation of the potential of these features was performed, this time for the prediction of allergenicity in general. The evaluation consisted of the following four key components. (1) A new high quality database consisting of 318 carefully selected, non-redundant allergens and 1,007 sequences carefully selected to be non-allergens. (2) Three different supervised algorithms: the kNN classifier, the Bayesian linear Gaussian classifier, and the Bayesian quadratic Gaussian classifier. (3) A large set of local alignment procedures defined using the FASTA3 alignment program by means of a wide range of different parameter settings. (4) Novel performance curves, alternative to conventional receiver-operating characteristic curves, to display not only average behaviors but also statistical variations due to small data sets. RESULTS: The linear Gaussian classifier proved most useful among the tested supervised machine learning algorithms, closely followed by the quadratic Gaussian equivalent and kNN. The overall best classification results were obtained with a novel feature vector consisting of the combined alignment scores derived from local alignment procedures using different substitution matrices. CONCLUSIONS: The models reported here should be useful as a part of an integrated assessment scheme for potential protein allergenicity and for future comparisons with alternative bioinformatic approaches.

Algorithms↗

PubMed1996

A generalized hidden Markov model for the recognition of human genes in DNA.

We present a statistical model of genes in DNA. A Generalized Hidden Markov Model (GHMM) provides the framework for describing the grammar of a legal parse of a DNA sequence (Stormo & Haussler 1994). Probabilities are assigned to transitions between states in the GHMM and to the generation of each nucleotide base given a particular state. Machine learning techniques are applied to optimize these probabilities using a standardized training set. Given a new candidate sequence, the best parse is deduced from the model using a dynamic programming algorithm to identify the path through the model with maximum probability. The GHMM is flexible and modular, so new sensors and additional states can be inserted easily. In addition, it provides simple solutions for integrating cardinality constraints, reading frame constraints, "indels", and homology searching. The description and results of an implementation of such a gene-finding model, called Genie, is presented. The exon sensor is a codon frequency model conditioned on windowed nucleotide frequency and the preceding codon. Two neural networks are used, as in (Brunak, Engelbrecht, & Knudsen 1991), for splice site prediction. We show that this simple model performs quite well. For a cross-validated standard test set of 304 genes [ftp:@www-hgc.lbl.gov/pub/genesets] in human DNA, our gene-finding system identified up to 85% of protein-coding bases correctly with a specificity of 80%. 58% of exons were exactly identified with a specificity of 51%. Genie is shown to perform favorably compared with several other gene-finding systems.

Chromosomes, Human↗

PubMed2026

Ensemble DNA methylation clock demonstrates Immune-metabolic aging signatures associated with mortality.

Aging is a multifactorial process that is best described in terms of the progressive acquisition of multiple layers of phenotypic changes, such as epigenetic modifications, inflammation, and metabolic dysregulation. DNA methylation clocks have been extensively used to construct epigenetic clocks based on the DNAm profiles that can be used to estimate biological age and predict age-associated outcomes. Nevertheless, the vast majority of clocks constructed so far have been based on linear models, which are unlikely to fully account for the heterogeneity and non-linearity of survival-related DNAm signatures. In this work, we constructed a heterogeneous stacked ensemble survival model based on DNAm data obtained from the Framingham Heart Study. We first identified 190 CpG loci using elastic net Cox regression and subsequently constructed a survival prediction model based on the fusion of five complementary survival models by means of a neural network meta-learner. The prediction power of the survival model was evaluated in an external validation cohort, where we observed strong performance for predicting all-cause mortality that significantly exceeded PhenoAge and was statistically comparable to GrimAge. These performance estimates were derived in cohorts of European ancestry and externally validated in postmenopausal women aged 50-79 years, and should therefore be interpreted as applicable only to demographically similar populations.

Humans↗

PubMed2006

Evaluation of different biological data and computational classification methods for use in protein interaction prediction.

