DeepRibo: precise gene annotation of prokaryotes using deep learning and ribosome profiling data

Clauwaert, Jim; Menschaert, Gerben; Waegeman, Willem

doi:10.1101/317180

Cited by 2 publications

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, overall this supports the result that 20 million reads are sufficient to detect most of the annotated genes in RIBO-seq experiments. Extensive further work on this question is however required, with recent improvements in gene prediction from RIBO-seq data [58][59][60] and many studies on previously unrecognised small proteins to take into consideration [16,30,57,61,62].…”

Section: Potential Influence Of Chloramphenicol On Read Lengthmentioning

confidence: 99%

Improving Bacterial Ribosome Profiling Data Quality

Glaub

Huptas

Neuhaus

et al. 2019

Preprint

View full text Add to dashboard Cite

Ribosome profiling (RIBO-seq) in prokaryotes has the potential to facilitate accurate detection of translation initiation sites, to increase understanding of translational dynamics, and has already allowed detection of many unannotated genes. However, protocols for ribosome profiling and corresponding data analysis are not yet standardized. To better understand the influencing factors, we analysed 48 ribosome profiling samples from 9 studies on E. coli K12 grown in LB medium. We particularly investigated the size selection step in each experiment since the selection for ribosome-protected footprints (RPFs) has been performed at various read lengths. We suggest choosing a size range between 22-30 nucleotides in order to obtain protein-coding fragments. In order to use RIBO-seq data for improving gene annotation of weakly expressed genes, the total amount of reads mapping to protein-coding sequences and not rRNA or tRNA is important, but no consensus about the appropriate sequencing depth has been reached. Again, this causes significant variation between studies. Our analysis suggests that 20 million non rRNA/tRNA mapping reads are required for global detection of translated annotated genes. Further, we highlight the influence of drug induced ribosome stalling, causing bias at translation start sites. Drug induced stalling may be especially useful for detecting weakly expressed genes. These suggestions should improve both gene detection and the comparability of resulting ribosome profiling datasets.

show abstract

Section: Potential Influence Of Chloramphenicol On Read Lengthmentioning

confidence: 99%

Improving Bacterial Ribosome Profiling Data Quality

Glaub

Huptas

Neuhaus

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

RiboReport - Benchmarking tools for ribosome profiling-based identification of open reading frames in bacteria

Gelhausen

Müller

Svensson

et al. 2021

Preprint

View full text Add to dashboard Cite

Small proteins, those encoded by open reading frames, with less than or equal to 50 codons, are emerging as an important class of cellular macromolecules in all kingdoms of life. However, they are recalcitrant to detection by proteomics or in silico methods. Ribosome profiling (Ribo-seq) has revealed widespread translation of sORFs in diverse species, and this has driven the development of ORF detection tools using Ribo-seq read signals. However, only a handful of tools have been designed for bacterial data, and have not yet been systematically compared. Here, we have performed a comprehensive benchmark of ORF prediction tools which handle bacterial Ribo-seq data. For this, we created a novel Ribo-seq dataset for E. coli, and based on this plus three publicly available datasets for different bacteria, we created a benchmark set by manual labeling of translated ORFs using their Ribo-seq expression profile. This was then used to investigate the predictive performance of four Ribo-seq-based ORF detection tools we found are compatible with bacterial data (REPARATION_blast, DeepRibo, Ribo-TISH and SPECtre). The tool IRSOM was also included as a comparison for tools using coding potential and RNA-seq coverage only. DeepRibo and REPARATION_blast robustly predicted translated ORFs, including sORFs, with no significant difference for those inside or outside of operons. However, none of the tools was able to predict a set of recently identified, novel, experimentally-verified sORFs with high sensitivity. Overall, we find there is potential for improving the performance, applicability, usability, and reproducibility of prokaryotic ORF prediction tools that use Ribo-Seq as input.

show abstract

DeepRibo: precise gene annotation of prokaryotes using deep learning and ribosome profiling data

Cited by 2 publications

References 45 publications

Improving Bacterial Ribosome Profiling Data Quality

Improving Bacterial Ribosome Profiling Data Quality

RiboReport - Benchmarking tools for ribosome profiling-based identification of open reading frames in bacteria

Contact Info

Product

Resources

About