Search

In this paper, we first propose a graph neural network encoding method for multiobjective evolutionary algorithm to handle the community detection problem in complex attribute networks. In the graph neural network encoding method, each edge in an attribute network is associated with a continuous variable. Through non-linear transformation, a continuous valued vector (i.e. a concatenation of the continuous variables associated with the edges) is transferred to a discrete valued community grouping solution. Further, two objective functions for single- and multi-attribute network are proposed to evaluate the attribute homogeneity of the nodes in communities, respectively. Based on the new encoding method and the two objectives, a multiobjective evolutionary algorithm (MOEA) based upon NSGA-II, termed as continuous encoding MOEA, is developed for the transformed community detection problem with continuous decision variables. Experimental results on single- and multi-attribute networks with different types show that the developed algorithm performs significantly better than some well-known evolutionary and non-evolutionary based algorithms. The fitness landscape analysis verifies that the transformed community detection problems have smoother landscapes than those of the original problems, which justifies the effectiveness of the proposed graph neural network encoding method.

Matrix factorization (MF) methods decompose a data matrix into a product of two-factor matrices (denoted as U and V ) which are with low ranks. In this article, we propose a generative latent variable model for the data matrix, in which each entry is assumed to be a Gaussian with mean to be the inner product of the corresponding columns of U and V . The prior of each column of U and V is assumed to be as a finite mixture of Gaussians. Further, we propose to model the attribute matrix with the data matrix jointly by considering them as conditional independence with respect to the factor matrix U , building upon previously defined model for the data matrix. Due to the intractability of the proposed models, we employ variational Bayes to infer the posteriors of the factor matrices and the clustering relationships, and to optimize for the model parameters. In our development, the posteriors and model parameters can be readily computed in closed forms, which is much more computationally efficient than existing sampling-based probabilistic MF models. Comprehensive experimental studies of the proposed methods on collaborative filtering and community detection tasks demonstrate that the proposed methods achieve the state-of-the-art performance against a great number of MF-based and non-MF-based algorithms.

Detecting overlapping communities of an attribute network is a ubiquitous yet very difficult task, which can be modeled as a discrete optimization problem. Besides the topological structure of the network, node attributes and node overlapping aggravate the difficulty of community detection significantly. In this article, we propose a novel continuous encoding method to convert the discrete-natured detection problem to a continuous one by associating each edge and node attribute in the network with a continuous variable. Based on the encoding, we propose to solve the converted continuous problem by a multiobjective evolutionary algorithm (MOEA) based on decomposition. To find the overlapping nodes, a heuristic based on double-decoding is proposed, which is only with linear complexity. Furthermore, a postprocess community merging method in consideration of node attributes is developed to enhance the homogeneity of nodes in the detected communities. Various synthetic and real-world networks are used to verify the effectiveness of the proposed approach. The experimental results show that the proposed approach performs significantly better than a variety of evolutionary and nonevolutionary methods on most of the benchmark networks.

This paper proposes a novel learning to learn method, called learning to learn iterative search algorithm (LISA), for signal detection in a multi-input multi-output (MIMO) system. The idea is to regard the signal detection problem as a decision making problem over tree. The goal is to learn the optimal decision policy. In LISA, deep neural networks are used as parameterized policy function. Through training, optimal parameters of the neural networks are learned and thus optimal policy can be approximated. Different neural network based architectures are used for fixed and varying channel models, respectively. LISA provides soft decisions and does not require any information about the additive white Gaussian noise. Simulation results show that LISA 1) obtains near maximum likelihood detection performance in both fixed and varying channel models under QPSK modulation; 2) achieves significantly better bit error rate (BER) performance than classical detectors and recently proposed deep/machine learning based detectors at various modulations and signal to noise (SNR) ratios both under i.i.d and correlated Rayleigh fading channels in the simulation experiments; 3) is robust to MIMO detection problems with imperfect channel state information; and 4) generalizes very well against channel correlation and SNRs.

