Neural Gene Expression Research Articles

Neuroprotective effects of blueberry anthocyanins against perfluorooctanoic sulfonate on planarian Dugesia japonica

In this study, the planarian Dugesia japonica was exposed to perfluorooctane sulfonate (PFOS) and blueberry anthocyanins (ANT) for 1–10 days to investigate the protective effects of ANT on neurotoxicity and DNA damage induced by PFOS. The expression of neural related genes (Djnlg, DjFoxD, DjFoxG, DjotxA, and DjotxB) in D. japonica following exposure was determined using quantitative real-time PCR (qPCR). Immunofluorescence was performed to determine the alterations in neural morphology. In addition, ELISA kits were used to measure level of the neurotransmitters Dopamine (DA), serotonin (5-HT) and γ-aminobutyric acid (GABA). Furthermore, single cell gel electrophoresis was measured to analyze DNA damage. In this study, PFOS treatment induced neural morphology defects, alterations in neural-related gene expression, alterations in neurotransmitter levels, and DNA damage. However, co-exposure to ANT and PFOS mitigated the damage to D. japonica induced by PFOS. Restoration of neurotransmitter contents and neural related genes expression were observed in planarians following co-application of ANT and PFOS, immunofluorescence showed that nerve morphology almost recovered, and DNA damage was decreased. The results of this study showed that ANT may have a protective effect against PFOS induced neurotoxicity and DNA damage.

Change in the developmental fate of the chick optic vesicle from the neural retina to the telencephalon.

The forebrain develops into the telencephalon, diencephalon, and optic vesicle (OV). The OV further develops into the optic cup, the inner and outer layers of which develop into the neural retina and retinal pigmented epithelium (RPE), respectively. We studied the change in fate of the OV by using embryonic transplantation and explant culture methods. OVs excised from 10-somite stage chick embryos were freed from surrounding tissues (the surface ectoderm and mesenchyme) and were transplanted back to their original position in host embryos. Expression of neural retina-specific genes, such as Rax and Vsx2 (Chx10), was downregulated in the transplants. Instead, expression of the telencephalon-specific gene Emx1 emerged in the proximal region of the transplants, and in the distal part of the transplants close to the epidermis, expression of an RPE-specific gene Mitf was observed. Explant culture studies showed that when OVs were cultured alone, Rax was continuously expressed regardless of surrounding tissues (mesenchyme and epidermis). When OVs without surrounding tissues were cultured in close contact with the anterior forebrain, Rax expression became downregulated in the explants, and Emx1 expression became upregulated. These findings indicate that chick OVs at stage 10 are bi-potential with respect to their developmental fates, either for the neural retina or for the telencephalon, and that the surrounding tissues have a pivotal role in their actual fates. An in vitro tissue culture model suggests that under the influence of the anterior forebrain and/or its surrounding tissues, the OV changes its fate from the retina to the telencephalon.

Predicting stable alluvial channel profiles using emotional artificial neural networks

Accurate prediction of the cross-sectional profile of stable alluvial channels is very important for hydraulic engineers in the design and construction of natural channels in urban watersheds. This paper presents the first-time application of Emotional Artificial Neural Network (EANN) modeling to predict the stable cross-sectional geometry of alluvial channel profiles. EANN applies emotional stimulus parameters to improve the network’s training process. The key input parameters of the EANN model include modified Froude number (Frm), dimensionless mean sediment size (d*) and dimensionless lateral distance from the channel centerline (x*), and the output (or target) is the dimensionless vertical boundary level of the channel cross section (y*). Several observational datasets are used with different hydraulic and geometric conditions to verify and validate the model. Feed forward neural network (FFNN) and Gene expression programming (GEP) models are also designed to make a better evaluation and comparison of EANN performance. Furthermore, the prediction accuracy of the new EANN model is compared with several popular existing relationships related to previous researchers. The results declared that the EANN model with low error values of correlation coefficient (R) equal to 0.99 and root mean square error (RMSE) equal to 0.00058 is more accurate than FFNN model (R = 0.76 and RMSE = 0.231), which represents a significant improvement in EANN performance compared to classical FFNN. It is found that the EANN model has the lowest RMSE compared to all previous models (RMSE = 0.13 for the best previous model related to Diplas, 1990). Uncertainty analysis is performed to evaluate the quantitative performance of the new EANN and existing models. The results indicate that EANN has the lowest Width of the Confidence Bounds (WCB) and the lowest Mean Error of Predictions (MEP) of ± 0.00004 and -0.00041 respectively compared to FFNN and GEP and also previous models. Therefore, the new EANN model is proposed as a superior alternative to existing models for river engineering applications in the design of stable natural alluvial channels.

