Integrated immunogenomic analysis of single-cell and bulk profiling reveals novel tumor antigens and subtype-specific therapeutic agents in lung adenocarcinoma.

Background: In recent years, mRNA-based vaccines with promising safety and functional characteristics have gained significant momentum in cancer immunotherapy. However, stable immunological molecular subtypes of lung adenocarcinoma (LUAD) and novel tumor antigens for LUAD mRNA vaccine development remain elusive. Therefore, a novel approach is urgently needed to identify suitable LUAD subtypes and potential tumor antigens. Methods: The Cancer Genome Atlas (TCGA), the Genotype Tissue Expression (GTEx), and Gene Expression Omnibus (GEO) databases were utilized to retrieve gene expression data. The LUAD Immunological Multi-Omics Classification (LIMOC) system was developed using seven machine learning (ML) algorithms by performing integrative immunogenomic analysis of single-cell and bulk tissue transcriptome profiling. Subsequently, a panel of approaches was applied to identify novel tumor antigens. Results: First, the LIMOC system was construct to identify three subtypes: LIMOC1, LIMOC2, and LIMOC3. Second, we identified CHIT1, LILRA4, and MEP1A as novel tumor antigens in LUAD; these genes were up-regulated, amplified, and mutated, and showed a positive association with APC infiltration, making them promising candidates for designing mRNA vaccines. Notably, the LIMOC2 subtype had the worst prognosis and could benefit most from mRNA immunization. Furthermore, we performed a comprehensive in silico screening of approximately 2000 compounds and identified Sorafenib and Azacitidine as potential subtype-specific therapeutic agents. Conclusions: Overall, our study established a robust LIMOC system and identified CHIT1, LILRA4, and MEP1A as promising tumor antigen candidates for development of anti-LUAD mRNA vaccines, particularly for the LIMOC2 subtype.

Application of Carbon Nanoparticles in Transoral Endoscopic Thyroidectomy Vestibular Approach for Unilateral Papillary Thyroid Cancer.

BACKGROUND: Transoral endoscopic thyroidectomy vestibular approach (TOETVA) is newly applied technology. Carbon nanoparticles (CNs) are novel lymph node tracers that have been widely used in China to help remove central lymph nodes (CLNs) and protect the parathyroid glands (PGs) in open thyroid cancer surgery. This study is to evaluate the effectiveness and safety of CNs in TOETVA. MATERIALS AND METHODS: A total of 158 patients who underwent TOETVA with unilateral papillary thyroid carcinoma were enrolled in this study from March 2019 to February 2022. The participants were divided into a CNs group (n=88) and a control group (n=70), based on whether they received a intraoperative injection of CNs or not. Meanwhile, the CNs group were additionally divided into 2 subgroups, leakage subgroup (n=26) and standard subgroup (n=62). The 2 groups and subgroups were compared in terms of patient characteristics, perioperative clinical results, and postoperative outcomes. RESULTS: All common metrics had no significant differences were found between the CNs group and the control group (P>0.05). The standard subgroup of CNs group had advantage over the control group on PGs identification (59/62 vs. 59/70 for superior PG, 56/62 vs. 52/70 for inferior PG, P<0.05). Moreover, the standard subgroup harvested more CLNs than the control group (8.97±2.96 vs. 7.47±2.93, P<0.05). More operation time was spent on the leakage subgroup of CNs group than the control group (160.00±17.61 vs. 140.00±13.32, P<0.05). Meanwhile, the leakage subgroup had disadvantage on intraoperative hemorrhage (26.15±10.80 vs. 21.21±7.09, P<0.05) and hospital durations (4.96±0.72 vs. 4.57±0.69, P<0.05). Furthermore, the leakage group identified fewer inferior PG than the control group (7/26 vs. 52/70, P<0.05). Contrary to the standard subgroup, the CLNs of the leakage subgroup was also unsatisfactory compared with the control group (4.96±1.84 vs. 7.47±2.93, P<0.05). CONCLUSIONS: The application of CNs suspension tracing technology has a definite effect in TOETVA. It can improve the thoroughness of lymph node dissection in the central region and enhance recognition of the PG. However, refined extracapsular anatomy is indispensable to prevent CN leakage. Leaked CNs will also be counterproductive to the operation.

Achieving deep intratumoral penetration and multimodal combined therapy for tumor through algal photosynthesis.

