Evolutionary feature selection (FS) methods face the challenge of "curse of dimensionality" when dealing with high-dimensional data. Focusing on this challenge, this article studies a variable-size ...cooperative coevolutionary particle swarm optimization algorithm (VS-CCPSO) for FS. The proposed algorithm employs the idea of "divide and conquer" in cooperative coevolutionary approach, but several new developed problem-guided operators/strategies make it more suitable for FS problems. First, a space division strategy based on the feature importance is presented, which can classify relevant features into the same subspace with a low computational cost. Following that, an adaptive adjustment mechanism of subswarm size is developed to maintain an appropriate size for each subswarm, with the purpose of saving computational cost on evaluating particles. Moreover, a particle deletion strategy based on fitness-guided binary clustering, and a particle generation strategy based on feature importance and crossover both are designed to ensure the quality of particles in the subswarms. We apply VS-CCPSO to 12 typical datasets and compare it with six state-of-the-art methods. The experimental results show that VS-CCPSO has the capability of obtaining good feature subsets, suggesting its competitiveness for tackling FS problems with high dimensionality.
Various real-world applications can be formulated as feature selection problems, which have been known to be NP-hard. In this paper, we propose an effective feature selection method based on firefly ...algorithm (FFA), called return-cost-based binary FFA (Rc-BBFA). The proposed method has the capability of preventing premature convergence and is particularly efficient attributed to the following three aspects. An indicator based on the return-cost is first defined to measure a firefly’s attractiveness from other fireflies. Then, a Pareto dominance-based strategy is presented to seek the attractive one for each firefly. Finally, a binary movement operator based on the return-cost attractiveness and the adaptive jump is developed to update the position of a firefly. The experimental results on a series of public datasets show that the proposed method is competitive in comparison with other feature selection algorithms, including the traditional algorithms, the GA-based algorithm, the PSO-based algorithm, and the FFA-based algorithms.
•Proposing a novel PSO-based feature selection algorithm with mutual information.•Presenting an effective swarm initialization strategy based on label correlation.•Designing two local search ...operators, the supplementary and deletion operators.•Giving an adaptive flip mutation to help particles jump out of local extremum.
Feature selection (FS) is an important data processing method in pattern recognition and data mining. Due to not considering characteristics of the FS problem itself, traditional particle update mechanisms and swarm initialization strategies adopted in most particle swarm optimization (PSO) limit their performance on dealing with high-dimensional FS problems. Focused on it, this paper proposes a novel feature selection algorithm based on bare bones PSO (BBPSO) with mutual information. Firstly, an effective swarm initialization strategy based on label correlation is developed, making full use of the correlation between features and class labels to accelerate the convergence of swarm. Then, in order to enhance the exploitation performance of the algorithm, two local search operators, i.e., the supplementary operator and the deletion operator, are developed based on feature relevance-redundancy. Furthermore, an adaptive flip mutation operator is designed to help particles jump out of local optimal solutions. We apply the proposed algorithm to typical datasets based on the K-Nearest Neighbor classifier (K-NN), and compare it with eleven state-of-the-art algorithms, SFS, PTA, SGA, BPSO, PSO(4-2), HPSO-LS, Binary BPSO, NaFA, IBFA, KPLS-mRMR and SMBA-CSFS. The experimental results show that the proposed algorithm can achieve a feature subset with better performance, and is a highly competitive FS algorithm.
The "curse of dimensionality" and the high computational cost have still limited the application of the evolutionary algorithm in high-dimensional feature selection (FS) problems. This article ...proposes a new three-phase hybrid FS algorithm based on correlation-guided clustering and particle swarm optimization (PSO) (HFS-C-P) to tackle the above two problems at the same time. To this end, three kinds of FS methods are effectively integrated into the proposed algorithm based on their respective advantages. In the first and second phases, a filter FS method and a feature clustering-based method with low computational cost are designed to reduce the search space used by the third phase. After that, the third phase applies oneself to finding an optimal feature subset by using an evolutionary algorithm with the global searchability. Moreover, a symmetric uncertainty-based feature deletion method, a fast correlation-guided feature clustering strategy, and an improved integer PSO are developed to improve the performance of the three phases, respectively. Finally, the proposed algorithm is validated on 18 publicly available real-world datasets in comparison with nine FS algorithms. Experimental results show that the proposed algorithm can obtain a good feature subset with the lowest computational cost.
