The individual contributions of blaB, blaGOB and blaCME on MICs of ß-lactams in Elizabethkingia anophelis.

BACKGROUND: The blaB, blaGOB and blaCME genes are thought to confer ß-lactam resistance to Elizabethkingia anophelis, based on experiments conducted primarily on Escherichia coli. OBJECTIVES: To determine the individual contributions of ß-lactamase genes to increased MICs in E. anophelis and to assess their impact on the in vivo efficacy of carbapenem therapy. METHODS: Scarless gene deletion of one or more ß-lactamase gene(s) was performed in three clinical E. anophelis isolates. MICs were determined by broth microdilution. Hydrolytic activity and expressions of ß-lactamase genes were measured by an enzymatic assay and quantitative RT-PCR, respectively. In vivo efficacy was determined using Galleria mellonella and murine thigh infection models. RESULTS: The presence of blaB resulted in >16-fold increases, while blaGOB caused 4-16-fold increases of carbapenem MICs. Hydrolysis of carbapenems was highest in lysates of blaB-positive strains, possibly due to the constitutionally higher expression of blaB. Imipenem was ineffective against blaB-positive isolates in vivo in terms of improvement of the survival of wax moth larvae and reduction of murine bacterial load. The deletion of blaB restored the efficacy of imipenem. The blaB gene was also responsible for a >4-fold increase of ampicillin/sulbactam and piperacillin/tazobactam MICs. The presence of blaCME, but not blaB or blaGOB, increased the MICs of ceftazidime and cefepime by 8-16- and 4-8-fold, respectively. CONCLUSIONS: The constitutionally and highly expressed blaB gene in E. anophelis was responsible for increased MICs of carbapenems and led to their poor in vivo efficacy. blaCME increased the MICs of ceftazidime and cefepime.

The mitochondria-related gene risk mode revealed p66Shc as a prognostic mitochondria-related gene of glioblastoma.

Numerous studies have highlighted the pivotal role of mitochondria-related genes (MRGs) in the initiation and progression of glioblastoma (GBM). However, the specific contributions of MRGs coding proteins to GBM pathology remain incompletely elucidated. The identification of prognostic MRGs in GBM holds promise for the development of personalized targeted therapies and the enhancement of patient prognosis. We combined differential expression with univariate Cox regression analysis to screen prognosis-associated MRGs in GBM. Based on the nine MRGs, the hazard ratio model was conducted using a multivariate Cox regression algorithm. SHC-related survival, pathway, and immune analyses in GBM cohorts were obtained from the Biomarker Exploration of the Solid Tumor database. The proliferation and migration of U87 cells were measured by CCK-8 and transwell assay. Apoptosis in U87 cells was evaluated using flow cytometry. Confocal microscopy was employed to measure mitochondrial reactive oxygen species (ROS) levels and morphology. The expression levels of SHC1 and other relevant proteins were examined via western blotting. We screened 15 prognosis-associated MRGs and constructed a 9 MRGs-based model. Validation of the model's risk score confirmed its efficacy in predicting the prognosis of patients with GBM. Furthermore, analysis revealed that SHC1, a constituent MRG of the prognostic model, was upregulated and implicated in the progression, migration, and immune infiltration of GBM. In vitro experiments elucidated that p66Shc, the longest isoform of SHC1, modulates mitochondrial ROS production and morphology, consequently promoting the proliferation and migration of U87 cells. The 9 MRGs-based prognostic model could predict the prognosis of GBM. SHC1 was upregulated and correlated with the prognosis of patients by involvement in immune infiltration. Furthermore, in vitro experiments demonstrated that p66Shc promotes U87 cell proliferation and migration by mediating mitochondrial ROS production. Thus, p66Shc may serve as a promising biomarker and therapeutic target for GBM.

De novo genome assembly and population genomics of a shrub tree Barthea barthei (Hance) krass provide insights into the adaptive color variations.

