Enhancing scientific discoveries in molecular biology with deep generative models

Lopez, Romain; Gayoso, Adam; Yosef, Nir

doi:10.15252/msb.20199198

Cited by 49 publications

(35 citation statements)

References 111 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…What we would really like to have is the ability to generate the molecules themselves 'de novo' (e.g. [59,64,65,84,[92][93][94][95][96][97][98][99][100][101][102][103][104][105][106][107]), by learning what amounts to a joint distribution over all the variables (both inputs and outputs). To this end, a generative model seeks to simulate or recreate how the data are generated 'in the real world'.…”

Section: Variational Autoencoders (Vaes) and Generative Methodsmentioning

confidence: 99%

Deep learning and generative methods in cheminformatics and chemical biology: navigating small molecule space intelligently

Kell

Samanta

Swainston

2020

Biochemical Journal

View full text Add to dashboard Cite

The number of ‘small’ molecules that may be of interest to chemical biologists — chemical space — is enormous, but the fraction that have ever been made is tiny. Most strategies are discriminative, i.e. have involved ‘forward’ problems (have molecule, establish properties). However, we normally wish to solve the much harder generative or inverse problem (describe desired properties, find molecule). ‘Deep’ (machine) learning based on large-scale neural networks underpins technologies such as computer vision, natural language processing, driverless cars, and world-leading performance in games such as Go; it can also be applied to the solution of inverse problems in chemical biology. In particular, recent developments in deep learning admit the in silico generation of candidate molecular structures and the prediction of their properties, thereby allowing one to navigate (bio)chemical space intelligently. These methods are revolutionary but require an understanding of both (bio)chemistry and computer science to be exploited to best advantage. We give a high-level (non-mathematical) background to the deep learning revolution, and set out the crucial issue for chemical biology and informatics as a two-way mapping from the discrete nature of individual molecules to the continuous but high-dimensional latent representation that may best reflect chemical space. A variety of architectures can do this; we focus on a particular type known as variational autoencoders. We then provide some examples of recent successes of these kinds of approach, and a look towards the future.

show abstract

Section: Variational Autoencoders (Vaes) and Generative Methodsmentioning

confidence: 99%

Deep learning and generative methods in cheminformatics and chemical biology: navigating small molecule space intelligently

Kell

Samanta

Swainston

2020

Biochemical Journal

View full text Add to dashboard Cite

show abstract

“…Some recent studies demonstrate deep learning networks trained over millions of articles generate extensive molecular interactions 31 and the potential relationship between molecules and disease only using articles a year (or years) before such a relationship was discovered 32 . Deep learning was also used to uncover hierarchical structure and functions of cells 33 , deep generative models for discovering hidden structures 34 , precision phenotyping to predict genetic anomalies 35 , and many more. The outcome of such approaches is a set of hypotheses generated by deep learning and other AI methods from unbiased data, and hypotheses are generated in an unbiased manner.…”

Section: Experimental Contextmentioning

confidence: 99%

Nobel Turing Challenge: creating the engine for scientific discovery

Kitano

2021

npj Syst Biol Appl

View full text Add to dashboard Cite

Scientific discovery has long been one of the central driving forces in our civilization. It uncovered the principles of the world we live in, and enabled us to invent new technologies reshaping our society, cure diseases, explore unknown new frontiers, and hopefully lead us to build a sustainable society. Accelerating the speed of scientific discovery is therefore one of the most important endeavors. This requires an in-depth understanding of not only the subject areas but also the nature of scientific discoveries themselves. In other words, the “science of science” needs to be established, and has to be implemented using artificial intelligence (AI) systems to be practically executable. At the same time, what may be implemented by “AI Scientists” may not resemble the scientific process conducted by human scientist. It may be an alternative form of science that will break the limitation of current scientific practice largely hampered by human cognitive limitation and sociological constraints. It could give rise to a human-AI hybrid form of science that shall bring systems biology and other sciences into the next stage. The Nobel Turing Challenge aims to develop a highly autonomous AI system that can perform top-level science, indistinguishable from the quality of that performed by the best human scientists, where some of the discoveries may be worthy of Nobel Prize level recognition and beyond.

show abstract

“…A special class of probabilistic models makes use of neural networks either as part of the generative model, or as a way to amortize the computational cost of inference. These so-called deep generative models (DGMs) have been successfully applied to many analysis tasks for single-cell omics (e.g., scVI [5], totalVI [21], PeakVI [24], SCALE [25], scPhere [26], scGen [27], CellBender [28], Dhaka [29], VASC [30], and scVAE [31]) as well as other areas of computational biology [32].…”

Section: Introductionmentioning

confidence: 99%

scvi-tools: a library for deep probabilistic analysis of single-cell omics data

Gayoso

Lopez

Xing

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Probabilistic models have provided the underpinnings for state-of-the-art performance in many single-cell omics data analysis tasks, including dimensionality reduction, clustering, differential expression, annotation, removal of unwanted variation, and integration across modalities. Many of the models being deployed are amenable to scalable stochastic inference techniques, and accordingly they are able to process single-cell datasets of realistic and growing sizes. However, the community-wide adoption of probabilistic approaches is hindered by a fractured software ecosystem resulting in an array of packages with distinct, and often complex interfaces. To address this issue, we developed scvi-tools (https://scvi-tools.org), a Python package that implements a variety of leading probabilistic methods. These methods, which cover many fundamental analysis tasks, are accessible through a standardized, easy-to-use interface with direct links to Scanpy, Seurat, and Bioconductor workflows. By standardizing the implementations, we were able to develop and reuse novel functionalities across different models, such as support for complex study designs through nonlinear removal of unwanted variation due to multiple covariates and reference-query integration via scArches. The extensible software building blocks that underlie scvi-tools also enable a developer environment in which new probabilistic models for single cell omics can be efficiently developed, benchmarked, and deployed. We demonstrate this through a code-efficient reimplementation of Stereoscope for deconvolution of spatial transcriptomics profiles. By catering to both the end user and developer audiences, we expect scvi-tools to become an essential software dependency and serve to formulate a community standard for probabilistic modeling of single cell omics.

show abstract

Enhancing scientific discoveries in molecular biology with deep generative models

Cited by 49 publications

References 111 publications

Deep learning and generative methods in cheminformatics and chemical biology: navigating small molecule space intelligently

Deep learning and generative methods in cheminformatics and chemical biology: navigating small molecule space intelligently

Nobel Turing Challenge: creating the engine for scientific discovery

scvi-tools: a library for deep probabilistic analysis of single-cell omics data

Contact Info

Product

Resources

About