The ERK inhibitor GDC-0994 selectively inhibits growth of BRAF mutant cancer cells.

BRAF or RAS mutation-induced aberrant activation of the mitogen-activated protein kinase (MAPK) pathway is frequently observed in human cancers. As the key downstream node of MAPK pathway, ERK1/2 is as an important therapeutic target. GDC-0994 (ravoxertinib), an orally bioavailable, highly selective small-molecule inhibitor of ERK1/2, showed acceptable safety and pharmacodynamic profile in a recent phase I clinical trial. In this study, we investigated dependence of the anti-tumor effect of ERK inhibitor GDC-0994 on genetic alterations in the MAPK pathway. The results showed that GDC-0994 sharply inhibited cell proliferation and colony formation and induced remarkable G1 phase cell-cycle arrest in cancer cells harboring BRAF mutation but had little effect on cell behaviors in most RAS mutant or wild-type cell lines. The expression of a large number of genes, particularly the genes in the cell cycle pathway, were significantly changed after GDC-0994 treatment in BRAF mutant cells, while no remarkable expression change of such genes was observed in wild-type cells. Moreover, GDC-0994 selectively inhibited tumor growth in a BRAF mutant xenograft mice model. Our findings demonstrate a BRAF mutation-dependent anti-tumor effect of GDC-0994 and provide a rational strategy for patient selection for ERK1/2 inhibitor treatment.

Therapeutic targeting of PLK1 in TERT promoter-mutant hepatocellular carcinoma.

BACKGROUND: Hotspot mutations in the promoter of telomerase reverse transcriptase (TERT) gene are the most common genetic variants in hepatocellular carcinoma (HCC) and associated with poor prognosis of the disease. However, no drug was currently approved for treating TERT promoter mutation positive HCC patients. Here, we aim to explore the potential therapeutic strategy for targeting TERT promoter mutation in HCC. METHODS: The Liver Cancer Model Repository database was used for screening potential drugs to selectively suppress the growth of TERT promoter mutant HCC cells. RNA-seq, CRISPR-Cas9 technology and siRNA transfection were performed for mechanistic studies. Cell counting kit-8 (CCK8) assay and the xenograft tumour models were used for cell growth detection in vitro and in vivo, respectively. Cell apoptosis and cell cycle arrest were analysed by Annexin V-FITC staining and/or propidium iodide staining. RESULTS: PLK1 inhibitors were remarkably more sensitive to HCC cells harbouring TERT promoter mutation than wild-type cells in vitro and in vivo, which were diminished after TERT promoter mutation was edited to the wild-type nucleotide. Comparing the HCC cells with wild-type promoter of TERT, PLK1 inhibitors specifically downregulated Smad3 to regulate TERT for inducing apoptosis and G2/M arrest in TERT mutant HCC cells. Moreover, knockout of Smad3 counteracted the effects of PLK1 inhibitors in TERT mutant HCC cells. Finally, a cooperative effect of PLK1 and Smad3 inhibition was observed in TERT mutant cells. CONCLUSIONS: PLK1 inhibition selectively suppressed the growth of TERT mutant HCC cells through Smad3, thus contributed to discover a novel therapeutic strategy to treat HCC patients harbouring TERT promoter mutations. KEY POINTS: TERT promoter mutation confers sensitivity to PLK1 inhibitors in HCC. The selective growth inhibition of TERT mutant HCC cells induced by PLK1 inhibitor was mediated by Smad3. Combined inhibition of PLK1 and Smad3 showed a cooperative anti-tumor effect in TERT mutant HCC cells.

Risk stratification by combining common genetic mutations and TERT promoter methylation in papillary thyroid cancer.