Protein-protein interactions play a key role in many biological systems. High-throughput methods can directly detect the set of interacting proteins in yeast, but the results are often incomplete and exhibit high false-positive and false-negative rates. Recently, many different research groups independently suggested using supervised learning methods to integrate direct and indirect biological data sources for the protein interaction prediction task. However, the data sources, approaches, and implementations varied. Furthermore, the protein interaction prediction task itself can be subdivided into prediction of (1) physical interaction, (2) co-complex relationship, and (3) pathway co-membership. To investigate systematically the utility of different data sources and the way the data is encoded as features for predicting each of these types of protein interactions, we assembled a large set of biological features and varied their encoding for use in each of the three prediction tasks. Six different classifiers were used to assess the accuracy in predicting interactions, Random Forest (RF), RF similarity-based k-Nearest-Neighbor, Naïve Bayes, Decision Tree, Logistic Regression, and Support Vector Machine. For all classifiers, the three prediction tasks had different success rates, and co-complex prediction appears to be an easier task than the other two. Independently of prediction task, however, the RF classifier consistently ranked as one of the top two classifiers for all combinations of feature sets. Therefore, we used this classifier to study the importance of different biological datasets. First, we used the splitting function of the RF tree structure, the Gini index, to estimate feature importance. Second, we determined classification accuracy when only the top-ranking features were used as an input in the classifier. We find that the importance of different features depends on the specific prediction task and the way they are encoded. Strikingly, gene expression is consistently the most important feature for all three prediction tasks, while the protein interactions identified using the yeast-2-hybrid system were not among the top-ranking features under any condition.

Computational Biology↗

PubMed2003

Off-pump coronary bypass surgery and all arterial conduits: learning experience at Bangkok Heart Institute.

Off-pump coronary artery bypass technique or bypass graft surgery without the use of a heart-lung machine has been introduced in the last six years, and now comprises approximately 25 per cent of all coronary artery bypass surgery being done in the world. One of the goals of beating heart surgery is to eliminate the complications associated with the use of cardiopulmonary bypass. The use of all arterial conduits for coronary artery bypass graft has become more acceptable after experiences gained and reports of better long-term results. From January 2001 to December 21 2002 the authors performed 251 off-pump procedures. One hundred and nine of these cases were done utilizing all arterial conduits. The data was stratified using the US National Society of Thoracic Surgeons Cardiac Surgery Database pre-operative risk module and divided into 3 groups as suggested: Low risk group with a predicted mortality of 0-1 per cent (2 patients); Medium risk group with a predicted mortality of 2-9 per cent (87 patients), and High risk group with a predicted mortality of 10+ per cent (10 patients). The predicted mortality of the entire group was 4.5 per cent. There were 90 males and 19 females with a mean age of 60.2 +/- 10.7 years, with 15.6 per cent of them older than 70 years. Pre-operative co-morbidities included 1/4 of the patients who had ejection fraction (EF) of equal to or less than 0.4, 4.5 per cent had unstable angina, 1.6 per cent had urgent/emergent status, 26.6 per cent underwent re-operative procedure, 1 per cent had pre-operative serum creatinine more than 2 mg per cent, 4.8 per cent had a history of stroke, 20.2 per cent had a history of congestive heart failure, 45.2 per cent had a history of previous myocardial infarction, 10.7 per cent had a history of chronic obstructive pulmonary disease, 46.9 per cent had a history of diabetes, 62 per cent had hypertension, and 20 patients (18.3%) required intra aortic balloon pump. Intra-operative parameters revealed 3.7 +/- 1.3 grafts/patient. The left internal mammary artery (LIMA) was used to the left anterior descending (LAD) in 6.4 per cent, or sequential with the diagonals 93.6 per cent. The 30 days mortality was 3.6 per cent (4 cases). Further analysis revealed that pre-operatively, none of these 4 cases was in the low predicted (predicted mortality of 0-1%) risk group, 2 of them were in the medium (predicted mortality of 2-9%) and the other 2 were in the high predicted risk (predicted mortality of 10+%) group. The skin-to-skin time was 4.1 hours and there were two conversions to on-pump in this group. Post-operatively, the intubation time was 4.7 hours. There was no peri-operative myocardial infarction, one patient required dialysis, and no patient experienced stroke. There was no sternal wound or arm wound infection, 9.5 per cent experienced temporal sensation impairment at the site of the radial artery harvesting at one month. Re-operation for bleeding occurred in 3 cases, and thirteen patients (14.3%) developed new atrial fibrillation. The authors are no longer making a one-foot long incision and spread ten inches wide like in the old days'. With the less invasive approach lessened in the recent past, the authors have found the less invasive the incision the less the pain after surgery. Totally eliminating the leg incision has allowed the patient to get up and mobilize on the same afternoon, if the procedure was done in the morning. All of these approaches combined with the off-pump technique, as far as the authors are concerned, will provide those who need coronary arterial bypass graft the best operative procedure.

