We present a cross-modality generation framework that learns to generate translated modalities from given modalities in MR images. Our proposed method performs Image Modality Translation (abbreviated as IMT) by means of a deep learning model that leverages conditional generative adversarial networks (cGANs). Our framework jointly exploits the low-level features (pixel-wise information) and high-level representations (e.g. brain tumors, brain structure like gray matter, etc.) between cross modalities which are important for resolving the challenging complexity in brain structures. Our framework can serve as an auxiliary method in medical use and has great application potential. Based on our proposed framework, we first propose a method for cross-modality registration by fusing the deformation fields to adopt the cross-modality information from translated modalities. Second, we propose an approach for MRI segmentation, translated multichannel segmentation (TMS), where given modalities, along with translated modalities, are segmented by fully convolutional networks (FCN) in a multichannel manner. Both of these two methods successfully adopt the crossmodality information to improve the performance without adding any extra data. Experiments demonstrate that our proposed framework advances the state-of-the-art on five brain MRI datasets. We also observe encouraging results in cross-modality registration and segmentation on some widely adopted brain datasets. Overall, our work can serve as an auxiliary method in medical use and be applied to various tasks in medical fields.

The efficacy of anaplastic lymphoma kinase (ALK) positive non-small-cell lung cancer (NSCLC) treatment with small molecule inhibitors is greatly challenged by acquired resistance. A recent study reported the newest generation inhibitor resistant mutation L1198F led to the resensitization to crizotinib, which is the first Food and Drug Administration (FDA) approved drug for the treatment of ALK-positive NSCLC. It is of great importance to understand how this extremely rare event occurred for the purpose of overcoming the acquired resistance of such inhibitors. In this study, we exploited molecular dynamics (MD) simulation to dissect the molecular mechanisms. Our MD results revealed that L1198F mutation of ALK resulted in the conformational change at the inhibitor site and altered the binding affinity of ALK to crizotinib and lorlatinib. L1198F mutation also affected the autoactivation of ALK as supported by the identification of His1124 and Tyr1278 as critical amino acids involved in ATP binding and phosphorylation. Our findings are valuable for designing more specific and potent inhibitors for the treatment of ALK-positive NSCLC and other types of cancer.

The inhibition of enhancer of zeste homolog 2 (EZH2) has been suggested to be synthetic lethal with polybromo-1 (PBRM1) deficiency, rendering EZH2 to be an attractive target for the treatment of PBRM1 frequently mutated cancers. In the current study, we combined computational and biochemical approaches to establish an efficient system for the screening and validation of synthetic lethal inhibitors from a large pool of chemical compounds. Five putative EZH2 inhibitors were identified through structure-based virtual screening from 47,737 chemical compounds and analyzed with molecular dynamics. The efficacy of these compounds against EZH2 was tested using PBRM1 deficient and wide-type cell lines. The compound L501-1669 selectively inhibited the proliferation of PBRM1-deficient cells and down-regulated the tri-methylation of histone H3 at Lysine 27 (H3K27me3). Importantly, we also observed an increase in apoptotic activities in L501-1669 treated PBRM1-deficient cells. Taken together, our results demonstrate that L501-1669 is a selective EZH2 inhibitor with promising application in the targeted therapy of PBRM1-deficient cancers.

No abstract