Privileged Scaffold Analysis of Natural Products with Deep Learning‐based Indication Prediction Model

Lai, Junyong; Hu, Jianxing; Wang, Yanxing; Zhou, Xin; Li, Yibo; Zhang, Liangren; Liu, Zhenming

doi:10.1002/minf.202000057

Cited by 10 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[143] Most recently, multi-task deep neural networks were trained on medical indication data and employed for identifying privileged molecular scaffolds in NPs (in this case, scaffolds for which multiple NPs built on the identical scaffold are active in the same indication). [144] Based on the predictions of these models, a privileged scaffold dataset for 100 indications was compiled that could serve as a starting point for NP-based drug discovery.…”

Section: Computational Methods For the Prediction Of The Macromoleculmentioning

confidence: 99%

Cheminformatics in Natural Product‐based Drug Discovery

Kirchmair

2020

Molecular Informatics

108

View full text Add to dashboard Cite

This review seeks to provide a timely survey of the scope and limitations of cheminformatics methods in natural product-based drug discovery. Following an overview of data resources of chemical, biological and structural information on natural products, we discuss, among other aspects, in silico methods for (i) data curation and natural products dereplication, (ii) analysis, visualization, navigation and comparison of the chemical space, (iii) quantification of natural product-likeness, (iv) prediction of the bioactivities (virtual screening, target prediction), ADME and safety profiles (toxicity) of natural products, (v) natural productsinspired de novo design and (vi) prediction of natural products prone to cause interference with biological assays. Among the many methods discussed are rule-based, similarity-based, shape-based, pharmacophore-based and network-based approaches, docking and machine learning methods.

show abstract

Section: Computational Methods For the Prediction Of The Macromoleculmentioning

confidence: 99%

Cheminformatics in Natural Product‐based Drug Discovery

Kirchmair

2020

Molecular Informatics

108

View full text Add to dashboard Cite

show abstract

“…A clear separation between the chemical space represented by MNP when compared to TNP when exploring ML techniques was observed [ 401 ]. A Generative Topographic Mapping (GTM) for chemical data visualization was also developed [ 401 ] in order to map the terrestrial and marine origin of the NP landscape for the external test set (a data set not used to build the model, comprising 3236 MNP and 3258 TNP) for the StreptomeDB 2.0 database (2877 unique microbial NP produced by the genus Streptomyces , an actinobacterium) [ 402 ] when comparing with the Pye data set (5486 unique microbial and MNP) [ 58 , 403 , 404 , 405 , 406 ] ( Figure 10 ).…”

Section: Chemoinformatics Tools To Facilitate Drug-lead Discoverymentioning

confidence: 99%

“…Entropy-based information metrics were used to identify the privileged scaffolds for each indication, and a Privileged Scaffold Dataset (PSD) of NP was built. In Figure 12 , some examples are shown [ 403 , 404 , 405 , 406 ].…”

Section: Chemoinformatics Tools To Facilitate Drug-lead Discoverymentioning

confidence: 99%

See 1 more Smart Citation

Advanced Methods for Natural Products Discovery: Bioactivity Screening, Dereplication, Metabolomics Profiling, Genomic Sequencing, Databases and Informatic Tools, and Structure Elucidation

et al. 2023

View full text Add to dashboard Cite

Natural Products (NP) are essential for the discovery of novel drugs and products for numerous biotechnological applications. The NP discovery process is expensive and time-consuming, having as major hurdles dereplication (early identification of known compounds) and structure elucidation, particularly the determination of the absolute configuration of metabolites with stereogenic centers. This review comprehensively focuses on recent technological and instrumental advances, highlighting the development of methods that alleviate these obstacles, paving the way for accelerating NP discovery towards biotechnological applications. Herein, we emphasize the most innovative high-throughput tools and methods for advancing bioactivity screening, NP chemical analysis, dereplication, metabolite profiling, metabolomics, genome sequencing and/or genomics approaches, databases, bioinformatics, chemoinformatics, and three-dimensional NP structure elucidation.

show abstract

“…In previous studies, the prediction of natural product bioactivities was commonly performed by models trained on datasets containing both human synthetic compounds and natural products [ 24 , 25 , 26 ]. Chen et al [ 27 ] managed to use structural information from conventional simple molecules to predict targets for natural products and macrocyclic ligands.…”

Section: Introductionmentioning

confidence: 99%

Target Prediction Model for Natural Products Using Transfer Learning

Qiang

Lai

Jin

et al. 2021

IJMS

Self Cite

View full text Add to dashboard Cite

A large proportion of lead compounds are derived from natural products. However, most natural products have not been fully tested for their targets. To help resolve this problem, a model using transfer learning was built to predict targets for natural products. The model was pre-trained on a processed ChEMBL dataset and then fine-tuned on a natural product dataset. Benefitting from transfer learning and the data balancing technique, the model achieved a highly promising area under the receiver operating characteristic curve (AUROC) score of 0.910, with limited task-related training samples. Since the embedding distribution difference is reduced, embedding space analysis demonstrates that the model’s outputs of natural products are reliable. Case studies have proved our model’s performance in drug datasets. The fine-tuned model can successfully output all the targets of 62 drugs. Compared with a previous study, our model achieved better results in terms of both AUROC validation and its success rate for obtaining active targets among the top ones. The target prediction model using transfer learning can be applied in the field of natural product-based drug discovery and has the potential to find more lead compounds or to assist researchers in drug repurposing.

show abstract

Privileged Scaffold Analysis of Natural Products with Deep Learning‐based Indication Prediction Model

Cited by 10 publications

References 23 publications

Cheminformatics in Natural Product‐based Drug Discovery

Cheminformatics in Natural Product‐based Drug Discovery

Advanced Methods for Natural Products Discovery: Bioactivity Screening, Dereplication, Metabolomics Profiling, Genomic Sequencing, Databases and Informatic Tools, and Structure Elucidation

Target Prediction Model for Natural Products Using Transfer Learning

Contact Info

Product

Resources

About