Aged↗

PubMed2000

Knowledge-based analysis of microarray gene expression data by using support vector machines.

We introduce a method of functionally classifying genes by using gene expression data from DNA microarray hybridization experiments. The method is based on the theory of support vector machines (SVMs). SVMs are considered a supervised computer learning method because they exploit prior knowledge of gene function to identify unknown genes of similar function from expression data. SVMs avoid several problems associated with unsupervised clustering methods, such as hierarchical clustering and self-organizing maps. SVMs have many mathematical features that make them attractive for gene expression analysis, including their flexibility in choosing a similarity function, sparseness of solution when dealing with large data sets, the ability to handle large feature spaces, and the ability to identify outliers. We test several SVMs that use different similarity metrics, as well as some other supervised learning methods, and find that the SVMs best identify sets of genes with a common function using expression data. Finally, we use SVMs to predict functional roles for uncharacterized yeast ORFs based on their expression data.

Algorithms↗

PubMed2007

Large-scale mapping and validation of Escherichia coli transcriptional regulation from a compendium of expression profiles.

Machine learning approaches offer the potential to systematically identify transcriptional regulatory interactions from a compendium of microarray expression profiles. However, experimental validation of the performance of these methods at the genome scale has remained elusive. Here we assess the global performance of four existing classes of inference algorithms using 445 Escherichia coli Affymetrix arrays and 3,216 known E. coli regulatory interactions from RegulonDB. We also developed and applied the context likelihood of relatedness (CLR) algorithm, a novel extension of the relevance networks class of algorithms. CLR demonstrates an average precision gain of 36% relative to the next-best performing algorithm. At a 60% true positive rate, CLR identifies 1,079 regulatory interactions, of which 338 were in the previously known network and 741 were novel predictions. We tested the predicted interactions for three transcription factors with chromatin immunoprecipitation, confirming 21 novel interactions and verifying our RegulonDB-based performance estimates. CLR also identified a regulatory link providing central metabolic control of iron transport, which we confirmed with real-time quantitative PCR. The compendium of expression data compiled in this study, coupled with RegulonDB, provides a valuable model system for further improvement of network inference algorithms using experimental data.

Algorithms↗

PubMed1998

How to interpret an anonymous bacterial genome: machine learning approach to gene identification.

