Dataset Information

A hybrid deep forest-based method for predicting synergistic drug combinations.

ABSTRACT: Combination therapy is a promising approach in treating multiple complex diseases. However, the large search space of available drug combinations exacerbates challenge for experimental screening. To predict synergistic drug combinations in different cancer cell lines, we propose an improved deep forest-based method, ForSyn, and design two forest types embedded in ForSyn. ForSyn handles imbalanced and high-dimensional data in medium-/small-scale datasets, which are inherent characteristics of drug combination datasets. Compared with 12 state-of-the-art methods, ForSyn ranks first on four metrics for eight datasets with different feature combinations. We conduct a systematic analysis to identify the most appropriate configuration parameters. We validate the predictive value of ForSyn with cell-based experiments on several previously unexplored drug combinations. Finally, a systematic analysis of feature importance is performed on the top contributing features extracted by ForSyn. The resulting key genes may play key roles on corresponding cancers.

SUBMITTER: Wu L

PROVIDER: S-EPMC10014304 | biostudies-literature | 2023 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A hybrid deep forest-based method for predicting synergistic drug combinations.

Wu Lianlian L Gao Jie J Zhang Yixin Y Sui Binsheng B Wen Yuqi Y Wu Qingqiang Q Liu Kunhong K He Song S Bo Xiaochen X

Cell reports methods 20230221 2

Combination therapy is a promising approach in treating multiple complex diseases. However, the large search space of available drug combinations exacerbates challenge for experimental screening. To predict synergistic drug combinations in different cancer cell lines, we propose an improved deep forest-based method, ForSyn, and design two forest types embedded in ForSyn. ForSyn handles imbalanced and high-dimensional data in medium-/small-scale datasets, which are inherent characteristics of dru ...[more]

PMID: 36936075

Similar Datasets

Project description:BackgroundThe discovery of anticancer drug combinations is a crucial work of anticancer treatment. In recent years, pre-screening drug combinations with synergistic effects in a large-scale search space adopting computational methods, especially deep learning methods, is increasingly popular with researchers. Although achievements have been made to predict anticancer synergistic drug combinations based on deep learning, the application of multi-task learning in this field is relatively rare. The successful practice of multi-task learning in various fields shows that it can effectively learn multiple tasks jointly and improve the performance of all the tasks.MethodsIn this paper, we propose MTLSynergy which is based on multi-task learning and deep neural networks to predict synergistic anticancer drug combinations. It simultaneously learns two crucial prediction tasks in anticancer treatment, which are synergy prediction of drug combinations and sensitivity prediction of monotherapy. And MTLSynergy integrates the classification and regression of prediction tasks into the same model. Moreover, autoencoders are employed to reduce the dimensions of input features.ResultsCompared with the previous methods listed in this paper, MTLSynergy achieves the lowest mean square error of 216.47 and the highest Pearson correlation coefficient of 0.76 on the drug synergy prediction task. On the corresponding classification task, the area under the receiver operator characteristics curve and the area under the precision-recall curve are 0.90 and 0.62, respectively, which are equivalent to the comparison methods. Through the ablation study, we verify that multi-task learning and autoencoder both have a positive effect on prediction performance. In addition, the prediction results of MTLSynergy in many cases are also consistent with previous studies.ConclusionOur study suggests that multi-task learning is significantly beneficial for both drug synergy prediction and monotherapy sensitivity prediction when combining these two tasks into one model. The ability of MTLSynergy to discover new anticancer synergistic drug combinations noteworthily outperforms other state-of-the-art methods. MTLSynergy promises to be a powerful tool to pre-screen anticancer synergistic drug combinations.

Project description:Echinococcosis is a zoonotic parasitic disease caused by the larvae of echinococcus tapeworms infesting the human body. Drug combination therapy is highly valued for the treatment of echinococcosis because of its potential to overcome resistance and enhance the response to existing drugs. Traditional methods of identifying drug combinations via biological experimentation is costly and time-consuming. Besides, the scarcity of existing drug combinations for echinococcosis hinders the development of computational methods. In this study, we propose a transfer learning-based model, namely TransferBAN-Syn, to identify synergistic drug combinations against echinococcosis based on abundant information of drug combinations against parasitic diseases. To the best of our knowledge, this is the first work that leverages transfer learning to improve prediction accuracy with limited drug combination data in echinococcosis treatment. Specifically, TransferBAN-Syn contains a drug interaction feature representation module, a disease feature representation module, and a prediction module, where the bilinear attention network is employed in the drug interaction feature representation module to deeply extract the fusion feature of drug combinations. Besides, we construct a special dataset with multi-source information and drug combinations for parasitic diseases, including 21 parasitic diseases and echinococcosis. TransferBAN-Syn is designed and initially trained on the abundant data from the 21 parasitic diseases, which serves as the source domain. The parameters in the feature representation modules of drug interactions and diseases are preserved from this source domain, and those in the prediction module are then fine-tuned to specifically identify the synergistic drug combinations for echinococcosis in the target domain. Comparison experiments have shown that TransferBAN-Syn not only improves the accuracy of predicting echinococcosis drug combinations but also enhances generalizability. Furthermore, TransferBAN-Syn identifies potential drug combinations that hold promise in the treatment of echinococcosis. TransferBAN-Syn not only offers new synergistic drug combinations for echinococcosis but also provides a novel approach for predicting potential drug pairs for diseases with limited combination data.

Dataset Information

A hybrid deep forest-based method for predicting synergistic drug combinations.

Publications

A hybrid deep forest-based method for predicting synergistic drug combinations.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets