Objective: The outbreak of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) has caused more than 26 million cases of Corona virus disease (COVID-19) in the world so far. To control the spread of the disease, screening large numbers of suspected cases for appropriate quarantine and treatment are a priority. Pathogenic laboratory testing is typically the gold standard, but it bears the burden of significant false negativity, adding to the urgent need of alternative diagnostic methods to combat the disease. Based on COVID-19 radiographic changes in CT images, this study hypothesized that artificial intelligence methods might be able to extract specific graphical features of COVID-19 and provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time for disease control. Methods: We collected 1065 CT images of pathogen-confirmed COVID-19 cases along with those previously diagnosed with typical viral pneumonia. We modified the inception transfer-learning model to establish the algorithm, followed by internal and external validation. Results: The internal validation achieved a total accuracy of 89.5% with a specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with a specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images, the first two nucleic acid test results were negative, and 46 were predicted as COVID-19 positive by the algorithm, with an accuracy of 85.2%. Conclusion: These results demonstrate the proof-of-principle for using artificial intelligence to extract radiological features for timely and accurate COVID-19 diagnosis. Key Points: • The study evaluated the diagnostic performance of a deep learning algorithm using CT images to screen for COVID-19 during the influenza season. • As a screening method, our model achieved a relatively high sensitivity on internal and external CT image datasets. • The model was used to distinguish between COVID-19 and other typical viral pneumonia, both of which have quite similar radiologic characteristics.

Colorectal cancer (CRC) remains one of the leading causes of cancer-related mortality worldwide. Its complexity is influenced by various signal transduction networks that govern cellular proliferation, survival, differentiation, and apoptosis. The pathogenesis of CRC is a testament to the dysregulation of these signaling cascades, which culminates in the malignant transformation of colonic epithelium. This review aims to dissect the foundational signaling mechanisms implicated in CRC, to elucidate the generalized principles underpinning neoplastic evolution and progression. We discuss the molecular hallmarks of CRC, including the genomic, epigenomic and microbial features of CRC to highlight the role of signal transduction in the orchestration of the tumorigenic process. Concurrently, we review the advent of targeted and immune therapies in CRC, assessing their impact on the current clinical landscape. The development of these therapies has been informed by a deepening understanding of oncogenic signaling, leading to the identification of key nodes within these networks that can be exploited pharmacologically. Furthermore, we explore the potential of integrating AI to enhance the precision of therapeutic targeting and patient stratification, emphasizing their role in personalized medicine. In summary, our review captures the dynamic interplay between aberrant signaling in CRC pathogenesis and the concerted efforts to counteract these changes through targeted therapeutic strategies, ultimately aiming to pave the way for improved prognosis and personalized treatment modalities in colorectal cancer.

Background: The outbreak of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) has caused more than 2.5 million cases of Corona Virus Disease (COVID-19) in the world so far, with that number continuing to grow. To control the spread of the disease, screening large numbers of suspected cases for appropriate quarantine and treatment is a priority. Pathogenic laboratory testing is the gold standard but is time-consuming with significant false negative results. Therefore, alternative diagnostic methods are urgently needed to combat the disease. Based on COVID-19 radiographical changes in CT images, we hypothesized that Artificial Intelligence’s deep learning methods might be able to extract COVID-19’s specific graphical features and provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time for disease control. Methods and Findings: We collected 1,065 CT images of pathogen-confirmed COVID-19 cases (325 images) along with those previously diagnosed with typical viral pneumonia (740 images). We modified the Inception transfer-learning model to establish the algorithm, followed by internal and external validation. The internal validation achieved a total accuracy of 89.5% with specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images that first two nucleic acid test results were negative, 46 were predicted as COVID-19 positive by the algorithm, with the accuracy of 85.2%. Conclusion: These results demonstrate the proof-of-principle for using artificial intelligence to extract radiological features for timely and accurate COVID-19 diagnosis. Author summary: To control the spread of the COVID-19, screening large numbers of suspected cases for appropriate quarantine and treatment measures is a priority. Pathogenic laboratory testing is the gold standard but is time-consuming with significant false negative results. Therefore, alternative diagnostic methods are urgently needed to combat the disease. We hypothesized that Artificial Intelligence’s deep learning methods might be able to extract COVID-19’s specific graphical features and provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time. We collected 1,065 CT images of pathogen-confirmed COVID-19 cases along with those previously diagnosed with typical viral pneumonia. We modified the Inception transfer-learning model to establish the algorithm. The internal validation achieved a total accuracy of 89.5% with specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images that first two nucleic acid test results were negative, 46 were predicted as COVID-19 positive by the algorithm, with the accuracy of 85.2%. Our study represents the first study to apply artificial intelligence to CT images for effectively screening for COVID-19.