BACKGROUND: Elevated interstitial fluid pressure within tumors, resulting from impaired lymphatic drainage, constitutes a critical barrier to effective drug penetration and therapeutic outcomes. RESULTS: In this study, based on the photosynthetic characteristics of algae, an active drug carrier (CP@ICG) derived from Chlorella pyrenoidosa (CP) was designed and constructed. Leveraging the hypoxia tropism and phototropism exhibited by CP, we achieved targeted transport of the carrier to tumor sites. Additionally, dual near-infrared (NIR) irradiation at the tumor site facilitated photosynthesis in CP, enabling the breakdown of excessive intratumoral interstitial fluid by generating oxygen from water decomposition. This process effectively reduced the interstitial pressure, thereby promoting enhanced perfusion of blood into the tumor, significantly improving deep-seated penetration of chemotherapeutic agents, and alleviating tumor hypoxia. CONCLUSIONS: CP@ICG demonstrated a combined effect of photothermal/photodynamic/starvation therapy, exhibiting excellent in vitro/in vivo anti-tumor efficacy and favorable biocompatibility. This work provides a scientific foundation for the application of microbial-enhanced intratumoral drug delivery and tumor therapy.

Shexiang Baoxin Pill enriches Lactobacillus to regulate purine metabolism in patients with stable coronary artery disease.

BACKGROUND: It has been clinically confirmed that the Shexiang Baoxin Pill (SBP) dramatically reduces the frequency of angina in patients with stable coronary artery disease (SCAD). However, potential therapeutic mechanism of SBP has not been fully explored. PURPOSE: The study explored the therapeutic mechanism of SBP in the treatment of SCAD patients. METHODS: We examined the serum metabolic profiles of patients with SCAD following SBP treatment. A rat model of acute myocardial infarction (AMI) was established, and the potential therapeutic mechanism of SBP was explored using metabolomics, transcriptomics, and 16S rRNA sequencing. RESULTS: SBP decreased inosine production and improved purine metabolic disorders in patients with SCAD and in animal models of AMI. Inosine was implicated as a potential biomarker for SBP efficacy. Furthermore, SBP inhibited the expression of genes involved in purine metabolism, which are closely associated with thrombosis, inflammation, and platelet function. The regulation of purine metabolism by SBP was associated with the enrichment of Lactobacillus. Finally, the effects of SBP on inosine production and vascular function could be transmitted through the transplantation of fecal microbiota. CONCLUSION: Our study reveals a novel mechanism by which SBP regulates purine metabolism by enriching Lactobacillus to exert cardioprotective effects in patients with SCAD. The data also provide previously undocumented evidence indicating that inosine is a potential biomarker for evaluating the efficacy of SBP in the treatment of SCAD.

Integrating single-cell and spatial analysis reveals MUC1-mediated cellular crosstalk in mucinous colorectal adenocarcinoma.

BACKGROUND: Mucinous colorectal adenocarcinoma (MCA) is a distinct subtype of colorectal cancer (CRC) with the most aggressive pattern, but effective treatment of MCA remains a challenge due to its vague pathological characteristics. An in-depth understanding of transcriptional dynamics at the cellular level is critical for developing specialised MCA treatment strategies. METHODS: We integrated single-cell RNA sequencing and spatial transcriptomics data to systematically profile the MCA tumor microenvironment (TME), particularly the interactome of stromal and immune cells. In addition, a three-dimensional bioprinting technique, canonical ex vivo co-culture system, and immunofluorescence staining were further applied to validate the cellular communication networks within the TME. RESULTS: This study identified the crucial intercellular interactions that engaged in MCA pathogenesis. We found the increased infiltration of FGF7+/THBS1+ myofibroblasts in MCA tissues with decreased expression of genes associated with leukocyte-mediated immunity and T cell activation, suggesting a crucial role of these cells in regulating the immunosuppressive TME. In addition, MS4A4A+ macrophages that exhibit M2-phenotype were enriched in the tumoral niche and high expression of MS4A4A+ was associated with poor prognosis in the cohort data. The ligand-receptor-based intercellular communication analysis revealed the tight interaction of MUC1+ malignant cells and ZEB1+ endothelial cells, providing mechanistic information for MCA angiogenesis and molecular targets for subsequent translational applications. CONCLUSIONS: Our study provides novel insights into communications among tumour cells with stromal and immune cells that are significantly enriched in the TME during MCA progression, presenting potential prognostic biomarkers and therapeutic strategies for MCA. KEY POINTS: Tumour microenvironment profiling of MCA is developed. MUC1+ tumour cells interplay with FGF7+/THBS1+ myofibroblasts to promote MCA development. MS4A4A+ macrophages exhibit M2 phenotype in MCA. ZEB1+ endotheliocytes engage in EndMT process in MCA.