Pareto Local Search (PLS) is a basic building block in many metaheuristics for Multiobjective Combinatorial Optimization Problem (MCOP). In this paper, an enhanced PLS variant called Parallel Pareto Local Search based on Decomposition (PPLS/D) is proposed. PPLS/D improves the efficiency of PLS using the techniques of parallel computation and problem decomposition. It decomposes the original search space into L subregions and executes L parallel processes searching in these subregions simultaneously. Inside each subregion, the PPLS/D process is guided by a unique scalar objective function. PPLS/D differs from the well-known Two Phase Pareto Local Search (2PPLS) in that it uses the scalar objective function to guide every move of the PLS procedure in a fine-grained manner. In the experimental studies, PPLS/D is compared against the basic PLS and a recently proposed PLS variant on the multiobjective Unconstrained Binary Quadratic Programming problems (mUBQPs) and the multiobjective Traveling Salesman Problems (mTSPs) with at most four objectives. The experimental results show that, no matter whether the initial solutions are randomly generated or generated by heuristic methods, PPLS/D always performs significantly better than the other two PLS variants.

Enhancer of Zeste Homolog 2 (EZH2), a key epigenetic regulator, is involved in breast cancer progression and metastasis. LOXL4 is increasingly recognized as an important player in cancer progression. To date, how EZH2 regulates LOXL4 in the progression of breast cancer remains unclear. Methods: We evaluated the association between LOX family proteins and EZH2 in invasive breast carcinoma through the starBase v2.0 analysis, and its correlation with breast tumorigenesis using the Oncomine dataset. We then applied miRcode data combined with gene expression omnibus (GEO) data to screen candidate miRNAs mediating the regulation of LOXL4 by EZH2. We explored the regulatory mechanism of EZH2, miR-29b/miR-30d, and LOXL4 in breast cancer cells by qRT-PCR, Western blotting, cell proliferation, colony formation, and wound healing assays, xenograft experiments, dual-luciferase reporter assay, and chromatin immunoprecipitation. All statistical tests were two-sided. Results: Inhibition of EZH2 or LOXL4, or miR-29b/miR-30d overexpression, decreased breast cancer cell proliferation, migration, and metastasis in vitro and in vivo. LOXL4 was identified as a direct target of miR-29b and miR-30d. EZH2 inhibition enhanced miR-30d and miR-29b transcription via promoter binding activity, leading to the reduced expression of LOXL4. Immunohistochemical analysis of human breast cancer specimens and flow cytometry analysis of tumor-infiltrating macrophages in mice showed a positive association of EZH2 with LOXL4 expression and macrophage infiltration. Conclusions: Our findings identified EZH2-miR-29b/miR-30d-LOXL4 signaling pathway was involved in breast tumorigenesis, and suggested that the epigenetic modulation represents a potential therapeutic target for breast cancer by controlling macrophage activation.

The COX/PGE2 pathway is widely involved in the development of tumors and the regulation of tumor immune cells such as T cells, NK cells and DCs. However, little information is available on the single nucleotide polymorphisms (SNPs) of COX/PGE2 pathway-related genes in patients with lung cancer.Seven SNPs of the PTGS2, PTGER2 and PTGIS genes were genotyped in a case-control cohort including 600 lung cancer cases and 600 controls using the MassARRAY platform.The minor alleles of PTGS2-rs4648298, PTGS2-rs2745557, PTGER2-rs2075797 and PTGIS-rs6125671 were all risk alleles that led to a different degree of elevated lung cancer risk (p 0.001). The rs4648298-TC/CC, rs2745557-GA/AA, rs2075797-CG/GG and rs6125671-TC/CC genotypes were markedly associated with an elevated risk of lung cancer (p 0.0001). Moreover, genetic model results showed that PTGS2-rs4648298 was correlated with a 4.91-, 6.90- and 4.21-fold increased risk of lung cancer under dominant, recessive and log-additive models, respectively (p 0.0001). Similarly, PTGS2-rs2745557, PTGER2-rs2075797 and PTGIS-rs6125671 were also related to an elevated risk of the disease under the three genetic models (p 0.001). In addition, stratification analysis based on smoking status and pathological types showed that these four SNPs were associated with the risk of lung cancer in both smokers and nonsmokers and in all three pathological types, including adenocarcinoma, squamous cell carcinoma, and small cell lung cancer (p 0.014).These results contribute to a better understanding of the pathogenesis of lung cancer and provide new clues for the early detection and personalized treatment of the disease.

