NPI-GNN: Predicting ncRNA-protein interactions with deep graph neural networks.

Noncoding RNAs (ncRNAs) play crucial roles in many biological processes. Experimental methods for identifying ncRNA-protein interactions (NPIs) are always costly and time-consuming. Many computational approaches have been developed as alternative ways. In this work, we collected five benchmarking datasets for predicting NPIs. Based on these datasets, we evaluated and compared the prediction performances of existing machine-learning based methods. Graph neural network (GNN) is a recently developed deep learning algorithm for link predictions on complex networks, which has never been applied in predicting NPIs. We constructed a GNN-based method, which is called Noncoding RNA-Protein Interaction prediction using Graph Neural Networks (NPI-GNN), to predict NPIs. The NPI-GNN method achieved comparable performance with state-of-the-art methods in a 5-fold cross-validation. In addition, it is capable of predicting novel interactions based on network information and sequence information. We also found that insufficient sequence information does not affect the NPI-GNN prediction performance much, which makes NPI-GNN more robust than other methods. As far as we can tell, NPI-GNN is the first end-to-end GNN predictor for predicting NPIs. All benchmarking datasets in this work and all source codes of the NPI-GNN method have been deposited with documents in a GitHub repo (https://github.com/AshuiRUA/NPI-GNN).

KNIndex: a comprehensive database of physicochemical properties for k-tuple nucleotides.

With the development of high-throughput sequencing technology, the genomic sequences increased exponentially over the last decade. In order to decode these new genomic data, machine learning methods were introduced for genome annotation and analysis. Due to the requirement of most machines learning methods, the biological sequences must be represented as fixed-length digital vectors. In this representation procedure, the physicochemical properties of k-tuple nucleotides are important information. However, the values of the physicochemical properties of k-tuple nucleotides are scattered in different resources. To facilitate the studies on genomic sequences, we developed the first comprehensive database, namely KNIndex (https://knindex.pufengdu.org), for depositing and visualizing physicochemical properties of k-tuple nucleotides. Currently, the KNIndex database contains 182 properties including one for mononucleotide (DNA), 169 for dinucleotide (147 for DNA and 22 for RNA) and 12 for trinucleotide (DNA). KNIndex database also provides a user-friendly web-based interface for the users to browse, query, visualize and download the physicochemical properties of k-tuple nucleotides. With the built-in conversion and visualization functions, users are allowed to display DNA/RNA sequences as curves of multiple physicochemical properties. We wish that the KNIndex will facilitate the related studies in computational biology.

Thermodynamics Irreversibilities Analysis of Oxy-Fuel Diffusion Flames: The Effect of Oxygen Concentration.

In studies on the combustion process, thermodynamic analysis can be used to evaluate the irreversibility of the combustion process and improve energy utilization efficiency. In this paper, the combustion process of a laminar oxy-fuel diffusion flame was simulated, and the entropy generation due to the irreversibilities of the radiation process, the heat conduction and heat convection process, the mass diffusion process, and the chemical reaction process was calculated. The effect of the oxygen concentration in the oxidizer on the entropy generation was analyzed. The results indicated that, as the oxygen concentration in the oxidizer increases, the radiative entropy generation first increases and then decreases, and the convective and conductive entropy generation, the mass diffusion entropy generation, the chemical entropy generation, and the total entropy generation gradually increase.

VisFeature: a stand-alone program for visualizing and analyzing statistical features of biological sequences.

SUMMARY: Many efforts have been made in developing bioinformatics algorithms to predict functional attributes of genes and proteins from their primary sequences. One challenge in this process is to intuitively analyze and to understand the statistical features that have been selected by heuristic or iterative methods. In this paper, we developed VisFeature, which aims to be a helpful software tool that allows the users to intuitively visualize and analyze statistical features of all types of biological sequence, including DNA, RNA and proteins. VisFeature also integrates sequence data retrieval, multiple sequence alignments and statistical feature generation functions. AVAILABILITY AND IMPLEMENTATION: VisFeature is a desktop application that is implemented using JavaScript/Electron and R. The source codes of VisFeature are freely accessible from the GitHub repository (https://github.com/wangjun1996/VisFeature). The binary release, which includes an example dataset, can be freely downloaded from the same GitHub repository (https://github.com/wangjun1996/VisFeature/releases). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Predicting protein sub-Golgi locations by combining functional domain enrichment scores with pseudo-amino acid compositions.

