Lars Gabriel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lars Gabriel has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Mario Stanke
Universität Greifswald, Institut für Mathematik und Informatik
5 shared publications - Katharina Jasmin Hoff
Institute of Mathematics and Computer Science, University of Greifswald, Greifswald, Germany
4 shared publications - Felix Becker
Universität Greifswald, Institut für Mathematik und Informatik
2 shared publications - Tomáš Brůna
U.S. Department of Energy Joint Genome Institute, Berkeley, CA USA
2 shared publications - Anish Krishnan
Department of Plant and Microbial Biology, University of California Berkeley, Berkeley, CA 94720, USA
1 shared publication - Asaf Salamov
U.S. Department of Energy Joint Genome Institute, Lawrence Berkeley National Laboratory, Berkeley, USA
1 shared publication
Latest Publications
- Open Access
Accurate ab initio gene prediction in eukaryotes with Tiberius in multiple clades
Eukaryotic genome annotation is currently bottlenecked by limitations in the generality, scalability and accuracy of computational methods. Deep learning approaches have recently achieved large improvements in ab initio gene prediction accuracy. We extend the deep learning-based ab initio gene predictor Tiberius beyond mammals by training lineage-specific models for Mesangiospermae, Fungi, Vertebrata, Insecta, Chlorophyta and Bacillariophyta. Across a benchmark of 33 species, Tiberius consistently achieves higher accuracy than the other evaluated ab initio methods, Helixer and ANNEVO, while also having the fastest runtimes overall. Compared with BRAKER3, which incorporates RNA-Seq and protein evidence, Tiberius approaches state-of-the-art accuracy in Mesangiospermae, Fungi, Bacillariophyta and Chlorophyta, while being on average 80 times faster when using a GPU. Availability and implementation: https://github.com/Gaius-Augustus/Tiberius
Open AccessAccurate ab initio gene prediction in eukaryotes with Tiberius in multiple clades
Eukaryotic genome annotation is currently bottlenecked by limitations in the generality, scalability and accuracy of computational methods. Deep learning approaches have recently achieved large improvements in ab initio gene prediction accuracy. We extend the deep learning-based ab initio gene predictor Tiberius beyond mammals by training lineage-specific models for Mesangiospermae, Fungi, Vertebrata, Insecta, Chlorophyta and Bacillariophyta. Across a benchmark of 33 species, Tiberius consistently achieves higher accuracy than the other evaluated ab initio methods, Helixer and ANNEVO, while also having the fastest runtimes overall. Compared with BRAKER3, which incorporates RNA-Seq and protein evidence, Tiberius approaches state-of-the-art accuracy in Mesangiospermae, Fungi, Bacillariophyta and Chlorophyta, while being on average 80 times faster when using a GPU. Availability and implementation: https://github.com/Gaius-Augustus/Tiberius
- Open Access
- 18 November 2024
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 40 (12)
Tiberius: end-to-end deep learning with an HMM for gene prediction
For more than 25 years, learning-based eukaryotic gene predictors were driven by hidden Markov models (HMMs), which were directly inputted a DNA sequence. Recently, Holst et al. demonstrated with their program Helixer that the accuracy of ab initio eukaryotic gene prediction can be improved by combining deep learning layers with a separate HMM postprocessor. We present Tiberius, a novel deep learning-based ab initio gene predictor that end-to-end integrates convolutional and long short-term memory layers with a differentiable HMM layer. Tiberius uses a custom gene prediction loss and was trained for prediction in mammalian genomes and evaluated on human and two other genomes. It significantly outperforms existing ab initio methods, achieving F1-scores of 62% at gene level for the human genome, compared to 21% for the next best ab initio method. In de novo mode, Tiberius predicts the exon-intron structure of two out of three human genes without error. Remarkably, even Tiberius’s ab initio accuracy matches that of BRAKER3, which uses RNA-seq data and a protein database. Tiberius’s highly parallelized model is the fastest state-of-the-art gene prediction method, processing the human genome in under 2 hours. https://github.com/Gaius-Augustus/Tiberius
- 18 November 2024
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 40 (12)
Open AccessTiberius: end-to-end deep learning with an HMM for gene prediction
For more than 25 years, learning-based eukaryotic gene predictors were driven by hidden Markov models (HMMs), which were directly inputted a DNA sequence. Recently, Holst et al. demonstrated with their program Helixer that the accuracy of ab initio eukaryotic gene prediction can be improved by combining deep learning layers with a separate HMM postprocessor. We present Tiberius, a novel deep learning-based ab initio gene predictor that end-to-end integrates convolutional and long short-term memory layers with a differentiable HMM layer. Tiberius uses a custom gene prediction loss and was trained for prediction in mammalian genomes and evaluated on human and two other genomes. It significantly outperforms existing ab initio methods, achieving F1-scores of 62% at gene level for the human genome, compared to 21% for the next best ab initio method. In de novo mode, Tiberius predicts the exon-intron structure of two out of three human genes without error. Remarkably, even Tiberius’s ab initio accuracy matches that of BRAKER3, which uses RNA-seq data and a protein database. Tiberius’s highly parallelized model is the fastest state-of-the-art gene prediction method, processing the human genome in under 2 hours. https://github.com/Gaius-Augustus/Tiberius
