Search

Abstract The efficacy of neoadjuvant chemotherapy (NACT) in patients with advanced gastric cancer (GC) varies greatly. Thus, we aimed to verify the predictive value of tumor‐infiltrating immune cells (TIICs) on the treatment response to NACT and the prognosis of patients with advanced GC, and to explore the impact of NACT on the tumor immune microenvironment (TIME). Paired tumor tissues (pre‐ and post‐NACT) from patients with advanced GC were collected for this study. TIICs were assessed using immunohistochemistry staining and analyzed using logistic regression to establish an immune microenvironment score for GC (ISGC score) and predict NACT efficacy. Kaplan–Meier curves were used to evaluate the survival outcome of patients. The results showed that TIME was dramatically heterogeneous between NACT response and nonresponse patients. In the validation cohort, the ISGC score demonstrated good predictive performance for treatment response to NACT. Moreover, high ISGC indicated better long‐term survival in patients with advanced GC. Furthermore, tumor‐infiltrated T cells (CD3+ and CD8+) and CD11c+ macrophages were significantly increased in the response group, while CD163+ macrophages and FOXP3+ Treg cells were decreased after NACT. However, opposite results were exhibited in the nonresponse group. Finally, we found that the percentage of programmed cell death ligand 1 (PD‐L1)‐positive tumors was 31% (32/104) pre‐NACT and 49% (51/104) post‐NACT, and almost all patients with elevated PD‐L1 were in the NACT response group. The ISGC model accurately predicted NACT efficacy and classified patients with GC into different survival groups. NACT regulates the TIME in GC, which may provide strategies for personalized immunotherapy.

Abstract Local integrated energy system (IES), usually a multi‐building heating and cooling system incorporating cogeneration systems and distributed energy resources (DERs), is becoming an efficient energy infrastructure for energy system decarbonization. However, for small and medium‐scale local IESs, the fluctuation of user loads seriously influences energy system operation, and the increasing DER penetration also enlarges the influence. Given the necessity of exploring an efficient way to handle the uncertainties in local IES, this paper proposes a reinforcement learning (RL) approach based on the improved TD3 algorithm. The mathematical model of local IES is first established considering supply‐ and load‐side flexible resources. The local IES dispatch problem is formulated as a Markov decision process (MDP), in which multi‐type uncertainties of renewable generation, electric load and heat load are considered. For solving the MDP, an improved twin delayed deep deterministic policy gradient (TD3) algorithm is proposed with a dynamic balance mechanism of exploration noise. Based on a local IES testbed in the Nantong Central Innovation District, China, a comparison analysis is conducted to verify the promoting effect of flexible resources on the operation economy and renewable energy consumption. The system operating cost reduces by 18.46%, and surplus renewable energy can all be accommodated considering flexible resources. The dispatch policies obtained by the deep deterministic policy gradient (DDPG), the improved TD3, the original TD3 and traditional optimization algorithms are also compared. The results reveal that the convergence stability and solving accuracy of the improved TD3 outperform the other two RL algorithms. Specifically, the system operating cost of the improved TD3 reduces by 2.76% compared with the DDPG, and the energy supply imbalance decreases by around 88%. Meanwhile, the improved TD3 exhibits better operation economy and adaptability to the uncertain environment than the deterministic optimization and intraday rolling algorithms.

Model soups synthesize multiple models after fine-tuning them with different hyperparameters based on the accuracy of the validation data. They train different models on the same training and validation data sets. In this study, we maximized the model fine-tuning accuracy using the inference time and memory cost of a single model. We extended the model soups to create subsets of k training and validation data using a method similar to k-fold cross-validation and trained models on these subsets. First, we showed the correlation between the validation and test data when the models are synthesized, such that their training data contain validation data. Thereafter, we showed that synthesizing k of these models, after synthesizing models based on subsets of the same training and validation data, provides a single model with high test accuracy. This study provides a method for learning models with both high accuracy and reliability for small datasets such as medical images.

In recent years, the number of similar software products with many common parts has been increasing due to the reuse and plagiarism of source code in the software development process. Pattern matching, which is an existing method for detecting similarity, cannot detect the similarities between these software products and other programs. It is necessary, for example, to detect similarities based on commonalities in both functionality and control structures. At the same time, detailed software analysis requires manual reverse engineering. Therefore, technologies that automatically identify similarities among the arge amounts of code present in software products in advance can reduce these oads. In this paper, we propose a representation earning model to extract feature expressions from assembly code obtained by statically analyzing such code to determine the similarity between software products. We use assembly code to eliminate the dependence on the existence of source code or differences in development anguage. The proposed approach makes use of Asm2Vec, an existing method, that is capable of generating a vector representation that captures the semantics of assembly code. The proposed method also incorporates information on the program control structure. The control structure can be represented by graph data. Thus, we use graph embedding, a graph vector representation method, to generate a representation vector that reflects both the semantics and the control structure of the assembly code. In our experiments, we generated expression vectors from multiple programs and used clustering to verify the accuracy of the approach in classifying similar programs into the same cluster. The proposed method outperforms existing methods that only consider semantics in both accuracy and execution time.