PURPOSE: Risk stratification based on somatic mutations in TERT promoter and BRAF/RAS has been well established for papillary thyroid cancer (PTC), and there is emerging evidence showed that TERT promoter methylation was frequently observed in thyroid cancer patients with adverse features. This study was aimed to comprehensive explore the prognostic value of BRAF/RAS mutations, TERT promoter mutations, and TERT promoter methylation in PTC. METHODS: The relationships of BRAF/RAS mutations, TERT promoter mutations, and TERT promoter methylation with clinical characteristics and outcomes of PTC were analyzed in 382 patients with PTC. RESULTS: TERT promoter mutation and hypermethylation were collectively observed in 52 (13.6%) samples and associated with BRAF/RAS mutation, aggressive clinical characteristics, and poor clinical outcomes of PTC. Coexistence of BRAF/RAS and TERT alterations was found in 45 of 382 (11.8%) PTC patients and strongly associated with old patient age, extrathyroidal extension, advanced pathologic T stage and metastasis. Importantly, patients with both BRAF/RAS and TERT alterations had higher rates of tumor recurrence (13.6% vs 1.5%, P = 0.042) and disease progression (24.4% vs 3.3%, P < 0.001) than patients without any alterations, and cox regression analysis revealed that the coexistence of BRAF/RAS and TERT alterations, but not BRAF/RAS or TERT alterations alone, increased the risk of progression-free interval with an adjusted HR of 10.35 (95% CI: 1.79-59.81, P = 0.009). CONCLUSIONS: This study suggested that comprehensively analysis of BRAF/RAS mutations, TERT promoter mutation and methylation is an effective strategy to identify high-risk patients with PTC.

Dendritic Cell-Mimicking Nanoparticles Promote mRNA Delivery to Lymphoid Organs.

Spleen and lymphoid organs are important targets for messenger RNA (mRNA) delivery in various applications. Current nanoparticle delivery methods rely on drainage to lymph nodes from intramuscular or subcutaneous injections. In difficult-to-transfect antigen-presenting cells (APCs), such as dendritic cells (DCs), effective mRNA transfection remains a significant challenge. In this study, a lymphatic targeting carrier using DC membranes is developed, that efficiently migrated to lymphoid organs, such as the spleen and lymph nodes. The nanoparticles contained an ionizable lipid (YK009), which ensured a high encapsulation efficacy of mRNA and assisted mRNA with endosomal escape after cellular uptake. Dendritic cell-mimicking nanoparticles (DCMNPs) showed efficient protein expression in both the spleen and lymph nodes after intramuscular injections. Moreover, in immunized mice, DCMNP vaccination elicited Spike-specific IgG antibodies, neutralizing antibodies, and Th1-biased SARS-CoV-2-specific cellular immunity. This work presents a powerful vaccine formula using DCMNPs, which represents a promising vaccine candidate for further research and development.

Methylation-Mediated Silencing of ATF3 Promotes Thyroid Cancer Progression by Regulating Prognostic Genes in the MAPK and PI3K/AKT Pathways.

Background: Aberrant expression of oncogenes and/or tumor suppressor genes (TSGs) drives the tumorigenesis and development of thyroid cancer. We investigated the expression and function of a member of the activating transcription factor (ATF)/cAMP-responsive element-binding protein (CREB) transcription factor (TF) family, ATF3, in thyroid cancer. Methods: Data from 80 patients with papillary thyroid cancer (PTC) in the First Affiliated Hospital of Sun Yat-sen University and 510 PTC samples in The Cancer Genome Atlas thyroid cancer database were utilized for gene expression and prognosis analyses. The survival data were analyzed by Kaplan-Meier curves and Cox regression with adjustment for age, sex, multilocality, extrathyroidal extension, lymph metastases, and history of neoadjuvant treatment. DNA methylation was analyzed by methylation-specific polymerase chain reaction (PCR) and bisulfite sequencing PCR. TFs binding to ATF3 promoter were identified by DNA pull-down combined with mass spectrum assay, and confirmed by quantitative PCR (qPCR), luciferase reporter assay, and chromatin immunoprecipitation (ChIP)-qPCR. We conducted functional assays in vitro and in a xenograft mouse model to evaluate the function of ATF3 in thyroid cancer. Integrated analyses based on RNA sequencing, ChIP-seq, and CUT&Tag assays were performed to explore the mechanisms underlying the function of ATF3. Results: ATF3 was significantly downregulated in PTC and patients with low ATF3 expression had reduced progression-free survival (adjusted hazard ratio = 0.50 [CI 0.26-0.98], p = 0.043). DNA hypermethylation in ATF3 promoter disrupted the binding of SP1 and MYC-MAX, leading to inactivation of the gene. ATF3 functioned as a TSG by inhibiting the proliferation and mobility of thyroid cancer cells. And ATF3 regulated the expression of a number of genes by binding to the regulatory elements of them, particularly for genes in MAPK and PI3K/AKT pathways. Among these target genes, filamin C was positively regulated by ATF3 and associated with a more favorable thyroid cancer prognosis, while dual specificity phosphatase 10, fibronectin-1, tenascin C, and CREB5 were negatively regulated by ATF3 and associated with a poorer prognosis. Conclusions: We observed that the promoter DNA hypermethylation decreased the expression of ATF3, which in turn promoted the progression of thyroid cancer, at least partially, by directly regulating prognosis-related genes in the MAPK and PI3K/AKT pathways.

