GraphMHC: Neoantigen prediction model applying the graph neural network to molecular structure.

Neoantigens are tumor-derived peptides and are biomarkers that can predict prognosis related to immune checkpoint inhibition by estimating their binding to major histocompatibility complex (MHC) proteins. Although deep neural networks have been primarily used for these prediction models, it is difficult to interpret the models reported thus far as accurately representing the interactions between biomolecules. In this study, we propose the GraphMHC model, which utilizes a graph neural network model applied to molecular structure to simulate the binding between MHC proteins and peptide sequences. Amino acid sequences sourced from the immune epitope database (IEDB) undergo conversion into molecular structures. Subsequently, atomic intrinsic informations and inter-atomic connections are extracted and structured as a graph representation. Stacked graph attention and convolution layers comprise the GraphMHC network which classifies bindings. The prediction results from the test set using the GraphMHC model showed a high performance with an area under the receiver operating characteristic curve of 92.2% (91.9-92.5%), surpassing a baseline model. Moreover, by applying the GraphMHC model to melanoma patient data from The Cancer Genome Atlas project, we found a borderline difference (0.061) in overall survival and a significant difference in stromal score between the high and low neoantigen load groups. This distinction was not present in the baseline model. This study presents the first feature-intrinsic method based on biochemical molecular structure for modeling the binding between MHC protein sequences and neoantigen candidate peptide sequences. This model can provide highly accurate responsibility information that can predict the prognosis of immune checkpoint inhibitors to cancer patients who want to apply it.

Antitumor activity of HM781-36B, a pan-HER tyrosine kinase inhibitor, in HER2-amplified breast cancer cells.

HM781-36B is an orally administered pan-human epidermal growth factor receptor (HER) inhibitor. To explore the role of pan-HER inhibitor in breast cancer, we investigated the antitumor effect and mechanisms of HM781-36B in breast cancer cell lines. Six breast cancer cell lines (BT474, MDA-MB-453, SK-BR-3, T47D, MCF-7, and MDA-MB-231) were tested. The growth inhibitory effect was assessed using the tetrazolium bromide [3-(4,5-dimethylthiazole-2-yl)-2,5-diphenyl-tetrazolium bromide] assay. The cell cycle at various concentrations of HM781-36B was analyzed by flow cytometry, and analysis of downstream molecules was performed by western blot analysis. Interaction of HM781-36B with cytotoxic chemotherapeutic agents was analyzed by combination index using CalcuSyn. The HER2-amplified cells (SK-BR-3, BT474, and MDA-MB-453) were sensitive to HM781-36B (IC50=0.001 µmol/l, 0.0012 µmol/l, and 0.0095 µmol/l, respectively). HM781-36B induced G1 arrest and resulted in apoptosis. It reduced the level of p-HER2, p-AKT, p-ERK, and p-STAT3. HM781-36B combined with 5-fluorouracil, cisplatin, paclitaxel, or gemcitabine showed a synergistic inhibitory effect on the HER2-amplified and on some of the HER2-nonamplified breast cancer cells. HM781-36B could be a promising treatment for HER2-amplified breast cancer as a single agent or in combination with cytotoxic agents and can be a candidate for treatment of HER2-nonamplified breast cancer in combination with cytotoxic agents.

Antitumor activity of HM781-36B, an irreversible Pan-HER inhibitor, alone or in combination with cytotoxic chemotherapeutic agents in gastric cancer.

Trastuzumab, a HER2 directed treatment has shown clinical benefit in HER2 amplified gastric cancer. This study demonstrated the potent antitumor activity of HM781-36B, a quinazoline-based irreversible pan-HER inhibitor, in HER2 amplified gastric cancer cells (SNU216 and N87) in vitro and in vivo. HM781-36B inhibited phosphorylation of HER family and downstream signaling molecules, and induced apoptosis and G1 arrest. Furthermore, HM781-36B exerted synergistic effects with chemotherapeutic agents in both HER2 amplified and HER2 non-amplified gastric cancer cells. Therefore, HM781-36B may be useful for the treatment of HER2 amplified gastric cancer alone or in combination with chemotherapeutic agents.

cDNA microarray gene expression analysis and toxicological phenotype for anticancer drug.

Toxicogenomics, the subdiscipline that merges genomics with toxicology, hold the promise to contributing toward the goal of elucidating mechanism by studying genomic profiling related with various drugs. The application of gene expression profiling technology to examine multiple genes and signaling pathways promises a significant advance in understanding the toxic mechanisms of various drugs and prediction of new drug candidate. Toxicogenomics is emerging field combining genomics and bioinformatics to identify and characterize mechanisms of toxicity of drug and various compounds. The principal hypothesis underlying on this field is that chemical-specific pattern of altered gene expression is related with each chemicals properties, especially toxicological property, and it will be revealed using high-density microarray analysis of sample from exposed organisms. So, in this study we compare the gene expression pattern of two anticancer drugs paclitaxel and orally absorbable paclitaxel, using the cDNA microarray. And from the result of this study, it is possible to provide the new possibility for genome-wide insight into mechanism of their anticancer activity and toxicological phenotype.