In this report we address the problem of accurate statistical modeling of DNA sequences, either coding or noncoding, for a bacterial species whose genome (or a large portion) was sequenced but not yet characterized experimentally. Availability of these models is critical for successful solution of the genome annotation task by statistical methods of gene finding. We present the method, GeneMark-Genesis, which learns the parameters of Markov models of protein-coding and noncoding regions from anonymous bacterial genomic sequence. These models are subsequently used in the GeneMark and GeneMark.hmm gene-finding programs. Although there is basically one model of a noncoding region for a given genome, several models of protein-coding region are automatically obtained by GeneMark-Genesis. The diversity of protein-coding models reflects the diversity of oligonucleotide compositions, particularly the diversity of codon usage strategies observed in genes from one and the same genome. In the simplest and the most important case, there are just two gene models-typical and atypical ones. We show that the atypical model allows one to predict genes that escape identification by the typical model. Many genes predicted by the atypical model appear to be horizontally transferred genes. The early versions of GeneMark-Genesis were used for annotating the genomes of Methanoccocus jannaschii and Helicobacter pylori. We report the results of accuracy testing of the full-scale version of GeneMark-Genesis on 10 completely sequenced bacterial genomes. Interestingly, the GeneMark.hmm program that employed the typical and atypical models defined by GeneMark-Genesis was able to predict 683 new atypical genes with 176 of them confirmed by similarity search.

Algorithms↗

PubMed2026

Spatial Multiomics Reveal Insights Into ADC Efficacy.

Antibody-drug conjugates (ADCs) have transformed the therapeutic landscape of solid tumors; however, responses remain heterogeneous and complex to predict. In addition, a growing number of multiple ADC targets are either approved or in late-stage clinical development, such as NECTIN-4, HER2, or TROP2 for metastatic urothelial cancer. Spatial multiomics-representing next-generation methods that couple high-plex RNA sequencing and multiplex protein imaging with precise x-y-z coordinates within tissues-offer a direct way to correlate (ADC) antigen expression, cell state information, and micro-anatomical context with patient treatment outcomes. In this review, we highlight suitability and technological advancements in current spatial transcriptomics and proteomics approaches to decode modes of action and resistance to ADCs and extract biological insights, particularly in metastatic urothelial cancer-and propose an integrative framework that combines spatial readouts with machine and/or deep learning-driven analytics to stratify patients, forecast on- and off-target toxicities, and guide next-generation linker-payload designs or combination therapies.

Humans↗

PubMed2006

Establishing glucose- and ABA-regulated transcription networks in Arabidopsis by microarray analysis and promoter classification using a Relevance Vector Machine.

Establishing transcriptional regulatory networks by analysis of gene expression data and promoter sequences shows great promise. We developed a novel promoter classification method using a Relevance Vector Machine (RVM) and Bayesian statistical principles to identify discriminatory features in the promoter sequences of genes that can correctly classify transcriptional responses. The method was applied to microarray data obtained from Arabidopsis seedlings treated with glucose or abscisic acid (ABA). Of those genes showing >2.5-fold changes in expression level, approximately 70% were correctly predicted as being up- or down-regulated (under 10-fold cross-validation), based on the presence or absence of a small set of discriminative promoter motifs. Many of these motifs have known regulatory functions in sugar- and ABA-mediated gene expression. One promoter motif that was not known to be involved in glucose-responsive gene expression was identified as the strongest classifier of glucose-up-regulated gene expression. We show it confers glucose-responsive gene expression in conjunction with another promoter motif, thus validating the classification method. We were able to establish a detailed model of glucose and ABA transcriptional regulatory networks and their interactions, which will help us to understand the mechanisms linking metabolism with growth in Arabidopsis. This study shows that machine learning strategies coupled to Bayesian statistical methods hold significant promise for identifying functionally significant promoter sequences.

Abscisic Acid↗

PubMed2026

Decoding cancer with artificial intelligence: Transforming research, diagnosis, and therapy with future insights.

