Few-Shot Drug Synergy Prediction With a Prior-Guided Hypernetwork Architecture

Zhang, Qingqing; Zhang, Shao-Wu; Feng, Yue-Hua; Shi, Jian-Yu

doi:10.1109/tpami.2023.3248041

Cited by 5 publications

(6 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While k-fold cross-validation (CV) techniques are commonly employed, certain studies have adopted specialized CV strategies to better simulate real-world scenarios. [67][68][69][70][71][72][73][74] These strategies include:…”

Section: Discussionmentioning

confidence: 99%

“…The evaluation of model performance is a crucial step in assessing the efficacy of these models. While k‐fold cross‐validation (CV) techniques are commonly employed, certain studies have adopted specialized CV strategies to better simulate real‐world scenarios 67–74 . These strategies include: Leave Cell Line Out (LCO): This strategy involves excluding specific cell lines from the training data, enabling assessment of the model's performance across different diseases.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning for predicting synergistic drug combinations: State‐of‐the‐arts and future directions

Wang,

Liu

2024

Clinical and Translational Dis

View full text Add to dashboard Cite

Combination therapy has emerged as an efficacy strategy for treating complex diseases. Its potential to overcome drug resistance and minimize toxicity makes it highly desirable. However, the vast number of potential drug pairs presents a significant challenge, rendering exhaustive clinical testing impractical. In recent years, deep learning‐based methods have emerged as promising tools for predicting synergistic drug combinations. This review aims to provide a comprehensive overview of applying diverse deep‐learning architectures for drug combination prediction. This review commences by elucidating the quantitative measures employed to assess drug combination synergy. Subsequently, we delve into the various deep‐learning methods currently employed for drug combination prediction. Finally, the review concludes by outlining the key challenges facing deep learning approaches and proposes potential challenges for future research.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Deep learning for predicting synergistic drug combinations: State‐of‐the‐arts and future directions

Wang,

Liu

2024

Clinical and Translational Dis

View full text Add to dashboard Cite

show abstract

“…Few-shot learning has emerged with techniques to train on tasks where only a few data points, usually less than 10, are available per task during the training process. − By making use of available information about a given task, machine learning models are now able to make predictions during inference on tasks where no training data is available. Such inference is called zero-shot . During the prediction of drug–target interactions, the protein targets corresponds to the different tasks of the problem.…”

Section: Introductionmentioning

confidence: 99%

“…Such inference is called zero-shot . 36 During the prediction of drug–target interactions, the protein targets corresponds to the different tasks of the problem. Figure 1 illustrates the difference between many-, few-, and zero-shot inference when modeling drug–target interactions.…”

Section: Introductionmentioning

confidence: 99%

“…However, no information about the protein targets was used and as such the prediction of parameters could not be task-conditioned nor could the resulting model perform zero-shot inference. Zhang et al 36 also propose the use of a HyperNetwork architecture in a drug discovery application, but rather for the prediction of drug synergy in cell lines of cancer patients. Their proposed HyperNetwork is designed for few-shot learning on cell lines with low amounts of data and can be understood as a task-conditioned prediction of parameters for the drug synergy model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HyperPCM: Robust Task-Conditioned Modeling of Drug–Target Interactions

Svensson,

Hoedt,

Hochreiter

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

A central problem in drug discovery is to identify the interactions between drug-like compounds and protein targets. Over the past few decades, various quantitative structure−activity relationship (QSAR) and proteo-chemometric (PCM) approaches have been developed to model and predict these interactions. While QSAR approaches solely utilize representations of the drug compound, PCM methods incorporate both representations of the protein target and the drug compound, enabling them to achieve above-chance predictive accuracy on previously unseen protein targets. Both QSAR and PCM approaches have recently been improved by machine learning and deep neural networks, that allow the development of drug−target interaction prediction models from measurement data. However, deep neural networks typically require large amounts of training data and cannot robustly adapt to new tasks, such as predicting interaction for unseen protein targets at inference time. In this work, we propose to use HyperNetworks to efficiently transfer information between tasks during inference and thus to accurately predict drug−target interactions on unseen protein targets. Our HyperPCM method reaches state-of-the-art performance compared to previous methods on multiple well-known benchmarks, including Davis, DUD-E, and a ChEMBL derived data set, and particularly excels at zero-shot inference involving unseen protein targets. Our method, as well as reproducible data preparation, is available at https://github.com/ml-jku/hyper-dti.

show abstract

Drug discovery and development in the era of artificial intelligence: From machine learning to large language models

Guan,

Wang

2024

Artificial Intelligence Chemistry

View full text Add to dashboard Cite

Few-Shot Drug Synergy Prediction With a Prior-Guided Hypernetwork Architecture

Cited by 5 publications

References 44 publications

Deep learning for predicting synergistic drug combinations: State‐of‐the‐arts and future directions

Deep learning for predicting synergistic drug combinations: State‐of‐the‐arts and future directions

HyperPCM: Robust Task-Conditioned Modeling of Drug–Target Interactions

Drug discovery and development in the era of artificial intelligence: From machine learning to large language models

Contact Info

Product

Resources

About