CT and CEA-based machine learning model for predicting malignant pulmonary nodules.

Computed tomography (CT), an efficient radiological technology, is used to detect lung cancer in the clinic. Carcinoembryonic antigen (CEA), a common tumor biomarker, is applied in the detection of various tumors. To highlight the advantages of two-dimensional techniques and assist clinicians in optimizing lung cancer diagnostic schemes, we established a favorable model combining CT and CEA. In the study, univariate analysis was performed to screen independent predictors in a training cohort of 271 patients with malignant pulmonary nodules (MPNs) and 92 with benign pulmonary nodules (BPNs). Six machine learning-based models involving five CT predictors (mediastinal lymph node enlargement, lobulation, vascular notch sign, spiculation, and nodule number) and lnCEA were constructed and validated in an independent cohort of 129 participants (92 MPNs and 37 BPNs) by SPSS Modeler. A nomogram and the Delong test were generated by R software. Finally, the model established by logistic regression had highest diagnostic efficiency (area under the curve [AUC] = 0.912). Moreover, the diagnostic ability of the logistic model in the validation cohort (AUC = 0.882, 80.4% sensitivity, 75.7% specificity) was higher than that of the Peking University model (AUC = 0.712, 68.5% sensitivity, 70.3% specificity) and the Mayo model (AUC = 0.745, 62.0% sensitivity, 75.7% specificity). Interestingly, for the participants with intermediate (10-30 mm) and CEA-negative nodule, the model reached an AUC of 0.835 (72.3% sensitivity, 83.3% specificity). The AUC for the early lung cancer was as high as 0.822 with 67.3% sensitivity and 78.9% specificity. As a conclusion, this promising model presents a new diagnostic strategy for the clinic to distinguish MPNs from BPNs.

Establishment and validation of a clinical model for diagnosing solitary pulmonary nodules.

OBJECTIVES: The main purpose of this study was to develop and validate a clinical model for estimating the risk of malignancy in solitary pulmonary nodules (SPNs). METHODS: A total of 672 patients with SPNs were retrospectively reviewed. The least absolute shrinkage and selection operator algorithm was applied for variable selection. A regression model was then constructed with the identified predictors. The discrimination, calibration, and clinical validity of the model were evaluated by the area under the receiver-operating-characteristic curve (AUC), calibration curve, and decision curve analysis (DCA). RESULTS: Ten predictors, including gender, age, nodule type, diameter, lobulation sign, calcification, vascular convergence sign, mediastinal lymphadenectasis, the natural logarithm of carcinoembryonic antigen, and combination of cytokeratin 19 fragment 21-1, were incorporated into the model. The prediction model demonstrated valuable prediction performance with an AUC of 0.836 (95% CI: 0.777-0.896), outperforming the Mayo (0.747, p = 0.024) and PKUPH (0.749, p = 0.018) models. The model was well-calibrated according to the calibration curves. The DCA indicated the nomogram was clinically useful over a wide range of threshold probabilities. CONCLUSION: This study proposed a clinical model for estimating the risk of malignancy in SPNs, which may assist clinicians in identifying the pulmonary nodules that require invasive procedures and avoid the occurrence of overtreatment.

Derivation and validation of a prediction model for patients with lung nodules malignancy regardless of mediastinal/hilar lymphadenopathy.

BACKGROUND: Clinical prediction models to classify lung nodules often exclude patients with mediastinal/hilar lymphadenopathy, although the presence of mediastinal/hilar lymphadenopathy does not always indicate malignancy. Herein, we developed and validated a multimodal prediction model for lung nodules in which patients with mediastinal/hilar lymphadenopathy were included. METHODS: A single-center retrospective study was conducted. We developed and validated a logistic regression model including patients with mediastinal/hilar lymphadenopathy. Discrimination of the model was assessed by area under the operating curve. Goodness of fit test was performed via the Hosmer-Lemeshow test, and a nomogram of the logistic regression model was drawn. RESULTS: There were 311 cases included in the final analysis. A logistic regression model was developed and validated. There were nine independent variables included in the model. The aera under the curve (AUC) of the validation set was 0.91 (95% confidence interval [CI]: 0.85-0.98). In the validation set with mediastinal/hilar lymphadenopathy, the AUC was 0.95 (95% CI: 0.90-0.99). The goodness-of-fit test was 0.22. CONCLUSIONS: We developed and validated a multimodal risk prediction model for lung nodules with excellent discrimination and calibration, regardless of mediastinal/hilar lymphadenopathy. This broadens the application of lung nodule prediction models. Furthermore, mediastinal/hilar lymphadenopathy added value for predicting lung nodule malignancy in clinical practice.

