Reduced Health-Related Quality of Life Due to Mobile Phone Dependence in a Sample of Chinese College Students: The Mediating Role of Chronotype and Sleep Quality.

PURPOSE: Presenting a chain mediation model to investigate whether mobile phone dependence results in a reduction in health-related quality of life (HRQoL) among Chinese college students, through the mediating effect of chronotype and sleep quality. DESIGN AND SETTING: A cross-sectional survey was conducted on students from a Chinese university using a validated structured questionnaire. SAMPLE: 2014 freshmen. MEASURES: The study measured the students' level of mobile phone dependence using the Self-rating Questionnaire for Adolescent Problematic Mobile Phone Use. Chronotype and sleep quality were measured by the Chinese version of the Morningness-Eveningness Questionnaire (MEQ) and the Pittsburgh Sleep Quality Index (PSQI), respectively. HRQoL was evaluated using the five-level EuroQol five-dimensional questionnaire (EQ-5D-5L), including a descriptive system and a visual analog scale (VAS). ANALYSIS: Descriptive statistical analysis, correlation analysis, and mediation analysis. RESULTS: Mobile phone dependence had a significant negative effect on HRQoL as indicated by both the EQ-5D-5L index score and EQ-VAS score (P < .001 for both). Additionally, it was found to significantly predict chronotype (MEQ score) (ß = -.546, P < .001) and sleep quality (PSQI score) (ß = .163, P < .001). Chronotype negatively predict sleep quality (ß = -.058, P < .001), and sleep quality was a significant negative predictor of HRQoL (EQ-5D-5L index score, ß = -.008, P < .001; EQ-VAS score, ß = -1.576, P < .001). CONCLUSION: Mobile phone dependence negatively impacts students' HRQoL through chronotype and sleep quality, and there is a chain mediating effect. Students should consider making lifestyle changes to improve their HRQoL and promote health.

Corneal stress‒strain index in relation to retinal nerve fibre layer thickness among healthy young adults.

BACKGROUND/OBJECTIVES: To determine the relationship between corneal stress-strain index (SSI) and retinal nerve fibre layer (RNFL) thickness. SUBJECTS/METHODS: 1645 healthy university students from a university-based study contributed to the analysis. The RNFL thickness was measured by high-definition optical coherence tomography (HD-OCT), axial length (AL) was measured by IOL Master, and corneal biomechanics including SSI, biomechanical corrected intraocular pressure (bIOP), and central corneal thickness (CCT) were measured by Corvis ST. Multivariate linear regression was performed to evaluate the relationship between the SSI and RNFL thickness after adjusting for potential covariates. RESULTS: The mean age of the participants was 19.0 ± 0.9 years, and 1132 (68.8%) were women. Lower SSI was significantly associated with thinner RNFL thickness ( ß =8.601, 95% confidence interval [CI] 2.999-14.203, P = 0.003) after adjusting for age, CCT, bIOP, and AL. No significant association between SSI and RNFL was found in men, while the association was significant in women in the fully adjusted model. The association was significant in the nonhigh myopic group ( P for trend = 0.021) but not in the highly myopic group. Eyes with greater bIOP and lower SSI had significantly thinner RNFL thickness. CONCLUSIONS: Eyes with lower SSI had thinner RNFL thickness after adjusting for potential covariates, especially those with higher bIOP. Our findings add novel evidence of the relationship between corneal biomechanics and retinal ganglion cell damage.

Distribution and determinants of corneal volume among healthy young Chinese adults: a cross-sectional study.

