The next level in chemical space navigation: going far beyond enumerable compound libraries

Hoffmann, Torsten; Gastreich, Marcus

doi:10.1016/j.drudis.2019.02.013

Cited by 190 publications

(188 citation statements)

References 40 publications

Supporting

Mentioning

184

Contrasting

Order By: Relevance

“…from public sources including ChEMBL (Gaulton et al, 2011), ZINC (Sterling and Irwin, 2015), PubChem (Kim et al, 2019), or commercial platforms such as SciFinder 3 and Reaxys 4 . As databases of chemical space grow ever larger, data mining techniques and algorithms to enable chemists to efficiently explore this space are crucial; for example, algorithms to assess synthetic tractability or analyze structural properties would be tremendously valuable (Hoffmann and Gastreich, 2019). Ideal databases for drug discovery include those that are properly curated, complete with positive and negative data, and replete with examples to capture a wide breadth of existing chemical space.…”

Section: Application Of Ai To De Novo Molecular Designmentioning

confidence: 99%

Exploring Novel Biologically-Relevant Chemical Space Through Artificial Intelligence: The NCATS ASPIRE Program

et al. 2020

View full text Add to dashboard Cite

In recent years, artificial intelligence (AI)/machine learning (ML; a subset of AI) have become increasingly important to the biomedical research community. These technologies, coupled to big data and cheminformatics, have tremendous potential to improve the design of novel therapeutics and to provide safe and effective drugs to patients. A National Center for Advancing Translational Sciences (NCATS) program called A Specialized Platform for Innovative Research Exploration (ASPIRE) leverages advances in AI/ML, automated synthetic chemistry, and high-throughput biology, and seeks to enable translation and drug development by catalyzing exploration of biologically active chemical space. Here we discuss the opportunities and challenges surrounding the application of AI/ML to the exploration of novel biologically relevant chemical space as part of ASPIRE.

show abstract

Section: Application Of Ai To De Novo Molecular Designmentioning

confidence: 99%

Exploring Novel Biologically-Relevant Chemical Space Through Artificial Intelligence: The NCATS ASPIRE Program

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Exploration of chemical space for the discovery of new molecules is a key challenge for the chemical community, e.g. pharmaceutical and olfactive industries [1,2]. Previously, exhaustive enumeration has been introduced with the creation of 26 M, 1G and 1.7G molecules in the databases GDB11, GDB13 and GDB17, respectively [3].…”

Section: Introductionmentioning

confidence: 99%

GEN: highly efficient SMILES explorer using autodidactic generative examination networks

et al. 2020

View full text Add to dashboard Cite

Recurrent neural networks have been widely used to generate millions of de novo molecules in defined chemical spaces. Reported deep generative models are exclusively based on LSTM and/or GRU units and frequently trained using canonical SMILES. In this study, we introduce Generative Examination Networks (GEN) as a new approach to train deep generative networks for SMILES generation. In our GENs, we have used an architecture based on multiple concatenated bidirectional RNN units to enhance the validity of generated SMILES. GENs autonomously learn the target space in a few epochs and are stopped early using an independent online examination mechanism, measuring the quality of the generated set. Herein we have used online statistical quality control (SQC) on the percentage of valid molecular SMILES as examination measure to select the earliest available stable model weights. Very high levels of valid SMILES (95-98%) can be generated using multiple parallel encoding layers in combination with SMILES augmentation using unrestricted SMILES randomization. Our trained models combine an excellent novelty rate (85-90%) while generating SMILES with strong conservation of the property space (95-99%). In GENs, both the generative network and the examination mechanism are open to other architectures and quality criteria.

show abstract

“…Improvements in this form of research, called hit-to-lead, can save significant time and money. The search for promising candidate drugs is a daunting task, since the state space of molecular libraries is in the millions, and possible drugs is in the tens of thousands or more [4].…”

Section: Introductionmentioning

confidence: 99%

Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference

Amodio

Shung

Burkhardt

et al. 2020

Preprint

View full text Add to dashboard Cite

In many important contexts involving measurements of biological entities, there are distinct categories of information: some information is easy-to-obtain information (EI) and can be gathered on virtually every subject of interest, while other information is hard-to-obtain information (HI) and can only be gathered on some of the biological samples. For example, in the context of drug discovery, measurements like the chemical structure of a drug are EI, while measurements of the transcriptome of a cell population perturbed with the drug is HI. In the clinical context, basic health monitoring is EI because it is already being captured as part of other processes, while cellular measurements like flow cytometry or even ultimate patient outcome are HI. We propose building a model to make probabilistic predictions of HI from EI on the samples that have both kinds of measurements, which will allow us to generalize and predict the HI on a large set of samples from just the EI. To accomplish this, we present a conditional Generative Adversarial Network (cGAN) framework we call the Feature Mapping GAN (FMGAN). By using the EI as conditions to map to the HI, we demonstrate that FMGAN can accurately predict the HI, with heterogeneity in cases of distributions of HI from EI. We show that FMGAN is flexible in that it can learn rich and complex mappings from EI to HI, and can take into account manifold structure in the EI space where available. We demonstrate this in a variety of contexts including generating RNA sequencing results on cell lines subjected to drug perturbations using drug chemical structure, and generating clinical outcomes from patient lab measurements. Most notably, we are able to generate synthetic flow cytometry data from clinical variables on a cohort of COVID-19 patients---effectively describing their immune response in great detail, and showcasing the power of generating expensive FACS data from ubiquitously available patient monitoring data.

show abstract

The next level in chemical space navigation: going far beyond enumerable compound libraries

Cited by 190 publications

References 40 publications

Exploring Novel Biologically-Relevant Chemical Space Through Artificial Intelligence: The NCATS ASPIRE Program

Exploring Novel Biologically-Relevant Chemical Space Through Artificial Intelligence: The NCATS ASPIRE Program

GEN: highly efficient SMILES explorer using autodidactic generative examination networks

Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference

Contact Info

Product

Resources

About