Transcriptome analysis reveals PRKCA as a potential therapeutic target for overcoming cisplatin resistance in lung cancer through ferroptosis.

Cisplatin-based chemotherapy is the current standard care for lung cancer patients; however, drug resistance frequently develops during treatment, thereby limiting therapeutic efficacy.The molecular mechanisms underlying cisplatin resistance remain elusive. In this study, we conducted an analysis of microarray data from the Gene Expression Omnibus (GEO) database under the accession numbers GSE21656, which encompassed expression profiling of cisplatin-resistant H460 (DDP-H460)and the parental cells (H460). Subsequently, we calculated the differentially expressed genes (DEGs) between DDP-H460 and H460. Gene Ontology (GO) enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis of DEGs demonstrated significant impact on the Rap1, PI3K/AKT and MAPK signaling pathways. Moreover, protein and protein interaction (PPI) network analysis identified PRKCA, DET1, and UBE2N as hub genes that potentially contribute predominantly to cisplatin resistance. Ultimately, PRKCA was selected for validation due to its significant prognostic effect, which predicts unfavorable overall survival and disease-free survival in patients with lung cancer. Network analysis conducted on The Cancer Genome Atlas (TCGA) database revealed a strong gene-level correlation between PRKCA and TP53, CDKN2A, BYR2, TTN, KRAS, and PIK3CA; whereas at the protein level, it exhibited a high correlation with EGFR, Lck, Bcl2, and Syk. The in vitro experiments revealed that PRKCA was upregulated in the cisplatin-resistant A549 cells (DDP-A549), while knockdown of PRKCA increased DDP-A549 apoptosis upon cisplatin treatment. Moreover, we observed that PRKCA knockdown attenuated DDP-A549 proliferation, migration and invasion ability. Western blot analysis demonstrated that PRKCA knockdown downregulated phosphorylation of PI3K expression while upregulated the genes involved in ferroptosis signaling. In summary, our results elucidate the role of PRKCA in acquiring resistance to cisplatin and underscore its potential as a therapeutic target for cisplatin-resistant lung cancer.

LRT-CLUSTER: A New Clustering Algorithm Based on Likelihood Ratio Test to Identify Driving Genes.

Somatic mutations often occur at high relapse sites in protein sequences, which indicates that the location clustering of somatic missense mutations can be used to identify driving genes. However, the traditional clustering algorithm has such problems as the background signal over-fitting, the clustering algorithm is not suitable for mutation data, and the performance of identifying low-frequency mutation genes needs to be improved. In this paper, we propose a linear clustering algorithm based on likelihood ratio test knowledge to identify driver genes. In this experiment, firstly, the polynucleotide mutation rate is calculated based on the prior knowledge of likelihood ratio test. Then, the simulation data set is obtained through the background mutation rate model. Finally, the unsupervised peak clustering algorithm is used to, respectively, evaluate the somatic mutation data and the simulation data to identify the driver genes. The experimental results show that our method achieves a better balance of precision and sensitivity. It can also identify the driver genes missed by other methods, making it an effective supplement to other methods. We also discover some potential linkages between genes and between genes and mutation sites, which is of great value to target drug therapy research. Method framework: Our proposed model framework is as follows. a. Counting mutation sites and the number of mutations in tumor gene elements. b. The nucleotide context mutation frequency is counted based on the likelihood ratio test knowledge, and the background mutation rate model is obtained. c. Based on Monte Carlo simulation method, data sets with the same number of mutations as gene elements are randomly sampled to obtain simulated mutation data, and the sampling frequency of each mutation site is related to the mutation rate of polynucleotide. d. The original mutation data and the simulated mutation data after random reconstruction are clustered by peak density, respectively, and the corresponding clustering scores are obtained. e. We can obtain the clustering information statistics in each gene segment and score of each gene segment from the original single nucleotide mutation data through step d. f. According to the observed score and the simulated clustering score, the p-value of the corresponding gene fragment is calculated. g. We can obtain the clustering information statistics in each gene segment and score of each gene segment from the simulated single nucleotide mutation data through step d.