Streamlined and on-demand preparation of mRNA products on a universal integrated platform.

Vaccines are used to protect human beings from various diseases. mRNA vaccines simplify the development process and reduce the production cost of conventional vaccines, making it possible to respond rapidly to acute and severe diseases, such as coronavirus disease 2019. In this study, a universal integrated platform for the streamlined and on-demand preparation of mRNA products directly from DNA templates was established. Target DNA templates were amplified in vitro by a polymerase chain reaction module and transcribed into mRNA sequences, which were magnetically purified and encapsulated in lipid nanoparticles. As an initial example, enhanced green fluorescent protein (eGFP) was used to test the platform. The expression capacity and efficiency of the products were evaluated by transfecting them into HEK-293T cells. The batch production rate was estimated to be 200-300 µg of eGFP mRNA in 8 h. Furthermore, an mRNA vaccine encoding the receptor-binding domain (RBD) of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike protein was produced by this platform. The proposed integrated platform shows advantages for the universal and on-demand preparation of mRNA products, offering the potential to facilitate broad access to mRNA technology and enable the development of mRNA products, including the rapid supply of new mRNA-based vaccines in pandemic situations and personalized mRNA-based therapies for oncology and chronic infectious diseases, such as viral hepatitis and acquired immune deficiency syndrome.

Highly sensitive droplet digital PCR for detection of RET fusion in papillary thyroid cancer.

BACKGROUND: Thyroid cancer is the most frequent malignancy of the endocrine system, of which papillary thyroid cancer (PTC) is the predominant form with a rapid increasing incidence worldwide. Rearranged during transfection (RET) fusions are common genetic drivers of PTC and the potent RET inhibitor selpercatinib has been recently approved for treating advanced or metastatic RET fusion-positive thyroid cancer. In this study we aimed to develop a droplet digital PCR (ddPCR) system to accurately detect RET fusion in PTC samples. METHODS: The frequency and distribution of RET fusions in PTC were analyzed using genomic data of 402 PTC patients in The Cancer Genome Atlas (TCGA) database. To establish the ddPCR system for detecting CCDC6::RET fusion, a plasmid containing CCDC6::RET infusion fragment was constructed as standard template, the annealing temperature and concentrations of primers and probe were optimized. The analytical performance of ddPCR and quantitative reverse transcription PCR (qRT-PCR) were assessed in standard templates and tissue samples from 112 PTC patients. Sanger sequencing was performed in all the RET fusion-positive samples identified by ddPCR. RESULTS: RET fusions were observed in 25 (6.2%) of the 402 TCGA samples, and 15 (60%) of the RET fusion-positive patients had the CCDC6::RET fusion. Compared with qRT-PCR, the ddPCR method showed a lower limit of detection (128.0 and 430.7 copies/reaction for ddPCR and qRT-PCR, respectively). When applying the two methods to 112 tissue samples of PTC, eleven (9.8%) CCDC6::RET fusion-positive samples were detected by qRT-PCR, while ddPCR identified 4 additional positive samples (15/112, 13.4%). All the CCDC6::RET fusion-positive cases identified by ddPCR were confirmed by Sanger sequencing except for one case with 0.14 copies/uL of the fusion. CONCLUSION: The accurate and sensitive ddPCR method reported here is powerful to detection CCDC6::RET fusion in PTC samples, application of this method would benefit more RET fusion-positive patients in the clinic.

