One of the most challenging issues when facing a Quantitative structure-activity relationship (QSAR) classification model is to deal with the descriptor selection. Penalized methods have been adapted and have gained popularity as a key for simultaneously performing descriptor selection and QSAR classification model estimation. However, penalized methods have drawbacks such as having biases and inconsistencies that make they lack the oracle properties. This paper proposes an adaptive penalized logistic regression (APLR) to overcome these drawbacks. This is done by employing a ratio (BWR) of the descriptors between-groups sum of squares (BSS) to the within-groups sum of squares (WSS) for each descriptor as a weight inside the L1-norm. The proposed method was applied to one dataset that consists of a diverse series of antimicrobial agents with their respective bioactivities against Candida albicans. By experimental study, it has been shown that the proposed method (APLR) was more efficient in the selection of descriptors and classification accuracy than the other competitive methods that could be used in developing QSAR classification models. Another dataset was also successfully experienced. Therefore, it can be concluded that the APLR method had significant impact on QSAR analysis and studies.
In high-dimensional quantitative structure-activity relationship (QSAR) modelling, penalization methods have been a popular choice to simultaneously address molecular descriptor selection and QSAR model estimation. In this study, a penalized linear regression model with L1/2-norm is proposed. Furthermore, the local linear approximation algorithm is utilized to avoid the non-convexity of the proposed method. The potential applicability of the proposed method is tested on several benchmark data sets. Compared with other commonly used penalized methods, the proposed method can not only obtain the best predictive ability, but also provide an easily interpretable QSAR model. In addition, it is noteworthy that the results obtained in terms of applicability domain and Y-randomization test provide an efficient and a robust QSAR model. It is evident from the results that the proposed method may possibly be a promising penalized method in the field of computational chemistry research, especially when the number of molecular descriptors exceeds the number of compounds.
A robust screening approach and a sparse quantitative structure-retention relationship (QSRR) model for predicting retention indices (RIs) of 169 constituents of essential oils is proposed. The proposed approach is represented in two steps. First, dimension reduction was performed using the proposed modified robust sure independence screening (MR-SIS) method. Second, prediction of RIs was made using the proposed robust sparse QSRR with smoothly clipped absolute deviation (SCAD) penalty (RSQSRR). The RSQSRR model was internally and externally validated based on [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], Y-randomization test, [Formula: see text], [Formula: see text], and the applicability domain. The validation results indicate that the model is robust and not due to chance correlation. The descriptor selection and prediction performance of the RSQSRR for training dataset outperform the other two used modelling methods. The RSQSRR shows the highest [Formula: see text], [Formula: see text], and [Formula: see text], and the lowest [Formula: see text]. For the test dataset, the RSQSRR shows a high external validation value ([Formula: see text]), and a low value of [Formula: see text] compared with the other methods, indicating its higher predictive ability. In conclusion, the results reveal that the proposed RSQSRR is an efficient approach for modelling high dimensional QSRRs and the method is useful for the estimation of RIs of essential oils that have not been experimentally tested.
A penalized quantitative structure-property relationship (QSPR) model with adaptive bridge penalty for predicting the melting points of 92 energetic carbocyclic nitroaromatic compounds is proposed. To ensure the consistency of the descriptor selection of the proposed penalized adaptive bridge (PBridge), we proposed a ridge estimator ([Formula: see text]) as an initial weight in the adaptive bridge penalty. The Bayesian information criterion was applied to ensure the accurate selection of the tuning parameter ([Formula: see text]). The PBridge based model was internally and externally validated based on [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], the Y-randomization test, [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text] and the applicability domain. The validation results indicate that the model is robust and not due to chance correlation. The descriptor selection and prediction performance of PBridge for the training dataset outperforms the other methods used. PBridge shows the highest [Formula: see text] of 0.959, [Formula: see text] of 0.953, [Formula: see text] of 0.949 and [Formula: see text] of 0.959, and the lowest [Formula: see text] and [Formula: see text]. For the test dataset, PBridge shows a higher [Formula: see text] of 0.945 and [Formula: see text] of 0.948, and a lower [Formula: see text] and [Formula: see text], indicating its better prediction performance. The results clearly reveal that the proposed PBridge is useful for constructing reliable and robust QSPRs for predicting melting points prior to synthesizing new organic compounds.
