Ensemble approach combining multiple methods improves human transcription start site prediction.
Ontology highlight
ABSTRACT: Background
The computational prediction of transcription start sites is an important unsolved problem. Some recent progress has been made, but many promoters, particularly those not associated with CpG islands, are still difficult to locate using current methods. These methods use different features and training sets, along with a variety of machine learning techniques and result in different prediction sets.Results
We demonstrate the heterogeneity of current prediction sets, and take advantage of this heterogeneity to construct a two-level classifier ('Profisi Ensemble') using predictions from 7 programs, along with 2 other data sources. Support vector machines using 'full' and 'reduced' data sets are combined in an either/or approach. We achieve a 14% increase in performance over the current state-of-the-art, as benchmarked by a third-party tool.Conclusions
Supervised learning methods are a useful way to combine predictions from diverse sources.
SUBMITTER: Dineen DG
PROVIDER: S-EPMC3053590 | biostudies-literature | 2010 Nov
REPOSITORIES: biostudies-literature
Publications
Ensemble approach combining multiple methods improves human transcription start site prediction.
Dineen David G DG Schröder Markus M Higgins Desmond G DG Cunningham Pádraig P
BMC genomics 20101130
<h4>Background</h4>The computational prediction of transcription start sites is an important unsolved problem. Some recent progress has been made, but many promoters, particularly those not associated with CpG islands, are still difficult to locate using current methods. These methods use different features and training sets, along with a variety of machine learning techniques and result in different prediction sets.<h4>Results</h4>We demonstrate the heterogeneity of current prediction sets, and ...[more]
Similar Datasets
Project description:With the growing number of completely sequenced bacterial genes, accurate gene prediction in bacterial genomes remains an important problem. Although the existing tools predict genes in bacterial genomes with high overall accuracy, their ability to pinpoint the translation start site remains unsatisfactory. In this paper, we present a novel approach to bacterial start site prediction that takes into account multiple features of a potential start site, viz., ribosome binding site (RBS) binding energy, distance of the RBS from the start codon, distance from the beginning of the maximal ORF to the start codon, the start codon itself and the coding/non-coding potential around the start site. Mixed integer programing was used to optimize the discriminatory system. The accuracy of this approach is up to 90%, compared to 70%, using the most common tools in fully automated mode (that is, without expert human post-processing of results). The approach is evaluated using Bacillus subtilis, Escherichia coli and Pyrococcus furiosus. These three genomes cover a broad spectrum of bacterial genomes, since B.subtilis is a Gram-positive bacterium, E.coli is a Gram-negative bacterium and P. furiosus is an archaebacterium. A significant problem is generating a set of 'true' start sites for algorithm training, in the absence of experimental work. We found that sequence conservation between P. furiosus and the related Pyrococcus horikoshii clearly delimited the gene start in many cases, providing a sufficient training set.
| S-EPMC148603 | biostudies-other
Project description:Predicting the location of functionally important sites from protein sequence and/or structure is a long-standing problem in computational biology. Most current approaches make use of sequence conservation, assuming that amino acid residues conserved within a protein family are most likely to be functionally important. Most often these approaches do not consider many residues that act to define specific sub-functions within a family, or they make no distinction between residues important for function and those more relevant for maintaining structure (e.g. in the hydrophobic core). Many protein families bind and/or act on a variety of ligands, meaning that conserved residues often only bind a common ligand sub-structure or perform general catalytic activities.Here we present a novel method for functional site prediction based on identification of conserved positions, as well as those responsible for determining ligand specificity. We define Specificity-Determining Positions (SDPs), as those occupied by conserved residues within sub-groups of proteins in a family having a common specificity, but differ between groups, and are thus likely to account for specific recognition events. We benchmark the approach on enzyme families of known 3D structure with bound substrates, and find that in nearly all families residues predicted by SDPsite are in contact with the bound substrate, and that the addition of SDPs significantly improves functional site prediction accuracy. We apply SDPsite to various families of proteins containing known three-dimensional structures, but lacking clear functional annotations, and discusse several illustrative examples.The results suggest a better means to predict functional details for the thousands of protein structures determined prior to a clear understanding of molecular function.
| S-EPMC2709924 | biostudies-literature
Project description:The accurate identification of promoter regions and transcription start sites is a challenge to the construction of human transcription regulation networks. Thus, an efficient prediction method based on theoretical formulation is necessary for this purpose. We used the method of increment diversity with quadratic discriminant analysis (IDQD) to predict transcription start sites (TSS). The method produced sensitivity and positive predictive value of more than 65% with positives to negatives ratio of 1:58. The performance evaluation using Receiver Operator Characteristics (ROC) showed an auROC (area under ROC) of greater than 96%. The evaluation by Precision Recall Curves (PRC) showed an auPRC (area under PRC) of about 26% for positives to negatives ratio of 1:679 and about 64% for positives to negatives ratio of 1:113. The results documented in this approach are either better or comparable to other known methods.