Significant improvements in genome sequencing and assembly technology have led to increasing numbers of high-quality genomes, revealing complex evolutionary scenarios such as multiple whole-genome duplication events, which hinders ancestral genome reconstruction via the currently available computational frameworks. Here, we present the Inferring Ancestor Genome Structure (IAGS) framework, a novel block/endpoint matching optimization strategy with single-cut-or-join distance, to allow ancestral genome reconstruction under both simple (single-copy ancestor) and complex (multicopy ancestor) scenarios. We evaluated IAGS with two simulated data sets and applied it to four different real evolutionary scenarios to demonstrate its performance and general applicability. IAGS is available at https://github.com/xjtu-omics/IAGS.

Objectives: This retrospective study examined the relevance and prognostic factors of whole-course conformal radiotherapy (CRT) and late-course accelerated hyperfractionation radiotherapy (LCAFRT) for esophageal squamous cell carcinoma (ESCC). Methods: A total of 110 patients with ESCC received whole-course CRT and LCAFRT between May 2004 and January 2015. All patients received conventional CRT of 2 Gy per day, up to 30–40 Gy, followed by LCAFRT using reduced fields at 1.5 Gy/fraction twice a day, up to 24–39 Gy, for a total dose of 60–69 Gy. Results: The median follow-up was 85 months. The whole groups 1-, 3-, and 5-year survival rates were 81.8%, 46.4%, and 41.8%, respectively. The local control rates for the whole group at 1, 3, and 5 years were 82.7%, 70.0%, and 68.2%, respectively. There were no significant differences among survival rates and local control rates between the 3D-CRT and intensity-modulated radiotherapy (IMRT) groups. The main reactions to acute radiotherapy were acute radiation tracheitis, esophagitis, and pneumonia. The tumor location and TNM stage were independent prognostic factors for overall survival. Conclusion: The results showed that whole-course CRT and LCAFRT for ESCC can improve survival and local control with a tolerable acute reaction compared to previous studies. Local recurrence and distant metastasis are the main failure modes of treatment. Advances in knowledge: Whole-course CRT and LCAFRT for ESCC can improve the survival and local control rate compared with previous studies from the 2DRT era. It might provide another treatment for patients with inoperable ESCC or refusing surgery.

Clinical benefit of neoadjuvant immunotherapy in resectable esophageal squamous cell carcinoma (ESCC). remains unclear. This study evaluated the efficacy and safety of the programmed death 1 (PD-1) inhibitor tislelizumab combined with chemotherapy as neoadjuvant therapy in patients with resectable ESCC.Treatment-naïve patients were enrolled and eligible patients received 3 cycles of neoadjuvant therapy with tislelizumab, carboplatin, and nab-paclitaxel. The primary endpoint was surgery patients major pathological response (MPR). Subgroup analysis was stratified by tumor downstaging, circumferential resection margin (CRM), PD-ligand 1 (PD-L1) expression, and tumor mutation burden (TMB). Safety was assessed by adverse events (AEs) and postoperative complications.Between September 2020 and March 2021, 45 patients were enrolled. Thirty-six (80.0%) of 45 patients underwent surgery, and 29 (80.5%) underwent successful R0 resection. MPR and pathological complete response (pCR) for surgery patients were 72.0% and 50.0%, respectively. Intention to treatment (ITT) patients MPR and PCR were 57.5% and 40%. Downgrading occurred in 75% of 36 patients. MPR and pCR were identified to be associated with tumor downstaging and CRM but not PD-L1 expression or TMB. TPS levels in MPR and pCR group were significantly higher than that in Non-MPR and Non-pCR group, respectively. Treatment-related AEs of grade 3-4 and immune-related AEs occurred in 42.2% and 22.2% of 45 patients, respectively, and postoperative complications occurred in 77.8% of 36 patients. No treatment-related surgical delay or death occurred. No associations between gene mutation and pathological efficacy were observed.Tislelizumab plus chemotherapy as neoadjuvant therapy demonstrates promising antitumor activity for resectable ESCC with high rates of MPR, pCR, and R0 resection, as well as acceptable tolerability.