Res-trans networks for lung nodule classification.

PURPOSE: Lung cancer usually presents as pulmonary nodules on early diagnostic images, and accurately estimating the malignancy of pulmonary nodules is crucial to the prevention and diagnosis of lung cancer. Recently, deep learning algorithms based on convolutional neural networks have shown potential for pulmonary nodules classification. However, the size of the nodules is very diverse, ranging from 3 to 30 mm, which makes classifying them to be a challenging task. In this study, we propose a novel architecture called Res-trans networks to classify nodules in computed tomography (CT) scans. METHODS: We designed local and global blocks to extract features that capture the long-range dependencies between pixels to adapt to the correct classification of lung nodules of different sizes. Specifically, we designed residual blocks with convolutional operations to extract local features and transformer blocks with self-attention to capture global features. Moreover, the Res-trans network has a sequence fusion block that aggregates and extracts the sequence feature information output by the transformer block that improves classification accuracy. RESULTS: Our proposed method is extensively evaluated on the public LIDC-IDRI dataset, which contains 1,018 CT scans. A tenfold cross-validation result shows that our method obtains better performance with AUC = 0.9628 and Accuracy = 0.9292 compared with recently leading methods. CONCLUSION: In this paper, a network that can capture local and global features is proposed to classify nodules in chest CT. Experimental results show that our proposed method has better classification performance and can help radiologists to accurately analyze lung nodules.

Humoral immune response to epidermal growth factor receptor in lung cancer.

The aim of this study was to explore the potential value of autoantibody to epidermal growth factor receptor (EGFR) in the diagnosis of lung cancer (LC) and its relation with EGFR mutations. Enzyme-linked immunosorbent assay (ELISA) was performed to detect the level of autoantibody to EGFR in sera from 254 LC patients and 222 normal controls (NCs). Besides, the mRNA and protein levels of EGFR were investigated in Gene Expression Profiling Interactive Analysis (GEPIA) and Human Protein Atlas (HPA) database, respectively. The level of autoantibody to EGFR (anti-EGFR) in LC even different types of LC was obviously higher than that in NC (P < 0.05). The area under the curve (AUC) of anti-EGFR was 0.695 (95% CI 0.645-0.742) when comparing LC patients with NC, while the AUC of carcinoembryonic antigen (CEA) was 0.681 (95% CI 0.629-0.730). Moreover, by integrating anti-EGFR with CEA to diagnose LC, the AUC was up to 0.784 (95% CI 0.737-0.826). However, the expression level of autoantibody to EGFR had no difference between LC patients with and without EGFR gene mutation (P > 0.05). EGFR mRNA expression level was obviously upregulated in squamous cell carcinoma (SCC) tissues compared with normal tissues (P < 0.05), but not in adenocarcinoma (ADC) (P > 0.05). The study confirmed that anti-EGFR could be a potential biomarker for LC diagnosis; additionally, it could improve the diagnostic value of CEA in clinical work.

A Diagnostic Model With IgM Autoantibodies and Carcinoembryonic Antigen for Early Detection of Lung Adenocarcinoma.