BACKGROUND: Several studies have previously reported the normal values of corneal volume (CV) in various populations, whereas little is known about the CV distribution in healthy young Chinese adults. Our study aimed to investigate the distribution of CV and its relationships with other ocular biometric parameters among healthy young Chinese adults. METHODS: A total of 1645 eyes from 1645 students at Dali University in Yunnan Province, China, were analyzed. Pentacam was used to measure CV. Central corneal thickness (CCT) and biomechanically corrected intraocular pressure (bIOP) were evaluated by Corvis-ST. Other biometrical parameters, including axial length (AL), keratometry, and white-to-white (WTW) distance, were measured using IOL Master. RESULTS: The mean age of the study population was 19.01 ± 0.92 years, and 68.81% of them were women. The CV was normally distributed in the whole sample, with a mean value of 61.23 ± 3.22 mm3. CV and CCT were significantly smaller in the Yi ethnic group than in the Han ethnic group (p < 0.01). CCT (coefficient: 0.085; p < 0.001) and keratometry (coefficient: 0.422; p < 0.001) were positively correlated with CV, while AL (coefficient: -0.204; p < 0.001), WTW distance (coefficient: -0.236; p < 0.001) and bIOP (coefficient: -0.06; p < 0.001) were inversely associated with CV. CONCLUSIONS: Our study provides an age-specific distribution of CV among healthy young Chinese adults. CCT, keratometry, AL, WTW distance and bIOP were important factors associated with CV.

Refractive associations with corneal biomechanical properties among young adults: a population-based Corvis ST study.

PURPOSE: To assess the associations of corneal biomechanical properties as measured by the Corvis ST with refractive errors and ocular biometry in an unselected sample of young adults. METHODS: A total of 1645 healthy university students underwent corneal biomechanical parameters measurement by the Corvis ST. The refractive status of the participants was measured using an autorefractor without cycloplegia. Ocular biometric parameters were measured using the IOL Master. RESULTS: After adjusting for the effect of age, sex, biomechanical-corrected intraocular pressure and central corneal thickness, axial length was significantly associated with A1 velocity (A1v, ß = -10.47), A2 velocity (A2v, ß = 4.66), A2 deflection amplitude (A2DeflA, ß = -6.02), HC deflection amplitude (HC-DeflA, ß = 5.95), HC peak distance (HC-PD, ß = 2.57), deformation amplitude ratio max (DA Rmax, ß = -0.36), Ambrósio's relational thickness to the horizontal profile (ARTh, ß = 0.002). For axial length / corneal radius ratio, only A1v (ß = -2.01), A1 deflection amplitude (A1DeflA, ß = 2.30), HC-DeflA (ß = 1.49), HC-PD (ß = -0.21), DA Rmax (ß = 0.07), stress-strain index (SSI, ß = -0.29), ARTh (ß < 0.001) were significant associates. A1v (ß = 23.18), HC-DeflA (ß = -15.36), HC-PD (ß = 1.27), DA Rmax (ß = -0.66), SSI (ß = 3.53), ARTh (ß = -0.02) were significantly associated with spherical equivalent. CONCLUSION: Myopic eyes were more likely to have more deformable corneas and corneas in high myopia were easier to deform and were even softer compared with those in the mild/moderate myopia.

Refractive Associations With Whole Eye Movement Distance and Time Among Chinese University Students: A Corvis ST Study.

Purpose: Eye movement has been frequently studied in clinical conditions, but the association with myopia has been less explored, especially in population-based samples. The purpose of this study was to assess the associations of eye movement measured by the Corvis ST with refractive status in healthy university students. Methods: A total of 1640 healthy students were included in the study (19.0 ± 0.9 years). Eye movement parameters (whole eye movement [WEM]; whole eye movement time [WEMT]) were measured by the Corvis ST. Spherical equivalent (SE) was measured using an autorefractor without cycloplegia. IOL Master was used to assess axial length (AL). Results: AL was negatively correlated with WEM and WEMT (rWEM = -0.28, rWEMT = -0.08), and SE was positively correlated with WEM and WEMT (rWEM = 0.21, rWEMT = 0.14). For the risk of high myopia, breakpoint analysis and restricted cubic spline model showed that the knots of the significant steep downward trend of WEM and WEMT were 0.27 mm and 20.4 ms, respectively. The piecewise linear regression model revealed a significant correlation between AL, SE, and WEM when the value of WEM was below 0.27 mm. Additionally, when WEMT exceeded 20.4 ms, a significant decrease in AL and an increase in SE were observed with increasing WEMT. Conclusions: A larger distance and longer duration of eye movement were correlated with a lower degree of myopia and shorter AL, and there was a threshold effect. Translational Relevance: The findings might aid in understanding the pathogenesis of myopia and provide a theoretical foundation for clinical diagnosis and prediction.

iAMY-RECMFF: Identifying amyloidgenic peptides by using residue pairwise energy content matrix and features fusion algorithm.