The tradeoff between exploration and exploitation is critical to the performance of an evolutionary algorithm . Different levels of exploration-exploitation tradeoff are required at different evolutionary stages for achieving a satisfactory performance of an evolutionary algorithm. In this paper, we propose a novel survival analysis method to intelligently guide the maintenance of the exploration-exploitation tradeoff in multiobjective evolutionary algorithms. The survival analysis stems from a deep understanding of the evolutionary search procedure. Through survival analysis, an indicator is derived, which is used to guide the adoption of appropriate recombination operators , based on the assumption that the roles of these operators in terms of their capabilities on exploration-exploitation can be asserted. In the developed algorithm, a differential evolution recombination operator and a new sampling strategy are hybridized. Empirical comparison with five well-known multiobjective evolutionary algorithms on a number of test instances with complex Pareto sets and Pareto fronts indicates the effectiveness and superiority of the developed algorithm in terms of commonly-used performance metrics on these test instances.

Background Lung cancer is a leading cause of cancer deaths worldwide. Low-dose computed tomography (LDCT) screening trials indicated that LDCT is effective for the early detection of lung cancer, but the findings were accompanied by high false positive rates. Therefore, the detection of lung cancer needs complementary blood biomarker tests to reduce false positive rates. Methods In order to evaluate the potential of metabolite biomarkers for diagnosing lung cancer and increasing the effectiveness of clinical interventions, serum samples from subjects participating in a low-dose CT-scan screening were analyzed by using untargeted liquid chromatography-hybrid quadrupole time-of-flight mass spectrometry (LC-Q-TOF-MS). Samples were acquired from 34 lung patients with ground glass opacity diagnosed lung cancer and 39 healthy controls. Results In total, we identified 9 metabolites in electron spray ionization (ESI)(+) mode and 7 metabolites in ESI(-) mode. L-(+)-gulose, phosphatidylethanolamine (PE)(22:2(13Z,16Z)/15:0), cysteinyl-glutamine, S-japonin, threoninyl-glutamine, chlorate, 3-oxoadipic acid, dukunolide A, and malonic semialdehyde levels were observed to be elevated in serum samples of lung cancer cases when compared to those of healthy controls. By contrast, 1-(2-furanylmethyl)-1H-pyrrole, 2,4-dihydroxybenzoic acid, monoethyl carbonate, guanidinosuccinic acid, pseudouridine, DIMBOA-Glc, and 4-feruloyl-1,5-quinolactone levels were lower in serum samples of lung cancer cases compared with those of healthy controls. Conclusions This study demonstrates evidence of early metabolic alterations that can possibly distinguish malignant ground glass opacity from benign ground glass opacity. Further studies in larger pools of samples are warranted.

In some real-world applications, it has been found that the performance of multiobjective optimization evolutionary algorithms (MOEAs) may deteriorate when boundary solutions in the Pareto front (PF) are more difficult to approximate than others. Such a problem feature, referred to as difficult-to-approximate (DtA) PF boundaries, is seldom considered in existing multiobjective optimization test problems. To fill this gap and facilitate possible systematic studies, we introduce a new test problem generator. The proposed generator enables the design of test problems with controllable difficulties regarding the feature of DtA PF boundaries. Three representative MOEAs, NSGA-II, SMS-EMOA, and MOEA/D-DRA, are performed on a series of test problems created using the proposed generator. Experimental results indicate that all the three algorithms perform poorly on the new test problems. Meanwhile, a modified variant of MOEA/D-DRA, denoted as MOEA/D-DRA-UT, is validated to be more effective in dealing with these problems. Subsequently, it is concluded that the rational allocation of computational resources between different PF parts is crucial for MOEAs to handle the problems with DtA PF boundaries.