Monkeypox virus quadrivalent mRNA vaccine induces immune response and protects against vaccinia virus.

Monkeypox has been declared a public health emergency by the World Health Organization. There is an urgent need for efficient and safe vaccines against the monkeypox virus (MPXV) in response to the rapidly spreading monkeypox epidemic. In the age of COVID-19, mRNA vaccines have been highly successful and emerged as platforms enabling rapid development and large-scale preparation. Here, we develop two MPXV quadrivalent mRNA vaccines, named mRNA-A-LNP and mRNA-B-LNP, based on two intracellular mature virus specific proteins (A29L and M1R) and two extracellular enveloped virus specific proteins (A35R and B6R). By administering mRNA-A-LNP and mRNA-B-LNP intramuscularly twice, mice induce MPXV specific IgG antibodies and potent vaccinia virus (VACV) specific neutralizing antibodies. Further, it elicits efficient MPXV specific Th-1 biased cellular immunity, as well as durable effector memory T and germinal center B cell responses in mice. In addition, two doses of mRNA-A-LNP and mRNA-B-LNP are protective against the VACV challenge in mice. And, the passive transfer of sera from mRNA-A-LNP and mRNA-B-LNP-immunized mice protects nude mice against the VACV challenge. Overall, our results demonstrate that mRNA-A-LNP and mRNA-B-LNP appear to be safe and effective vaccine candidates against monkeypox epidemics, as well as against outbreaks caused by other orthopoxviruses, including the smallpox virus.

Novel Ionizable Lipid Nanoparticles for SARS-CoV-2 Omicron mRNA Delivery.

mRNA-based therapy has emerged as the most promising nucleic acid therapy in the fight against COVID-19. However, a safe and efficacious systemic delivery remains a challenge for mRNA therapy. Lipid nanoparticles (LNPs) are currently widely used in mRNA delivery vehicles. Here, a series of ionizable LNPs is rationally designed. YK009-LNP is an optimal delivery platform to carry mRNA. YK009-LNP exhibits higher mRNA delivery efficiency, a more favorable biodistribution pattern, and better safety than the approved MC3-LNP. In addition, mRNA encoding severe acute respiratory syndrome coronavirus 2 Omicron receptor binding domain protein is synthesized and intramuscular administration of mice with YK009-LNP-Omicron mRNA induces a robust immune response and immune protective effect. A novel mRNA delivery vehicle with more powerful delivery efficiency and better safety than the approved LNPs is provided here.

Improving artificial intelligence pipeline for liver malignancy diagnosis using ultrasound images and video frames.

Recent developments of deep learning methods have demonstrated their feasibility in liver malignancy diagnosis using ultrasound (US) images. However, most of these methods require manual selection and annotation of US images by radiologists, which limit their practical application. On the other hand, US videos provide more comprehensive morphological information about liver masses and their relationships with surrounding structures than US images, potentially leading to a more accurate diagnosis. Here, we developed a fully automated artificial intelligence (AI) pipeline to imitate the workflow of radiologists for detecting liver masses and diagnosing liver malignancy. In this pipeline, we designed an automated mass-guided strategy that used segmentation information to direct diagnostic models to focus on liver masses, thus increasing diagnostic accuracy. The diagnostic models based on US videos utilized bi-directional convolutional long short-term memory modules with an attention-boosted module to learn and fuse spatiotemporal information from consecutive video frames. Using a large-scale dataset of 50 063 US images and video frames from 11 468 patients, we developed and tested the AI pipeline and investigated its applications. A dataset of annotated US images is available at https://doi.org/10.5281/zenodo.7272660.

Mitochondrial Micropeptide STMP1 Enhances Mitochondrial Fission to Promote Tumor Metastasis.