Various diseases, including Huntington's disease, Alzheimer's disease, and Parkinson's disease, have been reported to be linked to amyloid. Therefore, it is crucial to distinguish amyloid from non-amyloid proteins or peptides. While experimental approaches are typically preferred, they are costly and time-consuming. In this study, we have developed a machine learning framework called iAMY-RECMFF to discriminate amyloidgenic from non-amyloidgenic peptides. In our model, we first encoded the peptide sequences using the residue pairwise energy content matrix. We then utilized Pearson's correlation coefficient and distance correlation to extract useful information from this matrix. Additionally, we employed an improved similarity network fusion algorithm to integrate features from different perspectives. The Fisher approach was adopted to select the optimal feature subset. Finally, the selected features were inputted into a support vector machine for identifying amyloidgenic peptides. Experimental results demonstrate that our proposed method significantly improves the identification of amyloidgenic peptides compared to existing predictors. This suggests that our method may serve as a powerful tool in identifying amyloidgenic peptides. To facilitate academic use, the dataset and codes used in the current study are accessible at https://figshare.com/articles/online_resource/iAMY-RECMFF/22816916.

Identification of high-risk patterns of myopia in Chinese students based on four major behavioral risk factors: a latent class analysis.

BACKGROUND: Myopia is prevalent in children and adolescents. Understanding the effect of multiple behaviors and their latent patterns on ocular biometric parameters may help clinicians and public health practitioners understand the behavioral risk pattern of myopia from a person-centered perspective. The purpose of this study was to identify the patterns of four major behavioral risk factors associated with myopia, including time spent outdoors, digital screen time, sleep duration, and performance of Chinese eye exercises. The study also examined the relationships between these behavioral patterns and myopia as well as ocular biometric parameters in a sample of Chinese college students. METHODS: This study included 2014 students from the Dali University Students Eye Health Study. The average age of the subjects was 19.0 ± 0.9 years old, ranging from 15.7 to 25.1 years old. Each participant's refractive status was measured using an autorefractor without cycloplegia and ocular biometric parameters were measured using an IOL Master. Behavioral risk factors were collected using a pre-designed self-administered questionnaire. Latent class analysis (LCA) was performed to identify cluster patterns of various behaviors. RESULTS: The prevalence of myopia was 91.8% in this population. The 2-class model was selected for the LCA based on goodness-of-fit evaluation metrics. Among the overall study sample, 41.1% and 58.9% were assigned into the high-risk and low-risk class, respectively. The risk of myopia [odds ratio (OR) = 2.12, 95% confidence interval (CI) = 1.52-3.14], high myopia (OR = 1.43, 95% CI = 1.14-1.78) and axial length/corneal radius (AL/CR) ratio of more than 3.0 (OR = 1.82, 95% CI = 1.22-2.72) were significantly higher in the high-risk compared with low-risk class. CONCLUSIONS: Chinese university students showed differential risks of myopia and could be subdivided into high- and low-risk clusters based on four behavioral variables.

Mechanisms of MALAT1 regulating proliferative diabetic retinopathy via targeting miR-126-5p.