Seleno-amino Acid Metabolism Reshapes the Tumor Microenvironment: from Cytotoxicity to Immunotherapy.

Selenium (Se) is an essential trace element for biological processes. Seleno-amino acids (Se-AAs), known as the organic forms of Se, and their metabolic reprogramming have been increasingly recognized to regulate antioxidant defense, enzyme activity, and tumorigenesis. Therefore, there is emerging interest in exploring the potential application of Se-AAs in antitumor therapy. In addition to playing a vital role in inhibiting tumor growth, accumulating evidence has revealed that Se-AA metabolism could reshape the tumor microenvironment (TME) and enhance immunotherapy responses. This review presents a comprehensive overview of the current progress in multifunctional Se-AAs for antitumor treatment, with a particular emphasis on elucidating the crosstalk between Se-AA metabolism and various cell types in the TME, including tumor cells, T cells, macrophages, and natural killer cells. Furthermore, novel applications integrating Se-AAs are also discussed alongside prospects to provide new insights into this emerging field.

Efficient residual network using hyperspectral images for corn variety identification.

Corn seeds are an essential element in agricultural production, and accurate identification of their varieties and quality is crucial for planting management, variety improvement, and agricultural product quality control. However, more than traditional manual classification methods are needed to meet the needs of intelligent agriculture. With the rapid development of deep learning methods in the computer field, we propose an efficient residual network named ERNet to identify hyperspectral corn seeds. First, we use linear discriminant analysis to perform dimensionality reduction processing on hyperspectral corn seed images so that the images can be smoothly input into the network. Second, we use effective residual blocks to extract fine-grained features from images. Lastly, we detect and categorize the hyperspectral corn seed images using the classifier softmax. ERNet performs exceptionally well compared to other deep learning techniques and conventional methods. With 98.36% accuracy rate, the result is a valuable reference for classification studies, including hyperspectral corn seed pictures.

Photo-Deactivation Strategy for Switchable ATRP with the Assistance of Molecular Switches.

Light irradiation is an external stimulus, rapidly developed in switchable atom transfer radical polymerization (ATRP) via photo-activation methods in recent years. Herein, a photo-deactivation strategy is introduced to regulate ATRP with the assistance of photoswitchable hexaarylbiimidozole (HABI). Under visible light irradiation and in the presence of HABI, ATRP is greatly decelerated or quenched depending on the concentration of HABI. Interestingly, with visible light off, ATRP can proceed smoothly and follow a first-order kinetics. Moreover, photo-switchable ATRP alternatively with light off and on is demonstrated. Besides, the mechanism of photo-deactivation ATRP involving radical quenching is proposed in the presence of HABI.

Synergistic rosemary extract with TBHQ and citric acid improves oxidative stability and shelf life of peanut.

Lipid oxidation often accompanies the processing and storage of peanuts, which causes a serious waste of peanut resources. To solve the problem of being prone to oxidation in peanut processing, a ternary complex antioxidant based on rosemary extract (RE) was constructed to investigate its effect on the oxidative and thermal stability of peanuts, and the inhibition of peanut oxidation by compound antioxidants was revealed by dynamic Arrhenius formula and complexation theory. The results showed that there was a synergistic effect between RE and Tert-butyl hydroquinone (TBHQ), and the antioxidant effects of RE and TBHQ were 4.86 and 1.45 times higher when used in combination than when used alone, respectively. In addition, RE-TBHQ-CA (citric acid) effectively inhibited primary and secondary oxidation of peanuts with a shelf life 8.7 times longer than that of control peanuts. This study provides a novel antioxidant compounding idea, which has a positive effect on improving the quality of peanut and other nut products, prolonging the shelf life and reducing the waste of resources. PRACTICAL APPLICATION: Compounding a complex antioxidant that permits its use in peanuts. It was found that rosemary and TBHQ might have synergistic antioxidant effects. Meanwhile, this combination of RE-TBHQ-CA effectively inhibited the oxidation of peanut oils and prolonged the shelf life of peanuts. RE-TBHQ-CA is a highly efficient complex antioxidant that can reduce the amounts of antioxidants added while maintaining high antioxidant efficiency, which may be useful for the future preservation and storage of nut products as it positively affects the quality and shelf life of the product.

Visible-Light-Mediated Three-Component Strategy for the Synthesis of Isoxazolines and Isoxazoles.