Combining machine learning techniques has shown great potentials in evolutionary optimization since the domain knowledge of an optimization problem, if well learned, can be a great help for creating high-quality solutions. However, existing learning-based multiobjective evolutionary algorithms (MOEAs) spend too much computational overhead on learning. To address this problem, we propose a learning-based MOEA where an online learning algorithm is embedded within the evolutionary search procedure. The online learning algorithm takes the stream of sequentially generated solutions along the evolution as its training data. It is noted that the stream of solutions are temporal, dependent, nonstationary, and nonstatic. These data characteristics make existing online learning algorithm not suitable for the evolution data. We hence modify an existing online agglomerative clustering algorithm to accommodate these characteristics. The modified online clustering algorithm is applied to adaptively discover the structure of the Pareto optimal set; and the learned structure is used to guide new solution creation. Experimental results have shown significant improvement over four state-of-the-art MOEAs on a variety of benchmark problems.

In evolutionary optimization, the preselection is an efficient operator to improve the search efficiency, which aims to filter unpromising candidate solutions before fitness evaluation. Most existing preselection operators rely on fitness values, surrogate models, or classification models. Basically, the classification based preselection regards the preselection as a classification procedure, i.e., differentiating promising and unpromising candidate solutions. However, the difference between promising and unpromising classes becomes fuzzy as the running process goes on, as all the left solutions are likely to be promising ones. Facing this challenge, this paper proposes a fuzzy classification based preselection (FCPS) scheme, which utilizes the membership function to measure the quality of candidate solutions. The proposed FCPS scheme is applied to two state-of-the-art evolutionary algorithms on a test suite. The experimental results show the potential of FCPS on improving algorithm performance.

Complicated geometric shapes of Pareto fronts can cause difficulties for multiobjective evolutionary algorithms. To deal with these difficulties, efficient diversity strategies must be highly addressed in order to obtain a set of representative Pareto solutions. In decomposition-based multiobjective evolutionary algorithms, this is often done by optimizing multiple single objective subproblems defined by a set of weight vectors. For complicated Pareto fronts with extreme convexity, disconnection or degeneracy, however, it is nontrivial to set these weight vector properly. To overcome this shortcoming, we propose a new decomposition-based multiobjective evolutionary algorithm based on a hybrid weighting strategy, which optimizes both random subproblems and fixed subproblems. To maintain diversity of nondominated solutions stored in external population, a new archiving strategy based on adaptive Epsilon dominance is also suggested in our proposed algorithm. Our experimental results have showed that our proposed algorithm is superior to several other state-of-the-art multiobjective evolutionary algorithms on a set of benchmark multiobjective test problems with different challenging difficulties regarding the geometric shapes of Pareto fronts.

In this paper, we propose an adaptive multi-objective evolutionary algorithm for multi-objective optimization problems (MOPs). In the algorithm, a clustering approach is employed to learn the Pareto optimal set's manifold structure adaptively, in accordance with the regularity property of MOPs, along the evolution. An advanced sampling strategy is developed for the generation of promising offspring from the learned structure. To generate trial solution, each non-dominated solution at present generation is Gaussian-perturbed using the variance-covariance matrix within its cluster. The other new features include 1) an adaptive hybridization of the developed sampling strategy with a differential evolution (DE) operator which aims to combine local and global information; 2) a reusing scheme which is to reduce the computational cost on modeling (clustering); and 3) an adaptive strength Pareto based approach which is to adaptively determine the contribution of the developed sampling strategy and the DE operator for balancing exploration and exploitation. The developed algorithm was empirically compared with four well-known MOEAs on a number of test instances with complex Pareto optimal set structure and complicated Pareto fronts. Experimental results suggest that it outperforms the compared algorithms on these test instances in terms of two commonly-used measure metrics. The effectiveness of the developed sampling strategy, the reusing scheme, the hybrid strategy, and the adaptive strategy was also empirically validated.

