Enhancing scientific discoveries in molecular biology with deep generative models
Abstract Generative models provide a well‐established statistical framework for evaluating uncertainty and deriving conclusions from large data sets especially in the presence of noise, sparsity, and bias. Initially developed for computer vision and natural language processing, these models have bee...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Nature
2020-09-01
|
| Series: | Molecular Systems Biology |
| Subjects: | |
| Online Access: | https://doi.org/10.15252/msb.20199198 |
| _version_ | 1797285165543718912 |
|---|---|
| author | Romain Lopez Adam Gayoso Nir Yosef |
| author_facet | Romain Lopez Adam Gayoso Nir Yosef |
| author_sort | Romain Lopez |
| collection | DOAJ |
| description | Abstract Generative models provide a well‐established statistical framework for evaluating uncertainty and deriving conclusions from large data sets especially in the presence of noise, sparsity, and bias. Initially developed for computer vision and natural language processing, these models have been shown to effectively summarize the complexity that underlies many types of data and enable a range of applications including supervised learning tasks, such as assigning labels to images; unsupervised learning tasks, such as dimensionality reduction; and out‐of‐sample generation, such as de novo image synthesis. With this early success, the power of generative models is now being increasingly leveraged in molecular biology, with applications ranging from designing new molecules with properties of interest to identifying deleterious mutations in our genomes and to dissecting transcriptional variability between single cells. In this review, we provide a brief overview of the technical notions behind generative models and their implementation with deep learning techniques. We then describe several different ways in which these models can be utilized in practice, using several recent applications in molecular biology as examples. |
| first_indexed | 2024-03-07T17:59:19Z |
| format | Article |
| id | doaj.art-066fc029b4ee4c0e9c3581ee3ee16e1e |
| institution | Directory Open Access Journal |
| issn | 1744-4292 |
| language | English |
| last_indexed | 2024-03-07T17:59:19Z |
| publishDate | 2020-09-01 |
| publisher | Springer Nature |
| record_format | Article |
| series | Molecular Systems Biology |
| spelling | doaj.art-066fc029b4ee4c0e9c3581ee3ee16e1e2024-03-02T11:11:26ZengSpringer NatureMolecular Systems Biology1744-42922020-09-01169n/an/a10.15252/msb.20199198Enhancing scientific discoveries in molecular biology with deep generative modelsRomain Lopez0Adam Gayoso1Nir Yosef2Department of Electrical Engineering and Computer Sciences University of California Berkeley CA USACenter for Computational Biology University of California Berkeley CA USADepartment of Electrical Engineering and Computer Sciences University of California Berkeley CA USAAbstract Generative models provide a well‐established statistical framework for evaluating uncertainty and deriving conclusions from large data sets especially in the presence of noise, sparsity, and bias. Initially developed for computer vision and natural language processing, these models have been shown to effectively summarize the complexity that underlies many types of data and enable a range of applications including supervised learning tasks, such as assigning labels to images; unsupervised learning tasks, such as dimensionality reduction; and out‐of‐sample generation, such as de novo image synthesis. With this early success, the power of generative models is now being increasingly leveraged in molecular biology, with applications ranging from designing new molecules with properties of interest to identifying deleterious mutations in our genomes and to dissecting transcriptional variability between single cells. In this review, we provide a brief overview of the technical notions behind generative models and their implementation with deep learning techniques. We then describe several different ways in which these models can be utilized in practice, using several recent applications in molecular biology as examples.https://doi.org/10.15252/msb.20199198deep generative modelsmolecular biologyneural networks |
| spellingShingle | Romain Lopez Adam Gayoso Nir Yosef Enhancing scientific discoveries in molecular biology with deep generative models Molecular Systems Biology deep generative models molecular biology neural networks |
| title | Enhancing scientific discoveries in molecular biology with deep generative models |
| title_full | Enhancing scientific discoveries in molecular biology with deep generative models |
| title_fullStr | Enhancing scientific discoveries in molecular biology with deep generative models |
| title_full_unstemmed | Enhancing scientific discoveries in molecular biology with deep generative models |
| title_short | Enhancing scientific discoveries in molecular biology with deep generative models |
| title_sort | enhancing scientific discoveries in molecular biology with deep generative models |
| topic | deep generative models molecular biology neural networks |
| url | https://doi.org/10.15252/msb.20199198 |
| work_keys_str_mv | AT romainlopez enhancingscientificdiscoveriesinmolecularbiologywithdeepgenerativemodels AT adamgayoso enhancingscientificdiscoveriesinmolecularbiologywithdeepgenerativemodels AT niryosef enhancingscientificdiscoveriesinmolecularbiologywithdeepgenerativemodels |