Deregulation of METTL1-mediated N7- methylguanosine tRNA modification can promote oncogenesis. Here, the authors report that this modification regulates the translation of proteins in both the mTOR and negative regulators of autophagy pathways, resulting in the progression of esophageal squamous cell carcinoma.

Fake news on social media has become a social problem. Fake news refers to false information that is deliberately intended to deceive people. Several studies have been conducted on automatic detection systems that reduce the damage caused by fake news. However, most studies address the improvements made in detection accuracy, and real-world operations are rarely discussed. As the contents and expressions of fake news change over time, a model with a high detection accuracy loses accuracy after a few years. This phenomenon is called concept drift. As most conventional methods employ word representations, these methods exhibit accuracy degradation resulting from changes in word fads and usage. However, methods using the sentiment information of words can identify inflammatory sentences, which is a characteristic of fake news, and may suppress performance degradation caused by concept drift. In this study, a model using vector representations obtained from an emotion dictionary was compared with a model using conventional word embedding. Subsequently, we verified the resistance of the model to performance degradation. The results revealed the method using sentiment representation is less susceptible to concept drift. Models and learning methods that can achieve both detection accuracy and resistance to accuracy degradation can enable further development of fake news detection systems.

BackgroundMounting studies reveal the relationship between inflammatory markers and post-therapy prognosis. Yet, the role of the systemic inflammatory indices in preoperative microvascular invasion (MVI) prediction for hepatocellular carcinoma (HCC) remains unclear.Patients and MethodsIn this study, data of 1,058 cases of patients with HCC treated in the First Affiliated Hospital of Sun Yat-sen University from February 2002 to May 2018 were collected. Inflammatory factors related to MVI diagnosis in patients with HCC were selected by least absolute shrinkage and selection operator (LASSO) regression analysis and were integrated into an “Inflammatory Score.” A prognostic nomogram model was established by combining the inflammatory score and other independent factors determined by multivariate logistic regression analysis. The receiver operating characteristic (ROC) curve and the area under the curve (AUC) were used to evaluate the predictive efficacy of the model.ResultsSixteen inflammatory factors, including neutrophil-to-lymphocyte ratio, platelet-to-lymphocyte ratio, etc., were selected by LASSO regression analysis to establish an inflammatory score. Multivariate logistic regression analysis showed that inflammatory score (OR = 2.14, 95% CI: 1.63–2.88, p < 0.001), alpha fetoprotein (OR = 2.02, 95% CI: 1.46–2.82, p < 0.001), and tumor size (OR = 2.37, 95% CI: 1.70–3.30, p < 0.001) were independent factors for MVI. These three factors were then used to establish a nomogram for MVI prediction. The AUC for the training and validation group was 0.72 (95% CI: 0.68–0.76) and 0.72 (95% CI: 0.66–0.78), respectively.ConclusionThese findings indicated that the model drawn in this study has a high predictive value which is capable to assist the diagnosis of MVI in patients with HCC.

AimsTo evaluate the value of tumor-educated platelet (TEP) miR-18a-3p in the early diagnosis and chemotherapy efficacy monitoring of nasopharyngeal carcinoma (NPC).MethodsExpression levels of miR-18a-3p in platelets and plasma were detected by relative quantitative real-time PCR in NPC patients (n=54) and normal subjects (n=36). Diagnostic values of TEP miR-18a-3p for NPC was assessed by receiver operating characteristic (ROC) curve analysis. Follow up study was carried out to observe the dynamic changes of TEP miR-18a-3p with chemotherapy on 3 NPC patients.ResultsThe expression levels of TEP miR-18a-3p in NPC patients were significantly higher than that in healthy controls (p < 0.0001). ROC curve analysis showed that the area under the curve (AUC) value was 0.841, the sensitivity and specificity for the diagnosis of NPC were 87% and 72.7%. No correlation was found between expression levels of TEP miR-18a-3p and patients’ clinical parameters and their NPC tumor-node-metastasis (TNM) stage. The positive rate of TEP miR-18a-3p and EBV DNA for NPC diagnosis were 85.4% and 66.7%. TEP miR-18a-3p expression were down-regulated after 77.8% (7 of 9) of chemotherapy, and in 66.7% (2 of 3) patients, TEP miR-18a-3p levels decreased after 3 cycles of chemotherapy.ConclusionThe expression levels of TEP miR-18a-3p are upregulated in NPC and have a high probability to downregulated after chemotherapy, indicating a significant clinical value. TEP miR-18a-3p might serve as a novel type of liquid-biopsy biomarker for early diagnosis and chemotherapy efficacy monitoring in NPC.