- Open Access
Tiberius: End-to-End Deep Learning with an HMM for Gene Prediction
Motivation: For more than 25 years, learning-based eukaryotic gene predictors were driven by hidden Markov models (HMMs), which were directly inputted a DNA sequence. Recently, Holst et al. demonstrated with their program Helixer that the accuracy of ab initio eukaryotic gene prediction can be improved by combining deep learning layers with a separate HMM postprocessor. Results: We present Tiberius, a novel deep learning-based ab initio gene predictor that end-to-end integrates convolutional and long short-term memory layers with a differentiable HMM layer. Tiberius uses a custom gene prediction loss and was trained for prediction in mammalian genomes and evaluated on human and two other genomes. It significantly outperforms existing ab initio methods, achieving F1-scores of 62% at gene level for the human genome, compared to 21% for the next best ab initio method. In de novo mode, Tiberius predicts the exon-intron structure of two out of three human genes without error. Remarkably, even Tiberius’s ab initio accuracy matches that of BRAKER3, which uses RNA-seq data and a protein database. Tiberius’s highly parallelized model is the fastest state-of-the-art gene prediction method, processing the human genome in under 2 hours. Availability and Implementation: https://github.com/Gaius-Augustus/Tiberius Contact: { lars.gabriel@uni-greifswald.de , mario.stanke@uni-greifswald.de }
Open AccessTiberius: End-to-End Deep Learning with an HMM for Gene Prediction
Motivation: For more than 25 years, learning-based eukaryotic gene predictors were driven by hidden Markov models (HMMs), which were directly inputted a DNA sequence. Recently, Holst et al. demonstrated with their program Helixer that the accuracy of ab initio eukaryotic gene prediction can be improved by combining deep learning layers with a separate HMM postprocessor. Results: We present Tiberius, a novel deep learning-based ab initio gene predictor that end-to-end integrates convolutional and long short-term memory layers with a differentiable HMM layer. Tiberius uses a custom gene prediction loss and was trained for prediction in mammalian genomes and evaluated on human and two other genomes. It significantly outperforms existing ab initio methods, achieving F1-scores of 62% at gene level for the human genome, compared to 21% for the next best ab initio method. In de novo mode, Tiberius predicts the exon-intron structure of two out of three human genes without error. Remarkably, even Tiberius’s ab initio accuracy matches that of BRAKER3, which uses RNA-seq data and a protein database. Tiberius’s highly parallelized model is the fastest state-of-the-art gene prediction method, processing the human genome in under 2 hours. Availability and Implementation: https://github.com/Gaius-Augustus/Tiberius Contact: { lars.gabriel@uni-greifswald.de , mario.stanke@uni-greifswald.de }
- Open Access
- 20 September 2023
- Published by Oxford University Press (OUP) in Journal of Heredity
- Vol. 115 (1) , 86-93
A reference genome for ecological restoration of the sunflower sea star, Pycnopodia helianthoides
Wildlife diseases, such as the sea star wasting (SSW) epizootic that outbroke in the mid-2010s, appear to be associated with acute and/or chronic abiotic environmental change; dissociating the effects of different drivers can be difficult. The sunflower sea star, Pycnopodia helianthoides, was the species most severely impacted during the SSW outbreak, which overlapped with periods of anomalous atmospheric and oceanographic conditions, and there is not yet a consensus on the cause(s). Genomic data may reveal underlying molecular signatures that implicate a subset of factors and, thus, clarify past events while also setting the scene for effective restoration efforts. To advance this goal, we used Pacific Biosciences HiFi long sequencing reads and Dovetail Omni-C proximity reads to generate a highly contiguous genome assembly that was then annotated using RNA-seq informed gene prediction. The genome assembly is 484 Mb long, with contig N50 of 1.9 Mb, scaffold N50 of 21.8 Mb, BUSCO completeness score 96.1%, and 22 major scaffolds consistent with prior evidence that sea star genomes comprise 22 autosomes. These statistics generally fall between those of other recently assembled chromosome-scale assemblies for two species in the distantly related asteroid genus Pisaster. These novel genomic resources for Pycnopodia helianthoides will underwrite population genomic, comparative genomic, and phylogenomic analyses — as well as their integration across scales — of SSW and environmental stressors.