Conductive electrospun scaffolds with electrical stimulation for neural differentiation of conjunctiva mesenchymal stem cells.

An electrical stimulus is a new approach to neural differentiation of stem cells. In this work, the neural differentiation of conjunctiva mesenchymal stem cells (CJMSCs) on a new 3D conductive fibrous scaffold of silk fibroin (SF) and reduced graphene oxide (rGo) were examined. rGo (3.5% w/w) was dispersed in SF-acid formic solution (10% w/v) and conductive nanofibrous scaffold was fabricated using the electrospinning method. SEM and TEM microscopies were used for fibrous scaffold characterization. CJMSCs were cultured on the scaffold and 2 electrical impulse models (Current 1:115V/m, 100-Hz frequency and current 2:115v/m voltages, 0.1-Hz frequency) were applied for 7days. Also, the effect of the fibrous scaffold and electrical impulses on cell viability and neural gene expression were examined using MTT assay and qPCR analysis. Fibrous scaffold with the 220±20nm diameter and good dispersion of graphene nanosheets at the surface of nanofibers were fabricated. The MTT result showed the viability of cells on the scaffold, with current 2 lower than current 1. qPCR analysis confirmed that the expression of β-tubulin (2.4-fold P≤0.026), MAP-2 (1.48-fold; P≤0.03), and nestin (1.5-fold; P≤0.03) genes were higher in CJMSCs on conductive scaffold with 100-Hz frequency compared to 0.1-Hz frequency. Collectively, we proposed that SF-rGo fibrous scaffolds, as a new conductive fibrous scaffold with electrical stimulation are good strategies for neural differentiation of stem cells and the type of electrical pulses has an influence on neural differentiation and proliferation of CJMSCs.

Artificial intelligence (AI)-based friction factor models for large piping networks

In large piping networks, evaluation of friction factor is a time-consuming process and poses computational complexity. This is because the friction factor has to be evaluated for every pipe segment and that too by using implicit correlations. In the present study, this issue has been addressed by developing artificial intelligence (AI)-based friction factor models namely, support vector regression (SVR), artificial neural networks (ANN) and gene expression programing (GEP) to predict the friction factor for the turbulent flow regime. The developed models have been compared with the existing correlations based on the statistical parameters and have shown excellent prediction accuracy with the lowest average absolute relative error (AARE), root mean square error (RMSE) and highest correlation coefficient (R) as 1.43%, 0.0003, 0.9993 for SVR while for ANN they are 2.11%, 0.00095, 0.9978 and for GEP they are 7.14%, 0.0024, 0.9864, respectively. Leave-one-out cross-validation on the test set for SVR, ANN, and GEP are obtained as 0.9976, 0.9957, and 0.9726, respectively. Furthermore, the performance of these AI-based models, i.e. SVR, ANN, and GEP models and the various well-known correlations have been studied for estimating pipe friction factor in both smooth and rough pipes with different values of relative roughness. The SVR-based model significantly outperforms the existing correlations and the GEP-based model and marginally the ANN-based model. AI approach reduces the computational complexity and the time-consuming iterative solution of implicit correlations for large pipe networks without compromising the accuracy.

