Development of predictive QSAR models for the substrates/inhibitors of OATP1B1 by deep neural networks

Gui, Chunshan; Liu, Ying; Peng, Taotao

doi:10.1016/j.toxlet.2023.01.006

Cited by 6 publications

(2 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Gui et al . developed a deep regression model using data from 258 OATP1B1 substrates/inhibitors [19]; McLoughlin et al . explored various methods, to build an effective BSEP inhibitor prediction model [20]; Namasivayam et al .…”

Section: Introductionmentioning

confidence: 99%

“…In the past decade, machine learning models for prediction of compound-transporter interactions have gained popularity due to advances in artificial intelligence technology [16][17][18]. For instance, Gui et al developed a deep regression model using data from 258 OATP1B1 substrates/inhibitors [19]; McLoughlin et al explored various methods, to build an effective BSEP inhibitor prediction model [20]; Namasivayam et al focused on the study of multi-target inhibitors of ABC transporters [21,22]. While the models previously mentioned have shown excellent predictive performance and significantly advanced the field, there remains an opportunity for further exploration into the interrelations among transporters and the transferability of knowledge across different models.…”

mentioning

confidence: 99%

See 1 more Smart Citation

In Silicoprediction of inhibitors for multiple transporters via machine learning methods

Duan,

Lou,

et al. 2024

Molecular Informatics

View full text Add to dashboard Cite

Transporters play an indispensable role in facilitating the transport of nutrients, signaling molecules and the elimination of metabolites and toxins in human cells. Contemporary computational methods have been employed in the prediction of transporter inhibitors. However, these methods often focus on isolated endpoints, overlooking the interactions between transporters and lacking good interpretation. In this study, we integrated a comprehensive dataset and constructed models to assess the inhibitory effects on seven transporters. Both conventional machine learning and multi‐task deep learning methods were employed. The results demonstrated that the MLT‐GAT model achieved superior performance with an average AUC value of 0.882. It is noteworthy that our model excels not only in prediction performance but also in achieving robust interpretability, aided by GNN‐Explainer. It provided valuable insights into transporter inhibition. The reliability of our model's predictions positioned it as a promising and valuable tool in the field of transporter inhibition research. Related data and code were available at https://gitee.com/wutiantian99/transporter_code.git

show abstract

Section: Introductionmentioning

confidence: 99%