Almonertinib and alflutinib show novel inhibition on rare EGFR S768I mutant cells.

PURPOSE: EGFR classical mutations respond well to EGFR tyrosine kinase inhibitors. However, it is uncertain whether currently available EGFR-TKIs are effective against rare EGFR mutations and compound mutations. Herein, the effectiveness of almonertinib and alflutinib, the third-generation tyrosine kinase inhibitors developed in China, on rare EGFR S768I mutations and compound mutations is identified. METHODS: In this study, using CRISPR method, four EGFR S768I mutation cell lines were constructed, and the sensitivity of EGFR to almonertinib and alflutinib was tested, with positive controls being the 1st (gefitinib), 2nd (afatinib), and 3rd (osimertinib) generation drugs. RESULTS: The present results indicate that almonertinib and alflutinib can effectively inhibit cell viability and proliferation in rare EGFR S768I mutations through the ERK or AKT pathways in a time-dependent manner, by blocking the cell cycle and inhibiting apoptosis. CONCLUSIONS: These findings suggest that almonertinib and alflutinib may be potential therapeutic options for non-small cell lung cancer patients with the EGFR S768I mutation.

BDTX-189, a novel tyrosine kinase inhibitor, inhibits cell activity via ERK and AKT pathways in the EGFR C797S triple mutant cells.

The tertiary mutation C797S in the structural domain of the EGFR kinase is a common cause of resistance to third-generation EGFR tyrosine kinase inhibitors (TKIs). In this study, we used a potent, selective and irreversible inhibitor, BDTX-189, to target EGFR C797S triple mutant cells for cell activity. The study constructed the H1975-C797S (EGFR L858R/T790 M/C797S) cell line using the CRISPR/Cas9 method and investigated its potential as a fourth-generation tyrosine kinase inhibitor via chemosensitivity approach. The results demonstrated its ability to induce cytotoxic effects, and inhibit EGFR L858R/T790 M/C797S cell growth and proliferation in a dose-dependent manner. Meanwhile, BDTX-189 reduces the protein phosphorylation levels of EGFR, ERK, and AKT, promoting apoptosis. Furthermore, BDTX-189 not only inhibits common EGFR triple mutations but also effectively inhibits EGFR L858R mutation and EGFR L858R/T790 M mutation. These findings support the cytotoxic effect of BDTX-189 and its inhibitory effect on cell division and proliferation with the EGFR C797S triple mutation.

Neural networks based on attention architecture are robust to data missingness for early predicting hospital mortality in intensive care unit patients.

Background: Although the machine learning model developed on electronic health records has become a promising method for early predicting hospital mortality, few studies focus on the approaches for handling missing data in electronic health records and evaluate model robustness to data missingness. This study proposes an attention architecture that shows excellent predictive performance and is robust to data missingness. Methods: Two public intensive care unit databases were used for model training and external validation, respectively. Three neural networks (masked attention model, attention model with imputation, attention model with missing indicator) based on the attention architecture were developed, using masked attention mechanism, multiple imputation, and missing indicator to handle missing data, respectively. Model interpretability was analyzed by attention allocations. Extreme gradient boosting, logistic regression with multiple imputation and missing indicator (logistic regression with imputation, logistic regression with missing indicator) were used as baseline models. Model discrimination and calibration were evaluated by area under the receiver operating characteristic curve, area under precision-recall curve, and calibration curve. In addition, model robustness to data missingness in both model training and validation was evaluated by three analyses. Results: In total, 65,623 and 150,753 intensive care unit stays were respectively included in the training set and the test set, with mortality of 10.1% and 8.5%, and overall missing rate of 10.3% and 19.7%. attention model with missing indicator had the highest area under the receiver operating characteristic curve (0.869; 95% CI: 0.865 to 0.873) in external validation; attention model with imputation had the highest area under precision-recall curve (0.497; 95% CI: 0.480-0.513). Masked attention model and attention model with imputation showed better calibration than other models. The three neural networks showed different patterns of attention allocation. In terms of robustness to data missingness, masked attention model and attention model with missing indicator are more robust to missing data in model training; while attention model with imputation is more robust to missing data in model validation. Conclusions: The attention architecture has the potential to become an excellent model architecture for clinical prediction task with data missingness.