Lithium ions (Li+) and nanohydroxyapatite (nHAp) doped with Li+ enhance expression of late osteogenic markers in adipose-derived stem cells. Potential theranostic application of nHAp doped with Li+ and co-doped with europium (III) and samarium (III) ions

Lithium (Li+) ion due to its excellent bioactivity is one of the most well-studied element in bone-tissue engineering. In this study, we fabricated nanohydroxyapatite (nHAp) doped with Li+ ions (5 mol% Li+:nHAp) and co-doped with lanthanide ions. We investigated the effects of nHAp, 5 mol% Li+:nHAp or Li+ alone, on osteogenic differentiation of human Adipose Tissue-derived Stem Cells (hASCs), their proliferation, mitochondrial dynamics and apoptosis. Moreover, we monitored cell proliferation after treatment with samarium (III) (Sm3+) and europium (III) (Eu3+) ions co-doped 5 mol% Li+:nHAp as well as their luminescent property. The hASCs treated with 5 mol% Li+:nHAp and Li+ ions proliferated more rapidly and differentiated effectively than control cells without undergoing apoptosis. Both, 5 mol% Li+:nHAp and Li+ ions improved osteogenic differentiation of hASCs. Moreover they decreased expression of glycogen synthase kinase 3β (GSK3β) while increased β-catenin mRNA level. In addition, Li+, nHAp and 5 mol% Li+:nHAp improved mitochondrial dynamics and enhanced expression of neural differentiation marker genes. Collectively, the study indicates on pro-osteogenic and anti-apoptotic properties of nHAp doped with Li+ and Li+ alone. Moreover, unique properties of 5 mol% Li+:nHAp and 5 mol% Li+:nHAp co-doped with rare earth ions, such as Sm3+ and Eu3+ have shed a promising light on their potential application in theranostics.

Influential parameters on submerged discharge capacity of converging ogee spillways based on experimental study and machine learning-based modeling

AbstractOgee spillways with converging training walls are applied to lower the hazard of accidental flooding in locations with limited construction operations due to their unique structure. Hence, this type of structure is proposed as an emergency spillway. The present study aimed at experimental and machine learning-based modeling of the submerged discharge capacity of the converging ogee spillway. Two experimental models of Germi-Chay dam spillway were utilized: one model having a curve axis which was made in 1:50 scale and the other with a straight axis in 1:75 scale. Using visual observation, it was found that the total upstream head, the submergence degree, the ogee-crest geometries and the convergence angle of training walls are the crucial factors which alter the submerged discharge capacity of the converging ogee spillway. Furthermore, two machine-learning techniques (e.g. artificial neural networks and gene expression programming) were applied for modeling the submerged discharge capacity applying experimental data. These models were compared with four well-known traditional relationships with respect to their basic theoretical concept. The obtained results indicated that the length ratio () had the most effective role in estimating the submerged discharge capacity.

Inositol polyphosphate multikinase mediates extinction of fear memory

Inositol polyphosphate multikinase (IPMK), the key enzyme for the biosynthesis of higher inositol polyphosphates and phosphatidylinositol 3,4,5-trisphosphate, also acts as a versatile signaling player in regulating tissue growth and metabolism. To elucidate neurobehavioral functions of IPMK, we generated mice in which IPMK was deleted from the excitatory neurons of the postnatal forebrain. These mice showed no deficits in either novel object recognition or spatial memory. IPMK conditional knockout mice formed cued fear memory normally but displayed enhanced fear extinction. Signaling analyses revealed dysregulated expression of neural genes accompanied by selective activation of the mechanistic target of rapamycin (mTOR) regulatory enzyme p85 S6 kinase 1 (S6K1) in the amygdala following fear extinction. The IPMK mutants also manifested facilitated hippocampal long-term potentiation. These findings establish a signaling action of IPMK that mediates fear extinction.

Comparison of phenotypic markers and neural differentiation potential of human bone marrow stromal cells from the cranial bone and iliac crest.

Cellular therapies represent a new frontier in the treatment of neurological diseases. Accumulating evidence from preclinical studies of animal models suggests that mesenchymal stromal cells (MSCs), also known as mesenchymal stem cells, are an effective therapy for neurological diseases. In this study, we established human MSC lines from both cranial bone marrow (cBMMSCs) and iliac crest bone marrow (iBMMSCs) from the same donors and found that cBMMSCs show higher expression of neural crest-associated genes than iBMMSCs. Moreover, as observed in both mRNA and protein assays, neurogenic-induced cells from cBMMSCs expressed significantly higher levels of neural markers, such as NESTIN, SLUG, SOX9, and TWIST, than those from iBMMSCs. Thus, cBMMSCs showed a greater tendency than iBMMSCs to differentiate into neuron-like cells.