Protein palmitoylation is an increasingly investigated form of post-translational lipid modification that affects protein localization, accumulation, secretion and function. Recently, emerging findings have revealed that protein palmitoylation is crucial for many tumor-related signaling pathways, such as EGFR, RAS, PD-1/PD-L1 signaling, affecting the occurrence, progression and therapeutic response of tumors. Protein palmitoylation and its modifying enzymes, including palmitoylases and depalmitoylases, are expected to be new targets for effective tumor treatment. Recognizing the significance of palmitoylation modification on protein stability, localization and downstream signal regulation, this review focuses on the regulatory roles of protein palmitoylation and its modifying enzymes in tumor cell signal transduction, aiming to bring new ideas for effective cancer prevention and treatment.

Protein palmitoylation is a reversible fatty acyl modification that undertakes important functions in multiple physiological processes. Dysregulated palmitoylations are frequently associated with the formation of cancer. How palmitoyltransferases for S-palmitoylation are involved in the occurrence and development of hepatocellular carcinoma (HCC) is largely unknown. Chemical carcinogen diethylnitrosamine (DEN)-induced and DEN combined CCl4 HCC models were used in the zinc finger DHHC-type palmitoyltransferase 20 (ZDHHC20) knockout mice to investigate the role of ZDHHC20 in HCC tumourigenesis. Palmitoylation liquid chromatography-mass spectrometry analysis, acyl-biotin exchange assay, co-immunoprecipitation, ubiquitination assays, protein half-life assays and immunofluorescence microscopy were conducted to explore the downstream regulators and corresponding mechanisms of ZDHHC20 in HCC. Knocking out of ZDHHC20 significantly reduced hepatocarcinogenesis induced by chemical agents in the two HCC mouse models in vivo. 97 proteins with 123 cysteine sites were found to be palmitoylated in a ZDHHC20-dependent manner. Among these, fatty acid synthase (FASN) was palmitoylated at cysteines 1471 and 1881 by ZDHHC20. The genetic knockout or pharmacological inhibition of ZDHHC20, as well as the mutation of the critical cysteine sites of FASN (C1471S/C1881S) accelerated the degradation of FASN. Furthermore, ZDHHC20-mediated FASN palmitoylation competed against the ubiquitin-proteasome pathway via the E3 ubiquitin ligase complex SNX8-TRIM28. Our findings demonstrate the critical role of ZDHHC20 in promoting hepatocarcinogenesis, and a mechanism underlying a mutual restricting mode for protein palmitoylation and ubiquitination modifications.

Introduction: Small cell lung cancer (SCLC) has recently been characterized as heterogeneous tumors due to consensus nomenclature for distinct molecular subtypes on the basis of differential expression of four transcription markers (ASCL1, NEUROD1, POU2F3, and YAP1). It is necessary to validate molecular subtype classification in primary SCLC tumors by immunohistochemical (IHC) staining and investigate its relevance to survival outcomes.Methods: Using a large number of surgically resected primary SCLC tumors, we assessed the mRNA and protein levels of the four subtype markers (ASCL1, NEUROD1, POU2F3 and YAP1) in two independent cohorts, respectively. Next, molecular subtypes defined by the four subtype markers was conducted to identify the association with clinicopathologic characteristics, survival outcomes, the expression of classic neuroendocrine markers, and molecules related to tumor immune microenvironment.Results: Samples were categorized into four subtypes based on the relative expression levels of the four subtype markers, yielding to ASCL1, NEUROD1, POU2F3 and YAP1 subtypes, respectively. The combined neuroendocrine differentiation features were more prevalent in either ASCL1 or NEUROD1 subtypes. Kaplan-Meier analyses found that patients with tumors of the YAP1 subtype and ASCL1 subtype obtained the best and worst prognosis on both mRNA and IHC levels, respectively. Based on multivariate Cox proportional-hazards regression model, molecular subtype classification determined by IHC was identified as an independent indicator for survival outcomes in primary SCLC tumors. Correlation analyses indicated that the four subtype markers in SCLC cancer cells were interacted with its tumor immune microenvironment. Specifically, tumors positive for YAP1 was associated with fewer CTLA4⁺ T cell infiltration, while more immune-inhibitory receptors (FoxP3,PD1, and CTLA4) and fewer immune-promoting receptor (CD8) were found in tumors positive for ASCL1.Conclusions: We validated the new molecular subtype classification and clinical relevance on both mRNA and protein levels from primary SCLC tumors. The molecular subtypes determined by IHC could be a pre-selected effective biomarker significantly influenced on prognosis in patients with SCLC, which warrants further studies to provide better preventative and therapeutic options for distinct molecular subtypes.