The application of multiobjective approaches for sparse reconstruction is a relatively new research topic in the area of compressive sensing. Unlike conventional iterative thresholding methods, multiobjective approaches attempt to find a set of solutions called Pareto front (PF) with different sparsity levels. The major focus of the existing sparse multiobjective approaches is to find the knee region of PF, where the K-sparse solution should reside. However, the strategies in these approaches for finding the knee region of PF are not very reliable due to the sensitivities on the setting of control parameters or noise levels. In this paper, we propose a new strategy based on Gaussian mixture models (GMMs) within a decomposition-based multiobjective framework for sparse reconstruction. The basic idea is to cluster the population found by a chain-based search procedure into two subsets via GMM. One of them with the small values of loss function should include the knee region. Our proposed algorithm was tested on a set of six artificial instance sets at four different noise levels. The experimental results showed that our proposed algorithm is superior to two existing sparse multiobjective approaches and one iterative thresholding algorithm.

Adaptive parameter control and mutation operator selection are two important research avenues in differential evolution (DE). Existing works consider the two avenues independently. In this paper, we propose to unify the two modules and develop a unified parameterized mutation operator. With different settings of the parameters, different mutation operators can be retrieved. Further, the settings of the parameters closely relate to the control parameters of the DE. By determining the parameters we can achieve adaptive parameter control and mutation operator selection simultaneously. We propose to use a neural network to output the parameters and learn the network parameter by the natural evolution strategies algorithm under the consideration of modeling the evolution process as a Markov Decision Process. Experimental results on the CEC 2018 test suite show that the proposed method performs significantly better than traditional DEs with different operators and an advanced adaptive DE. We further analyze the time complexity and population diversity of the proposed method. The analysis shows that our method can achieve a balanced exploration and exploitation with a properly learned network.

Purpose: This retrospective study was designed to analyze the effect and prognostic factors of whole-course conformal radiotherapy and late-course accelerated hyperfractionation radiotherapy (LCAFRT) for esophageal squamous cell carcinoma (ESCC).Methods and materials: A total of 110 patients with ESCC received whole-course conformal radiotherapy and LCAFRT in Chaozhou City People’s hospital between May 2004 and January 2015. All patients received conventional conformal radiotherapy of 2 Gy per day up to 30–40 Gy, followed by accelerated hyperfractionation conformal radiotherapy using reduced fields at 1.5 Gy/fraction twice a day up to 24–39 Gy, with a total dose of 60–69 Gy.Results: Median follow-up was 85 months (2–170 months). The one-, three-, and five-year survival rates were 81.82%, 46.36%, and 41.82%, respectively. The median survival time was 31.8 months. The local control rates for the whole group at 1, 3, and 5 years were 82.73%, 70%, and 68.18%, respectively. There were no significant differences among 1-, 3-, and 5-year survival rates and local control rates between the three-dimensional conformal radiotherapy group and intensity-modulated radiotherapy group. The main reactions to acute radiotherapy were acute radiation tracheitis, esophagitis, and pneumonia. Multivariate analysis showed that the tumor location and TNM stage were independent prognostic factors.Conclusion: The results from this study showed that whole-course conformal radiotherapy and LCAFRT for ESCC can further improve survival and local control with a tolerable acute reaction compared to previous studies. Local recurrence and distant metastasis are the main failure modes of treatment.

Additional file 1: Figure S1. qRT-PCR analysis of CASC15 RNA levels in A549 and H1299 cells, which were treated with si-Control or si-CASC15 for 48 hours. Figure S2. Western blot analysis of SOX4 protein levels in A549 and H1299 cells, which were treated with si-Control or si-SOX4 for 48 hours. Figure S3. Tumor volume in nude mice injected with A549 and H129 cells with stable knockdown of CASC15, or concurrent overexpression of SOX4. Figure S4. Representative IHC staining of HIF-1α and ISH staining of CASC15 in A549-shControl and A549-shHIF1A xenograft tissues. Figure S5. Western blot analysis of SOX4 protein levels in CASC15-overexpressing H1299 cells and control cells. Figure S6. RNA-IP assay detecting potential interactions between CASC15 RNA and WDR5 protein in A549 and H1299 cells. U1 snRNA, which was reported not binding to WDR5, was used as a negative control. Table S1. The characteristics of 35 NSCLC patients included in the tissue microarray in our study. Table S2. Primer sequences for qRT-PCR.