Engineered cementitious composite (ECC) was discovered as a new substitute of conventional concrete as it provides better results in terms of tensile strain, reaching beyond 3%. From then, more studies were done to partially replace crumb rubber with sand to achieve a more sustainable and eco-friendlier composite from the original ECC. However, the elastic modulus of ECC was noticeably degraded. This could bring potential unseen dangerous consequences as the fatigue might happen at any time without any sign. The replacement of crumb rubber was then found to not only bring a more sustainable and eco-friendlier result but also increase the ductility and the durability of the composite, with lighter specific gravity compared to conventional concrete. This study investigated the effects of crumb rubber (CR) and graphene oxide (GO) toward the deformable properties of rubberized ECC, including the compressive strength, elastic modulus, Poisson's ratio, and drying shrinkage. Central composite design (CCD) was utilized to provide 13 reasonable trial mixtures with the ranging level of CR replacement from 0-30% and that of GO from 0.01-0.08%. The results show that GO increased the strength of the developed GO-RECC. It was also found that the addition of CR and GO to ECC brought a notable improvement in mechanical and deformable properties. The predicted model that was developed using response surface methodology (RSM) shows that the variables (compression strength, elastic modulus, Poisson's ratio, and drying shrinkage) rely on the independent (CR and GO) variables and are highly correlated.
The objective of this research was to determine the durability of an engineered cementitious composite (ECC) incorporating crumb rubber (CR) and graphene oxide (GO) with respect to resistance to acid and sulphate attacks. To obtain the mix designs used for this study, response surface methodology (RSM) was utilized, which yielded the composition of 13 mixes containing two variables (crumb rubber and graphene oxide). The crumb rubber had a percentage range of 0-10%, whereas the graphene oxide was tested in the range of 0.01-0.05% by volume. Three types of laboratory tests were used in this study, namely a compressive test, an acid attack test to study its durability against an acidic environment, and a sulphate attack test to examine the length change while exposed to a sulphate solution. Response surface methodology helped develop predictive responsive models and multiple objectives that aided in the optimization of results obtained from the experiments. Furthermore, a rubberized engineered cementitious composite incorporating graphene oxide yielded better chemical attack results compared to those of a normal rubberized engineered cementitious composite. In conclusion, nano-graphene in the form of graphene oxide has the ability to enhance the properties and overcome the limitations of crumb rubber incorporated into an engineered cementitious composite. The optimal mix was attained with 10% crumb rubber and 0.01 graphene oxide that achieved 43.6 MPa compressive strength, 29.4% weight loss, and 2.19% expansion. The addition of GO enhances the performance of rubberized ECC, contributing to less weight loss due to the deterioration of acidic media on the ECC. It also contributes to better resistance to changes in the length of the rubberized ECC samples.
An experimental study is conducted to determine the influence of secondary reinforcement on the behaviour of corbels fabricated with three different types of high-performance fiber-reinforced cementitious composites, including engineered cementitious concrete (ECC); high-performance steel fiber-reinforced composite (HPSFRC); and hybrid fiber-reinforced composite (HyFRC). Two shear span-to-depth ratios (a/d = 0.75 and 1.0) are explored. The mechanical properties of the composites in terms of tensile, compressive, and flexural strengths are investigated. Next, the structural behaviour of the high-performance cementitious composite corbels in terms of ultimate load capacity, ductility, and failure modes under the three-point bending test are investigated. The secondary reinforcement is proven to significantly affect stiffness and ultimately load capacity of all three high-performance composite corbels with an aspect ratio of 0.75. However, the secondary reinforcement was more impactful for the HPSFRC corbels, with 51% increase of ultimate strength. Moreover, in terms of damage, fewer cracks occurred in ECC corbels. HPSFRC corbels displayed the highest level of ductility and deformation capacity compared to the other specimens. The results were comparatively analyzed against the predicted results using truss and plastic truss models which provided relatively reliable shear strength.
