br coating can improve the stability
coating can improve the stability of [email protected]/BSA both in water and in serum. Therefore, BSA coating is promising to prolong the circulation time and promote the EPR eﬀect of the drug carriers to achieve a better therapeutic eﬀect.
In summary, a novel redox- and enzyme-responsive [email protected]/BSA was demonstrated for co-delivery of apoptotic peptide KLA and anti-cancer drug DOX in tumor cells. The BSA layer of the [email protected] MSN-SS-KLA/BSA could maintain the stability of [email protected]/ BSA in both aqueous solution and serum within 24 h. Once entering tumor cell, the loaded KLA and DOX can be released quickly due to the cleavage of disulfide bonds and degradation of BSA. In vitro cytotoxicity studies prove that the [email protected]/BSA has the ability of sy-nergetic eﬀect on inhibition of tumor cells, which will find great
potential for cancer treatment.
Conflicts of interest
There are no conflicts of interest to declare.
This work was funded by Zhejiang Provincial Natural Science Foundation of China (LY17E030005), the National Natural Science Foundation of China (Grants 21404091 and 21404089) and Zhejiang Provincial Public Welfare Technology Research Project (2018C37034).
Appendix A. Supplementary data
Supplementary material related to this article can be found, in the
Fig. 8. The particle size distributions of [email protected]/BSA in aqueous solution (A) and 100% serum (B) over time; the particle size distributions of [email protected] in aqueous solution (C), 100% serum (D) over time.
 Y. Uchida, Y. Murakami, Trilayered polymeric micelle: a newly developed macro-molecular assembly that can incorporate Trichostatin A (TSA) compounds, Colloids Surf. B Biointerfaces 79 (2010) 198–204.
 X.K. Xue, X.X. Tang, J. Huang, X.Z. Zhang, J.H. Yu, Y.Z. Zhang, S.B. Gui, Anti-tumor eﬃcacy of polymer-platinum(II) complex micelles fabricated from folate con-jugated PEG-graft-α,β-poly [(N-amino acidyl)-aspartamide] and cis-di-chlorodiammine platinum(II) in tumor-bearing mice, Colloids Surf. B Biointerfaces 85 (2011) 280–288.
 K.P. Liu, Y.M. Wang, H.M. Li, Y.X. Duan, A facile one-pot synthesis of starch functionalized graphene as nano-carrier for pH sensitive and starch-mediated drug delivery, Colloids Surf. B Biointerfaces 128 (2015) 86–93.
 J. Zhang, D. Wu, M. Li, J. Feng, Multifunctional mesoporous silica nanoparticles based on charge-reversal plug gate nanovalves and acid-decomposable ZnO quantum dots for intracellular drug delivery, ACS Appl. Mater. Interfaces 7 (2015) 26666–26673.
Contents lists available at ScienceDirect
Expert Systems With Applications
journal homepage: www.elsevier.com/locate/eswa
A dynamic gradient boosting machine using genetic optimizer for practical breast cancer prognosis
Hongya Lu, Haifeng Wang, Sang Won Yoon∗ Department of Systems Science and Industrial Engineering, State University of New York at Binghamton, Binghamton, NY 13902, United States
Breast cancer prognosis
Adaptive linear regression
This research proposes a novel genetic algorithm-based online gradient boosting (GAOGB) model for in-cremental breast cancer (BC) prognosis. The development of clinical information collection technologies has brought in increasingly large amounts of stream data for BC research. Traditional batch learning mod-els have shown limitations in: (1) real-time prognosis accuracy from losing the information of incremen-tal changes of a patient’s pathological condition by time; (2) high redundancy due to the time required to retrain models every time new data are received. Online boosting is an e cient technique for learning from data streams. However, di culties in parameter assignment and the lack of adaptiveness for batch learning base learners can degrade the performances of typical online boosting algorithms. The main ob-jective of this research is to propose an incremental learning model for BC survivability prediction. To render a boosting algorithm with superiority in global optimal parameters, the genetic algorithm (GA) is integrated to an online gradient boosting scenario at the parameter selection phase, enabling real-time optimization. To enhance adaptiveness, an adaptive linear regressor is adopted as the base learner with minimal computational efforts, and updated in symphony with the online boosting model. The proposed GAOGB model is comprehensively evaluated on the U.S. National Cancer Institute’s Surveillance, Epidemi-ology, and End Results (SEER) program breast cancer dataset in terms of accuracy, area under the curve (AUC), sensitivity, specificity, retraining time, and variation at each iteration. Experimental results show that the proposed GAOGB model achieves statistically outstanding online learning effectiveness. With a highest 28% improvement on testing accuracy over its base learners, outperforming current state-of-art online learning methods, and approximating batch learning boosting algorithms, the GAOGB algorithm validates the impact of parameter, adaptiveness and convergence in devising practical online learning algorithms. The proposed GAOGB model demonstrates potential for practical incremental breast cancer prognosis, promising a combination of training effectiveness and e ciency.