Curcumin Induces Neural Differentiation of Human Pluripotent Embryonal Carcinoma Cells through the Activation of Autophagy.

Curcumin is a natural polyphenolic compound, isolated from Curcuma longa, and is an important ingredient of Asian foods. Curcumin has revealed its strong activities of anti-inflammatory, antioxidant, and anticancer. The efficient amount of curcumin could induce differentiation of stem cells and promoted the differentiation of glioma-initiating cells; however, the mechanisms underlying neural induction of curcumin have not yet been revealed. In this study, neural-inducing ability of curcumin was explored by using human pluripotent embryonal carcinoma cells, NTERA2 cells. The cells were induced toward neural lineage with curcumin and were compared with a standard neutralizing agent (retinoic acid). It was found that, after 14 days of the induction by curcumin, NTERA2 cells showed neuronal morphology and expressed neural-specific genes, including NeuroD, TUJ1, and PAX6. Importantly, curcumin activated neurogenesis of NTERA2 cells via the activation of autophagy, since autophagy-related genes, such as LC3, LAMP1, and ATG5, were upregulated along with the expression of neural genes. The inhibition of autophagy by chloroquine suppressed both autophagy and neural differentiation, highlighting the positive role of autophagy during neural differentiation. This autophagy-mediated neural differentiation of curcumin was found to be an ROS-dependent manner; curcumin induced ROS generation and suppressed antioxidant gene expression. Altogether, this study proposed the neural-inducing activity of curcumin via the regulation of autophagy within NTERA2 cells and underscored the health beneficial effects of curcumin for neurodegenerative disorders, such as Alzheimer's disease and Parkinson's disease.

Conserved transcriptomic profiles underpin monogamy across vertebrates

Social monogamy, typically characterized by the formation of a pair bond, increased territorial defense, and often biparental care, has independently evolved multiple times in animals. Despite the independent evolutionary origins of monogamous mating systems, several homologous brain regions and neuropeptides and their receptors have been shown to play a conserved role in regulating social affiliation and parental care, but little is known about the neuromolecular mechanisms underlying monogamy on a genomic scale. Here, we compare neural transcriptomes of reproductive males in monogamous and nonmonogamous species pairs of Peromyscus mice, Microtus voles, parid songbirds, dendrobatid frogs, and Xenotilapia species of cichlid fishes. We find that, while evolutionary divergence time between species or clades did not explain gene expression similarity, characteristics of the mating system correlated with neural gene expression patterns, and neural gene expression varied concordantly across vertebrates when species transition to monogamy. Our study provides evidence of a universal transcriptomic mechanism underlying the evolution of monogamy in vertebrates.

Research on fractal image compression hybrid algorithm based on convolutional neural network and gene expression programming

Regarding the problems of insufficient image segmentation intelligence, low compression rate, slow speed for global searching to find the optimal fractal image compression encoding, and bad decoding effect, this article proposes the fractal image compression hybrid algorithm based on convolutional neural network and gene expression programming. Firstly, according to the accurate and fast image classification of deep convolutional neural network and the fast search and matching encoding advantages of gene expression programming, it realizes theoretically the action mechanism of fractal image compression hybrid encoding by combining the convolutional neural network and the gene expression programming; then, it uses the deep convolutional neural network to train and classify the image, and uses the adaptive quadtree segmentation method to segment the classified image, thus generating the domain block and range block classification set. According to the action mechanism of gene expression programming in fractal image compression encoding, it then quickly obtains the optimal solution of fractal image compression encoding by searching and encoding the sub-blocks of range block classification set and the classification set corresponding to the domain. Finally, in the CPU/GPU environment, it conducts the comparative experiment with basic fractal image compression algorithm and fractal image compression algorithm based on convolutional neural network. The experimental results show that this proposed algorithm outperforms similar algorithms in terms of image segmentation speed and accuracy as well as fractal compression encoding speed and compression ratio. Therefore, this algorithm is a fractal image compression algorithm with intelligent segmentation, fast encoding and high compression ratio.