Flower color is a classic example of an ecologically important trait under selection in plants. Understanding the genetic mechanisms underlying shifts in flower color can provide key insights into ecological speciation. In this study, we investigated the genetic basis of flower color divergence in Barthea barthei, a shrub tree species exhibiting natural variation in flower color. We assembled a high-quality genome assembly for B. barthei with a contig N50 of 2.39 Mb and a scaffold N50 of 16.21 Mb. The assembly was annotated with 46,430 protein-coding genes and 1,560 non-coding RNAs. Genome synteny analysis revealed two recent tetraploidization events in B. barthei, estimated to have occurred at approximately 17 and 63 million years ago. These tetraploidization events resulted in massive duplicated gene content, with over 70% of genes retained in collinear blocks. Gene family members of the core regulators of the MBW complex were significantly expanded in B. barthei compared to Arabidopsis, suggesting that these duplications may have provided raw genetic material for the evolution of novel regulatory interactions and the diversification of anthocyanin pigmentation. Transcriptome profiling of B. barthei flowers revealed differential expression of 9 transcription factors related to anthocyanin biosynthesis between the two ecotypes. Six of these differentially expressed transcription factors were identified as high-confidence candidates for adaptive evolution based on positive selection signals. This study provides insights into the genetic basis of flower color divergence and the evolutionary mechanisms underlying ecological adaptation in plants.

A high-quality chromosome-level genome assembly of Ficus hirta.

Ficus species (Moraceae) play pivotal roles in tropical and subtropical ecosystems. Thriving across diverse habitats, from rainforests to deserts, they harbor a multitude of mutualistic and antagonistic interactions with insects, nematodes, and pathogens. Despite their ecological significance, knowledge about the genomic background of Ficus remains limited. In this study, we report a chromosome-level reference genome of F. hirta, with a total size of 297.27 Mb, containing 28,625 protein-coding genes and 44.67% repeat sequences. These findings illuminate the genetic basis of Ficus responses to environmental challenges, offering valuable genomic resources for understanding genome size, adaptive evolution, and co-evolution with natural enemies and mutualists within the genus.

Decrypting orphan GPCR drug discovery via multitask learning.

The drug discovery of G protein-coupled receptors (GPCRs) superfamily using computational models is often limited by the availability of protein three-dimensional (3D) structures and chemicals with experimentally measured bioactivities. Orphan GPCRs without known ligands further complicate the process. To enable drug discovery for human orphan GPCRs, multitask models were proposed for predicting half maximal effective concentrations (EC50) of the pairs of chemicals and GPCRs. Protein multiple sequence alignment features, and physicochemical properties and fingerprints of chemicals were utilized to encode the protein and chemical information, respectively. The protein features enabled the transfer of data-rich GPCRs to orphan receptors and the transferability based on the similarity of protein features. The final model was trained using both agonist and antagonist data from 200 GPCRs and showed an excellent mean squared error (MSE) of 0.24 in the validation dataset. An independent test using the orphan dataset consisting of 16 receptors associated with less than 8 bioactivities showed a reasonably good MSE of 1.51 that can be further improved to 0.53 by considering the transferability based on protein features. The informative features were identified and mapped to corresponding 3D structures to gain insights into the mechanism of GPCR-ligand interactions across the GPCR family. The proposed method provides a novel perspective on learning ligand bioactivity within the diverse human GPCR superfamily and can potentially accelerate the discovery of therapeutic agents for orphan GPCRs.

Odorant-Binding and Chemosensory Proteins in Fig Wasps: Evolutionary Insights From Comparative Studies.

Fig wasps (Agaonidae; Hymenoptera) are the only pollinating insects of fig trees (Ficus; Moraceae), forming the most closely and highly specific mutualism with the host. We used transcriptome sequences of 25 fig wasps from six genera to explore the evolution of key molecular components of fig wasp chemosensory genes: odorant-binding proteins (OBPs) and chemosensory proteins (CSPs). We identified a total 321 OBPs and 240 CSPs, with each species recording from 6 to 27 OBP genes and 6-19 CSP genes. 318 OBP genes are clustered into 17 orthologous groups and can be divided into two groups: PBP sensitive to pheromone and GOBP sensitive to general odor molecules, such as alcohols, esters, acids, ketones, and terpenoids. 240 CSP genes are clustered into 12 orthologous groups, which can be divided into three major groups and have functions, such as olfactory, tissue formation and/or regeneration, developmental, and some specific and unknown function. The gene sequences of most orthologous groups vary greatly among species and are consistent with the phylogenetic relationships between fig wasps. Strong purifying selection of both OBP and CSP genes was detected, as shown by low ω values. A positive selection was detected in one locus in CSP1. In conclusion, the evolution of chemosensory proteins OBPs and CSPs in fig wasps is relatively conservative, and they play an indispensable role in the life activities of fig wasps. Our results provide a starting point for understanding the molecular basis of the chemosensory systems of fig wasps.

Visualizing the DNA repair process by a photolyase at atomic resolution.