| S-EPMC2374378 | biostudies-literature
Project description:One of the fundamental processes that determine cellular fate is regulation of gene transcription. Understanding these regulatory processes is therefore essential for understanding cellular responses to changes in environmental conditions. At the core promoter, the regulatory region containing the transcription start site (TSS), all inputs regulating transcription are integrated. Here, we used Cap Analysis of Gene Expression (CAGE) to analyze the pattern of TSSs at four different environmental conditions (limited in ethanol, limited in nitrogen, limited in glucose and limited in glucose under anaerobic conditions) using the Saccharomyces cerevisiae strain CEN.PK113-7D. With this experimental setup, we were able to show that the TSS landscape in yeast is stable at different metabolic states of the cell. We also show that the spatial distribution of transcription initiation events, described by the shape index, has a surprisingly strong negative correlation with measured gene expression levels, meaning that genes with higher expression levels tend to have a broader distribution of TSSs. Our analysis supplies a set of high-quality TSS annotations useful for metabolic engineering and synthetic biology approaches in the industrially relevant laboratory strain CEN.PK113-7D, and provides novel insights into yeast TSS dynamics and gene regulation.
| S-EPMC7612425 | biostudies-literature
Project description:The transcriptional activity of Transposable Elements (TEs) has been involved in numerous pathological processes, including neurodegenerative diseases such as amyotrophic lateral sclerosis and frontotemporal lobar degeneration. The TE expression analysis from short-read sequencing technologies is, however, challenging due to the multitude of similar sequences derived from singular TEs subfamilies and the exaptation of TEs within longer coding or non-coding RNAs. Specialised tools have been developed to quantify the expression of TEs that either relies on probabilistic re-distribution of multimapper count fractions or allow for discarding multimappers altogether. Until now, the benchmarking across those tools was largely limited to aggregated expression estimates over whole TEs subfamilies. Here, we compared the performance of recently published tools (SQuIRE, TElocal, SalmonTE) with simplistic quantification strategies (featureCounts in unique, fraction and random modes) at the individual loci level. Using simulated datasets, we examined the false discovery rate and the primary driver of those false positive hits in the optimal quantification strategy. Our findings suggest a high false discovery number that exceeds the total number of correctly recovered active loci for all the quantification strategies, including the best performing tool TElocal. As a remedy, filtering based on the minimum number of read counts or baseMean expression improves the F1 score and decreases the number of false positives. Finally, we demonstrate that additional profiling of Transcription Start Site mapping statistics (using a k-means clustering approach) significantly improves the performance of TElocal while reporting a reliable set of detected and differentially expressed TEs in human simulated RNA-seq data.
| S-EPMC9633680 | biostudies-literature
Project description:Transcription start site (TSS) evolution remains largely undescribed in Drosophila, likely due to limited annotations in non-melanogaster species. In this study, we introduce a concise new method that selectively sequences from the 5'-end of mRNA and used it to identify TSS in four Drosophila species, including Drosophila melanogaster, D. simulans, D. sechellia, and D. pseudoobscura. For verification, we compared our results in D. melanogaster with known annotations, published 5'-rapid amplification of cDNA ends data, and with RNAseq from the same mRNA pool. Then, we paired 2,849 D. melanogaster TSS with its closest equivalent TSS in each species (likely to be its true ortholog) using the available multiple sequence alignments. Most of the D. melanogaster TSSs were successfully paired with an ortholog in each species (83%, 86%, and 55% for D. simulans, D. sechellia, and D. pseudoobscura, respectively). On the basis of the number and distribution of reads mapped at each TSS, we also estimated promoter-specific expression (PSE) and TSS peak shape, respectively. Among paired TSS orthologs, the location and promoter activity were largely conserved. TSS location appears important as PSE, and TSS peak shape was more frequently divergent among TSS that had moved. Unpaired TSS were surprisingly common in D. pseudoobscura. An increased mutation rate upstream of TSS might explain this pattern. We found an enrichment of ribosomal protein genes among diverged TSS, suggesting that TSS evolution is not uniform across the genome.
| S-EPMC3708499 | biostudies-literature
Project description:Here, we report the genome-wide identification of small RNAs associated with transcription start sites (TSSs), termed tssRNAs, in Mycoplasma pneumoniae. tssRNAs were also found to be present in a different bacterial phyla, Escherichia coli. Similar to the recently identified promoter-associated tiny RNAs (tiRNAs) in eukaryotes, tssRNAs are associated with active promoters. Evidence suggests that these tssRNAs are distinct from previously described abortive transcription RNAs. ssRNAs have an average size of 45 bases and map exactly to the beginning of cognate full-length transcripts and to cryptic TSSs. Expression of bacterial tssRNAs requires factors other than the standard RNA polymerase holoenzyme. We have found that the RNA polymerase is halted at tssRNA positions in vivo, which may indicate that a pausing mechanism exists to prevent transcription in the absence of genes. These results suggest that small RNAs associated with TSSs could be a universal feature of bacterial transcription.