Micropeptides are a recently discovered class of molecules that play vital roles in various cellular processes, including differentiation, proliferation, and apoptosis. Here, we sought to identify cancer-associated micropeptides and to uncover their mechanistic functions. A micropeptide named short transmembrane protein 1 (STMP1) that localizes at the inner mitochondrial membrane was identified to be upregulated in various cancer types and associated with metastasis and recurrence of hepatocellular carcinoma. Both gain- and loss-of-function studies revealed that STMP1 increased dynamin-related protein 1 (DRP1) activation to promote mitochondrial fission and enhanced migration of tumor cells. STMP1 silencing inhibited in vivo tumor metastasis in xenograft mouse models. Overexpression of STMP1 led to redistribution of mitochondria to the leading edge of cells and enhanced lamellipodia formation. Treatment with a DRP1 inhibitor abrogated the promotive effect of STMP1 on mitochondrial fission, lamellipodia formation, and tumor cell migration in vitro and metastasis in vivo. Furthermore, STMP1 interacted with myosin heavy chain 9 (MYH9), the subunit of nonmuscle myosin II, and silencing MYH9 abrogated STMP1-induced DRP1 activation, mitochondrial fission, and cell migration. Collectively, this study identifies STMP1 as a critical regulator of metastasis and a novel unit of the mitochondrial fission protein machinery, providing a potential therapeutic target for treating metastases. SIGNIFICANCE: This study identifies the mitochondrial micropeptide STMP1 as a regulator of metastasis that promotes mitochondrial fission and tumor cell migration via DRP1 and MYH9.

Mitochondrial micropeptide STMP1 promotes G1/S transition by enhancing mitochondrial complex IV activity.

The roles of micropeptides in cell cycle regulation and cancer development remain largely unknown. Here we found that a micropeptide STMP1 (small transmembrane protein 1) was up-regulated in multiple malignancies including hepatocellular carcinoma (HCC), and its high level was associated with short recurrence-free survival of HCC patients. Gain- and loss-of-function analyses revealed that STMP1 accelerated cell proliferation and clonogenicity in vitro and tumor growth in vivo, and silencing STMP1 blocked G1/S transition. Mechanistically, STMP1 promoted the mRNA and protein levels of CCNE2, CDK2, and E2F1. STMP1 was localized in the inner membrane of mitochondria and interacted with mitochondrial complex IV and then enhanced its activity. Moreover, treatment with the mitochondrial complex IV inhibitor tetrathiomolybdate dramatically abrogated the promoting effect of STMP1 on cell proliferation and the expression of cyclin E2, CDK2, and E2F1. These results suggest that STMP1 may promote G1/S transition and cell proliferation by enhancing mitochondrial complex IV activity, which highlights STMP1 as a new regulator of the cell cycle and a potential target for anti-cancer therapy.

UHPLC-MS/MS Method for Quantifying Fangchinoline, Tetrandrine and Calycosin-7-O-ß-D-Glucoside of Fangji Huangqi Decoction in Rat Plasma and Its Application to a Pharmacokinetic Study.

Fangji Huangqi Decoction is composed of Stephaniae Tetrandrae Radix, Astragli Radix, Atractylodis Macrocephalae Rhizoma and Glycyrrhizae Radix Et Rhizoma. It is a classic traditional Chinese medicine formula for the treatment of chronic glomerulonephritis in China. However, its pharmacokinetic characteristics in vivo are still unclear. In this study, a method for quantifying fangchinoline, tetrandrine and calycosin-7-O-ß-D-glucoside, the main active constituents of Fangji Huangqi Decoction, in rat plasma by using ultrahigh-performance liquid chromatography-tandem mass spectrometry technique was developed. Plasma samples were processed with a deproteinization procedure using acetonitrile, followed by chromatographic separation on a Shim-pack XR-ODS C18 column using gradient elution of 0.1% aqueous formic acid and acetonitrile at 0.4 mL/min. The analytes and internal standard, diphenhydramine hydrochloride, were detected using positive electrospray ionization in multiple reactions monitoring mode. The optimized mass transition ion-pairs (m/z) were 609.3/367.3 for fangchinoline, 623.3/174.3 for tetrandrine, 447.2/285.1 for calycosin-7-O-ß-D-glucoside and 256.2/167.1 for diphenhydramine hydrochloride, respectively. The developed method was validated for intraday and interday precision and accuracy whose values fell in the acceptable limits. Recovery efficiency of all the analytes was found to be >90.5%. Matrix effect was found to be negligible. Stability results showed that the analytes were stable under all conditions. The validated method was successfully used for studying the pharmacokinetics of the three compounds in rat plasma after oral administration of Fangji Huangqi Decoction.