- 20 September 2023
- Published by Oxford University Press (OUP) in Journal of Heredity
- Vol. 115 (1) , 86-93
Open AccessA reference genome for ecological restoration of the sunflower sea star, Pycnopodia helianthoides
Wildlife diseases, such as the sea star wasting (SSW) epizootic that outbroke in the mid-2010s, appear to be associated with acute and/or chronic abiotic environmental change; dissociating the effects of different drivers can be difficult. The sunflower sea star, Pycnopodia helianthoides, was the species most severely impacted during the SSW outbreak, which overlapped with periods of anomalous atmospheric and oceanographic conditions, and there is not yet a consensus on the cause(s). Genomic data may reveal underlying molecular signatures that implicate a subset of factors and, thus, clarify past events while also setting the scene for effective restoration efforts. To advance this goal, we used Pacific Biosciences HiFi long sequencing reads and Dovetail Omni-C proximity reads to generate a highly contiguous genome assembly that was then annotated using RNA-seq informed gene prediction. The genome assembly is 484 Mb long, with contig N50 of 1.9 Mb, scaffold N50 of 21.8 Mb, BUSCO completeness score 96.1%, and 22 major scaffolds consistent with prior evidence that sea star genomes comprise 22 autosomes. These statistics generally fall between those of other recently assembled chromosome-scale assemblies for two species in the distantly related asteroid genus Pisaster. These novel genomic resources for Pycnopodia helianthoides will underwrite population genomic, comparative genomic, and phylogenomic analyses — as well as their integration across scales — of SSW and environmental stressors.
- Open Access
- 31 August 2023
- Published by Springer Nature in BMC Bioinformatics
- Vol. 24 (1) , 1-21
Galba: genome annotation with miniprot and AUGUSTUS
Background: The Earth Biogenome Project has rapidly increased the number of available eukaryotic genomes, but most released genomes continue to lack annotation of protein-coding genes. In addition, no transcriptome data is available for some genomes. Results: Various gene annotation tools have been developed but each has its limitations. Here, we introduce GALBA, a fully automated pipeline that utilizes miniprot, a rapid protein-to-genome aligner, in combination with AUGUSTUS to predict genes with high accuracy. Accuracy results indicate that GALBA is particularly strong in the annotation of large vertebrate genomes. We also present use cases in insects, vertebrates, and a land plant. GALBA is fully open source and available as a docker image for easy execution with Singularity in high-performance computing environments. Conclusions: Our pipeline addresses the critical need for accurate gene annotation in newly sequenced genomes, and we believe that GALBA will greatly facilitate genome annotation for diverse organisms.