| S-EPMC3377991 | biostudies-literature
Project description:Genome-wide, high-throughput methods for transcription start site (TSS) detection have shown that most promoters have an array of neighboring TSSs where some are used more than others, forming a distribution of initiation propensities. TSS distributions (TSSDs) vary widely between promoters and earlier studies have shown that the TSSDs have biological implications in both regulation and function. However, no systematic study has been made to explore how many types of TSSDs and by extension core promoters exist and to understand which biological features distinguish them. In this study, we developed a new non-parametric dissimilarity measure and clustering approach to explore the similarities and stabilities of clusters of TSSDs. Previous studies have used arbitrary thresholds to arrive at two general classes: broad and sharp. We demonstrated that in addition to the previous broad/sharp dichotomy an additional category of promoters exists. Unlike typical TATA-driven sharp TSSDs where the TSS position can vary a few nucleotides, in this category virtually all TSSs originate from the same genomic position. These promoters lack epigenetic signatures of typical mRNA promoters and a substantial subset of them are mapping upstream of ribosomal protein pseudogenes. We present evidence that these are likely mapping errors, which have confounded earlier analyses, due to the high similarity of ribosomal gene promoters in combination with known G addition bias in the CAGE libraries. Thus, previous two-class separations of promoter based on TSS distributions are motivated, but the ultra-sharp TSS distributions will confound downstream analyses if not removed.
| S-EPMC3160847 | biostudies-literature
Project description:BACKGROUND:The elucidation of mammalian transcriptional regulatory networks holds great promise for both basic and translational research and remains one the greatest challenges to systems biology. Recent reverse engineering methods deduce regulatory interactions from large-scale mRNA expression profiles and cross-species conserved regulatory regions in DNA. Technical challenges faced by these methods include distinguishing between direct and indirect interactions, associating transcription regulators with predicted transcription factor binding sites (TFBSs), identifying non-linearly conserved binding sites across species, and providing realistic accuracy estimates. METHODOLOGY/PRINCIPAL FINDINGS:We address these challenges by closely integrating proven methods for regulatory network reverse engineering from mRNA expression data, linearly and non-linearly conserved regulatory region discovery, and TFBS evaluation and discovery. Using an extensive test set of high-likelihood interactions, which we collected in order to provide realistic prediction-accuracy estimates, we show that a careful integration of these methods leads to significant improvements in prediction accuracy. To verify our methods, we biochemically validated TFBS predictions made for both transcription factors (TFs) and co-factors; we validated binding site predictions made using a known E2F1 DNA-binding motif on E2F1 predicted promoter targets, known E2F1 and JUND motifs on JUND predicted promoter targets, and a de novo discovered motif for BCL6 on BCL6 predicted promoter targets. Finally, to demonstrate accuracy of prediction using an external dataset, we showed that sites matching predicted motifs for ZNF263 are significantly enriched in recent ZNF263 ChIP-seq data. CONCLUSIONS/SIGNIFICANCE:Using an integrative framework, we were able to address technical challenges faced by state of the art network reverse engineering methods, leading to significant improvement in direct-interaction detection and TFBS-discovery accuracy. We estimated the accuracy of our framework on a human B-cell specific test set, which may help guide future methodological development.
| S-EPMC2845628 | biostudies-literature
Project description:More than half of Caenorhabditis elegans pre-mRNAs lose their original 5' ends in a process termed "trans-splicing" in which the RNA extending from the transcription start site (TSS) to the site of trans-splicing of the primary transcript, termed the "outron," is replaced with a 22-nt spliced leader. This complicates the mapping of TSSs, leading to a lack of available TSS mapping data for these genes. We used growth at low temperature and nuclear isolation to enrich for transcripts still containing outrons, applying a modified SAGE capture procedure and high-throughput sequencing to characterize 5' termini in this transcript population. We report from this data both a landscape of 5'-end utilization for C. elegans and a representative collection of TSSs for 7351 trans-spliced genes. TSS distributions for individual genes were often dispersed, with a greater average number of TSSs for trans-spliced genes, suggesting that trans-splicing may remove selective pressure for a single TSS. Upstream of newly defined TSSs, we observed well-known motifs (including TATAA-box and SP1) as well as novel motifs. Several of these motifs showed association with tissue-specific expression and/or conservation among six worm species. Comparing TSS features between trans-spliced and non-trans-spliced genes, we found stronger signals among outron TSSs for preferentially positioning of flanking nucleosomes and for downstream Pol II enrichment. Our data provide an enabling resource for both experimental and theoretical analysis of gene structure and function in C. elegans.
| S-EPMC3730108 | biostudies-literature