A long non-coding RNA-based signature predicts early recurrence in hepatocellular carcinoma.

BACKGROUND: Early recurrence is the main obstacle for long-term survival of hepatocellular carcinoma (HCC) patients after curative resection. OBJECTIVE: We aimed to develop a long non-coding RNA (lncRNA) based signature to predict early recurrence. METHODS: Using bioinformatics analysis and quantitative reverse transcription PCR (RT-qPCR), we screened for lncRNA candidates that were abnormally expressed in HCC. The expression levels of candidate lncRNAs were analyzed in HCC tissues from 160 patients who underwent curative resection, and a risk model for the prediction of recurrence within 1 year (early recurrence) of HCC patients was constructed with linear support vector machine (SVM). RESULTS: An lncRNA-based classifier (Clnc), which contained nine differentially expressed lncRNAs including AF339810, AK026286, BC020899, HEIH, HULC, MALAT1, PVT1, uc003fpg, and ZFAS1 was constructed. In the test set, this classifier reliably predicted early recurrence (AUC, 0.675; sensitivity, 72.0%; specificity, 63.1%) with an odds ratio of 4.390 (95% CI, 2.120-9.090). Clnc showed higher accuracy than traditional clinical features, including tumor size, portal vein tumor thrombus (PVTT) in predicting early recurrence (AUC, 0.675 vs 0.523 vs 0.541), and had much higher sensitivity than Barcelona Clinical Liver Cancer (BCLC; 72.0% vs 50.0%), albeit their AUCs were comparable (0.675 vs 0.678). Moreover, combining Clnc with BCLC significantly increased the AUC, compared with Clnc or BCLC alone in predicting early recurrence (all P< 0.05). Finally, logistic and Cox regression analyses suggested that Clnc was an independent prognostic factor and associated with the early recurrence and recurrence-free survival of HCC patients after resection, respectively (all P= 0.001). CONCLUSIONS: Our lncRNA-based classifier Clnc can predict early recurrence of patients undergoing surgical resection of HCC.

Rational preparation and application of a mRNA delivery system with cytidinyl/cationic lipid.

The messenger RNA (mRNA)-based therapy, especially mRNA vaccines, has shown its superiorities in versatile design, rapid development and scale production, since the outbreak of coronavirus disease 2019 (COVID-19). Although the Pfizer-BioNTech and Moderna COVID-19 mRNA vaccines had been approved for application, unexpected adverse events were reported to be most likely associated with the mRNA delivery systems. Thus, the development of mRNA delivery system with good efficacy and safety remains a challenge. Here, for the first time, we report that the neutral cytidinyl lipid, 2-(4-amino-2-oxopyrimidin-1-yl)-N-(2,3-dioleoyl-oxypropyl) acetamide (DNCA), and the cationic lipid, dioleoyl-3,3'-disulfanediylbis-[2-(2,6-diaminohexanamido)] propanoate (CLD), could encapsulate and deliver the COVID-19 mRNA-1096 into the cytoplasm to induce robust adaptive immune response. In the formulation, the molar ratio of DNCA/CLD to a single nucleotide of COVID-19 mRNA-1096 was about 0.9: 0.5: 1 (the N/P ratio was about 7: 1). The DNCA/CLD-mRNA-1096 lipoplexes were rationally prepared by the combination of the lipids DNCA/CLD with the aqueous mRNA solution under mild sonication to stimulate multiple interactions, including H-bonding, π-stacking and electrostatic force between the lipids and the mRNA. After intramuscular applications of the DNCA/CLD-mRNA-1096 lipoplexes, robust neutralizing antibodies and long-lived Th1-biased SARS-CoV-2-specific cell immunity were detected in the immunized mice, thus suggesting the DNCA/CLD a promising mRNA delivery system. Moreover, our study might also inspire better ideas for developing mRNA delivery systems.