Photolyases, a ubiquitous class of flavoproteins, use blue light to repair DNA photolesions. In this work, we determined the structural mechanism of the photolyase-catalyzed repair of a cyclobutane pyrimidine dimer (CPD) lesion using time-resolved serial femtosecond crystallography (TR-SFX). We obtained 18 snapshots that show time-dependent changes in four reaction loci. We used these results to create a movie that depicts the repair of CPD lesions in the picosecond-to-nanosecond range, followed by the recovery of the enzymatic moieties involved in catalysis, completing the formation of the fully reduced enzyme-product complex at 500 nanoseconds. Finally, back-flip intermediates of the thymine bases to reanneal the DNA were captured at 25 to 200 microseconds. Our data cover the complete molecular mechanism of a photolyase and, importantly, its chemistry and enzymatic catalysis at work across a wide timescale and at atomic resolution.

Analysis of structure-activity relationship of indol-3-yl-N-phenylcarbamic amides as potent STING inhibitors.

A structure-activity relationship (SAR) study of stimulator of interferon gene (STING) inhibition was performed using a series of indol-3-yl-N-phenylcarbamic amides and indol-2-yl-N-phenylcarbamic amides. Among these analogs, compounds 10, 13, 15, 19, and 21 inhibited the phosphorylation of STING and interferon regulatory factor 3 (IRF3) to a greater extent than the reference compound, H-151. All five analogs showed stronger STING inhibition than H-151 on the 2',3'-cyclic GMP-AMP-induced expression of interferon regulatory factors (IRFs) in a STINGR232 knock-in THP-1 reporter cell line. The half-maximal inhibitory concentration of the most potent compound, 21, was 11.5 nM. The molecular docking analysis of compound 21 and STING combined with the SAR study suggested that the meta- and para-positions of the benzene ring of the phenylcarbamic amide moiety could be structurally modified by introducing halides or alkyl substituents.

Marine diterpenoid targets STING palmitoylation in mammalian cells.

Natural products are important sources of therapeutic agents and useful drug discovery tools. The fused macrocycles and multiple stereocenters of briarane-type diterpenoids pose a major challenge to total synthesis and efforts to characterize their biological activities. Harnessing a scalable source of excavatolide B (excB) from cultured soft coral Briareum stechei, we generated analogs by late-stage diversification and performed structure-activity analysis, which was critical for the development of functional excB probes. We further used these probes in a chemoproteomic strategy to identify Stimulator of Interferon Genes (STING) as a direct target of excB in mammalian cells. We showed that the epoxylactone warhead of excB is required to covalently engage STING at its membrane-proximal Cys91, inhibiting STING palmitoylation and signaling. This study reveals a possible mechanism-of-action of excB, and expands the repertoire of covalent STING inhibitors.

A chromosome-scale genome assembly of Castanopsis hystrix provides new insights into the evolution and adaptation of Fagaceae species.

Fagaceae species dominate forests and shrublands throughout the Northern Hemisphere, and have been used as models to investigate the processes and mechanisms of adaptation and speciation. Compared with the well-studied genus Quercus, genomic data is limited for the tropical-subtropical genus Castanopsis. Castanopsis hystrix is an ecologically and economically valuable species with a wide distribution in the evergreen broad-leaved forests of tropical-subtropical Asia. Here, we present a high-quality chromosome-scale reference genome of C. hystrix, obtained using a combination of Illumina and PacBio HiFi reads with Hi-C technology. The assembled genome size is 882.6 Mb with a contig N50 of 40.9 Mb and a BUSCO estimate of 99.5%, which are higher than those of recently published Fagaceae species. Genome annotation identified 37,750 protein-coding genes, of which 97.91% were functionally annotated. Repeat sequences constituted 50.95% of the genome and LTRs were the most abundant repetitive elements. Comparative genomic analysis revealed high genome synteny between C. hystrix and other Fagaceae species, despite the long divergence time between them. Considerable gene family expansion and contraction were detected in Castanopsis species. These expanded genes were involved in multiple important biological processes and molecular functions, which may have contributed to the adaptation of the genus to a tropical-subtropical climate. In summary, the genome assembly of C. hystrix provides important genomic resources for Fagaceae genomic research communities, and improves understanding of the adaptation and evolution of forest trees.

Commelinadanxiaensis (Commelinaceae), a new species from Guangdong, China.

Commelinadanxiaensis (Commelinaceae), a remarkable new species from Mount Danxia, Guangdong Province, China, is described and illustrated. This species is similar to C.communis in inflorescences and flowers but readily distinguishable in its nearly erect stems, larger flowers, and different petal colouration.