Immunoglobulin M (IgM) autoantibodies, as the early appearing antibodies in humoral immunity when stimulated by antigens, might be excellent biomarkers for the early detection of lung cancer (LC). We aimed to develop a multi-analyte integrative model combining IgM autoantibodies and a traditional tumor biomarker that could be a valuable and powerful auxiliary diagnostic tool and might improve the accuracy of early detection of lung adenocarcinoma (LUAD). A customized protein array based on cancer driver genes was constructed and applied in the discovery cohort consisting of 68 LUAD patients and 68 normal controls (NCs); 31 differentially expressed IgM autoantibodies were identified. The top 5 candidate IgM autoantibodies [based on the area under the receiver operating characteristic curve (AUC) ranking], namely, TSHR, ERBB2, survivin, PIK3CA, and JAK2, were validated in the validation cohort using enzyme-linked immunosorbent assay (ELISA), which included 147 LUAD samples, 72 lung squamous cell carcinoma (LUSC) samples, 44 small cell lung carcinoma (SCLC) samples, and 147 NCs. These indicators presented diagnostic capacity for LUAD, with AUCs of 0.599, 0.613, 0.579, 0.601, and 0.633, respectively (p < 0.05). However, none of them showed a significant difference between the SCLC and NC groups, and only the IgM autoantibody against JAK2 showed a higher expression in LUSC than in NC (p = 0.046). Through logistic regression analysis, with the five IgM autoantibodies and carcinoembryonic antigen (CEA), one diagnostic model was constructed for LUAD. The model yielded an AUC of 0.827 (sensitivity = 56.63%, specificity = 93.98%). The diagnostic efficiency was superior to that of either CEA (AUC = 0.692) or IgM autoantibodies alone (AUC = 0.698). Notably, the accuracy of this model in early-stage LUAD reached 83.02%. In conclusion, we discovered and identified five novel IgM indicators and developed a multi-analyte model combining IgM autoantibodies and CEA, which could be a valuable and powerful auxiliary diagnostic tool and might improve the accuracy of early detection of LUAD.

The circular RNA of peripheral blood mononuclear cells: Hsa_circ_0005836 as a new diagnostic biomarker and therapeutic target of active pulmonary tuberculosis.

It has been reported that circular RNA (circRNA) is associated with human cancer. However, few studies have been reported in active pulmonary tuberculosis (APTB). The global circRNA expression was detected in the peripheral blood mononuclear cells (PBMCs) of APTB patients (n=5) and health controls (HC) (n=5) by using high-throughput sequencing. According to the systematical bioinformatics analysis, the basic content of circRNAs and their fold changes in the two groups were calculated. We selected 6 significant differentially expressed circRNAs, hsa_circ_0005836, hsa_circ_0009128, hsa_circ_0003519, hsa_circ_0023956, hsa_circ_0078768, and hsa_circ_0088452 and validated the expression in PBMCs from APTB (n=10) and HC (n=10) by real-time quantitative reverse transcription-polymerase chain reactions (qRT-PCRs). Further, the verification of these specific circRNAs (hsa_circ_0005836 and hsa_circ_0009128) between APTB (n=34) and HC (n=30) in PBMCs was also conducted by qRT-PCRs. The RNA-seq data showed the significant differential expression of the 523 circRNAs between the APTB and HC groups (199 circRNAs were significantly up-regulated and 324 circRNAs were down-regulated). Hsa_circ_0005836 and hsa_circ_0009128 expression was significantly down-regulated in the PBMCs of APTB (P<0.05) in the samples of APTB compared to HC in our study. The gene ontology based enrichment analysis of the circRNA-miRNA-mRNAs network showed that cellular catabolic process (P=7.10E-08), regulation of metabolic process (P=2.10E-06), catalytic activity (P=3.67E-08), protein binding (P=1.71E-07), cell part (P=3.46E-06), intracellular part (P=1.71E-07), and intracellular (P=3.67E-08) were recognized in the comparisons between APTB and HC. Based on KEGG analysis, HTLV-I infection, regulation of actin cytoskeleton, neurotrophin signaling pathway and mTOR signaling pathway were relevant during tuberculosis bacillus infection. We found for the first time that hsa_circ_0005836 and hsa_circ_0009128 were significantly down-regulated in the PBMCs of APTB compared with HC. Our findings indicate hsa_circ_0005836 might serve as a novel potential biomarker for TB infection.

Crystal structure of tetracarbonyl(2,2'-dipyridylamine)tungsten.

Tetracarbonyl(2,2'-dipyridylamine)tungsten was prepared from W(CO)6 and 2,2'-dipyridylamine in toluene. The structure was determined by an X-ray diffraction analysis. Crystal data: triclinic; space group, P-1 (No.2); a = 8.454(1)A, b = 13.369(2)A, c = 6.9452(9) A, a= 85.88(1) degrees, beta = 68.28(1) degrees, gamma = 80.93(1) degrees, V= 720.0(1)AI; Z = 2.

Synthesis and characterization of amidate bridged dimeric and oligomeric platinum complexes having short platinum-platinum interactions.