A Review of the Recent Findings on Ductal Carcinoma In Situ of the Breast (DCIS)

Ductal Carcinoma in Situ is an entity which bears the risk of progression into Invasive Breast Carcinoma of No Special Type (IBC of NST). Evidence suggests that the malignant potential is already present in the non invasive period. Currently, the tumor microenvironment interaction has gained importance since the genetic and translational modifications of the DCIS lesion itself does not inform about the probability of malignancy sufficient for the risk stratification concerning the prognosis of the entity. Recent evidence underlines the interaction of the surrounding cells as affecting the fate of DCIS. Reproducibility of a diagnosis and grading of DCIS is another problem which is tried to be overcome with the incorporation of deep learning convolutional neural network analyses and various gene expression assays. This summarizes the findings of the recent studies to elucidate the transition of DCIS to IBC of NST regarding the histopathology, molecular biology while reflecting on the current prognostic data of DCIS with the treatment methods that are in application.

A Gain of Function Mutation in the NSD2 Histone Methyltransferase Drives Glucocorticoid Resistance of Acute Lymphoblastic Leukemia

▪Acute lymphoblastic leukemia (ALL) is the most common diagnosed pediatric cancer. Despite improvements in chemotherapy that have increased the 5-year survival rate to close to 90%, 15-20% of these patients may relapse with the majority of such children succumbing to this disease. Pediatric ALL patients, particularly those in relapse can harbor a specific point mutation (E1099K) in NSD2 (nuclear receptor binding SET domain protein 2) gene, also known as MMSET or WHSC1, which encodes a histone methyl transferase specific for H3K36me2. To understand the biological processes mediated by mutant NSD2, we used CRISPR-Cas9 gene editing to disrupt the NSD2E1099K mutant allele in two B-ALL cell lines (RCH-ACV and SEM) and one T-ALL cell line (RPMI-8402) and inserted the E1099K mutation into three ALL cell lines (697, CEM, MOLT4). Cell lines in which the NSD2E1099K mutant allele is present display increased global levels of H3K36me2 and decreased H3K27me3. NSD2E1099K cells compared to cells in which the mutation is removed demonstrate enhanced cell growth, colony formation and migration. NSD2 mutant cell lines assayed by RNA-Seq exhibit an aberrant gene signature, mostly representing gene activation, with activation of signaling pathways, genes implicated in the epithelial mesenchymal transition and prominent expression of neural genes not generally found in hematopoietic tissues. Accordingly, NSD2E1099K cell lines showed prominent tropism to the central neural system (CNS) in xenografts.The NSD2 mutation is found prominently in children who relapse early from therapy for ALL, and NSD2E1099K cells are particularly resistant to glucocorticoids (GC). Reversion of NSD2E1099K mutation to wild type NSD2 conferred glucocorticoid sensitivity to both B and T cell lines. GC response upon disruption of mutant NSD2 was accompanied by cell cycle arrest and apoptosis. Mice xenografted with NSD2E1099K cells were completely resistant to GC treatment while treatment of mice injected with isogenic NSD2 wild-type cells led to significant tumor reduction and survival extension. RNA-Seq analysis showed that GC transcriptional response was almost completely blocked in NSD2E1099K cells, correlating with their lack of biological response. GC treatment activated apoptotic pathways and downregulated cell cycle and DNA repair pathways only in NSD2 wild-type cells. Furthermore, in NSD2 mutant cells, there was lower basal expression level of glucocorticoid receptor (GR) and GR levels were not significantly induced by GC. Accordingly, after treatment with GC, there was significantly less DNA-binding activity of the GR in NSD2E1099K cells than that of NSD2 wild-type cells. The key pro-apoptotic regulators Bim and BMF failed to be activated by GC in NSD2E1099K cells but were prominently activated when the NSD2 mutation was removed. In conclusion, these studies demonstrate that the NSD2E1099K mutation may play an important role in treatment failure of pediatric ALL relapse by causing GC resistance. Future studies will determine how NSD2 which generally activates genes paradoxically blocks the ability of GC and the GR to induce critical pro-death genes. DisclosuresLicht:Celgene: Research Funding.