Isoxazolines and isoxazoles commonly serve as core structures of many therapeutic agents and natural products. However, the metal-free and catalysis-free strategy for the synthesis of these privileged motifs at room temperature remains a challenging task. Herein, we report a three-component strategy to afford diverse isoxazolines and isoxazoles via [3 + 2] cycloadditions of in situ-formed nitronates and olefins/alkynes under visible-light irradiation.

Adaptive sequential design for phase II single-arm oncology trials: an expansion of Simon's design.

Single-arm phase II trials are very common in oncology. A fixed sample trial may lack sufficient power if the true efficacy is less than the assumed one. Adaptive designs have been proposed in the literature. We propose a Simon's design based, adaptive sequential design. Simon's design is the most used fixed sample design for single-arm phase II oncology trials. A prominent feature of Simon's design is that it minimizes the sample size when there is no clinically meaningful efficacy. We identify Simon's trial as a special group sequential design. Established methods for sample size re-estimation (SSR) can be readily applied to Simon's design. Simulations show that simply adding SSR to Simon's design may still not provide desirable power. We propose some expansions to Simon's design. The expanded design with SSR can provide even more power.

In silico study of androgen receptor N-terminal domain and exploration of its modulators.

The androgen receptor (AR, Uniprot: P10275) signaling plays a key role in the progression of prostate cancer, various AR-related ligands have been reported to treat prostate cancer. However, some resistance mechanisms limited the treating effect of these ligands. Since DBD binding or the allosteric binding sites in LBD of AR may allow the circumvention of some drug resistance mechanisms, anti-resistance is expected especially through the NTD (N-terminal domain) targeting. What's more, studies have shown that compounds including EPI-001 and its derivatives which bind to the Tau-5 region on NTD could be promising molecules for AR-based therapeutics. Herein, we employed aMD (accelerated molecular dynamics) simulation to fold Tau-5 unit proteins into native structure correctly. Subsequently, based on the predicted structural features of Tau-5, the virtual screening was conducted to discover new compounds targeting AR-NTD. We picked up 8 compounds (according to their docking scores and partly similar structural consists as known AR ligands) and analyzed their interaction with Tau-5, compared with the positive control EPI-001, four of the pick-up compounds showed better glide scores. Interestingly, although compound 8 had a lower docking score, it consisted of a similar component as the ligand EIQPN and the amide derivatives, this predicts that compound 8 has also the potential to be modified into an excellent AR-NTD binding molecule. These 8 compounds were all commercially available and could be tested to check whether there was a hit compound to bind the AR-NTD and to regulate its bio-activities. Together, this study described an in silico VLS approach to discover AR-NTD ligands and provided more choices for developing AR-targeted therapies.Communicated by Ramaswamy H. Sarma.

Safety-Preserving Lyapunov-Based Model Predictive Rendezvous Control for Heterogeneous Marine Vehicles Subject to External Disturbances.

This article investigates the cooperative rendezvous control problem for perturbed heterogeneous marine systems composed of an autonomous underwater vehicle (AUV) and an autonomous surface vehicle (ASV). A novel Lyapunov-based model predictive control (LMPC) framework is presented to accomplish safe and precise rendezvous under input limitations and external disturbances. First, by incorporating the prescribed performance control (PPC) technique into the LMPC framework, we transform the original ascending state of the AUV into a self-constrained state, which serves as the decision variable of the model predictive control (MPC) optimization problem. Then, PPC-aided auxiliary control laws based on disturbance observers (DOBs) are designed to establish a robust contractive constraint to provide stability margins. Combining the LMPC with the PPC technique makes the original state-constrained problem an equivalent state-constraint-free problem. By addressing the MPC problem for the equivalent unconstrained system, the proposed method preserves the rendezvous safety. With the robust contractive constraint, the proposed safety-preserving LMPC (SP-LMPC) controller can inherit robustness and stability from the robust auxiliary control laws. Furthermore, theoretical analyses are conducted to assess recursive feasibility and closed-loop stability. With comprehensive theoretical support, the proposed method provides a new framework to simultaneously address state constraints and disturbances for highly nonlinear marine systems. Finally, simulations and comparisons are conducted to demonstrate the effectiveness and advantages of the proposed algorithm.

Offline Reinforcement Learning With Behavior Value Regularization.

