Neuraldecipher – reverse-engineering extended-connectivity fingerprints (ECFPs) to their molecular structures

Le, Tuan; Winter, Robin; Noé, Frank; Clevert, Djork-Arné

doi:10.1039/d0sc03115a

Cited by 42 publications

(37 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…20 This work is, in that sense, loosely related to our previously published NeuralDecipher model that is able to reverseengineer molecular structures from folded extended-connectivity fingerprints. 21 Both works rely on the autoencoder by Winter et al 20 (Figure 2). This autoencoder was trained to translate an input molecule SMILES representation into the corresponding canonical SMILES representation.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Img2Mol – accurate SMILES recognition from molecular graphical depictions

Clevert

Winter

et al. 2021

Chem. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

“… 20 This work is, in that sense, loosely related to our previously published Neuraldecipher model that is able to reverse-engineer molecular structures from folded extended-connectivity fingerprints. 21 Both studies rely on the autoencoder developed by Winter et al 20 ( Fig. 2 ).…”

Section: Methodsmentioning

confidence: 99%

Img2Mol – accurate SMILES recognition from molecular graphical depictions

Clevert

Winter

et al. 2021

Chem. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Nonetheless, while we have argued that the amount of public data is increasing at a fast pace, most of the structural activity/ property relationship data are still generated by commercial research organizations, publishers, and pharmaceutical companies [95][96][97], which often consider the generated data as a differentiating asset to be kept confidential. Recent developments have shown that molecular structures can often be partially recovered from molecular descriptors, which may further complicate data sharing even at the latent feature level [98]. Attempts to overcome such limitations, for example, by developing federated and intellectual property (IP)preserving learning techniques, are underway [99].…”

Section: Article Highlightsmentioning

confidence: 99%

Artificial intelligence in drug discovery: recent advances and future perspectives

Jiménez-Luna

Grisoni

Weskamp

et al. 2021

Expert Opinion on Drug Discovery

248

144

View full text Add to dashboard Cite

Introduction: Artificial intelligence (AI) has inspired computer-aided drug discovery. The widespread adoption of machine learning, in particular deep learning, in multiple scientific disciplines, and the advances in computing hardware and software, among other factors, continue to fuel this development. Much of the initial skepticism regarding applications of AI in pharmaceutical discovery has started to vanish, consequently benefitting medicinal chemistry. Areas covered: The current status of AI in chemoinformatics is reviewed. The topics discussed herein include quantitative structure-activity/property relationship and structure-based modeling, de novo molecular design, and chemical synthesis prediction. Advantages and limitations of current deep learning applications are highlighted, together with a perspective on next-generation AI for drug discovery. Expert opinion: Deep learning-based approaches have only begun to address some fundamental problems in drug discovery. Certain methodological advances, such as message-passing models, spatial-symmetry-preserving networks, hybrid de novo design, and other innovative machine learning paradigms, will likely become commonplace and help address some of the most challenging questions.Open data sharing and model development will play a central role in the advancement of drug discovery with AI.

show abstract

“…Recently, there was a new publication called ChemPix [ 15 ], a deep learning-based method that was developed to recognize hand drawn hydrocarbon chemical structures. Another recent publication describes SMILES generation from images [ 16 ] where an encoder–decoder method with a pre-trained decoder is used from previous work [ 17 ]. These contributions demonstrate an increasing interest in this field of research.…”

Section: Introductionmentioning

confidence: 99%

DECIMER 1.0: deep learning for chemical image recognition using transformers

Rajan

Zielesny²,

Steinbeck

2021

J Cheminform

View full text Add to dashboard Cite

The amount of data available on chemical structures and their properties has increased steadily over the past decades. In particular, articles published before the mid-1990 are available only in printed or scanned form. The extraction and storage of data from those articles in a publicly accessible database are desirable, but doing this manually is a slow and error-prone process. In order to extract chemical structure depictions and convert them into a computer-readable format, Optical Chemical Structure Recognition (OCSR) tools were developed where the best performing OCSR tools are mostly rule-based. The DECIMER (Deep lEarning for Chemical ImagE Recognition) project was launched to address the OCSR problem with the latest computational intelligence methods to provide an automated open-source software solution. Various current deep learning approaches were explored to seek a best-fitting solution to the problem. In a preliminary communication, we outlined the prospect of being able to predict SMILES encodings of chemical structure depictions with about 90% accuracy using a dataset of 50–100 million molecules. In this article, the new DECIMER model is presented, a transformer-based network, which can predict SMILES with above 96% accuracy from depictions of chemical structures without stereochemical information and above 89% accuracy for depictions with stereochemical information.

show abstract

Neuraldecipher – reverse-engineering extended-connectivity fingerprints (ECFPs) to their molecular structures

Abstract: Protecting molecular structures from disclosure against external parties is of great relevance for industrial and private associations, such as pharmaceutical companies. Within the framework of external collaborations, it is common...

Cited by 42 publications

References 32 publications

Img2Mol – accurate SMILES recognition from molecular graphical depictions

Img2Mol – accurate SMILES recognition from molecular graphical depictions

Artificial intelligence in drug discovery: recent advances and future perspectives

DECIMER 1.0: deep learning for chemical image recognition using transformers

Contact Info

Product

Resources

About