Predicting Shear Capacity of FRP-Reinforced Concrete Beams without Stirrups by Artificial Neural Networks, Gene Expression Programming, and Regression Analysis

The shear strength prediction of fiber-reinforced polymer- (FRP-) reinforced concrete beams is one of the most complicated issues in structural engineering applications. Developing accurate and reliable prediction models is necessary and cost saving. This paper proposes three new prediction models, utilizing artificial neural networks (ANNs) and gene expression programming (GEP), as a recently developed artificial intelligent techniques, and nonlinear regression analysis (NLR) as a conventional technique. For this purpose, a large database including 269 shear test results of FRP-reinforced concrete members was collected from the literature. The performance of the proposed models is compared with a large number of available codes and previously proposed equations. The comparative statistical analysis confirmed that the ANNs, GEP, and NLR models, in sequence, showed excellent performance, great efficiency, and high level of accuracy over all other existing models. The ANNs model, and to a lower level the GEP model, showed the superiority in accuracy and efficiency, while the NLR model showed that it is simple, rational, and yet accurate. Additionally, the parametric study indicated that the ANNs model defines accurately the interaction of all parameters on shear capacity prediction and have a great ability to predict the actual response of each parameter in spite of its complexity and fluctuation nature.

IGFBP2 promotes neural stem cell maintenance and proliferation differentially associated with glioblastoma subtypes

Neural stem cells (NSCs) give rise to the central nervous system (CNS) and persist in certain areas of adult brains for replenishing damaged differentiated cells. The loss of the balance between NSC self-renewal and differentiation could lead to tumor formation such as the occurrence of glioblastoma (GBM), the most common and deadly human brain tumor, which could be derived from neural stem or stem-like cells. Early studies showed that insulin-like growth factor binding protein 2 (IGFBP2) mRNA levels were maintained high during the fetal brain development but decreased in the adult brains. We previously reported that IGFBP2 was frequently overexpressed in GBMs, which was correlated with GBM recurrence and poor survival and promoted glioma progression. However, the role of IGFBP2 in the CNS was not investigated yet, whose understanding will help elucidate IGFBP2 functions in GBM. In the study, we identify IGFBP2 as a critical molecule for mouse NSC maintenance. IGFBP2 is highly expressed in NSCs, and its expression exhibits an apical-basal pattern in the neural tube with a higher apical level and decreased with NSC differentiation during the CNS development. IGFBP2 promotes NSC self-renewal and proliferation but inhibits its differentiation to neurons and astrocytes. The knockdown of IGFBP2 significantly affected the expression of cell cycle, Notch pathway, and neural stemness and differentiation genes in NSCs. Further, the expression of IGFBP2-regulated cell cycle genes is significantly correlated with IGFBP2 expression in non-Mesenchymal GBM subtypes including Classical, Proneural, and Neural subtypes and of its Notch pathway genes differentially associated in the four GBM subtypes, altogether suggesting its critical and similar functions in NSCs and GBM cells.

Sequence Alterations of Cortical Genes Linked to Individual Connectivity of the Human Brain.

Individual differences in humans are driven by unique brain structural and functional profiles, presumably mediated in part through differential cortical gene expression. However, the relationships between cortical gene expression profiles and individual differences in large-scale neural network organization remain poorly understood. In this study, we aimed to investigate whether the magnitude of sequence alterations in regional cortical genes mapped onto brain areas with high degree of functional connectivity variability across individuals. First, human genetic expression data from the Allen Brain Atlas was used to identify protein-coding genes associated with cortical areas, which delineated the regional genetic signature of specific cortical areas based on sequence alteration profiles. Thereafter, we identified brain regions that manifested high degrees of individual variability by using test-retest functional connectivity magnetic resonance imaging and graph-theory analyses in healthy subjects. We found that rates of genetic sequence alterations shared a distinct spatial topography with cortical regions exhibiting individualized (highly-variable) connectivity profiles. Interestingly, gene expression profiles of brain regions with highly individualized connectivity patterns and elevated number of sequence alterations are devoted to neuropeptide-signaling-pathways and chemical-synaptic-transmission. Our findings support that genetic sequence alterations may underlie important aspects of brain connectome individualities in humans. Significance Statement: The neurobiological underpinnings of our individuality as humans are still an unsolved question. Although the notion that genetic variation drives an individual's brain organization has been previously postulated, specific links between neural connectivity and gene expression profiles have remained elusive. In this study, we identified the magnitude of population-based sequence alterations in discrete cortical regions and compared them to the brain topological distribution of functional connectivity variability across an independent human sample. We discovered that brain regions with high degree of connectional individuality are defined by increased rates of genetic sequence alterations; these findings specifically implicated genes involved in neuropeptide-signaling pathways and chemical-synaptic transmission. These observations support that genetic sequence alterations may underlie important aspects of the emergence of the brain individuality across humans.