Offline reinforcement learning (offline RL) aims to find task-solving policies from prerecorded datasets without online environment interaction. It is unfortunate that extrapolation errors can cause over-optimistic Q -value estimates when learning with a fixed dataset, limiting the performance of the learned policy. To tackle this issue, this article proposes an offline actor-critic with behavior value regularization (OAC-BVR) method. In the policy evaluation stage, the difference between the Q -function and the value of the behavior policy is considered as the regularization term, driving the learned value function to approach the value of the behavior policy. The convergence of the proposed policy evaluation with behavior value regularization (PE-BVR) and the value function difference are analyzed, respectively. Compared with existing offline actor-critic methods, the proposed OAC-BVR method integrates the value of the behavior policy, thereby simultaneously alleviating over-optimistic Q -value estimates and reducing Q -function bias. Experimental results on the D4RL MuJoCo and Maze2d datasets demonstrate the validity of the proposed PE-BVR and the performance advantage of OAC-BVR over the state-of-the-art offline RL algorithms. The code of OAC-BVR is available at https://github.com/LongyangHuang/OAC-BVR.

In Silico Discovery of Stapled Peptide Inhibitor Targeting the Nur77-PPARγ Interaction and Its Anti-Breast-Cancer Efficacy.

The binding of peroxisome proliferator-activated receptor γ (PPARγ) to the orphan nuclear receptor Nur77 facilitates the ubiquitination and degradation of Nur77, and leads to aberrant fatty acid uptake for breast cancer progression. Because of its crucial role in clinical prognosis, the interaction between Nur77 and PPARγ is an attractive target for anti-breast-cancer therapy. However, developing an inhibitor of the Nur77-PPARγ interaction poses a technical challenge due to the absence of the crystal structure of PPARγ and its corresponding interactive model with Nur77. Here, ST-CY14, a stapled peptide, is identified as a potent modulator of Nur77 with a KD value of 3.247 × 10-8 M by in silico analysis, rational design, and structural modification. ST-CY14 effectively increases Nur77 protein levels by blocking the Nur77-PPARγ interaction, thereby inhibiting lipid metabolism in breast tumor cells. Notably, ST-CY14 significantly suppresses breast cancer growth and bone metastasis in mice. The findings demonstrate the feasibility of exploiting directly Nur77-PPARγ interaction in breast cancer, and generate what to the best knowledge is the first direct inhibitor of the Nur77-PPARγ interaction available for impeding fatty acid uptake and therapeutic development.

Acetone Serving as a Solvent and Interaction Partner Promotes the Direct Olefination of N-Tosylhydrazones under Visible Light.

The photochemistry of noncovalent interactions to promote organic transformations is an emerging approach to providing fresh opportunities in synthetic chemistry. Generally, the external substance is necessary to add as an interaction partner, thereby sacrificing the atom economy of the reaction. Herein, we describe a catalyst-free and noncovalent interaction-mediated strategy to access the olefination of N-tosylhydrazones using acetone as a solvent and an interaction partner. This protocol also features broad substrate scope, excellent functional group compatibility, and mild reaction conditions without transition metals. Moreover, the gram-scale synthesis of olefins and the generation of pharmaceutical intermediates highlighted its practical applicability. Lastly, mechanistic studies indicate that the reaction was initiated via noncovalent interactions between acetone and N-tosylhydrazone anion, which is also supported by density functional theory calculations.

High expression of KIFC1 is a poor prognostic biomarker and correlates with TP53 mutation in lung cancer.

The Kinesin Family Member C1 (KIFC1) is highly expressed in a variety of tumors. Since it is linked with tumorigenesis and progression, KIFC1 has emerged as a promising candidate for targeted chemotherapies. Thus, this study aims to find out the association between KIFC1 and lung cancer. The original data were assessed from The Cancer Genome Atlas and Gene Expression Omnibus databases. Compared to normal lung tissues, both mRNA and protein levels of KIFC1 were significantly increased in lung cancer tissues. The upregulation of KIFC1 was significantly correlated with sex, pathological stage, and TMN stage. Survival analysis revealed that increased KIFC1 expression was associated with poor overall survival, first-progression survival and post-progression survival in lung cancer. Based on the Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analysis, we observed that KIFC1 upregulation was linked to enrichment of the cell cycle and TP53 signaling pathway. Additionally, the overexpression of KIFC1 was positively correlated with TP53 mutations in lung cancer. Based on real-world cohort results, western blotting and RT-qPCR showed high-KIFC1 expression in lung cancer, which may be related to the malignancy of lung cancer. Finally, experiments in vitro showed that KIFC1 inhibitor could significantly inhibit the proliferation and invasion of lung cancer cells. In conclusion, KIFC1 is a poor prognostic biomarker, and patients with high-KIFC1 levels may benefit from targeted therapy.