Unsupervised feature selection plays an important role in machine learning and data mining, which is very challenging because of unavailable class labels. We propose an unsupervised feature selection ...framework by combining the discriminative information of class labels with the subspace learning in this paper. In the proposed framework, the nonnegative Laplacian embedding is first utilized to produce pseudo labels, so as to improve the classification accuracy. Then, an optimal feature subset is selected by the subspace learning guiding by the discriminative information of class labels, on the premise of maintaining the local structure of data. We develop an iterative strategy for updating similarity matrix and pseudo labels, which can bring about more accurate pseudo labels, and then we provide the convergence of the proposed strategy. Finally, experimental results on six real-world datasets prove the superiority of the proposed approach over seven state-of-the-art ones.
Sterol-regulated HMG-CoA reductase (HMGCR) degradation and SREBP-2 cleavage are two major feedback regulatory mechanisms governing cholesterol biosynthesis. Reportedly, lanosterol selectively ...stimulates HMGCR degradation, and cholesterol is a specific regulator of SREBP-2 cleavage. However, it is unclear whether other endogenously generated sterols regulate these events. Here, we investigated the sterol intermediates from the mevalonate pathway of cholesterol biosynthesis using a CRISPR/Cas9-mediated genetic engineering approach. With a constructed HeLa cell line expressing the mevalonate transporter, we individually deleted genes encoding major enzymes in the mevalonate pathway, used lipidomics to measure sterol intermediates, and examined HMGCR and SREBP-2 statuses. We found that the C4-dimethylated sterol intermediates, including lanosterol, 24,25-dihydrolanosterol, follicular fluid meiosis activating sterol, testis meiosis activating sterol, and dihydro-testis meiosis activating sterol, were significantly upregulated upon mevalonate loading. These intermediates augmented both degradation of HMGCR and inhibition of SREBP-2 cleavage. The accumulated lanosterol induced rapid degradation of HMGCR, but did not inhibit SREBP-2 cleavage. The newly synthesized cholesterol from the mevalonate pathway is dispensable for inhibiting SREBP-2 cleavage. Together, these results suggest that lanosterol is a bona fide endogenous regulator that specifically promotes HMGCR degradation, and that other C4-dimethylated sterol intermediates may regulate both HMGCR degradation and SREBP-2 cleavage.
The proliferation and migration of vascular smooth muscle cells (VSMCs) are essential events in venous neointimal hyperplasia (VNH), a culprit of arteriovenous fistula (AVF) malfunction. Mitotic ...arrest‐deficient protein 2B (MAD2B) is a critical regulator of cell proliferation and differentiation in many scenarios. To address the role of MAD2B in VSMCs proliferation and migration during VNH, AVFs from patients with end‐stage renal disease (ESRD) and chronic kidney disease (CKD) mice were used to evaluate MAD2B expression. In cultured VSMCs treated with platelet‐derived growth factor‐BB (PDGF‐BB), the effect of MAD2B on VSMCs proliferation and migration was detected by cell counting kit‐8 (CCK8) assay, immunofluorescence, wound‐healing scratch and transwell assays. Besides, we exploited different small interfering RNAs (siRNAs) to explore the potential mechanisms in the issue. Furthermore, rapamycin was applied to reveal whether MAD2B‐associated pathways were involved in its inhibitory effect on VSMCs proliferation and migration. Accordingly, we found that MAD2B expression was enhanced in AVFs from patients with ESRD, CKD mice and VSMCs stimulated by PDGF‐BB. Meanwhile, inhibition of MAD2B alleviated VSMCs proliferation and migration while the number of ski‐related novel gene (SnoN)‐positive VSMCs was also increased in vivo and in vitro. Moreover, gene deletion of MAD2B decreased the level of SnoN protein in PDGF‐BB‐stimulated VSMCs. Furthermore, rapamycin suppressed the increased expressions of MAD2B and SnoN induced by PDGF‐BB. Thus, our study demonstrates that inhibition of MAD2B suppresses the proliferation and migration of VSMCs during VNH via reducing SnoN expression. Moreover, rapamycin exerts an inhibitory effect on intimal hyperplasia, possibly via the MAD2B‐SnoN axis.
