An enhanced cascade-based deep forest model for drug combination prediction

Lin, Weiping; Wu, Lianlian; Zhang, Yixin; Wen, Yao; Yan, Bowei; Dai, Chong; Liu, Kun-Hong; He, Song; Bo, Xiaochen

doi:10.1093/bib/bbab562

Cited by 28 publications

(22 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The concept of combined therapeutics has resulted in development of several types of new cancer drugs with higher efficacy, lower therapeutic dosage, and less drug resistance emergence. Furthermore, combining plant derivate compounds may result in compositions with higher chemopreventive effects (Wagner, 2011;Lotfi-Attari et al, 2017;Bagheri et al, 2018;Adlravan et al, 2021;Lin et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Development of PEGylated PLGA Nanoparticles Co-Loaded with Bioactive Compounds: Potential Anticancer Effect on Breast Cancer Cell Lines

Mohammadinejad

Jafari-Gharabaghlou

Zarghami

2022

Asian Pac J Cancer Prev

View full text Add to dashboard Cite

Objective:The incidence of breast cancer continues to rise despite decades of laboratory, epidemiological and clinical research. Breast cancer is still the leading cause of cancer death in women. Cyclin D1 is one of the most important oncoproteins associated with cancer cell proliferation and is overexpressed in more than 50% of cases. Curcumin and chrysin are plant-derived components that are believed to assist in inhibiting the viability of breast cancer cells. These agents are involved in cancer cells' growth and reducing cyclin D1 expression. In this study, the hypothesis of combining curcumin and chrysin is applied to analyze the potential synergistic effect in inhibiting cancer cell proliferation and down-regulation of cyclin D1. Furthermore, applying PLGA-PEG NPs could improve the bioavailability of free curcumin and chrysin components and at the same time increases the anti-cancer potential of this compound. Methods: PLGA-PEG NPs were synthesized via the ring-opening polymerization technique and characterized with FT-IR and FE-SEM for chemical structure and morphological characteristics, respectively. Next, curcumin and chrysin were loaded in PLGA-PEG NPs and MTT assay was performed to assess the cytotoxic effect of these agents. T-47D cells were treated with appropriate concentrations of these agents and cyclin D1 expression level was evaluated by real-time PCR. Results: The obtained results from FT-IR and FE-SEM techniques illustrated that curcumin and chrysin were efficiently encapsulated into PLGA-PEG NPs. Curcumin, chrysin, and curcumin-chrysin in free and nano-encapsulated forms exhibited an anti-cancer effect on T-47D cells in a time-and dose-dependent manner, especially in a combination of free and encapsulated forms demonstrated synergistic anti-cancer effects. Compared to free form, Nano-curcumin, Nano-chrysin, and Nano-combination remarkably down-regulated cyclin D1 gene expression. (p-value < 0.05). Conclusion: Our results revealed that the curcumin-chrysin combination has a synergistic effect and the encapsulated form of this nano-component has more inhibition on cyclin D1 expression.

show abstract

Section: Introductionmentioning

confidence: 99%

Development of PEGylated PLGA Nanoparticles Co-Loaded with Bioactive Compounds: Potential Anticancer Effect on Breast Cancer Cell Lines

Mohammadinejad

Jafari-Gharabaghlou

Zarghami

2022

Asian Pac J Cancer Prev

View full text Add to dashboard Cite

show abstract

“…A key role may be played by the top 10 genes involved in cancer cell lines. For example, the PGM1 of key genes under the MCF7 cell line, is proven to be associated with breast cancer [ 51 ]. The TSPAN14 of key genes under the A549 cell line, is found to be a potential biomarker and provides a theoretical basis for the pathogenesis of lung adenocarcinoma [ 52 ].…”

Section: Resultsmentioning

confidence: 99%

“…In recent years, tree models have made progress in predicting drug combinations. Wu et al proposed an enhanced deep forest method which can alleviate the unbalanced data problem [ 51 ]. This may suggest that improving the structure and adopting an unbalanced strategy, such as positive data argument, can alleviate the issue.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