Genome-Wide Histone H3K27 Acetylation Profiling Identified Genes Correlated With Prognosis in Papillary Thyroid Carcinoma.

Thyroid carcinoma (TC) is the most common endocrine malignancy, and papillary TC (PTC) is the most frequent subtype of TC, accounting for 85-90% of all the cases. Aberrant histone acetylation contributes to carcinogenesis by inducing the dysregulation of certain cancer-related genes. However, the histone acetylation landscape in PTC remains elusive. Here, we interrogated the epigenomes of PTC and benign thyroid nodule (BTN) tissues by applying H3K27ac chromatin immunoprecipitation followed by deep sequencing (ChIP-seq) along with RNA-sequencing. By comparing the epigenomic features between PTC and BTN, we detected changes in H3K27ac levels at active regulatory regions, identified PTC-specific super-enhancer-associated genes involving immune-response and cancer-related pathways, and uncovered several genes that associated with disease-free survival of PTC. In summary, our data provided a genome-wide landscape of histone modification in PTC and demonstrated the role of enhancers in transcriptional regulations associated with prognosis of PTC.

A deep-learning pipeline for the diagnosis and discrimination of viral, non-viral and COVID-19 pneumonia from chest X-ray images.

Common lung diseases are first diagnosed using chest X-rays. Here, we show that a fully automated deep-learning pipeline for the standardization of chest X-ray images, for the visualization of lesions and for disease diagnosis can identify viral pneumonia caused by coronavirus disease 2019 (COVID-19) and assess its severity, and can also discriminate between viral pneumonia caused by COVID-19 and other types of pneumonia. The deep-learning system was developed using a heterogeneous multicentre dataset of 145,202 images, and tested retrospectively and prospectively with thousands of additional images across four patient cohorts and multiple countries. The system generalized across settings, discriminating between viral pneumonia, other types of pneumonia and the absence of disease with areas under the receiver operating characteristic curve (AUCs) of 0.94-0.98; between severe and non-severe COVID-19 with an AUC of 0.87; and between COVID-19 pneumonia and other viral or non-viral pneumonia with AUCs of 0.87-0.97. In an independent set of 440 chest X-rays, the system performed comparably to senior radiologists and improved the performance of junior radiologists. Automated deep-learning systems for the assessment of pneumonia could facilitate early intervention and provide support for clinical decision-making.

Clinical longitudinal evaluation of COVID-19 patients and prediction of organ-specific recovery using artificial intelligence.

Within COVID-19 there is an urgent unmet need to predict at the time of hospital admission which COVID-19 patients will recover from the disease, and how fast they recover to deliver personalized treatments and to properly allocate hospital resources so that healthcare systems do not become overwhelmed. To this end, we have combined clinically salient CT imaging data synergistically with laboratory testing data in an integrative machine learning model to predict organ-specific recovery of patients from COVID-19. We trained and validated our model in 285 patients on each separate major organ system impacted by COVID-19 including the renal, pulmonary, immune, cardiac, and hepatic systems. To greatly enhance the speed and utility of our model, we applied an artificial intelligence method to segment and classify regions on CT imaging, from which interpretable data could be directly fed into the predictive machine learning model for overall recovery. Across all organ systems we achieved validation set area under the receiver operator characteristic curve (AUC) values for organ-specific recovery ranging from 0.80 to 0.89, and significant overall recovery prediction in Kaplan-Meier analyses. This demonstrates that the synergistic use of an artificial intelligence (AI) framework applied to CT lung imaging and a machine learning model that integrates laboratory test data with imaging data can accurately predict the overall recovery of COVID-19 patients from baseline characteristics.