Golgi apparatus is an important subcellular organelle that participates the secretion pathway. The role of Golgi apparatus in cellular process is related with Golgi-resident proteins. Knowing the sub-Golgi locations of Golgi-resident proteins is helpful in understanding their molecular functions. In this work, we proposed a computational method to predict the sub-Golgi locations for the Golgi-resident proteins. We take three sub-Golgi locations into consideration: the cis-Golgi network (CGN), the Golgi stack and the trans-Golgi network (TGN). By combining Pseudo-Amino Acid Compositions (Type-II PseAAC) and the Functional Domain Enrichment Score (FunDES), our method not only achieved better performances than existing methods, but also capable of recognizing proteins of the Golgi stack location, which is never considered in other state-of-the-art works.

Prepubertal exposure to polycyclic aromatic hydrocarbons are associated with early pubertal development onset in boys: A longitudinal study.

OBJECTIVE: To investigate the effects of polycyclic aromatic hydrocarbons(PAHs) on puberty in boys. METHODS: 695 subjects were selected from four primary schools in Chongqing, China. 675 urine samples from these boys were collected four PAH metabolites: 1-hydroxypyrene, 2-hydroxynaphthoic, 2-hydroxyfluorene, and 9-hydroxyphenanthrene. Pubertal development of 695 boys was assessed at follow-up visits starting in December 2015 and occurring every six months thereafter until now, data used in this article ending in June 2021. A total of 12 follow-up visits were performed. Cox proportional hazards regression models were used to analyze the relationship between PAH metabolite concentrations and indicators of pubertal timing. RESULTS: The mean age at puberty onset of testicular volume, facial hair, pubic hair, first ejaculation, and axillary hair in boys was 11.66, 12.43, 12.51, 12.72 and 13.70 years, respectively. Cox proportional hazards regression models showed that boys with moderate level of 1-OHPyr exposure was associated with earlier testicular development (hazard ratio [HR] = 1.276, 95% confidence interval [CI]: 1.006-1.619), with moderate level of 2-OHNap were at higher risk of early testicular development (HR = 1.273, 95% CI: 1.002-1.617) and early axillary hair development (HR = 1.355, 95% CI: 1.040-1.764), with moderate level of 2-OHFlu was associated with earlier pubic hair development (HR = 1.256, 95% CI: 1.001-1.577), with high level of 9-OHPhe were at higher risk of early fisrt ejaculation (HR = 1.333, 95% CI: 1.005-1.767) and early facial hair development (HR = 1.393, 95% CI: 1.059-1.831). CONCLUSION: Prepubertal exposure to PAHs may be associated with earlier pubertal development in boys.

The influence of the trajectory of obesity indicators on the age of pubertal onset and pubertal tempo in girls: A longitudinal study in Chongqing, China.