Approximating the Pareto fronts (PFs) of multiobjective optimization problems (MOPs) with a population of nondominated solutions is a common strategy in evolutionary multiobjective optimization (EMO). In the case of two or three objectives, the PFs of MOPs can be well approximated by the populations including several dozens or hundreds of nondominated solutions. However, this is not the case when approximating the PFs of many-objective optimization problems (MaOPs). Due to the high dimensionality in the objective space, almost all EMO algorithms with Pareto dominance encounter the difficulty in converging towards the PFs of MaOPs. In contrast, most of efficient EMO algorithms for many-objective optimization use the idea of decomposition in fitness assignment. It should be pointed out that small population size is often used in these many-objective optimization algorithms, which focus on the approximation of PFs along some specific search directions. In this paper, we studied the extensions of two well-known algorithms (i.e., NSGA-II and MOEA/D) with the ability to find a large population of nondominated solutions with good spread. A region-based archiving method is also suggested to reduce the computational complexity of updating external population. Our experimental results showed that these two extensions have good potential to find the PFs of MaOPs.

Ever-increasing concerns over air quality and the newly emerged internet of things (IoT) for future environmental monitoring are stimulating the development of ultrasensitive room-temperature gas sensors, especially for nitrogen dioxide (NO

Background Accumulating evidence has demonstrated that long non-coding RNAs (lncRNAs) are involved in the hypoxia-related cancer process and play pivotal roles in enabling malignant cells to survive under hypoxic stress. However, the molecular crosstalk between lncRNAs and hypoxia signaling cascades in non-small cell lung cancer (NSCLC) remains largely elusive. Methods Firstly, we identified differentially expressed lncRNA cancer susceptibility candidate 15 (CASC15) as associated with NSCLC based on bioinformatic data. The clinical significance of CASC15 in lung cancer was investigated by Kaplan-Meier survival analysis. Then, we modulated CASC15 expression in NSCLC cell lines by RNAi. CCK-8 and transwell assays were carried out to examine the effects of CASC15 on proliferation and migration of NSCLC cells. Upstream activator and downstream targets of CASC15 were validated by luciferase reporter assay, qRT-PCR, Western blotting, and chromatin immunoprecipitation (ChIP). Lastly, RNA in situ hybridization (RNA-ISH) and immunohistochemistry (IHC) were performed to confirm the genetic relationships between CASC15 and related genes in clinical samples. Results CASC15 was highly expressed in NSCLC tissues and closely associated with poor prognosis. Loss-of-function analysis demonstrated that CASC15 was essential for NSCLC cell migration and growth. Mechanistic study revealed that CASC15 was transcriptionally activated by hypoxia signaling in NSCLC cells. Further analysis showed that hypoxia-induced CASC15 transactivation was mainly dependent on hypoxia-inducible factor 1α (HIF-1α) and hypoxia response elements (HREs) located in CASC15 promoter. CASC15 promotes the expression of its chromosomally nearby gene, SOX4. Then SOX4 functions to stabilize β-catenin protein, thereby enhancing the proliferation and migration of NSCLC cells. HIF-1α/CASC15/SOX4/β-catenin pathway was activated in a substantial subset of NSCLC patients. Conclusions HIF-1α/CASC15/SOX4/β-catenin axis plays an essential role in the development and progression of NSCLC. The present work provides new evidence that lncRNA CASC15 holds great promise to be used as novel biomarkers for NSCLC. Blocking the HIF-1α/CASC15/SOX4/β-catenin axis can serve as a potential therapeutic strategy for treating NSCLC.

