Prednimustine combined with mitoxantrone and 5-fluorouracil for first and second-line chemotherapy in advanced breast cancer

Predicting synergistic anticancer drug combination based on low-rank global attention mechanism and bilinear predictor

MOTIVATION

Drug combination therapy has exhibited remarkable therapeutic efficacy and has gradually become a promising clinical treatment strategy of complex diseases such as cancers. As the related databases keep expanding, computational methods based on deep learning model have become powerful tools to predict synergistic drug combinations. However, predicting effective synergistic drug combinations is still a challenge due to the high complexity of drug combinations, the lack of biological interpretability, and the large discrepancy in the response of drug combinations in vivo and in vitro biological systems.

RESULTS

Here, we propose DGSSynADR, a new deep learning method based on global structured features of drugs and targets for predicting synergistic anticancer drug combinations. DGSSynADR constructs a heterogeneous graph by integrating the drug-drug, drug-target, protein-protein interactions and multi-omics data, utilizes a low-rank global attention (LRGA) model to perform global weighted aggregation of graph nodes and learn the global structured features of drugs and targets, and then feeds the embedded features into a bilinear predictor to predict the synergy scores of drug combinations in different cancer cell lines. Specifically, LRGA network brings better model generalization ability, and effectively reduces the complexity of graph computation. The bilinear predictor facilitates the dimension transformation of the features and fuses the feature representation of the two drugs to improve the prediction performance. The loss function Smooth L1 effectively avoids gradient explosion, contributing to better model convergence. To validate the performance of DGSSynADR, we compare it with seven competitive methods. The comparison results demonstrate that DGSSynADR achieves better performance. Meanwhile, the prediction of DGSSynADR is validated by previous findings in case studies. Furthermore, detailed ablation studies indicate that the one-hot coding drug feature, LRGA model and bilinear predictor play a key role in improving the prediction performance.

AVAILABILITY AND IMPLEMENTATION

DGSSynADR is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/DHUDBlab/DGSSynADR.

Haematological toxicity: a marker of adjuvant chemotherapy efficacy in stage II and III breast cancer

Two hundred and eleven patients with node-positive stage II and III breast cancer were treated with eight cycles of adjuvant chemotherapy comprising cyclophosphamide, doxorubicin and oral ftorafur (CAFt), with and without tamoxifen. All patients had undergone radical surgery, and 148 patients were treated with post-operative radiotherapy in two randomized studies. The impact of haematological toxicity of CAFt on distant disease-free (DDFS) and overall survival (OS) was recorded. Dose intensity of all given cycles (DI), dose intensity of the two initial cycles (DI2) and total dose (TD) were calculated separately for all chemotherapy drugs and were correlated with DDFS and OS. Patients with a lower leucocyte nadir during the chemotherapy had significantly better DDFS and OS (P = 0.01 and 0.04 respectively). Dose intensity of the two first cycles also correlated significantly with DDFS (P = 0.05) in univariate but not in multivariate analysis, while the leucocyte nadir retained its prognostic value. These results indicate that the leucocyte nadir during the adjuvant chemotherapy is a biological marker of chemotherapy efficacy; this presents the possibility of establishing an optimal dose intensity for each patient. The initial dose intensity of adjuvant chemotherapy also seems to be important in assuring the optimal effect of adjuvant chemotherapy.