Objective: This study aims to explore the influence of the trajectory of obesity indicators on the onset age of different pubertal development characteristics and pubertal tempo among girls. Methods: Our longitudinal cohort study recruited 734 girls at baseline in May 2014 from a district of Chongqing and followed them at 6-month intervals. Data were available from baseline to the 14th follow-up with a full record of height, weight, waist circumference (WC), breast development, pubic hair, and armpit hair development, as well as the age of menarche. The Group-Based Trajectory Model (GBTM) was fitted for the optimum trajectory of the body mass index (BMI), WC, and waist-to-height ratio (WHtR) of girls before the pubertal onset and menarche. The ANOVA and multiple linear regression model were conducted to analyze the influence of the trajectory of obesity indicators on the onset age of different pubertal development characteristics and pubertal tempo in girls. Results: Compared with the healthy (gradual BMI increase) group before pubertal onset, the overweight (persistent BMI increase) group has an earlier onset age of breast development (B: -0.331, 95%CI: -0.515, -0.147) and pubic hair development (B: -0.341, 95%CI: -0.546, -0.136). The B2-B5 development time was shorter in girls in the overweight (persistent BMI increase) group (B: -0.568, 95%CI: -0.831, -0.305) and the obese (rapid BMI increase) group (B: -0.328, 95%CI: -0.524, -0.132). The age of menarche was earlier, and the B2-B5 development time was shorter in girls in the overweight (persistent BMI increase) group than in girls in the healthy (gradual BMI increase) group before menarche (B: -0.276, 95%CI: -0.406, -0.146; B: -0.263, 95%CI: -0.403, -0.123). Girls with high WC (rapid WC increase) before menarche had an earlier age of menarche than normal WC (gradual WC increase) (B: -0.154, 95%CI: -0.301, -0.006), and the B2-B5 development time was shorter in girls in the overweight (gradual WHtR increase) group than in girls in the healthy (persistent WHtR increase) (B: -0.278, 95%CI: -0.529, -0.027) group. Conclusion: Among girls, overweight and obesity (BMI scale) before pubertal onset can not only influence pubertal onset age but also accelerate B2-B5 pubertal tempo. Overweight (BMI scale) and high WC before menarche also have an impact on the age of menarche. Overweight (WHtR scale) before menarche is significantly associated with B2-B5 pubertal tempo.

Emotional and Behavioral Changes in Preschool Firstborn Children During Transition to Siblinghood: A Mixed Methods Study.

Purpose: To help firstborn children in families expecting a second child navigate the role transition more smoothly, we investigated the emotional and behavioral changes of firstborn children during the transition to siblinghood (TTS) and the factors that contribute to these changes. Patients and Methods: From March to December 2019, a total of 97 firstborn children (Mage=3.00± 0.97, and female = 51) were included in the study through a questionnaire survey of their mothers, and two follow-up visits were conducted in Chongqing, China. Individual in-depth interviews were conducted with 14 mothers. Results: Both quantitative and qualitative results suggest that emotional and behavioral problems of firstborn children tend to increase during TTS, particularly in issues such as anxiety/depression, somatic complaints, withdrawal, sleep problems, attention problems, and aggressive behavior, as well as internalization problems, externalization problems and total problems in the quantitative study (P<0.05). A poor father-child relationship may increase emotional and behavioral problems in firstborn children (P=0.05). Further qualitative analysis found that younger age and outgoing personality of the firstborn child may improve the emotional and behavioral problems. Conclusion: The firstborn children did have more emotional and behavioral problems during TTS. But these problems can be regulated by family factors and their own characteristics.

Recent Advances in Predicting Protein-lncRNA Interactions Using Machine Learning Methods.

Long non-coding RNAs (LncRNAs) are a type of RNA with little or no protein-coding ability. Their length is more than 200 nucleotides. A large number of studies have indicated that lncRNAs play a significant role in various biological processes, including chromatin organizations, epigenetic programmings, transcriptional regulations, post-transcriptional processing, and circadian mechanism at the cellular level. Since lncRNAs perform vast functions through their interactions with proteins, identifying lncRNA-protein interaction is crucial to the understandings of the lncRNA molecular functions. However, due to the high cost and time-consuming disadvantage of experimental methods, a variety of computational methods have emerged. Recently, many effective and novel machine learning methods have been developed. In general, these methods fall into two categories: semisupervised learning methods and supervised learning methods. The latter category can be further classified into the deep learning-based method, the ensemble learning-based method, and the hybrid method. In this paper, we focused on supervised learning methods. We summarized the state-of-the-art methods in predicting lncRNA-protein interactions. Furthermore, the performance and the characteristics of different methods have also been compared in this work. Considering the limits of the existing models, we analyzed the problems and discussed future research potentials.

Polycyclic aromatic hydrocarbons are associated with later puberty in girls: A longitudinal study.