Cancer remains one of the leading global health burdens, with increasing complexity in genomic, imaging, and clinical datasets presenting significant challenges for effective management. Artificial intelligence (AI) has emerged as a powerful tool to address these challenges by enabling pattern recognition, knowledge integration, and data-driven decision-making. This review highlights recent advances in the application of AI across cancer research, diagnosis, and therapy. In research, AI accelerates drug discovery and repurposing, enhances genomic data interpretation, and facilitates biomarker identification through multi-omics integration. In diagnosis, AI has demonstrated high technical performance in radiology for lesion detection and image segmentation, in pathology for tumour grading and molecular prediction, and in liquid biopsy for non-invasive biomarker analysis. In therapy, AI supports precision medicine by predicting treatment responses, monitoring disease progression, and optimizing clinical trial design. Despite these advances, barriers such as data heterogeneity, algorithmic bias, interpretability, and regulatory challenges remain. Future directions, including explainable AI, federated learning, multimodal modelling, and digital twins, hold promise for translating AI-driven innovations into routine oncology practice. Significance Statement This review provides a timely synthesis of recent (2020-2025) advances in artificial intelligence across cancer research, diagnosis, and therapy, highlighting applications in drug discovery, genomics, multi-omics biomarker identification, and clinical decision-making. By integrating technological progress with translational and clinical relevance, this work serves as a valuable resource for bridging AI innovation with precision oncology practice. As a narrative review, the literature was identified through targeted PubMed, Scopus, and Google Scholar searches, combining terms for artificial intelligence, machine learning, and deep learning with cancer-related keywords, with priority given to peer-reviewed studies published between 2020 and 2025, seminal earlier works, and official regulatory or guideline documents. Within each domain, representative studies were selected to illustrate methodological diversity, clinical context, and current translational readiness rather than to provide exhaustive coverage of an extremely rapidly evolving field.

Artificial intelligence↗

PubMedDate not supplied

Support vector machines for predictive modeling in heterogeneous catalysis: a comprehensive introduction and overfitting investigation based on two real applications.

This works provides an introduction to support vector machines (SVMs) for predictive modeling in heterogeneous catalysis, describing step by step the methodology with a highlighting of the points which make such technique an attractive approach. We first investigate linear SVMs, working in detail through a simple example based on experimental data derived from a study aiming at optimizing olefin epoxidation catalysts applying high-throughput experimentation. This case study has been chosen to underline SVM features in a visual manner because of the few catalytic variables investigated. It is shown how SVMs transform original data into another representation space of higher dimensionality. The concepts of Vapnik-Chervonenkis dimension and structural risk minimization are introduced. The SVM methodology is evaluated with a second catalytic application, that is, light paraffin isomerization. Finally, we discuss why SVMs is a strategic method, as compared to other machine learning techniques, such as neural networks or induction trees, and why emphasis is put on the problem of overfitting.

Alkenes↗

PubMed2025

dbscATAC: a resource of single-cell super-enhancers/enhancers and gene markers derived from scATAC-seq data.

MOTIVATION: scATAC-seq enables high-resolution mapping of cis-regulatory elements. It has been widely applied to uncover cell-type-specific regulatory networks and complement scRNA-seq analysis in numerous studies. However, a large number of datasets generated by scATAC-seq remain underutilized due to limited exploration of super-enhancers/typical enhancers and gene markers. A comprehensive resource enabling cell-type-specific annotation of cis-regulatory elements and their dynamic enhancer-gene linkages remains an urgent unmet need for scATAC-seq. RESULTS: We present dbscATAC, a specialized single-cell database for annotating super-enhancers, gene markers, and enhancer-gene interactions derived from scATAC-seq data. Using improved machine learning algorithms, we identified 213 835 super-enhancers across 520 tissue/cell types from three species, as well as 347 484 gene markers, 13 470 526 enhancers, and 10 402 346 enhancer-gene interactions derived from 1 668 076 single cells spanning 1028 tissue/cell types in 13 species. An easy-to-use online platform with multiple analytic modules and hierarchical query options was developed for searching, browsing and visualizing single-cell super-enhancers, enhancers, and gene markers. dbscATAC provides a comprehensive resource to facilitate the exploration of enhancer landscapes, gene regulation, and cell-type-specific characteristics in single-cell epigenomics. AVAILABILITY AND IMPLEMENTATION: The database with all the super-enhancer/enhancer annotation data is available at http://singlecelldb.com/dbscATAC/index.php. And the source code of dbscATAC for prediction of SEs, enhancers, and gene markers are available at https://github.com/EvansGao/dbscATAC. The source code, tissue/cell type description, and data summary can be downloaded at DOI: 10.6084/m9.figshare.28706414.scATAC-seq, Database, Super-enhancers/enhancers, Gene markers.