Static analysis of elastic cable structures under mechanical load using discrete catenary theory.

In this paper, the nonlinear mechanical response of elastic cable structures under mechanical load is studied based on the discrete catenary theory. A cable net is discretized into multiple nodes and edges in our numerical approach, which is followed by an analytical formulation of the elastic energy and the associated Hessian matrix to realize the dynamic simulation. A fully implicit framework is proposed based on the discrete differential geometry (DDG) theory. The equilibrium configuration of a target object is derived by adding damping force into the system, known as the dynamic relaxation method. The mechanical response of a single suspended cable is investigated and compared with the analytical solution for cross-validation. A more intricate scenario is further discussed in detail, where a structure consisting of multiple slender cables is connected through joints. Utilizing the robustness and efficiency of our discrete numerical framework, a systematic parameter sweep is performed to quantify the force displacement relationships of nets with the different number of cables and different directions of fibers. Finally, an empirical scaling law is provided to account for the rigidity of elastic cable net in terms of its geometric properties, material characteristics, component numbers, and cable orientations. Our results would provide new insight in revealing the connections between flexible structures and tensegrity structures, and could motivate innovative designs in both mechanical and civil engineered equipment.

Aqueous Solution-Grown Crystalline Phosphorus Doped Indium Oxide for Thin-Film Transistors Applications.

Solution-grown indium oxide (In2O3) based thin-film transistors (TFTs) hold good prospects for emerging advanced electronics due to their excellent mobility, prominent transparency, and possibility of low-cost and scalable manufacturing; however, pristine In2O3 TFTs suffer from poor switching characteristics due to intrinsic oxygen-vacancy-related defects and require external doping. According to Shanmugam's theory, among potential dopants, phosphorus (P) has a large dopant-oxygen bonding strength (EM-O) and high Lewis acid strength (L) that would suppress oxygen-vacancy related defects and mitigate dopant-induced carrier scattering; however, P-doped In2O3 (IPO) TFTs have not yet been demonstrated. Here, we report aqueous solution-grown crystalline IPO TFTs for the first time. It is suggested that the incorporation of P could effectively inhibit oxygen-vacancy-related defects while maintaining high mobility. This work experimentally demonstrates that dopant with high EM-O and L is promising for emerging oxide TFTs.

Metagenomics next-generation sequencing for the diagnosis of central nervous system infection: A systematic review and meta-analysis.

Objective: It is widely acknowledged that central nervous system (CNS) infection is a serious infectious disease accompanied by various complications. However, the accuracy of current detection methods is limited, leading to delayed diagnosis and treatment. In recent years, metagenomic next-generation sequencing (mNGS) has been increasingly adopted to improve the diagnostic yield. The present study sought to evaluate the value of mNGS in CNS infection diagnosis. Methods: Following the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) 2022 guidelines, we searched relevant articles published in seven databases, including PubMed, Web of Science, and Cochrane Library, published from January 2014 to January 2022. High-quality articles related to mNGS applications in the CNS infection diagnosis were included. The comparison between mNGS and the gold standard of CNS infection, such as culture, PCR or serology, and microscopy, was conducted to obtain true positive (TP), true negative (TN), false positive (FP), and false negative (FN) values, which were extracted for sensitivity and specificity calculation. Results: A total of 272 related studies were retrieved and strictly selected according to the inclusion and exclusion criteria. Finally, 12 studies were included for meta-analysis and the pooled sensitivity was 77% (95% CI: 70-82%, I 2 = 39.69%) and specificity was 96% (95% CI: 93-98%, I 2 = 72.07%). Although no significant heterogeneity in sensitivity was observed, a sub-group analysis was conducted based on the pathogen, region, age, and sample pretreatment method to ascertain potential confounders. The area under the curve (AUC) of the summary receiver operating characteristic curve (SROC) of mNGS for CNS infection was 0.91 (95% CI: 0.88-0.93). Besides, Deek's Funnel Plot Asymmetry Test indicated no publication bias in the included studies (Figure 3, p > 0.05). Conclusion: Overall, mNGS exhibits good sensitivity and specificity for diagnosing CNS infection and diagnostic performance during clinical application by assisting in identifying the pathogen. However, the efficacy remains inconsistent, warranting subsequent studies for further performance improvement during its clinical application. Study registration number: INPLASY202120002.

In vitro and in vivo efficacy of minocycline-based therapy for Elizabethkingia anophelis and the impact of reduced minocycline susceptibility.