The objective of this study is to explore associations between PAH exposures and puberty timing in girls. Beginning in May 2014, 734 girls age 7.2-11.8 years in Chongqing, China, were enrolled in a prospective cohort study. They were followed up every 6 months from enrollment through June 2021, at which point participants were ages 13.6-18.3 years. Metabolite concentrations of four PAHs (1-hydroxypyrene [1-OHPyr], 2-hydroxynaphthalene [2-OHNap], 2-hydroxyfluorine [2-OHFlu], and 9-hydroxyphenanthrene [9-OHPhe]) were measured in urine samples at baseline. At each follow up visit, the Tanner's Sexual Maturity Rating scale was administered. Cox proportional hazards models were used to estimate associations between four urinary PAH metabolite concentrations and four markers of puberty: menarche, breast development, pubic hair development, and axillary hair development. Geometric mean concentrations of 1-OHPyr, 2-OHNap, 2-OHFlu and 9-OHPhe in urine were 0.47 µg/L, 3.31 µg/L, 1.49 µg/L, 3.75 µg/L, respectively. There were statistically significant associations between several urinary PAH metabolite concentrations and puberty outcomes. PAH metabolite concentrations were grouped as Low (<25th percentile, referent group), Moderate (25th-75th percentile) or High (>75th). Girls with moderate levels of 1-OHPyr were at higher risk of delayed pubic hair development (hazard ratio [HR]: 0.82, 95 % confidence interval [CI]: 0.68-0.99). Delayed breast development (HR: 0.77, 95 % CI: 0.60-0.99) and pubic hair development (HR: 0.76, 95 % CI: 0.60-0.95) were associated with high 2-OHNap. High c 2-OHFlu was associated with delayed pubic hair development (HR: 0.77, 95 % CI: 0.61-0.96). Delayed breast (HR: 0.79, 95 % CI: 0.64-0.97), pubic hair (HR: 0.79, 95 % CI: 0.65-0.96) and axillary hair development (HR: 0.80, 95 % CI: 0.65-0.99) was associated with moderate 9-OHPhe. In conclusion, PAH exposure may delay puberty onset in girls.

Emotional and Behavioral Changes and Related Factors of Firstborn School-Aged Compared to Same Age Only Children.

Objective: To compare the emotional and behavioral characteristics of firstborn children during the pregnancy of a second child and only children of school-age in urban districts of Chongqing, China, and to explore the influencing factors of emotional and behavioral problems. Methods: We recruited mothers of firstborn children and only children from two hospitals and one primary school using purposive sampling. Questionnaires and the Parental Child Behavior Checklist (CBCL) were used to collect basic information, family socioeconomic status, family atmosphere and emotional and behavioral characteristics of their children in the survey. Results: The sample consisted of 1,155 children, including 477 firstborn children and 678 only children. The average scores of internalizing (4.47), externalizing (6.05), total problems (22.04), and six emotional and behavioral of firstborn children were significantly lower than those of only children (p < 0.05). When adjusted for children's demographic, socioeconomic and family relationship covariates, the scores of firstborn children internalizing problems (ß = -1.423, p = 0.000), externalizing problems (ß = -0.661, p = 0.048), and total problems (ß = -4.387, p = 0.000) were also significantly lower than those of only children. All children with more difficult parenting and development temperament, greater family economic pressure, poorer relationships between mother and child, less harmonious family atmosphere and father's permissive parenting style had more internalizing problems, externalizing problems and total problems (p < 0.05). Boys had more externalizing problems (ß = 1.939, 95% CI = 1.380-2.497) and total problems (ß = 4.908, 95% CI = 3.045-6.772) than girls. Conclusion: Firstborn children had fewer emotional and behavioral problems than their counterparts who were only children. This research helps to understand the social impact of the implementation of the two-child policy in multiple dimensions.

DDA-SKF: Predicting Drug-Disease Associations Using Similarity Kernel Fusion.