OBJECTIVE: Diabetic retinopathy (DR) is the primary reason for blindness among the middle-aged and elderly. It can progress to proliferative diabetic retinopathy (PDR), a condition that is accompanied by retinal neovascularization as the disease worsens. Understanding the pathogenesis of PDR can facilitate the development of treatments. In this study, we aimed to investigate the involvement in the lncRNA MALAT1 (MALAT1)/miR-126-5p axis in modulating PDR progression. METHODS: Rat retinal endothelial cells (RECs) was induced with 30 mM glucose to build an in vitro PDR model. MALAT1 was down-regulated using siRNA sequences, and miR-126-5p was up-regulated with miRNA mimics. Dual-luciferase reporter assay and RNA immunoprecipitation assay were carried out to identify and validate the targeting relationship between MALAT1 and miR-126-5p. Angiogenesis, cell proliferation and cell migration were detected using tubule formation, CCK-8, and scratch assays, respectively. Western blots quantified angiogenesis- and migration-associated genes vascular endothelial growth factor (VEGF), MMP2 and MMP9, while qPCR measured MALAT1 and miR-126-5p levels. RESULTS: In high-glucose induced RECs, MALAT1 was up-regulated while miR-126-5p was down-regulated. The angiogenesis as well as the proliferation and migration capacities of high glucose-induced RECs were suppressed when MALAT1 was down-regulated or miR-126-5p was up-regulated, accompanied by reductions in VEGF, MMP-2 and MMP9. RNA immunoprecipitation assay confirmed that miR-126-5p could be enriched in MALAT1 sequences. Dual-luciferase reporter assay confirmed the targeted inhibition of miR-126-5p by MALAT1. Downregulating miR-126-5p counteracted the effect of MALAT1 downregulation on RECs induced by high glucose. CONCLUSIONS: MALAT1 promotes PDR by inhibiting miR126-5p and inducing REC proliferation, migration and angiogenesis.

Integrating temporal and spatial variabilities for identifying ion binding proteins in phage.

Recent studies reported that ion binding proteins (IBPs) in phage play a key role in developing drugs to treat diseases caused by drug-resistant bacteria. Therefore, correct recognition of IBPs is an urgent task, which is beneficial for understanding their biological functions. To explore this issue, a new computational model was developed to identify IBPs in this study. First, we used the physicochemical (PC) property and Pearson's correlation coefficient (PCC) to denote protein sequences, and the temporal and spatial variabilities were employed to extract features. Next, a similarity network fusion algorithm was employed to capture the correlation characteristics between these two different kinds of features. Then, a feature selection method called F-score was utilized to remove the influence of redundant and irrelative information. Finally, these reserved features were fed into support vector machine (SVM) to discriminate IBPs from non-IBPs. Experimental results showed that the proposed method has significant improvement in the classification performance, as compared with the state-of-the-art approach. The Matlab codes and dataset used in this study are available at https://figshare.com/articles/online_resource/iIBP-TSV/21779567 for academic use.

Associations between sleep characteristics, chronotype and body mass index among Chinese college freshmen.

Research indicates that sleep problem is a behavioral risk factor of obesity. However, few research have applied a multi-dimensional approach to investigate the relationship between sleep health and adiposity. Therefore, the current study aimed to examine the associations of sleep characteristics (duration, quality) and chronotype with overweight/obesity as measured by body mass index. Data were obtained from 2014 college students from the Dali University in the Yunnan province of China in the year 2021. Sleep characteristics and chronotype were measured using self-reported questionnaires. The presence of overweight/obesity was assessed by anthropometric measurements. Multiple logistic regression models and restricted cubic spline hazard models were established to examine associations between sleep characteristics, chronotype and adiposity. After adjusting for demographic characteristics and other obesity-related behavioral risk factors, evening type was positively associated with overweight/obesity, and an L-shaped dose-effect relationship was observed between chronotype scores and the presence of overweight/obesity. However, sleep duration and quality were not associated with the presence of overweight/obesity in the logistic regression models and restrictive cubic splines models. This study indicated that Chinese college students who had the evening chronotype were more likely to be affected by overweight/obesity. Chronotype as an important dimension of sleep health should be incorporated in obesity intervention programs.

Sleep quality as a mediator of the relationship between screen time and negative emotions among Chinese college freshmen.

College freshmen are special populations facing great challenges in adapting to the brand new environment, and their lifestyle and emotional states are worthy of attention. Especially during the COVID-19 pandemic, their screen time and prevalence of negative emotions were significantly increased, but few studies have focused on such situation of college freshmen and illustrated relevant mechanisms. Thus, based on a sample of Chinese college freshmen during the COVID-19 pandemic, the current study aimed to investigate the association between their screen time and negative emotions (depression, anxiety and stress), and further explore the mediating effects of sleep quality. Data from 2,014 college freshmen was analyzed. The screen time was self-reported by participants using predesigned questionnaires. The Pittsburgh Sleep Quality Index (PSQI) and Chinese Version of Depression Anxiety and Stress Scale-21 (DASS-21) were used to assess sleep quality and emotional states, respectively. The mediation analysis was conducted to examine the meditation effect. Results indicated that participants with negative emotions tended to have longer daily screen time and worse sleep quality, sleep quality partially mediated the association between screen time and negative emotions.The critical role of sleep quality and related intervention measures should be recognized and implemented.