OBJECTIVES: Elizabethkingia anophelis is inherently resistant to multiple antibiotics, except minocycline. This study aimed to determine the in vitro and in vivo efficacy of minocycline monotherapy and combination therapy against susceptible strains and the impact of reduced minocycline susceptibility. METHODS: Three clinical isolates and one laboratory-induced mutant with reduced minocycline susceptibility were included. Time-kill and checkerboard assays were used to assess in vitro efficacy and synergy, respectively. Galleria mellonella infection and mouse pneumonia models were used to assess in vivo efficacy, and a mouse thigh infection model was used to determine the bacterial load. RESULTS: Minocycline monotherapy exerted a modest inhibitory effect on three clinical minocycline-susceptible E. anophelis isolates in vitro, but delayed G. mellonella death and improved infected mouse survival; it also significantly reduced the in vivo bacterial load. Minocycline had decreased efficacy on G. mellonella and mice infected by the mutant with reduced minocycline susceptibility. Genome comparison revealed several spontaneous mutations associated with reduced minocycline susceptibility. Among eight antibiotics tested in combination with minocycline, rifampin consistently showed in vitro synergy. The addition of rifampin (1 mg/L) reduced the mutant prevention concentration of minocycline from 2-4 mg/L to < 0.5 mg/L. However, compared with monotherapy, the combination of rifampin and minocycline did not further reduce the bacterial load or improve the survival of G. mellonella or mice. CONCLUSION: Minocycline monotherapy was in vivo effective against susceptible E. anophelis. Reduced minocycline susceptibility due to spontaneous mutation decreased its therapeutic efficacy. In combination with rifampin, it prevented the in vitro emergence of reduced susceptibility but did not provide additional in vivo survival benefit.

Water-Induced Nanometer-Thin Crystalline Indium-Praseodymium Oxide Channel Layers for Thin-Film Transistors.

We report water-induced nanometer-thin crystalline indium praseodymium oxide (In-Pr-O) thin-film transistors (TFTs) for the first time. This aqueous route enables the formation of dense ultrathin (~6 nm) In-Pr-O thin films with near-atomic smoothness (~0.2 nm). The role of Pr doping is investigated by a battery of experimental techniques. It is revealed that as the Pr doping ratio increases from 0 to 10%, the oxygen vacancy-related defects could be greatly suppressed, leading to the improvement of TFT device characteristics and durability. The optimized In-Pr-O TFT demonstrates state-of-the-art electrical performance with mobility of 17.03 ± 1.19 cm2/Vs and on/off current ratio of ~106 based on Si/SiO2 substrate. This achievement is due to the low electronegativity and standard electrode potential of Pr, the high bond strength of Pr-O, same bixbyite structure of Pr2O3 and In2O3, and In-Pr-O channel's nanometer-thin and ultrasmooth nature. Therefore, the designed In-Pr-O channel holds great promise for next-generation transistors.

The complete chloroplast genome sequence of Rubus peltatus Maxim. (Rosaceae).

Rubus peltatus Maxim. (Bull. Acad. Imp. 1871) is a wild species endemic to East and Southeast China. However, genetic resources were unavailable for this species. It holds great potential for domestication or other breeding purposes with the extraordinary large yellow fruits. The complete chloroplast genome sequence of R. peltatus, assembled with Illumina Hiseq X Ten platform sequencing data, was reported. The chloroplast genome was 155,582 bp in length. The large single-copy (LSC) and small single-copy (SSC) of 85,329 bp and 18,779 bp were separated by two inverted repeats (IRs) of 25,737 bp. The chloroplast genome of R. peltatus contains 130 genes, including eight transfer RNA genes, 36 ribosomal RNA genes, and 86 protein-coding genes. Phylogenetic analysis supports R. peltatus has a close relationship with the R. cochinchinensis and R. takesimensis.

Dynamic interaction nursing intervention on functional rehabilitation and self-care ability of patients after aneurysm surgery.

