1
|
Gündüz HA, Mreches R, Moosbauer J, Robertson G, To XY, Franzosa EA, Huttenhower C, Rezaei M, McHardy AC, Bischl B, Münch PC, Binder M. Optimized model architectures for deep learning on genomic data. Commun Biol 2024; 7:516. [PMID: 38693292 PMCID: PMC11063068 DOI: 10.1038/s42003-024-06161-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2023] [Accepted: 04/08/2024] [Indexed: 05/03/2024] Open
Abstract
The success of deep learning in various applications depends on task-specific architecture design choices, including the types, hyperparameters, and number of layers. In computational biology, there is no consensus on the optimal architecture design, and decisions are often made using insights from more well-established fields such as computer vision. These may not consider the domain-specific characteristics of genome sequences, potentially limiting performance. Here, we present GenomeNet-Architect, a neural architecture design framework that automatically optimizes deep learning models for genome sequence data. It optimizes the overall layout of the architecture, with a search space specifically designed for genomics. Additionally, it optimizes hyperparameters of individual layers and the model training procedure. On a viral classification task, GenomeNet-Architect reduced the read-level misclassification rate by 19%, with 67% faster inference and 83% fewer parameters, and achieved similar contig-level accuracy with ~100 times fewer parameters compared to the best-performing deep learning baselines.
Collapse
Affiliation(s)
- Hüseyin Anil Gündüz
- Department of Statistics, LMU Munich, Munich, Germany
- Munich Center for Machine Learning, Munich, Germany
| | - René Mreches
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, 38124, Braunschweig, Germany
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany
| | - Julia Moosbauer
- Department of Statistics, LMU Munich, Munich, Germany
- Munich Center for Machine Learning, Munich, Germany
| | - Gary Robertson
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, 38124, Braunschweig, Germany
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany
| | - Xiao-Yin To
- Department of Statistics, LMU Munich, Munich, Germany
- Munich Center for Machine Learning, Munich, Germany
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, 38124, Braunschweig, Germany
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany
| | - Eric A Franzosa
- Department of Biostatistics, Harvard School of Public Health, Boston, MA, USA
| | - Curtis Huttenhower
- Department of Biostatistics, Harvard School of Public Health, Boston, MA, USA
| | - Mina Rezaei
- Department of Statistics, LMU Munich, Munich, Germany
- Munich Center for Machine Learning, Munich, Germany
| | - Alice C McHardy
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, 38124, Braunschweig, Germany
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany
- German Centre for Infection Research (DZIF), partner site Hannover Braunschweig, Braunschweig, Germany
| | - Bernd Bischl
- Department of Statistics, LMU Munich, Munich, Germany
- Munich Center for Machine Learning, Munich, Germany
| | - Philipp C Münch
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, 38124, Braunschweig, Germany.
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany.
- Department of Biostatistics, Harvard School of Public Health, Boston, MA, USA.
- German Centre for Infection Research (DZIF), partner site Hannover Braunschweig, Braunschweig, Germany.
| | - Martin Binder
- Department of Statistics, LMU Munich, Munich, Germany.
- Munich Center for Machine Learning, Munich, Germany.
| |
Collapse
|
2
|
Gündüz HA, Binder M, To XY, Mreches R, Bischl B, McHardy AC, Münch PC, Rezaei M. A self-supervised deep learning method for data-efficient training in genomics. Commun Biol 2023; 6:928. [PMID: 37696966 PMCID: PMC10495322 DOI: 10.1038/s42003-023-05310-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2023] [Accepted: 09/01/2023] [Indexed: 09/13/2023] Open
Abstract
Deep learning in bioinformatics is often limited to problems where extensive amounts of labeled data are available for supervised classification. By exploiting unlabeled data, self-supervised learning techniques can improve the performance of machine learning models in the presence of limited labeled data. Although many self-supervised learning methods have been suggested before, they have failed to exploit the unique characteristics of genomic data. Therefore, we introduce Self-GenomeNet, a self-supervised learning technique that is custom-tailored for genomic data. Self-GenomeNet leverages reverse-complement sequences and effectively learns short- and long-term dependencies by predicting targets of different lengths. Self-GenomeNet performs better than other self-supervised methods in data-scarce genomic tasks and outperforms standard supervised training with ~10 times fewer labeled training data. Furthermore, the learned representations generalize well to new datasets and tasks. These findings suggest that Self-GenomeNet is well suited for large-scale, unlabeled genomic datasets and could substantially improve the performance of genomic models.
