Purpose: We investigated the antitumor activity of the combination of two different humanized monoclonal human epidermal growth factor receptor (HER) 2 antibodies, pertuzumab and trastuzumab, for gastric cancer. Experimental Design: Tumor mouse xenograft models were used to examine antitumor activity. Cell proliferation was examined using crystal violet staining. HER family proteins' expression was analyzed by ELISA and immunohistochemistry. Phosphorylated proteins and heterodimers were detected by Western blotting and in situ proximity ligation assay (PLA), respectively. Apoptosis activity was examined by caspase 3/7 activity. Antibody-dependent cellular cytotoxicity (ADCC) activity was detected by xCELLigence. Microvessel density was examined by CD31 staining. Results: Pertuzumab in combination with trastuzumab showed significant antitumor activity compared with each monotherapy in NCI-N87, an HER2-positive human gastric cancer xenograft model. The efficacy was stronger than that of the maximum effective dose with each monotherapy. Similar antitumor activity was shown in 4-1ST, another HER2-positive gastric cancer model, but not in MKN-28, an HER2-negative model. Combining pertuzumab with trastuzumab enhanced cell growth inhibition and apoptosis activity by inhibiting EGFR-HER2 heterodimerization and the phosphorylation of these receptors and their downstream factors. This effect was also seen in HER2-HER3 signaling. Furthermore, pertuzumab in combination with trastuzumab potentiated the ADCC activity of those antibodies and reduced tumor microvessel density. Conclusions: We showed the significantly enhanced efficacy of pertuzumab combining with trastuzumab for HER2 overexpressing gastric cancer through the potentiation of cell growth inhibition, apoptosis activity, cell killing activity by ADCC, and antiangiogenic activity. This study suggests the clinical benefit of combination therapy with pertuzumab and trastuzumab for patients with HER2-positive gastric cancers. Clin Cancer Res; 17(15); 5060–70. ©2011 AACR.

Deep learning is developing as an important technology to perform various tasks in cheminformatics. In particular, graph convolutional neural networks (GCNs) have been reported to perform well in many types of prediction tasks related to molecules. Although GCN exhibits considerable potential in various applications, appropriate utilization of this resource for obtaining reasonable and reliable prediction results requires thorough understanding of GCN and programming. To leverage the power of GCN to benefit various users from chemists to cheminformaticians, an open-source GCN tool, kGCN, is introduced. To support the users with various levels of programming skills, kGCN includes three interfaces: a graphical user interface (GUI) employing KNIME for users with limited programming skills such as chemists, as well as command-line and Python library interfaces for users with advanced programming skills such as cheminformaticians. To support the three steps required for building a prediction model, i.e., pre-processing, model tuning, and interpretation of results, kGCN includes functions of typical pre-processing, Bayesian optimization for automatic model tuning, and visualization of the atomic contribution to prediction for interpretation of results. kGCN supports three types of approaches, single-task, multi-task, and multi-modal predictions. The prediction of compound-protein interaction for four matrixmetalloproteases, MMP-3, -9, -12 and -13, in the inhibition assays is performed as a representative case study using kGCN. Additionally, kGCN provides the visualization of atomic contributions to the prediction. Such visualization is useful for the validation of the prediction models and the design of molecules based on the prediction model, realizing “explainable AI” for understanding the factors affecting AI prediction. kGCN is available at https://github.com/clinfo.

Here, we have constructed neural network-based models that predict atomic partial charges with high accuracy at low computational cost. The models were trained using high-quality data acquired from quantum mechanics calculations using the fragment molecular orbital method. We have succeeded in obtaining highly accurate atomic partial charges for three representative molecular systems of proteins, including one large biomolecule (approx. 2000 atoms). The novelty of our approach is the ability to take into account the electronic polarization in the system, which is a system-dependent phenomenon, being important in the field of drug design. Our high-precision models are useful for the prediction of atomic partial charges and expected to be widely applicable in structure-based drug designs such as structural optimization, high-speed and high-precision docking, and molecular dynamics calculations.