Enhancer Elements, Genetic↗

PubMed2022

Improving risk indexes for Alzheimer's disease and related dementias for use in midlife.

Knowledge of a person's risk for Alzheimer's disease and related dementias (ADRDs) is required to triage candidates for preventive interventions, surveillance, and treatment trials. ADRD risk indexes exist for this purpose, but each includes only a subset of known risk factors. Information missing from published indexes could improve risk prediction. In the Dunedin Study of a population-representative New Zealand-based birth cohort followed to midlife (N = 938, 49.5% female), we compared associations of four leading risk indexes with midlife antecedents of ADRD against a novel benchmark index comprised of nearly all known ADRD risk factors, the Dunedin ADRD Risk Benchmark (DunedinARB). Existing indexes included the Cardiovascular Risk Factors, Aging, and Dementia index (CAIDE), LIfestyle for BRAin health index (LIBRA), Australian National University Alzheimer's Disease Risk Index (ANU-ADRI), and risks selected by the Lancet Commission on Dementia. The Dunedin benchmark was comprised of 48 separate indicators of risk organized into 10 conceptually distinct risk domains. Midlife antecedents of ADRD treated as outcome measures included age-45 measures of brain structural integrity [magnetic resonance imaging-assessed: (i) machine-learning-algorithm-estimated brain age, (ii) log-transformed volume of white matter hyperintensities, and (iii) mean grey matter volume of the hippocampus] and measures of brain functional integrity [(i) objective cognitive function assessed via the Wechsler Adult Intelligence Scale-IV, (ii) subjective problems in everyday cognitive function, and (iii) objective cognitive decline measured as residualized change in cognitive scores from childhood to midlife on matched Weschler Intelligence scales]. All indexes were quantitatively distributed and proved informative about midlife antecedents of ADRD, including algorithm-estimated brain age (β's from 0.16 to 0.22), white matter hyperintensities volume (β's from 0.16 to 0.19), hippocampal volume (β's from -0.08 to -0.11), tested cognitive deficits (β's from -0.36 to -0.49), everyday cognitive problems (β's from 0.14 to 0.38), and longitudinal cognitive decline (β's from -0.18 to -0.26). Existing indexes compared favourably to the comprehensive benchmark in their association with the brain structural integrity measures but were outperformed in their association with the functional integrity measures, particularly subjective cognitive problems and tested cognitive decline. Results indicated that existing indexes could be improved with targeted additions, particularly of measures assessing socioeconomic status, physical and sensory function, epigenetic aging, and subjective overall health. Existing premorbid ADRD risk indexes perform well in identifying linear gradients of risk among members of the general population at midlife, even when they include only a small subset of potential risk factors. They could be improved, however, with targeted additions to more holistically capture the different facets of risk for this multiply determined, age-related disease.

Alzheimer’s disease↗

PubMed2004

Predicting thermal displacements in modular tool systems.

