Modeling DTA by Combining Multiple-Instance Learning with a Private-Public Mechanism

Wang, Chuyu; Chen, Yuanlong; Zhao, Lingling; Wang, Junjie; Wen, Naifeng

doi:10.3390/ijms231911136

Cited by 2 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the Davis dataset, the MSE metric of the DoubleSG-DTA model was 0.219, 0.004 lower than the best DMIL-PPDTA [ 18 ] model in the sequence-based models, and the CI and

metrics of our model were 0.902 and 0.725, 0.009 and 0.04 higher than FNN [ 20 ] model in the sequence-based models, respectively. When comparing with the best GraphDTA [ 11 ] model in the graph-based models, the CI value was increased by 0.009 and the MSE value was decreased by 4.37%.…”

Section: Resultsmentioning

confidence: 84%

“…In this part, we conducted experiments applying the MSE(↓), CI(↑), and

(↑) to assess the DoubleSG-DTA method and previous studies on the above three benchmark datasets, including DeepDTA [ 8 ], GraphDTA [ 11 ], MATT-DTI [ 13 ], AttentionDTA [ 16 ], DeepCDA [ 17 ], and DMIL-PPDTA [ 18 ]. Besides, we also benchmarked our work against proteochemometrics methods [ 35 ], including the support vector machine (SVM), feedforward neural network (FNN), SimBoost [ 12 ], Random Forest (RF) [ 14 ], and KronRLS [ 15 ].…”

Section: Methodsmentioning

confidence: 99%

“…Transformer-based works have come to the fore in various natural language processing (NLP) tasks. DMIL-PPDTA utilized the transformer encoder to enrich word embeddings of drug and protein sequences, aiming to learn hidden associations from the raw data [ 18 ]. DeepAtom [ 19 ] extrapolated node-level interaction information relevant to binding from the voxelized protein–compound complex structures.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DoubleSG-DTA: Deep Learning for Drug Discovery: Case Study on the Non-Small Cell Lung Cancer with EGFRT790M Mutation

Qian

Xianyu

et al. 2023

Pharmaceutics

View full text Add to dashboard Cite

drug–targeted therapies are promising approaches to treating tumors, and research on receptor–ligand interactions for discovering high-affinity targeted drugs has been accelerating drug development. This study presents a mechanism-driven deep learning-based computational model to learn double drug sequences, protein sequences, and drug graphs to project drug–target affinities (DTAs), which was termed the DoubleSG-DTA. We deployed lightweight graph isomorphism networks to aggregate drug graph representations and discriminate between molecular structures, and stacked multilayer squeeze-and-excitation networks to selectively enhance spatial features of drug and protein sequences. What is more, cross-multi-head attentions were constructed to further model the non-covalent molecular docking behavior. The multiple cross-validation experimental evaluations on various datasets indicated that DoubleSG-DTA consistently outperformed all previously reported works. To showcase the value of DoubleSG-DTA, we applied it to generate promising hit compounds of Non-Small Cell Lung Cancer harboring EGFRT790M mutation from natural products, which were consistent with reported laboratory studies. Afterward, we further investigated the interpretability of the graph-based “black box” model and highlighted the active structures that contributed the most. DoubleSG-DTA thus provides a powerful and interpretable framework that extrapolates for potential chemicals to modulate the systemic response to disease.

show abstract

“…Considering the Davis dataset, the MSE metric of the DoubleSG-DTA model was 0.219, 0.004 lower than the best DMIL-PPDTA [ 18 ] model in the sequence-based models, and the CI and

Section: Resultsmentioning

confidence: 84%

“…In this part, we conducted experiments applying the MSE(↓), CI(↑), and

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DoubleSG-DTA: Deep Learning for Drug Discovery: Case Study on the Non-Small Cell Lung Cancer with EGFRT790M Mutation

Qian

Xianyu

et al. 2023

Pharmaceutics

View full text Add to dashboard Cite

show abstract

SAFE-MIL: a statistically interpretable framework for screening potential targeted therapy patients based on risk estimation

Guan,

Xue,

Wang

et al. 2024

Front. Genet.

View full text Add to dashboard Cite

Patients with the target gene mutation frequently derive significant clinical benefits from target therapy. However, differences in the abundance level of mutations among patients resulted in varying survival benefits, even among patients with the same target gene mutations. Currently, there is a lack of rational and interpretable models to assess the risk of treatment failure. In this study, we investigated the underlying coupled factors contributing to variations in medication sensitivity and established a statistically interpretable framework, named SAFE-MIL, for risk estimation. We first constructed an effectiveness label for each patient from the perspective of exploring the optimal grouping of patients’ positive judgment values and sampled patients into 600 and 1,000 groups, respectively, based on multi-instance learning (MIL). A novel and interpretable loss function was further designed based on the Hosmer-Lemeshow test for this framework. By integrating multi-instance learning with the Hosmer-Lemeshow test, SAFE-MIL is capable of accurately estimating the risk of drug treatment failure across diverse patient cohorts and providing the optimal threshold for assessing the risk stratification simultaneously. We conducted a comprehensive case study involving 457 non-small cell lung cancer patients with EGFR mutations treated with EGFR tyrosine kinase inhibitors. Results demonstrate that SAFE-MIL outperforms traditional regression methods with higher accuracy and can accurately assess patients’ risk stratification. This underscores its ability to accurately capture inter-patient variability in risk while providing statistical interpretability. SAFE-MIL is able to effectively guide clinical decision-making regarding the use of drugs in targeted therapy and provides an interpretable computational framework for other patient stratification problems. The SAFE-MIL framework has proven its effectiveness in capturing inter-patient variability in risk and providing statistical interpretability. It outperforms traditional regression methods and can effectively guide clinical decision-making in the use of drugs for targeted therapy. SAFE-MIL offers a valuable interpretable computational framework that can be applied to other patient stratification problems, enhancing the precision of risk assessment in personalized medicine. The source code for SAFE-MIL is available for further exploration and application at https://github.com/Nevermore233/SAFE-MIL.

show abstract

Modeling DTA by Combining Multiple-Instance Learning with a Private-Public Mechanism

Cited by 2 publications

References 26 publications

DoubleSG-DTA: Deep Learning for Drug Discovery: Case Study on the Non-Small Cell Lung Cancer with EGFRT790M Mutation

DoubleSG-DTA: Deep Learning for Drug Discovery: Case Study on the Non-Small Cell Lung Cancer with EGFRT790M Mutation

SAFE-MIL: a statistically interpretable framework for screening potential targeted therapy patients based on risk estimation

Contact Info

Product

Resources

About