Smoking, alcohol consumption and corneal biomechanical parameters among Chinese university students.

BACKGROUND/OBJECTIVES: Smoking and alcohol consumption are important risk factors for several ocular disorders, but their effects on corneal biomechanics remain unclear. Our study aims to explore the association between smoking and alcohol consumption with corneal biomechanical parameters measured by Corvis-ST (CST) among university students. SUBJECTS/METHODS: A total of 1645 healthy university students from a university-based study were included, and all participants underwent corneal biomechanical parameters measurement by CST. We selected 10 reliable parameters that can reflect the corneal deformation response. All participants had a standardised interview to determine their smoking and alcohol consumption status. RESULTS: The mean age of the participants was 19.0 ± 0.9 years, and 1132 (68.8%) were women. Smoking was significantly associated with stiffer corneas. Smokers showed significantly slower second applanation velocity (A2v) (ß = 0.007 m/s, 95% confidence interval 0.001 to 0.014, P = 0.032) and lower integrated radius (IR) (ß = -0.214 mm-1, 95% confidence interval -0.420 to -0.007, P = 0.043) than non-smokers after adjusting for age, gender, eye-rubbing, myopia, and body mass index (BMI). Smokers with BMI no less than 24.0 showed slower A2v and lower IR. Alcohol consumption and passive smoking were found no significant association with corneal biomechanics. CONCLUSION: Smokers had less deformable corneas, especially those with BMI no less than 24.0. Our findings provide new evidence for the association between smoking and ocular disorders associated with corneal biomechanics like glaucoma.

Identification of tumor homing peptides by utilizing hybrid feature representation.

Cancer is one of the serious diseases, recent studies reported that tumor homing peptides (THPs) play a key role in treatment of cancer. Due to the experimental methods are time-consuming and expensive, it is urgent to develop automatic computational approaches to identify THPs. Hence, in this study, we proposed a novel machine learning methods to distinguish THPs from non-THPs, in which the peptide sequences firstly encoded by pseudo residue pairwise energy content matrix (PseRECM) and pseudo physicochemical property (PsePC). Moreover, the least absolute shrinkage and selection operator (LAASO) was employed to select optimal features from the extracted features. All of these selected features were fed into support vector machine (SVM) for identifying THPs. We achieved 89.02%, 88.49%, and 94.58% classification accuracy on the Main, Small, and Main90 dataset, respectively. Experimental results showed that our proposed method outperforms the existing predictors on the same benchmark datasets. It indicates that the proposed method may be a useful tool in identifying THPs. The datasets and codes used in current study are available at https://figshare.com/articles/online_resource/iTHPs/16778770.Communicated by Ramaswamy H. Sarma.

Association between parental control and depressive symptoms among college freshmen in China: The chain mediating role of chronotype and sleep quality.

BACKGROUND: College freshmen tend to have more psychological and behavioral problems compared with other populations, especially depressive symptoms. Perceived parental control has been proved to play a significant role in mental health among children and adolescents. Based on the theoretical and empirical research of chronotype and sleep quality, this study constructed a chain mediating model to examine whether they mediated the relationship between parental control and depressive symptoms among Chinese college freshmen. METHODS: A total of 2014 college freshmen from Dali University were recruited to participate in this study and completed self-report Parental Bonding Instrument (PBI), Morningness-Eveningness Questionnaire (MEQ), Pittsburgh Sleep Quality Index (PSQI) and Self-Rating Depression Scale (SDS). PROCESS 3.5 for SPSS was applied to determine the chain mediating effect of chronotype and sleep quality between parental control and depressive symptoms. RESULTS: College freshmen with depressive symptoms have higher levels of parental control and worse subjective sleep quality than normal population (all p < 0.001). All study variables are correlated with each other, while chronotype has no significant association with depressive symptoms (r = -0.03, p > 0.05). Both maternal and paternal control have a direct link with depressive symptoms (ß = 0.86, p < 0.001; ß = 0.88, p < 0.001). Parental control could affect depressive symptoms via the independent mediating effect of sleep quality and the chain mediating effect of chronotype and sleep quality. The total indirect effects of maternal and paternal control on depressive symptoms are 0.93 and 0.94, respectively. CONCLUSIONS: Chronotype and sleep quality could mediate the association between parental control and depressive symptoms.