In the last decade, there has been an increasing interest in compensating thermally induced errors to improve the manufacturing accuracy of modular tool systems. These modular tool systems are interfaces between spindle and workpiece and consist of several complicatedly formed parts. Their thermal behavior is dominated by nonlinearities, delay and hysteresis effects even in tools with simpler geometry and it is difficult to describe it theoretically. Due to the dominant nonlinear nature of this behavior the so far used linear regression between the temperatures and the displacements is insufficient. Therefore, in this study we test the hypothesis whether we can reliably predict such thermal displacements via nonlinear temperature-displacement regression functions. These functions are estimated first from learning measurements using the alternating conditional expectation (ACE) algorithm and then tested on independent data sets. First, we analyze data that were generated by a finite element spindle model. We find that our approach is a powerful tool to describe the relation between temperatures and displacements for simulated data. Next, we analyze the temperature-displacement relationship in a silent real experimental setup, where the tool system is thermally forced. Again, the ACE algorithm is powerful to estimate the deformation with high precision. The corresponding errors obtained by using the nonlinear regression approach are 10-fold lower in comparison to multiple linear regression analysis. Finally, we investigate the thermal behavior of a modular tool system in a working milling machine and again get promising results. The thermally induced errors can be estimated with 1-2 microm accuracy using this nonlinear regression analysis. Therefore, this approach seems to be very useful for the development of new modular tool systems.

Computer Simulation↗

PubMed2005

RASE: recognition of alternatively spliced exons in C.elegans.

MOTIVATION: Eukaryotic pre-mRNAs are spliced to form mature mRNA. Pre-mRNA alternative splicing greatly increases the complexity of gene expression. Estimates show that more than half of the human genes and at least one-third of the genes of less complex organisms, such as nematodes or flies, are alternatively spliced. In this work, we consider one major form of alternative splicing, namely the exclusion of exons from the transcript. It has been shown that alternatively spliced exons have certain properties that distinguish them from constitutively spliced exons. Although most recent computational studies on alternative splicing apply only to exons which are conserved among two species, our method only uses information that is available to the splicing machinery, i.e. the DNA sequence itself. We employ advanced machine learning techniques in order to answer the following two questions: (1) Is a certain exon alternatively spliced? (2) How can we identify yet unidentified exons within known introns? RESULTS: We designed a support vector machine (SVM) kernel well suited for the task of classifying sequences with motifs having positional preferences. In order to solve the task (1), we combine the kernel with additional local sequence information, such as lengths of the exon and the flanking introns. The resulting SVM-based classifier achieves a true positive rate of 48.5% at a false positive rate of 1%. By scanning over single EST confirmed exons we identified 215 potential alternatively spliced exons. For 10 randomly selected such exons we successfully performed biological verification experiments and confirmed three novel alternatively spliced exons. To answer question (2), we additionally used SVM-based predictions to recognize acceptor and donor splice sites. Combined with the above mentioned features we were able to identify 85.2% of skipped exons within known introns at a false positive rate of 1%. AVAILABILITY: Datasets, model selection results, our predictions and additional experimental results are available at http://www.fml.tuebingen.mpg.de/~raetsch/RASE SUPPLEMENTARY INFORMATION: http://www.fml.tuebingen.mpg.de/raetsch/RASE.

Algorithms↗

PubMed2002

Feature subset selection for splice site prediction.

MOTIVATION: The large amount of available annotated Arabidopsis thaliana sequences allows the induction of splice site prediction models with supervised learning algorithms (see Haussler (1998) for a review and references). These algorithms need information sources or features from which the models can be computed. For splice site prediction, the features we consider in this study are the presence or absence of certain nucleotides in close proximity to the splice site. Since it is not known how many and which nucleotides are relevant for splice site prediction, the set of features is chosen large enough such that the probability that all relevant information sources are in the set is very high. Using only those features that are relevant for constructing a splice site prediction system might improve the system and might also provide us with useful biological knowledge. Using fewer features will of course also improve the prediction speed of the system. RESULTS: A wrapper-based feature subset selection algorithm using a support vector machine or a naive Bayes prediction method was evaluated against the traditional method for selecting features relevant for splice site prediction. Our results show that this wrapper approach selects features that improve the performance against the use of all features and against the use of the features selected by the traditional method. AVAILABILITY: The data and additional interactive graphs on the selected feature subsets are available at http://www.psb.rug.ac.be/gps

Arabidopsis↗