- 31 August 2023
- Published by Springer Nature in BMC Bioinformatics
- Vol. 24 (1) , 1-21
Open AccessGalba: genome annotation with miniprot and AUGUSTUS
Background: The Earth Biogenome Project has rapidly increased the number of available eukaryotic genomes, but most released genomes continue to lack annotation of protein-coding genes. In addition, no transcriptome data is available for some genomes. Results: Various gene annotation tools have been developed but each has its limitations. Here, we introduce GALBA, a fully automated pipeline that utilizes miniprot, a rapid protein-to-genome aligner, in combination with AUGUSTUS to predict genes with high accuracy. Accuracy results indicate that GALBA is particularly strong in the annotation of large vertebrate genomes. We also present use cases in insects, vertebrates, and a land plant. GALBA is fully open source and available as a docker image for easy execution with Singularity in high-performance computing environments. Conclusions: Our pipeline addresses the critical need for accurate gene annotation in newly sequenced genomes, and we believe that GALBA will greatly facilitate genome annotation for diverse organisms.
- Top Cited PapersOpen Access
- 25 November 2021
- Published by Springer Nature in BMC Bioinformatics
- Vol. 22 (1) , 1-12
TSEBRA: transcript selector for BRAKER
Background: BRAKER is a suite of automatic pipelines, BRAKER1 and BRAKER2, for the accurate annotation of protein-coding genes in eukaryotic genomes. Each pipeline trains statistical models of protein-coding genes based on provided evidence and, then predicts protein-coding genes in genomic sequences using both the extrinsic evidence and statistical models. For training and prediction, BRAKER1 and BRAKER2 incorporate complementary extrinsic evidence: BRAKER1 uses only RNA-seq data while BRAKER2 uses only a database of cross-species proteins. The BRAKER suite has so far not been able to reliably exceed the accuracy of BRAKER1 and BRAKER2 when incorporating both types of evidence simultaneously. Currently, for a novel genome project where both RNA-seq and protein data are available, the best option is to run both pipelines independently, and to pick one, likely better output. Therefore, one or another type of the extrinsic evidence would remain unexploited. Results: We present TSEBRA, a software that selects gene predictions (transcripts) from the sets generated by BRAKER1 and BRAKER2. TSEBRA uses a set of rules to compare scores of overlapping transcripts based on their support by RNA-seq and homologous protein evidence. We show in computational experiments on genomes of 11 species that TSEBRA achieves higher accuracy than either BRAKER1 or BRAKER2 running alone and that TSEBRA compares favorably with the combiner tool EVidenceModeler. Conclusion: TSEBRA is an easy-to-use and fast software tool. It can be used in concert with the BRAKER pipeline to generate a gene prediction set supported by both RNA-seq and homologous protein evidence.
- 25 November 2021
- Published by Springer Nature in BMC Bioinformatics
- Vol. 22 (1) , 1-12
Top Cited PapersOpen AccessTSEBRA: transcript selector for BRAKER
Background: BRAKER is a suite of automatic pipelines, BRAKER1 and BRAKER2, for the accurate annotation of protein-coding genes in eukaryotic genomes. Each pipeline trains statistical models of protein-coding genes based on provided evidence and, then predicts protein-coding genes in genomic sequences using both the extrinsic evidence and statistical models. For training and prediction, BRAKER1 and BRAKER2 incorporate complementary extrinsic evidence: BRAKER1 uses only RNA-seq data while BRAKER2 uses only a database of cross-species proteins. The BRAKER suite has so far not been able to reliably exceed the accuracy of BRAKER1 and BRAKER2 when incorporating both types of evidence simultaneously. Currently, for a novel genome project where both RNA-seq and protein data are available, the best option is to run both pipelines independently, and to pick one, likely better output. Therefore, one or another type of the extrinsic evidence would remain unexploited. Results: We present TSEBRA, a software that selects gene predictions (transcripts) from the sets generated by BRAKER1 and BRAKER2. TSEBRA uses a set of rules to compare scores of overlapping transcripts based on their support by RNA-seq and homologous protein evidence. We show in computational experiments on genomes of 11 species that TSEBRA achieves higher accuracy than either BRAKER1 or BRAKER2 running alone and that TSEBRA compares favorably with the combiner tool EVidenceModeler. Conclusion: TSEBRA is an easy-to-use and fast software tool. It can be used in concert with the BRAKER pipeline to generate a gene prediction set supported by both RNA-seq and homologous protein evidence.