Integrating multiple sequence features for identifying anticancer peptides.

As one of the most terrible diseases, cancer causes millions of deaths worldwide every year. The popular treatment approaches, such as radiotherapy and chemotherapy, have been used in against cancer cells. However, those traditional therapies have side effects on normal cells, time-consuming and expensive. Recent studies showed that anticancer peptides (ACP) may be a potential choice instead of traditional approaches for treating cancer. Therefore, it is desired to develop a computational method to identify anticancer peptides. In this study, a support vector machine (SVM) based computational model was proposed to discriminate anticancer peptides from non-anticancer peptides. In the model, peptide sequences were firstly encoded by amino acids physicochemical (PC) properties and residue pairwise energy content matrix (RECM). Then, Pearson's correlation coefficient, high-order correlation information, and discrete wavelet transform were employed to extract useful information from PC and RECM matrix. The least absolute shrinkage and selection operator (LASSO) algorithm was applied to select discriminative features. Finally, these selected features were fed into SVM for distinguishing ACP from non-ACP. Experimental results demonstrated that the proposed method is powerful, it indicates that our proposed method may be a hopeful tool in discriminating anticancer peptides from non-anticancer peptides. The codes and datasets used in current work are available at https://figshare.com/articles/online_resource/iACP/16866232.

iTTCA-MFF: identifying tumor T cell antigens based on multiple feature fusion.

Cancer is a terrible disease, recent studies reported that tumor T cell antigens (TTCAs) may play a promising role in cancer treatment. Since experimental methods are still expensive and time-consuming, it is highly desirable to develop automatic computational methods to identify tumor T cell antigens from the huge amount of natural and synthetic peptides. Hence, in this study, a novel computational model called iTTCA-MFF was proposed to identify TTCAs. In order to describe the sequence effectively, the physicochemical (PC) properties of amino acid and residue pairwise energy content matrix (RECM) were firstly employed to encode peptide sequences. Then, two different approaches including covariance and Pearson's correlation coefficient (PCC) were used to collect discriminative information from PC and RECM matrixes. Next, an effective feature selection approach called the least absolute shrinkage and selection operator (LAASO) was adopted to select the optimal features. These selected optimal features were fed into support vector machine (SVM) for identifying TTCAs. We performed experiments on two different datasets, experimental results indicated that the proposed method is promising and may play a complementary role to the existing methods for identifying TTCAs. The datasets and codes can be available at https://figshare.com/articles/online_resource/iTTCA-MFF/17636120 .

Mojiangia oreophila (Crepidinae, Cichorieae, Asteraceae), a new species and genus from Mojiang County, SW Yunnan, China, and putative successor of the maternal Faberia ancestor.

A single small population of chasmophytic plants is described as M ojiangia oreophila, a monotypic genus in the subtribe Crepidinae, characterised by a unique combination of morphological features, in particular densely long-papillose homomorphic achenes with five main ribs each accompanied by two secondary ribs, coarse brownish pappus bristles, moderately many-flowered capitula, a small involucre with numerous outer phyllaries, perennial rosette herb growth and brown-woolly caudex and leaf axils. Molecular phylogenetic analysis detected that in the nrITS phylogeny M. oreophila forms a clade of its own in the Crepidinae; in the plastid DNA phylogeny it is nested in the clade formed by the hybridogenous genus Faberia, the maternal ancestor of which comes from the Crepidinae and the paternal ancestor from the Lactucinae, where Faberia is placed in nrITS phylogenies. M. oreophila shares several morphological features with Faberia and also shares the expected chromosome number of 2n = 16 with its hitherto unknown maternal ancestor. M. oreophila may therefore be a successor of the maternal ancestor of Faberia. Alternatively, cytonuclear discordance is to be assumed in Mojiangia, caused by chloroplast capture as a result of hybridisation and introgression with Faberia.