BACKGROUND The aim of this study was to construct a nomogram to predict the prognosis of patients with gastrointestinal stromal tumor (GIST). MATERIAL AND METHODS We enrolled 4086 GIST patients listed in the SEER database from 1998 to 2015. They were separated to 2 groups: an experimental group (n=2862) and a verification group (n=1224). A nomogram was constructed by using statistically significant prognostic factors. RESULTS A nomogram that included age, sex, marital status, tumor location, grade, SEER stage, tumor size, and surgical management was developed. It can be used to predict overall survival (OS), while adding AJCC 7th TNM stage can predict cancer-specific survival (CSS). The C-index used to forecast OS and CSS nomograms was 0.778 (95% CI, 0.76-0.79) and 0.818 (95% CI, 0.80-0.84), respectively. CONCLUSIONS The nomogram can effectively predict 3- and 5-year CSS in patients with GIST, and its use can improve clinical practice.

This article proposes a novel landscape smoothing method for the symmetric traveling salesman problem (TSP). We first define the homotopic convex (HC) transformation of a TSP as a convex combination of a well-constructed simple TSP and the original TSP. The simple TSP, called the convex-hull TSP, is constructed by transforming a known local or global optimum. We observe that controlled by the coefficient of the convex combination, with local or global optimum: 1) the landscape of the HC transformed TSP is smoothed in terms that its number of local optima is reduced compared to the original TSP and 2) the fitness distance correlation of the HC transformed TSP is increased. Furthermore, we observe that the smoothing effect of the HC transformation depends highly on the quality of the used optimum. A high-quality optimum leads to a better smoothing effect than a low-quality optimum. We then propose an iterative algorithmic framework in which the proposed HC transformation is combined within a heuristic TSP solver. It works as an escaping scheme from local optima aiming to improve the global searchability of the combined heuristic. Case studies using the 3-Opt and the Lin-Kernighan local search as the heuristic solver show that the resultant algorithms significantly outperform their counterparts and two other smoothing-based TSP heuristic solvers on most of the test instances with up to 20,000 cities.

Tuning hyper-parameters for evolutionary algorithms is an important issue in computational intelligence. Performance of an evolutionary algorithm depends not only on its operation strategy design, but also on its hyper-parameters. Hyper-parameters can be categorized in two dimensions as structural/numerical and time-invariant/time-variant. Particularly, structural hyper-parameters in existing studies are usually tuned in advance for time-invariant parameters, or with hand-crafted scheduling for time-invariant parameters. In this paper, we make the first attempt to model the tuning of structural hyper-parameters as a reinforcement learning problem, and present to tune the structural hyper-parameter which controls computational resource allocation in the CEC 2018 winner algorithm by Q-learning. Experimental results show favorably against the winner algorithm on the CEC 2018 test functions.

This paper proposes a simple but promising clustering-based multi-objective evolutionary algorithm, termed as CMOEA. At each generation, CMOEA first divides the current population into several subpopulations by Gaussian mixture clustering. To generate offsprings, the search stage, either exploration or exploitation, is determined by the relative difference between the subpopulations’ hypervolumes of two adjacent generations. CMOEA selects the parents from different subpopulations in case of exploration stage, and from the same subpopulation in case of exploitation stage. In the environmental selection phase, the hypervolume indicator is used to update the population. Simulation experiments on nine multi-objective problems show that CMOEA is competitive with five popular multi-objective evolutionary algorithms.

The goal in sparse approximation is to find a sparse representation of a system. This can be done by minimizing a data-fitting term and a sparsity term at the same time. This sparse term imposes penalty for sparsity. In classical iterative thresholding methods, these two terms are often combined into a single function, where a relaxed parameter is used to balance the error and the sparsity. It is acknowledged that the setting of relaxed parameter is sensitive to the performance of iterative thresholding methods. In this paper, we proposed to address this difficulty by finding a set of nondominated solutions with different sparsity levels via multiobjective evolutionary algorithms (MOEAs). A new MOEA/D is developed specifically for sparse optimization, in which a chain-based random local search (CRLS) is employed for optimizing subproblems with various sparsity levels. The performance of the proposed algorithm, denoted by MOEA/D-CRLS, is tested on a set of sixteen noise-free or noisy test problems. Our experimental results suggest that MOEA/D-CRLS is competitive regarding the solution precision on the noise-free test problems, and clearly superior on the noisy test problems against three existing representative sparse optimization methods.