Drug repositioning provides a promising and efficient strategy to discover potential associations between drugs and diseases. Many systematic computational drug-repositioning methods have been introduced, which are based on various similarities of drugs and diseases. In this work, we proposed a new computational model, DDA-SKF (drug-disease associations prediction using similarity kernels fusion), which can predict novel drug indications by utilizing similarity kernel fusion (SKF) and Laplacian regularized least squares (LapRLS) algorithms. DDA-SKF integrated multiple similarities of drugs and diseases. The prediction performances of DDA-SKF are better, or at least comparable, to all state-of-the-art methods. The DDA-SKF can work without sufficient similarity information between drug indications. This allows us to predict new purpose for orphan drugs. The source code and benchmarking datasets are deposited in a GitHub repository (https://github.com/GCQ2119216031/DDA-SKF).

LPI-SKF: Predicting lncRNA-Protein Interactions Using Similarity Kernel Fusions.

Long non-coding RNAs (lncRNAs) play an important role in serval biological activities, including transcription, splicing, translation, and some other cellular regulation processes. lncRNAs perform their biological functions by interacting with various proteins. The studies on lncRNA-protein interactions are of great value to the understanding of lncRNA functional mechanisms. In this paper, we proposed a novel model to predict potential lncRNA-protein interactions using the SKF (similarity kernel fusion) and LapRLS (Laplacian regularized least squares) algorithms. We named this method the LPI-SKF. Various similarities of both lncRNAs and proteins were integrated into the LPI-SKF. LPI-SKF can be applied in predicting potential interactions involving novel proteins or lncRNAs. We obtained an AUROC (area under receiver operating curve) of 0.909 in a 5-fold cross-validation, which outperforms other state-of-the-art methods. A total of 19 out of the top 20 ranked interaction predictions were verified by existing data, which implied that the LPI-SKF had great potential in discovering unknown lncRNA-protein interactions accurately. All data and codes of this work can be downloaded from a GitHub repository (https://github.com/zyk2118216069/LPI-SKF).

Predicting lncRNA-Protein Interactions With miRNAs as Mediators in a Heterogeneous Network Model.

Long non-coding RNAs (lncRNAs) play important roles in various biological processes, where lncRNA-protein interactions are usually involved. Therefore, identifying lncRNA-protein interactions is of great significance to understand the molecular functions of lncRNAs. Since the experiments to identify lncRNA-protein interactions are always costly and time consuming, computational methods are developed as alternative approaches. However, existing lncRNA-protein interaction predictors usually require prior knowledge of lncRNA-protein interactions with experimental evidences. Their performances are limited due to the number of known lncRNA-protein interactions. In this paper, we explored a novel way to predict lncRNA-protein interactions without direct prior knowledge. MiRNAs were picked up as mediators to estimate potential interactions between lncRNAs and proteins. By validating our results based on known lncRNA-protein interactions, our method achieved an AUROC (Area Under Receiver Operating Curve) of 0.821, which is comparable to the state-of-the-art methods. Moreover, our method achieved an improved AUROC of 0.852 by further expanding the training dataset. We believe that our method can be a useful supplement to the existing methods, as it provides an alternative way to estimate lncRNA-protein interactions in a heterogeneous network without direct prior knowledge. All data and codes of this work can be downloaded from GitHub (https://github.com/zyk2118216069/LncRNA-protein-interactions-prediction).

Network propagation with dual flow for gene prioritization.

Based on the hypothesis that the neighbors of disease genes trend to cause similar diseases, network-based methods for disease prediction have received increasing attention. Taking full advantage of network structure, the performance of global distance measurements is generally superior to local distance measurements. However, some problems exist in the global distance measurements. For example, global distance measurements may mistake non-disease hub proteins that have dense interactions with known disease proteins for potential disease proteins. To find a new method to avoid the aforementioned problem, we analyzed the differences between disease proteins and other proteins by using essential proteins (proteins encoded by essential genes) as references. We find that disease proteins are not well connected with essential proteins in the protein interaction networks. Based on this new finding, we proposed a novel strategy for gene prioritization based on protein interaction networks. We allocated positive flow to disease genes and negative flow to essential genes, and adopted network propagation for gene prioritization. Experimental results on 110 diseases verified the effectiveness and potential of the proposed method.