Cholesterol from low-density lipoprotein (LDL) can be transported to many organelle membranes by non-vesicular mechanisms involving sterol transfer proteins (STPs). Fatty acid-binding protein (FABP) ...7 was identified in our previous study searching for new regulators of intracellular cholesterol trafficking. Whether FABP7 is a bona fide STP remains unknown. Here, we found that FABP7 deficiency resulted in the accumulation of LDL-derived cholesterol in lysosomes and reduced cholesterol levels on the plasma membrane. A crystal structure of human FABP7 protein in complex with cholesterol was resolved at 2.7 Å resolution. In vitro, FABP7 efficiently transported the cholesterol analog dehydroergosterol between the liposomes. Further, the silencing of FABP3 and 8, which belong to the same family as FABP7, caused robust cholesterol accumulation in lysosomes. These two FABP proteins could transport dehydroergosterol in vitro as well. Collectively, our results suggest that FABP3, 7, and 8 are a new class of STPs mediating cholesterol egress from lysosomes.
Several genetic studies have identified a rare variant of triggering receptor expressed on myeloid cells 2 (TREM2) as a risk factor for Alzheimer’s disease (AD). However, findings on the effects of ...TREM2 on Aβ deposition are quite inconsistent in animal studies, requiring further investigation. In this study, we investigated whether elevation of TREM2 mitigates Aβ pathology in TgCRND8 mice. We found that peripheral nerve injury resulted in a robust elevation of TREM2 exclusively in reactive microglia in the ipsilateral spinal cord of aged TgCRND8 mice at the age of 20 months. TREM2 expression appeared on day 1 post-injury and the upregulation was maintained for at least 28 days. Compared to the contralateral side, neither amyloid beta plaque load nor soluble Aβ40 and Aβ42 levels were attenuated upon TREM2 induction. We further showed direct evidence that TREM2 elevation in reactive microglia did not affect amyloid-β pathology in plaque-bearing TgCRND8 mice by applying anti-TREM2 neutralizing antibody to selectively block TREM2. Our results question the ability of TREM2 to ameliorate established Aβ pathology, discouraging future development of disease-modifying pharmacological treatments targeting TREM2 in the late stage of AD.
•Novel asymmetric metallophthalocyanines (ZnPcNO2-OPh and CuPcNO2-OPh) were synthesized.•They were applied in perovskite solar cells as hole transporting material.•The cell devices based on ...ZnPcNO2-OPh obtains a high open-circuit voltage of 1.071V.•The power conversion efficiency of the device based on dopant-free ZnPcNO2-OPh is up to 14.35%.
Two novel asymmetric metallophthalocyanines with different metal core (2,9,16-triphenoxy-23-nitrophthalocyaninatozinc, ZnPcNO2-OPh and 2,9,16-triphenoxy-23-nitrophthalocyaninatocopper, CuPcNO2-OPh) are synthesized and employed as hole transporting materials (HTMs) for perovskite ((FAPbI3)0.85(MAPbBr3)0.15) solar cells (PSCs), reaching high power conversion efficiency (PCE). Both of the two metallophthalocyanines show particular solubility, absorption, thermal stability and suitable energy levels. Results confirm that the photovoltaic performance is strongly influenced by the core metals. The optimized devices based on ZnPcNO2-OPh exhibit a maximum power conversion efficiency (PCE) of 14.35% with a high open-circuit voltage (VOC) of 1.071V under standard global 100mWcm−2 AM 1.5G illumination, while devices based on CuPcNO2-OPh show a lower PCE of 12.72% with a VOC of 1.064V. This newly developed perovskite solar cells demonstrated dramatically enhanced durability under ambient atmosphere. This study provides a promising prospect for an alternative approach based on the highly stable asymmetric metallophthalocyanine complexes to enhance the stability of perovskite solar cells.