Genetic functions-based modelling for pier scour depth prediction in coarse bed streams

Bridge pier scour in coarse bed streams is a significant problem that needs to be addressed in bridge design. To accurately predict the scouring process by means of inductive modelling, extensive studies have been conducted using both laboratory and on-site field data. Several techniques have been used previously, including conventional regression models as well as more complex models such as those based on artificial intelligence techniques. In this research, a relatively new technique based on genetic algorithms, named genetic functions (GF), was investigated to predict pier scour depth in coarse bed streams. The primary motivation was to obtain a relatively simple and compact explicit functional approximation for pier scour depth prediction in coarse bed streams using on-site measurements. The data used in the model development contained a total of 125 on-site measurements from coarse bed streams. The performance of the GF-based technique was compared with other empirical models based on regression artificial neural networks and gene expression programming. The performance of the GF-based model was found to be highly encouraging in predicting bridge pier scour depth. GF have the added advantage of providing a relatively simple, easy to use and explicit functional expression for pier scour depth.

Stable alluvial channel design using evolutionary neural networks

Accurate prediction of the long-term average dimensions of alluvial stable channels is a significant problem in river engineering. The goal of this research is to investigate the effect of flow discharge (Q), mean sediment size (d50) and Shields parameter (τ∗) on the stable channel dimensions by employing non-linear regression (NLR) and two Artificial Intelligence (AI) methods, including: Generalized Structure of Group Method of Data Handling (GS-GMDH) neural network and Gene Expression Programming (GEP). Discharge, grain size and Shields parameter from 85 gaging stations situated in three stable Iranian rivers were used as input data for the three methods to estimate the water-surface width (W), average flow depth (D) and longitudinal slope (S) of the rivers. Based on the results, it was found that the GS-GMDH produced more accurate results for simulating the channel width with a Mean Absolute Relative Error (MARE) value of 0.055; and GEP produced better estimations for channel depth and slope with MARE values of 0.035 and 0.03, respectively. Furthermore, by employing Artificial Intelligence (AI) methods (GS-GMDH and GEP), the RMSE values decreased by 22%, 25% and 75% in predicting width, depth, and slope, respectively, compared to NLR method. The overall results showed that the AI methods generally produced better estimations than the non-linear regression method. To determine the effect of each input variable (Q, d50, τ∗) on the target variables (W, D, S), a sensitivity analysis comprising various combinations of input variables was conducted. Based on the results, the flow discharge had a dominant role on depth and width estimation of stable channels. In slope estimation, the most important parameter was τ∗ and then d50, while the discharge had a weak effect on slope prediction. In general, the Shields parameter was the most effective parameter in depth and specially slope estimation of stable channels.

Gene expression programming and artificial neural network to estimate atmospheric temperature in Tabuk, Saudi Arabia

Climate change is not a myth. There is enough evidence to showcase the impact of climate change. Town planners and authorities are looking for potential models to predict the climatic factors in advance. Being an agricultural area in Saudi Arabia, Tabuk region gets greater interest in developing such a model to predict the atmospheric temperature.Therefore, this paper presents two different studies based on artificial neural networks (ANNs) and gene expression programming (GEP) to predict the atmospheric temperature in Tabuk. Atmospheric pressure, rainfall, relative humidity and wind speed are used as the input variables in the developed models. Multilayer perceptron neural network model (ANN model), which is high in precession in producing results, is selected for this study. The GEP model that is based on evolutionary algorithms also produces highly accurate results in nonlinear models. However, the results show that the GEP model outperforms the ANN model in predicting atmospheric temperature in Tabuk region. The developed GEP-based model can be used by the town and country planers and agricultural personals.Graphical abstract