How to combine science and technology with the humanities in the research on ancient cities to reveal ancient peoples’ urban planning thoughts is worthy of in-depth study. The capitals of the Western Han dynasty as well as the Sui and Tang dynasties were some of the greatest cities in the world at the time. This paper takes them as its subjects and puts forward a method to study the spatial relationship between ancient cities and the natural environment by combining spatial information technology and cultural analysis. Firstly, satellite images, elevation maps, urban ichnographies, and literature materials were collected and sorted to deeply understand the cultural thoughts involved in ancient urban planning; based on this, key element points were marked and rechecked on the spot, and the above drawings were accurately superimposed by GIS technology to form a geographic information base that integrated multisource information. Then, Python was used to construct a “decision model of spatial relationship between urban elements and natural elements”, and rules as well as parameters were set through man–machine collaboration. The decision model was used to test the geographic information base, and the information of strong correlations between urban objects and natural objects was outputted. The drawings were exported after screening, and a visual expression was realized with Illustrator software. The research results indicated that this analysis method was feasible, effective, and easy to promote. The new archaeological discoveries included eight important line segments with a 9:6 proportional relationship (which represents the balance of Yin and Yang) and two important line segments with a 9:5 proportional relationship (which represents the supreme imperial power) in the capitals of the Western Han dynasty as well as the Sui and Tang dynasties, and 16 contraposition lines in a positive direction or oblique 45° direction (which reflects the close relationship between urban elements and natural elements). We consider that the two capitals were intentionally closely related to natural environments such as mountain peaks and valley entrances in the planning stage, and that proportions and scales with profound humanistic meaning were selected. The capital of the Sui and Tang dynasties was specially aligned with the capital of the Western Han dynasty in space. These characteristics embody ancient Chinese Confucian cultural thoughts such as the “integration of yang and yin”, “harmony between nature and humans”, the “supremacy of emperors”, and the “use of numbers and shapes to convey meaning”.

The full electrification of ports is a promising prospect for saving energy and reducing greenhouse gas emissions. The control scheme of the reefer container is particularly important for the energy management of the port, as the operation of the reefer container is one of the main energy consumers of ports. This paper proposes a reefer container hierarchical control scheme that contains a day-ahead module and intra-day module which is used to generate a rough scheduling strategy based on forecast data and fine-tuning the strategy, respectively. The final strategy should realize the economical operation while ensuring that each reefer container does not exceed the temperature limit during operation. Numerical analysis on the reefer container park with 200 and 850 containers using the Time of Use (TOU) tariff and super-peak tariff is fully analyzed. In the case of 200 containers, the proposed method helps reduce operating costs by about 14.7%, and 18% in the scenario of 850 containers. The proposed method can effectively save container operating costs and ensure that the internal temperature of the container does not exceed the limit while changing the distribution of energy which could help alleviate the peak load problem of the port electric system.

Preterm births are rising in Canada and worldwide. As clinicians strive to identify preterm neonates at greatest risk of significant developmental or motor problems, accurate predictive tools are required. Infants at highest risk will be able to receive early developmental interventions, and will also enable clinicians to implement and evaluate new methods to improve outcomes. While severe white matter injury (WMI) is associated with adverse developmental outcome, more subtle injuries are difficult to identify and the association with later impairments remains unknown. Thus, our goal was to develop an automated method for detection and visualization of brain abnormalities in MR images acquired in very preterm born neonates. We have developed a technique to detect WMI in T1-weighted images acquired in 177 very preterm born infants (24–32 weeks gestation). Our approach uses a stochastic process that estimates the likelihood of intensity variations in nearby pixels; with small variations being more likely than large variations. We first detect the boundaries between normal and injured regions of the white matter. Following this we use a measure of pixel similarity to identify WMI regions. Our algorithm is able to detect WMI in all of the images in the ground truth dataset with some false positives in situations where the white matter region is not segmented accurately.

Novel biomarkers are of particular interest for predicting cancer prognosis. This study aimed to explore the associations between enhancer of zeste homolog 2 (EZH2) and patient survival in various cancers.Relevant literature was retrieved from PubMed and Web of Science databases. Pooled hazard ratios (HRs), odds ratios (ORs), and 95% confidence intervals (CIs) were calculated.Forty-nine studies (8,050 patients) were included. High EZH2 expression was significantly associated with shorter overall (hazard ratio [HR] 1.74, 95% CI: 1.46-2.07), disease-free (HR 1.59, 95% CI: 1.27-1.99), metastasis-free (HR 2.19, 95% CI: 1.38-3.47), progression-free (HR 2.53, 95% CI: 1.52-4.21), cancer-specific (HR 3.13, 95% CI: 1.70-5.74), and disease-specific (HR 2.29, 95% CI: 1.56-3.35) survival, but not recurrence-free survival (HR 1.38, 95% CI: 0.93-2.06). Moreover, EZH2 expression significantly correlated with distant metastasis (OR 3.25, 95% CI: 1.07-9.87) in esophageal carcinoma; differentiation (OR 3.00, 95% CI: 1.37-6.55) in non-small cell lung cancer; TNM stage (OR 3.18, 95% CI: 2.49-4.08) in renal cell carcinoma; and histological grade (OR 4.50, 95% CI: 3.33-6.09), estrogen receptor status (OR 0.15, 95% CI: 0.11-0.20) and progesterone receptor status (OR 0.30, 95% CI: 0.23-0.39) in breast cancer.Our results suggested that EZH2 might be an independent prognostic factor for multiple survival measures in different cancers.