Collapse
Affiliation(s)
- Hüseyin Anil Gündüz
- Department of Statistics, LMU Munich, Munich, Germany
- Munich Center for Machine Learning, Munich, Germany
| | - Martin Binder
- Department of Statistics, LMU Munich, Munich, Germany
- Munich Center for Machine Learning, Munich, Germany
| | - Xiao-Yin To
- Department of Statistics, LMU Munich, Munich, Germany
- Munich Center for Machine Learning, Munich, Germany
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, 38124, Braunschweig, Germany
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany
| | - René Mreches
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, 38124, Braunschweig, Germany
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany
| | - Bernd Bischl
- Department of Statistics, LMU Munich, Munich, Germany
- Munich Center for Machine Learning, Munich, Germany
| | - Alice C McHardy
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, 38124, Braunschweig, Germany
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany
| | - Philipp C Münch
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, 38124, Braunschweig, Germany.
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany.
- German Center for Infection Research (DZIF), partner site Hannover Braunschweig, Braunschweig, Germany.
- Department of Biostatistics, Harvard School of Public Health, Boston, MA, USA.
| | - Mina Rezaei
- Department of Statistics, LMU Munich, Munich, Germany.
- Munich Center for Machine Learning, Munich, Germany.
| |
Collapse
|
3
|
Deng ZL, Münch PC, Mreches R, McHardy AC. Rapid and accurate identification of ribosomal RNA sequences via deep learning. Nucleic Acids Res 2022; 50:e60. [PMID: 35188571 PMCID: PMC9177968 DOI: 10.1093/nar/gkac112] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2021] [Revised: 01/28/2022] [Accepted: 02/07/2022] [Indexed: 11/14/2022] Open
Abstract
Advances in transcriptomic and translatomic techniques enable in-depth studies of RNA activity profiles and RNA-based regulatory mechanisms. Ribosomal RNA (rRNA) sequences are highly abundant among cellular RNA, but if the target sequences do not include polyadenylation, these cannot be easily removed in library preparation, requiring their post-hoc removal with computational techniques to accelerate and improve downstream analyses. Here, we describe RiboDetector, a novel software based on a Bi-directional Long Short-Term Memory (BiLSTM) neural network, which rapidly and accurately identifies rRNA reads from transcriptomic, metagenomic, metatranscriptomic, noncoding RNA, and ribosome profiling sequence data. Compared with state-of-the-art approaches, RiboDetector produced at least six times fewer misclassifications on the benchmark datasets. Importantly, the few false positives of RiboDetector were not enriched in certain Gene Ontology (GO) terms, suggesting a low bias for downstream functional profiling. RiboDetector also demonstrated a remarkable generalizability for detecting novel rRNA sequences that are divergent from the training data with sequence identities of <90%. On a personal computer, RiboDetector processed 40M reads in less than 6 min, which was ∼50 times faster in GPU mode and ∼15 times in CPU mode than other methods. RiboDetector is available under a GPL v3.0 license at https://github.com/hzi-bifo/RiboDetector.
Collapse
Affiliation(s)
- Zhi-Luo Deng
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, Braunschweig, Germany
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany
| | - Philipp C Münch
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, Braunschweig, Germany
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany
| | - René Mreches
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, Braunschweig, Germany
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany
| | - Alice C McHardy
- Department for Computational Biology of Infection Research, Helmholtz Center for Infection Research, Braunschweig, Germany
- Braunschweig Integrated Centre of Systems Biology (BRICS), Technische Universität Braunschweig, Braunschweig, Germany
| |
Collapse
|