A number of pivalamidate bridged dinuclear [PtII2(RNH2)4(NHCOtBu)2]2+, [PtIII2LL (RNH2)4(NHCOtBu)2]n+ (2RNH2 = 2NH3, 1,2-ethylenediamine, 1,2-diaminocyclohexane; L, L' = NO3-, H2O, or ketonate), trinuclear [{PtII(dap)(NHCOtBu)2}2PdIII]3+ (dap = 1,2-diaminopropane), tetranuclear [{PtII2(NH3)2(DACH)(NHCOtBu)2}2]4+ (DACH = 1,2-diaminocyclohexane), pentanuclear [{Pt2(C5H7O)(NH3)2Cl2(NHCOtBu)2}2PtCl4], and hexanuclear [Pt2(NH3)2(en)(NHCOtBu)2Pt(NO2)4]2 platinum complexes containing Pt(II)-Pt(II), Pt(II)-Pt(III), Pt(II)-Pd(III), and Pt(III)-Pt(III) interactions have been prepared and structurally characterized. The Pt-Pt interactions are characteristic of covalent, dative, or orbital symmetric Pt-Pt bonds. The dimeric Pt(III) complexes are able to activate C-H bonds of ketones to afford ketonate platinum(III) complexes. The Pt-Pt bonds are either doubly amidate-bridged or ligand unsupported. Their distances are 2.99-3.22 A for Pt(II)-Pt(II), 2.59-2.72 A for Pt(III)-Pt(III), 2.98 A for Pt(II)-Pt(III), and 2.66 A for Pt(II)-Pd(III) bonds depending on the oxidation states of the two metals and the ancillary ligands.

Synthesis and structural characterization of one- and two-dimensional coordination polymers based on platinum-silver metallic backbones.

Seven Pt-Ag coordination polymers [Pt(NH3)2(NHCO(t)Bu)2Ag(H2O)](ClO4) (1), [Pt2(dap)2(NHCO(t)Bu)4Ag2(NO3)(ClO4)] (dap = 1,2-diaminopropane, 2), [Pt2(en)2(NHCO(t)Bu)4Ag2(m-C6H4(CO2)2)].3H2O (en = ethylenediamine, 3), [Pt2(NH3)2(NHCO(t)Bu)2Ag2(p-C6H4(CO2)2)].2H2O (4), [Pt3(en)3(NHCO(t)Bu)6Ag2(p-C6H4(CO2)2)(1.5)].6H2O (5), [Pt(NH3)2(NHCO(t)Bu)4Ag(4-C5H4NCO2)2].10H2O (6), and [Pt2(en)2(NHCO(t)Bu)4Ag2(4-C5H4NCO2)](ClO4) (7) were synthesized from the corresponding [Pt(RNH2)2(NHCO(t)Bu)2] and Ag salts, respectively, and their structures were determined by X-ray crystallography. The Pt and Ag units aggregate into one-dimensional chains based on Pt-Ag backbones. Compounds 1, 2, and 6 possess an extended zigzag Pt-Ag chain motif, and the metallic chains arrange in a parallel fashion into layered structures. Compounds 3-5, and 7 form 2-D brick wall sheets due to the coordination of the bifunctional anions to the Ag+ ions of the neighboring chains. These polymers are constructed based on the Pt-Ag interactions and the coordination of amidate oxygen atoms to Ag ions. There are three kinds of short Pt-Ag bonds observed in the structures of these compounds. The Pt-Ag metallic backbone is formed by the stacking unsupported Pt-Ag bonds, the amidate doubly bridged Pt-Ag bonds, and the amidate singly bridged Pt-Ag bonds. In the chains, the Pt-Ag bond distances are quite short, and appear in the range of 2.78-2.97 A, which are comparable to known Pt-Ag dative bonds.

Luminescent amidate-bridged one-dimensional platinum(II)-thallium(I) coordination polymers assembled via metallophilic attraction.