Blocking Ubiquitin-Specific Protease 7 Induces Ferroptosis in Gastric Cancer via Targeting Stearoyl-CoA Desaturase.

Gastric cancer (GC) presents a formidable global health challenge, and conventional therapies face efficacy limitations. Ubiquitin-specific protease 7 (USP7) plays pivotal roles in GC development, immune response, and chemo-resistance, making it a promising target. Various USP7 inhibitors have shown selectivity and efficacy in preclinical studies. However, the mechanistic role of USP7 has not been fully elucidated, and currently, no USP7 inhibitors have been approved for clinical use. In this study, DHPO is identified as a potent USP7 inhibitor for GC treatment through in silico screening. DHPO demonstrates significant anti-tumor activity in vitro, inhibiting cell viability and clonogenic ability, and preventing tumor migration and invasion. In vivo studies using orthotopic gastric tumor mouse models validate DHPO's efficacy in suppressing tumor growth and metastasis without significant toxicity. Mechanistically, DHPO inhibition triggers ferroptosis, evidenced by mitochondrial alterations, lipid Reactive Oxygen Species (ROS), Malondialdehyde (MDA) accumulation, and iron overload. Further investigations unveil USP7's regulation of Stearoyl-CoA Desaturase (SCD) through deubiquitination, linking USP7 inhibition to SCD degradation and ferroptosis induction. Overall, this study identifies USP7 as a key player in ferroptosis of GC, elucidates DHPO's inhibitory mechanisms, and highlights its potential for GC treatment by inducing ferroptosis through SCD regulation.

Molecularly Imprinted Heterostructure-Assisted Laser Desorption Ionization Mass Spectrometry Analysis and Imaging of Quinolones.

Quinolone residues resulting from body metabolism and waste discharge pose a significant threat to the ecological environment and to human health. Therefore, it is essential to monitor quinolone residues in the environment. Herein, an efficient and sensitive matrix-assisted laser desorption/ionization mass spectrometry (MALDI/MS) method was devised by using a novel molecularly imprinted heterojunction (MIP-TNs@GCNs) as the matrix. Molecularly imprinted titanium dioxide nanosheets (MIP-TNs) and graphene-like carbon nitrides (GCNs) were associated at the heterojunction interface, allowing for the specific, rapid, and high-throughput ionization of quinolones. The mechanism of MIP-TNs@GCNs was clarified using their adsorption properties and laser desorption/ionization capability. The prepared oxygen-vacancy-rich MIP-TNs@GCNs heterojunction exhibited higher light absorption and ionization efficiencies than TNs and GCNs. The good linearity (in the quinolone concentration range of 0.5-50 pg/µL, R2 > 0.99), low limit of detection (0.1 pg/µL), good reproducibility (n = 8, relative standard deviation [RSD] < 15%), and high salt and protein resistance for quinolones in groundwater samples were achieved using the established MIP-TNs@GCNs-MALDI/MS method. Moreover, the spatial distributions of endogenous compounds (e.g., amino acids, organic acids, and flavonoids) and xenobiotic quinolones from Rhizoma Phragmitis and Rhizoma Nelumbinis were visualized using the MIP-TNs@GCNs film as the MALDI/MS imaging matrix. Because of its superior advantages, the MIP-TNs@GCNs-MALDI/MS method is promising for the analysis and imaging of quinolones and small molecules.

Data Augmentation of a Corrosion Dataset for Defect Growth Prediction of Pipelines Using Conditional Tabular Generative Adversarial Networks.

Due to corrosion characteristics, there are data scarcity and uneven distribution in corrosion datasets, and collecting high-quality data is time-consuming and sometimes difficult. Therefore, this work introduces a novel data augmentation strategy using a conditional tabular generative adversarial network (CTGAN) for enhancing corrosion datasets of pipelines. Firstly, the corrosion dataset is subjected to data cleaning and variable correlation analysis. The CTGAN is then used to generate external environmental factors as input variables for corrosion growth prediction, and a hybrid model based on machine learning is employed to generate corrosion depth as an output variable. The fake data are merged with the original data to form the synthetic dataset. Finally, the proposed data augmentation strategy is verified by analyzing the synthetic dataset using different visualization methods and evaluation indicators. The results show that the synthetic and original datasets have similar distributions, and the data augmentation strategy can learn the distribution of real corrosion data and sample fake data that are highly similar to the real data. Predictive models trained on the synthetic dataset perform better than predictive models trained using only the original dataset. In comparative tests, the proposed strategy outperformed other data generation methods.