BACKGROUND: Nursing practices based on the dynamic interaction model have been shown to be superior to generic nursing practices. However, whether this model is effective in patients recovering from intracranial aneurysm surgery is not well studied. AIM: To investigate the effect of nursing based on a dynamic interaction model on functional rehabilitation of patients after aneurysm surgery. METHODS: A total of 86 cases in our hospital with intracranial aneurysm from April 2019 to April 2021, were selected and divided into the study group and the control group, with 43 patients in each group. The control group received routine nursing, and the research group received nursing intervention based on a dynamic interaction model. The daily living ability (activities of daily living, ADL), cognitive function (Simple Intelligent Mental State Scale, MMSE), quality of life (Generic Quality of Life Inventory-74, GQOL-74), self-care ability (Exercise of Self-Care Agency scale), incidence of complications, and nursing satisfaction were recorded before and after intervention. RESULTS: Before intervention, ADL (52.09 ± 6.44), MMSE (18.03 ± 4.11), and GQOL-74 (53.68 ± 4.34) scores in the study group were not significantly different from those in the control group (ADL: 50.97 ± 7.32, MMSE: 17.59 ± 3.82, GQOL-74: 55.06 ± 3.98) (P > 0.05). After intervention, ADL (86.12 ± 5.07), MMSE (26.64 ± 2.66), and GQOL-74 (83.13 ± 5.67) scores in the study group were higher than those in the control group (ADL: 79.81 ± 6.35, MMSE: 24.51 ± 3.00, and GQOL-74: 77.96 ± 6.27) (P < 0.05). Before intervention, self-concept (17.46 ± 4.44), self-care skills (25.22 ± 4.20), self-care knowledge (22.35 ± 4.74), and self-care responsibility (15.06 ± 3.29) scores in the study group was similar to those in the control group (self-concept: 16.89 ± 5.53, self-care skills: 24.59 ± 4.46, self-care knowledge: 21.80 ± 3.61, and self-care responsibility: 14.83 ± 3.11) (P > 0.05). After the intervention, self-concept (26.01 ± 3.18), self-care skills (37.68 ± 6.05), self-care knowledge (45.56 ± 5.83), and self-care responsibility (22.01 ± 3.77) scores in the study group were higher than those in the control group (self-concept: 22.97 ± 3.46, self-care skills: 33.02 ± 5.65, self-care skills knowledge: 36.81 ± 5.54, and self-care responsibility: 17.97 ± 3.56 points) (P < 0.05). The incidence of complications in the study group (4.65%) was lower than that in the control group (18.60%) (P < 0.05). Nursing satisfaction in the study group (95.35%) was higher than that in the control group (81.40%) (P < 0.05). CONCLUSION: Nursing intervention based on a dynamic interaction model can improve postoperative cognitive function, daily living ability, self-care ability, quality of life, and patient satisfaction, while reducing the risk of complications.

PET/CT Based EGFR Mutation Status Classification of NSCLC Using Deep Learning Features and Radiomics Features.

Purpose: This study aimed to compare the performance of radiomics and deep learning in predicting EGFR mutation status in patients with lung cancer based on PET/CT images, and tried to explore a model with excellent prediction performance to accurately predict EGFR mutation status in patients with non-small cell lung cancer (NSCLC). Method: PET/CT images of 194 NSCLC patients from Xijing Hospital were collected and divided into a training set and a validation set according to the ratio of 7:3. Statistics were made on patients' clinical characteristics, and a large number of features were extracted based on their PET/CT images (4306 radiomics features and 2048 deep learning features per person) with the pyradiomics toolkit and 3D convolutional neural network. Then a radiomics model (RM), a deep learning model (DLM), and a hybrid model (HM) were established. The performance of the three models was compared by receiver operating characteristic (ROC) curves, sensitivity, specificity, accuracy, calibration curves, and decision curves. In addition, a nomogram based on a deep learning score (DS) and the most significant clinical characteristic was plotted. Result: In the training set composed of 138 patients (64 with EGFR mutation and 74 without EGFR mutation), the area under the ROC curve (AUC) of HM (0.91, 95% CI: 0.86-0.96) was higher than that of RM (0.82, 95% CI: 0.75-0.89) and DLM (0.90, 95% CI: 0.85-0.95). In the validation set composed of 57 patients (32 with EGFR mutation and 25 without EGFR mutation), the AUC of HM (0.85, 95% CI: 0.77-0.93) was also higher than that of RM (0.68, 95% CI: 0.52-0.84) and DLM (0.79, 95% CI: 0.67-0.91). In all, HM achieved better diagnostic performance in predicting EGFR mutation status in NSCLC patients than two other models. Conclusion: Our study showed that the deep learning model based on PET/CT images had better performance than radiomics model in diagnosing EGFR mutation status of NSCLC patients based on PET/CT images. Combined with the most statistically significant clinical characteristic (smoking) and deep learning features, our hybrid model had better performance in predicting EGFR mutation types of patients than two other models, which could enable NSCLC patients to choose more personalized treatment schemes.