Development of Ligand‐based Big Data Deep Neural Network Models for Virtual Screening of Large Compound Libraries

Xiao, Tao; Qi, Xingxing; Chen, Yu Zong; Jiang, Yuyang

doi:10.1002/minf.201800031

Cited by 17 publications

(7 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Among the other methods, DNN is a powerful tool that can deal with large data without manual engineering. It is built on six datasets collected from the ChEMBL database (EGFR inhibitors); the DNN model also obtained high performance in comparison with the RF method by cross-validation or screening a large compound library (PubChem, ChemDiv database) [ 87 ]. Besides, the least-squares- SVM (LS-SVM) and genetic algorithm-MLR algorithms has been conducted to predict IC 50 of poly ADP-ribose polymerase-1 inhibitors for breast cancer, the outcomes (R 2 , F, RMSE, Q 2 cv ) proved that LS–SVM had good potential mathematical optimization base in comparison with MLR [ 88 ].…”

Section: Ligand-based Virtual Screeningmentioning

confidence: 99%

Opportunities and challenges in application of artificial intelligence in pharmacology

et al. 2023

View full text Add to dashboard Cite

Artificial intelligence (AI) is a machine science that can mimic human behaviour like intelligent analysis of data. AI functions with specialized algorithms and integrates with deep and machine learning. Living in the digital world can generate a huge amount of medical data every day. Therefore, we need an automated and reliable evaluation tool that can make decisions more accurately and faster. Machine learning has the potential to learn, understand and analyse the data used in healthcare systems. In the last few years, AI is known to be employed in various fields in pharmaceutical science especially in pharmacological research. It helps in the analysis of preclinical (laboratory animals) and clinical (in human) trial data. AI also plays important role in various processes such as drug discovery/manufacturing, diagnosis of big data for disease identification, personalized treatment, clinical trial research, radiotherapy, surgical robotics, smart electronic health records, and epidemic outbreak prediction. Moreover, AI has been used in the evaluation of biomarkers and diseases. In this review, we explain various models and general processes of machine learning and their role in pharmacological science. Therefore, AI with deep learning and machine learning could be relevant in pharmacological research.

show abstract

Section: Ligand-based Virtual Screeningmentioning

confidence: 99%

Opportunities and challenges in application of artificial intelligence in pharmacology

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Still, some authors have described methods which involve training or refining a model for target-specific recall of novel hits leveraging datasets of known actives. 46 Others have attempted to address the large training set limitation and improve the applicability of deep learning models in several ways. Altae-Tran et al 40 leveraged the "one-shot learning" framework, to carry out virtual screening supported by anywhere between 1 and 10 known actives and decoys, each, per target.…”

Section: Two Of the Earliest Reports Of Deep Learning Architectures Amentioning

confidence: 99%

“…Namely, since any prospective application of LBVS would only be able to benefit from a few known actives, the requirement for a large training set presents a significant limitation. Still, some authors have described methods that involve training or refining a model for target-specific recall of novel hits leveraging datasets of known actives . Others have attempted to address the large training set limitation and improve the applicability of deep learning models in several ways.…”

Section: Related Workmentioning

confidence: 99%

Improved Scaffold Hopping in Ligand-Based Virtual Screening Using Neural Representation Learning

Stojanović¹,

Popović²,

Tijanić³

et al. 2020

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Deep learning has demonstrated significant potential in advancing state of the art in many problem domains, especially those benefiting from automated feature extraction. Yet the methodology has seen limited adoption in the field of ligand-based virtual screening (LBVS), as traditional approaches typically require large, target-specific training sets, which limits their value in most prospective applications. Here, we report the development of a neural network architecture, and a learning framework designed to yield a generally applicable tool for LBVS. Our approach uses the molecular graph as input, and involves learning a representation that places compounds of similar biological profiles in close proximity within a hyperdimensional feature space; this is achieved by simultaneously leveraging historical screening data against a multitude of targets during training. Cosine distance between molecules in this space becomes a general similarity metric, and can readily be used to rank order database compounds in LBVS workflows. We demonstrate the resulting model generalizes exceptionally well to compounds and targets not used in its training. In three commonly employed LBVS benchmarks, our method outperforms popular fingerprinting algorithms without the need for any target-specific training. Moreover, we show the learned representation yields superior performance in scaffold hopping tasks, and is largely orthogonal to existing fingerprints. Summarily, we have developed and validated a framework for learning a molecular representation that is applicable to LBVS in a target-agnostic fashion, with as few as one query compound. Our approach can also enable organizations to generate additional value from large screening data repositories, and to this end we are making its implementation freely available at https://github.com/totient-bio/gatnn-vs File list (2) download file view on ChemRxiv GATNN VS.pdf (5.45 MiB) download file view on ChemRxiv GATNN VS SI Text.pdf (4.46 MiB)

show abstract

“…Compared to traditional ML methods with manually designed features, DNN facilitates the utilization of large data sets by automatically learning features from raw input data and having fewer generalization errors [25]. Recently, sophisticated deep learning methods have been applied in VS due to the high recall and low false-positive rates, and could be combined with other methods to develop more efficient and accurate VS methods to discover novel active molecules [26][27][28]. However, as far as we know, research on ML predictive models for VS of kinase inhibitors was quite limited, and lacked bioactivity validation [5,20,29,30].…”

Section: Introductionmentioning

confidence: 99%

Discovery of novel JAK1 inhibitors through combining machine learning, structure-based pharmacophore modeling and bio-evaluation

Wang

Sun

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Janus kinase 1 (JAK1) plays a critical role in most cytokine-mediated inflammatory, autoimmune responses and various cancers via the JAK/STAT signaling pathway. Inhibition of JAK1 is therefore an attractive therapeutic strategy for several diseases. Recently, high-performance machine learning techniques have been increasingly applied in virtual screening to develop new kinase inhibitors. Our study aimed to develop a novel layered virtual screening method based on machine learning (ML) and pharmacophore models to identify the potential JAK1 inhibitors. Methods Firstly, we constructed a high-quality dataset comprising 3834 JAK1 inhibitors and 12230 decoys, followed by established a series of classification models based on a combination of three molecular descriptors and six ML algorithms. To further screen potential compounds, we constructed several pharmacophore models based on Hiphop and receptor-ligand algorithms. We then used molecular docking to filter the recognized compounds. Finally, the binding stability and enzyme inhibition activity of the identified compounds were assessed by molecular dynamics (MD) simulations and in vitro enzyme activity tests. Results The best performance ML model DNN-ECFP4 and two pharmacophore models Hiphop3 and 6TPF 08 were utilized to screen the ZINC database. A total of 13 potentially active compounds were screened and the MD results demonstrated that all of the above molecules could bind with JAK1 stably in dynamic conditions. Among the shortlisted compounds, the four purchasable compounds demonstrated significant kinase inhibition activity, with Z-10 being the most active (IC50 = 194.9 nM). Conclusion The current study provides an efficient and accurate integrated model. The hit compounds were promising candidates for the further development of novel JAK1 inhibitors.

show abstract

Development of Ligand‐based Big Data Deep Neural Network Models for Virtual Screening of Large Compound Libraries

Cited by 17 publications

References 63 publications

Opportunities and challenges in application of artificial intelligence in pharmacology

Opportunities and challenges in application of artificial intelligence in pharmacology

Improved Scaffold Hopping in Ligand-Based Virtual Screening Using Neural Representation Learning

Discovery of novel JAK1 inhibitors through combining machine learning, structure-based pharmacophore modeling and bio-evaluation

Contact Info

Product

Resources

About