Identifying N7-methylguanosine sites by integrating multiple features.

Recent studies reported that N7-methylguanosine (m7G) plays a vital role in gene expression regulation. As a consequence, determining the distribution of m7G is a crucial step towards further understanding its biological functions. Although biological experimental approaches are capable of accurately locating m7G sites, they are labor-intensive, costly, and time-consuming. Therefore, it is necessary to develop more effective and robust computational methods to replace, or at least complement current experimental methods. In this study, we developed a novel sequence-based computational tool to identify RNA m7G sites. In this model, 22 kinds of dinucleotide physicochemical (PC) properties were employed to encode the RNA sequence. Three types of descriptors, including auto-covariance, cross-covariance, and discrete wavelet transform were adopted to extract effective features from the PC matrix. The least absolute shrinkage and selection operator (LASSO) algorithm was utilized to reduce the influence of irrelevant or redundant features. Finally, these selected features were fed into a support vector machine (SVM) for distinguishing m7G from non-m7G sites. The proposed method significantly outperforms existing predictors across all evaluation metrics. It indicates that the approach is effective in identifying RNA m7G sites.

iDHS-DT: Identifying DNase I hypersensitive sites by integrating DNA dinucleotide and trinucleotide information.

DNase I hypersensitive sites (DHSs) is important for identifying the location of gene regulatory elements, such as promoters, enhancers, silencers, and so on. Thus, it is crucial for discriminating DHSs from non-DHSs. Although some traditional methods, such as Southern blots and DNase-seq technique, have the ability to identify DHSs, these approaches are time-consuming, laborious, and expensive. To address these issues, researchers paid their attention on computational approaches. Therefore, in this study, we developed a novel predictor called iDHS-DT to identify DHSs. In this predictor, the DNA sequences were firstly denoted by physicochemical properties (PC) of DNA dinucleotide and trinucleotide. Then, three different descriptors, including auto-covariance, cross-covariance, and discrete wavelet transform were used to collect related features from the PC matrix. Next, the least absolute shrinkage and selection operator (LASSO) algorithm was employed to remove these irrelevant and redundant features. Finally, these selected features were fed into support vector machine (SVM) for distinguishing DHSs from non-DHSs. The proposed method achieved 97.64% and 98.22% classification accuracy on dataset S1 and S2, respectively. Compared with the existing predictors, our proposed model has significantly improvement in classification performance. Experimental results demonstrated that the proposed method is powerful in identifying DHSs.

m7G-DPP: Identifying N7-methylguanosine sites based on dinucleotide physicochemical properties of RNA.

N7-methylguanosine (m7G) modification is one of the most common post-transcriptional RNA modifications, which play vital role in the regulation of gene expression. Dysfunction of m7G may result to developmental defects and the appearance of some serious diseases. Thus, it is an urgent task to fast and accurate identifying m7G sites. In view of experimental approaches are costly and time-consuming, researchers focused their attention on computational models. Hence, in current study, we proposed a novel predictor called m7G-DPP to identify m7G sites. In the predictor, the RNA sequences were firstly encoded by physicochemical (PC) properties of dinucleotide. Then, sliding window approach was adopted to divide PC matrix into multiple matrixes, and Pearson's correlation coefficient (PCC), dynamic time warping (DTW), and distance correlation (DC) were employed to extract classification features at each window. Next, the least absolute shrinkage and selection operator (LASSO) algorithm was applied to select discriminative features. Finally, these selected features were fed into support vector machine to identify m7G sites. Experimental results showed that the proposed method is effective, which may play a complementary role in current m7G sites prediction studies. The MATLAB codes and dataset can be obtained from website at https://figshare.com/articles/online_resource/m7G-DPP/15000348.