VAE-Sim: a novel molecular similarity measure based on a variational autoencoder

Samanta, Soumitra; O’Hagan, Steve; Swainston, Neil; Roberts, Timothy J.; Kell, Douglas B.

doi:10.1101/2020.06.26.172908

Cited by 13 publications

(6 citation statements)

References 88 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The causal relation has the potential for generalizability. It was first defined by Kingma and Welling in 2013 and since then has found wide applications in many research fields. ,,, In the field of new material discovery, the VAE also came into use in some studies. For example, by combining the VAE and nondominated sorting genetic algorithm, Lee et al pinpointed several novel thermomechanically controlled and processed steel alloys, and the predictions agree with the rule-based thermodynamic calculation tool .…”

Section: Methodsmentioning

confidence: 99%

From Drug Molecules to Thermoset Shape Memory Polymers: A Machine Learning Approach

Yan

Feng

2021

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

Ultraviolet (UV)-curable thermoset shape memory polymers (TSMPs) with high recovery stress but mild glass transition temperature (T g ) are highly desired for 3D/4D printing lightweight load-bearing structures and devices. However, a bottleneck is that high recovery stress usually means high T g . For a few TSMPs with high recovery stress, their T g values are close to the decomposition temperature, and thus, the shape memory effect cannot be triggered safely and effectively. While machine learning (ML) has served as a useful tool to discover new materials and drugs, the grand challenge of using ML to discover new TSMPs persists in the very limited data available. Here, we report an enhanced ML approach by combining the transfer learning− variational autoencoder with a weighted-vector combination method. By learning a large data set with drug molecules in a pretraining process, we were able to effectively map the TSMPs to a hidden space that is much closer to a Gaussian distribution. Through this approach, we created a large compositional space and were able to discover five new types of UV-curable TSMPs with desired properties, one of which was validated by the experiments. Our contribution includes (1) representing the features of TSMPs by drug molecules to overcome the barrier of a limited training data set and (2) developing a ML framework that is able to overcome the barrier of mapping the molar ratio information. It is shown that this approach can effectively learn TSMP features by utilizing the relatedness between the data-scarce (and biased) TSMP target and data-abundant drug source, and the result is much more accurate and more robust than the benchmark set by the support vector machine method using direct label encoding and Morgan encoding. Therefore, it is believed that this framework is a state-of-the-art study in the TSMP field. This study opens new opportunities for discovering not only new TSMPs but also other thermoset polymers.

show abstract

Section: Methodsmentioning

confidence: 99%

From Drug Molecules to Thermoset Shape Memory Polymers: A Machine Learning Approach

Yan

Feng

2021

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

show abstract

“…Thus, the purpose of the present article is to describe our own implementation of a simple VAE and its use in molecular similarity measurements as applied, in particular, to the set of drugs, metabolites and natural products that we have been using previously [25,[99][100][101][102][103][104] as our benchmark for similarity metrics. A preprint was deposited at bioRxiv [105].…”

Section: Drugmentioning

confidence: 99%

VAE-Sim: A Novel Molecular Similarity Measure Based on a Variational Autoencoder

et al. 2020

Self Cite

View full text Add to dashboard Cite

Molecular similarity is an elusive but core “unsupervised” cheminformatics concept, yet different “fingerprint” encodings of molecular structures return very different similarity values, even when using the same similarity metric. Each encoding may be of value when applied to other problems with objective or target functions, implying that a priori none are “better” than the others, nor than encoding-free metrics such as maximum common substructure (MCSS). We here introduce a novel approach to molecular similarity, in the form of a variational autoencoder (VAE). This learns the joint distribution p(z|x) where z is a latent vector and x are the (same) input/output data. It takes the form of a “bowtie”-shaped artificial neural network. In the middle is a “bottleneck layer” or latent vector in which inputs are transformed into, and represented as, a vector of numbers (encoding), with a reverse process (decoding) seeking to return the SMILES string that was the input. We train a VAE on over six million druglike molecules and natural products (including over one million in the final holdout set). The VAE vector distances provide a rapid and novel metric for molecular similarity that is both easily and rapidly calculated. We describe the method and its application to a typical similarity problem in cheminformatics.

show abstract

“…This is largely seen to contain the ∼150 000 natural products, ∼150 fluorophores, ∼1100 endogenous human metabolites (Recon2) and 1387 marketed drugs studied previously [25]. Molecules were extracted by the present authors [26] to a latent space of 100 dimensions using methods described in [27] and their vector values in the latent space used as the input to the UMAP algorithm.…”

Section: A Brief History Of Virtual Screening and The Multilayer Percmentioning

confidence: 99%

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

Kell

Samanta

Swainston

2020

Biochemical Journal

Self Cite

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

VAE-Sim: a novel molecular similarity measure based on a variational autoencoder

Cited by 13 publications

References 88 publications

From Drug Molecules to Thermoset Shape Memory Polymers: A Machine Learning Approach

From Drug Molecules to Thermoset Shape Memory Polymers: A Machine Learning Approach

VAE-Sim: A Novel Molecular Similarity Measure Based on a Variational Autoencoder

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

Contact Info

Product

Resources

About