The neutral square-planar complexes [Pt(RNH2)2(NHCO(t)Bu)2] (R = H, 1; Et, 2) and [Pt(DACH)(NHCO(t)Bu)2] (DACH = 1,2-diaminocyclohexane, 3) act as metalloligands and make bonds to closed-shell Tl(I) ions to afford one- and two-dimensional platinum-thallium oligomers or polymers based on heterobimetallic backbones. A series of heteronuclear platinum(II)-thallium(I) complexes have been synthesized and structurally characterized. The structures of the Pt-Tl compounds resulted from [Pt(RNH2)2(NHCO(t)Bu)2] and TlX [X = NO3(-), ClO4(-), PF6(-), and Cp2Fe(CO2)2(2-)] are dependent on both counteranions and the amine substituents. The compounds [Pt(NH3)2(NHCO(t)Bu)2Tl]X (X = NO3(-), 8; ClO4(-), 9) adopt one-dimensional zigzag chain structures consisting of repeatedly stacked [Pt(NH3)2(NHCO(t)Bu)2Tl]+ units, whereas [{Pt(NH3)2(NHCO(t)Bu)2}2Tl2]X2 (X = PF6(-), 10) consists of a helical chain. Compound 3 reacts with Tl+ to give [{Pt(DACH)(NHCO(t)Bu)2}2Tl](NO3) x [Pt(DACH)(NHCO(t)Bu)2] x 3 H2O (14) and one-dimensional polymeric [{Pt(DACH)(NHCO(t)Bu)2}2Tl2]X2 (X = ClO4(-), 15; PF6(-), 16). Reactions of [Pt(DACH)(NHCOCH3)2] with Tl+ ions afford one-dimensional coordination polymers [{Pt(DACH)(NHCOCH3)2}2Tl2]X2 (X = NO3(-), 17; ClO4(-), 18; PF6(-), 19). The polymeric [{Pt(DACH)(NHCOR')2}2Tl2]2+ (R = CH3, (t)Bu) complexes adopt helical structures, which are generated around the crystallographic 2(1) screw axis. The distance between the coils corresponds to the unit cell length, which ranges from 22.58 to 22.68 A. The platinum-thallium bond distances fall in a narrow range around 3.0 A. The complexes derived from [Pt(NH3)2(NHCO(t)Bu)2] are luminescent at 77 K. The trinuclear complexes [{Pt(RNH2)(NHCO(t)Bu)2}2Tl]+ do not emit at room temperature but are emissive at 77 K, whereas the polymeric platinum-thallium complexes containing 1,2-diaminocyclohexane are intensively luminescent at both room temperature and 77 K. The color variations are interesting; 15 exhibits intense yellow-green, 16 exhibits green, and 17-19 exhibit blue luminescence. The presence of bonding between platinum and thallium is supported by the short metal-metal separations and the strong low-energy luminescence of these compounds in their solid states.

Spectral and structural characterization of amidate-bridged platinum-thallium complexes with strong metal-metal bonds.

The reactions of [Pt(NH3)2(NHCOtBu)2] and TlX3 (X = NO3-, Cl-, CF3CO2-) yielded dinuclear [{Pt(ONO2)(NH3)2(NHCOtBu)}Tl(ONO2)2(MeOH)] (2) and trinuclear complexes [{PtX(RNH2)2(NHCOtBu)2}2Tl]+ [X = NO3- (3), Cl- (5), CF3CO2- (6)], which were spectroscopically and structurally characterized. Strong Pt-Tl interaction in the complexes in solutions was indicated by both 195Pt and 205Tl NMR spectra, which exhibit very large one-bond spin-spin coupling constants between the heteronuclei (1J(PtTl)), 146.8 and 88.84 kHz for 2 and 3, respectively. Both the X-ray photoelectron spectra and the 195Pt chemical shifts reveal that the complexes have Pt centers whose oxidation states are close to that of Pt(III). Characterization of these complexes by X-ray diffraction analysis confirms that the Pt and Tl atoms are held together by very short Pt-Tl bonds and are supported by the bridging amidate ligands. The Pt-Tl bonds are shorter than 2.6 Angstrom, indicating a strong metal-metal attraction between these two metals. Compound 2 was found to activate the C-H bond of acetone to yield a platinum(IV) acetonate complex. This reactivity corresponds to the property of Pt(III) complexes. Density functional theory calculations were able to reproduce the large magnitude of the metal-metal spin-spin coupling constants. The couplings are sensitive to the computational model because of a delicate balance of metal 6s contributions in the frontier orbitals. The computational analysis reveals the role of the axial ligands in the magnitude of the coupling constants.