DEML: Drug Synergy and Interaction Prediction Using Ensemble-Based Multi-Task Learning

Wang

Dong²,

et al. 2023

Molecules

Self Cite

View full text Add to dashboard Cite

Synergistic drug combinations have demonstrated effective therapeutic effects in cancer treatment. Deep learning methods accelerate identification of novel drug combinations by reducing the search space. However, potential adverse drug–drug interactions (DDIs), which may increase the risks for combination therapy, cannot be detected by existing computational synergy prediction methods. We propose DEML, an ensemble-based multi-task neural network, for the simultaneous optimization of five synergy regression prediction tasks, synergy classification, and DDI classification tasks. DEML uses chemical and transcriptomics information as inputs. DEML adapts the novel hybrid ensemble layer structure to construct higher order representation using different perspectives. The task-specific fusion layer of DEML joins representations for each task using a gating mechanism. For the Loewe synergy prediction task, DEML overperforms the state-of-the-art synergy prediction method with an improvement of 7.8% and 13.2% for the root mean squared error and the R2 correlation coefficient. Owing to soft parameter sharing and ensemble learning, DEML alleviates the multi-task learning ‘seesaw effect’ problem and shows no performance loss on other tasks. DEML has a superior ability to predict drug pairs with high confidence and less adverse DDIs. DEML provides a promising way to guideline novel combination therapy strategies for cancer treatment.

show abstract

“…We combined all drugs and removed the existing drug pairs in the original training data, yielding 439 drug pairs in total. These novel drug combinations were tested on three typical cell lines (HCT116, HT29 and A375) [Lin et al, 2022]. Figure 5) showed the distribution of all predicted probabilities on three cell lines.…”

Section: Results and Analysismentioning

confidence: 99%

DTSyn: a dual-transformer-based neural network to predict synergistic drug combinations

Gao²,

Fang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Drug combination therapies are superior to monotherapy for cancer treatment in many ways when addressing tumor heterogeneity issue. For wet-lab experiment, screening out novel synergistic drug pairs is challenging due to the enormous searching space of possible drug pairs. Thus, computational methods have been developed to predict drug pairs with potential synergistic function. Notwithstanding the success of current models, the power of generalization to other datasets as wells as understanding of mechanism for chemical-chemical interaction or chemical-sample interaction are lack of study, hindering current algorithms from real application. In this paper, we proposed a deep neural model termed DTSyn (Dual Transformer model for drug pair Synergy prediction) based on multi-head attention mechanism to identify novel drug combinations. We designed a fine-granularity transformer for capturing chemical substructure-gene and gene-gene associations and a coarse-granularity transformer for extracting and chemical-chemical and chemical-cell line interactions. DTSyn achieves highest Receiver operating characteristic area under curve (ROC AUC) of 0.73, 0.78. 0.82 and 0.81 on four different cross validation tasks, outperforming all competing methods. Further, DTSyn achieved best True Positive Rate (TPR) over five independent datasets. The ablation study showed that both transformer blocks contributed to the performance of DTSyn. In addition, DTSyn can extract interactions among chemicals and cell lines, which may represent the mechanisms of drug action. Thus, we envision our model a valuable tool to prioritize synergistic drug pairs by utilizing chemicals and transcriptome data.

show abstract

An enhanced cascade-based deep forest model for drug combination prediction

Cited by 28 publications

References 78 publications

Development of PEGylated PLGA Nanoparticles Co-Loaded with Bioactive Compounds: Potential Anticancer Effect on Breast Cancer Cell Lines

Development of PEGylated PLGA Nanoparticles Co-Loaded with Bioactive Compounds: Potential Anticancer Effect on Breast Cancer Cell Lines

DEML: Drug Synergy and Interaction Prediction Using Ensemble-Based Multi-Task Learning

DTSyn: a dual-transformer-based neural network to predict synergistic drug combinations

Contact Info

Product

Resources

About