Time-varying binary gravitational search algorithm (TVBGSA) is proposed for predicting antidiabetic activity of 134 dipeptidyl peptidase-IV (DPP-IV) inhibitors. To improve the performance of the binary gravitational search algorithm (BGSA) method, we propose a dynamic time-varying transfer function. A new control parameter, μ , is added in the original transfer function as a time-varying variable. The TVBGSA-based model was internally and externally validated based on
Q
int
2
,
Q
L G O
2
,
Q
B o o t
2
,
M S
E
t r a i n
,
Q
e x t
2
,
M S
E
t e s t
, Y-randomization test, and applicability domain evaluation. The validation results indicate that the proposed TVBGSA model is robust and not due to chance correlation. The descriptor selection and prediction performance of TVBGSA outperform BGSA method. TVBGSA shows higher
Q
int
2
of 0.957,
Q
L G O
2
of 0.951,
Q
B o o t
2
of 0.954,
Q
e x t
2
of 0.938, and lower
M S
E
t r a i n
and
M S
E
t e s t
compared to obtained results by BGSA, indicating the best prediction performance of the proposed TVBGSA model. The results clearly reveal that the proposed TVBGSA method is useful for constructing reliable and robust QSARs for predicting antidiabetic activity of DPP-IV inhibitors prior to designing and experimental synthesizing of new DPP-IV inhibitors.
An improved binary differential search (improved BDS) algorithm is proposed for QSAR classification of diverse series of antimicrobial compounds against Candida albicans inhibitors. The transfer functions is the most important component of the BDS algorithm, and converts continuous values of the donor into discrete values. In this paper, the eight types of transfer functions are investigated to verify their efficiency in improving BDS algorithm performance in QSAR classification. The performance was evaluated using three metrics: classification accuracy (CA), geometric mean of sensitivity and specificity (G-mean), and area under the curve. The Kruskal-Wallis test was also applied to show the statistical differences between the functions. Two functions, S1 and V4, show the best classification achievement, with a slightly better performance of V4 than S1. The V4 function takes the lowest iterations and selects the fewest descriptors. In addition, the V4 function yields the best CA and G-mean of 98.07% and 0.977%, respectively. The results prove that the V4 transfer function significantly improves the performance of the original BDS.
One of the recently developed metaheuristic algorithms, the coyote optimization algorithm (COA), has shown to perform better in a number of difficult optimization tasks. The binary form, BCOA, is used in this study as a solution to the descriptor selection issue in classifying diverse antifungal series. Z-shape transfer functions (ZTF) are evaluated to verify their efficiency in improving BCOA performance in QSAR classification based on classification accuracy (CA), the geometric mean of sensitivity and specificity (G-mean), and the area under the curve (AUC). The Kruskal-Wallis test is also applied to show the statistical differences between the functions. The efficacy of the best suggested transfer function, ZTF4, is further assessed by comparing it to the most recent binary algorithms. The results prove that ZTF, especially ZTF4, significantly improves the performance of the original BCOA. The ZTF4 function yields the best CA and G-mean of 99.03% and 0.992%, respectively. It shows the fastest convergence behaviour compared to other binary algorithms. It takes the fewest iterations to reach high classification performance and selects the fewest descriptors. In conclusion, the obtained results indicate the ability of the ZTF4-based BCOA to find the smallest subset of descriptors while maintaining the best classification accuracy performance.
The horse herd optimization algorithm (HOA), one of the more contemporary metaheuristic algorithms, has demonstrated superior performance in a number of challenging optimization tasks. In the present work, the descriptor selection issue is resolved by classifying different essential oil retention indices using the binary form, BHOA. Based on internal and external prediction criteria, Z-shape transfer functions (ZTF) were tested to verify their efficiency in improving BHOA performance in QSPR modelling for predicting retention indices of essential oils. The evaluation criteria involved the mean-squared error of the training and testing datasets (MSE), and leave-one-out internal and external validation (Q2). The degree of convergence of the proposed Z-shaped transfer functions was compared. In addition, K-fold cross validation with k = 5 was applied. The results show that ZTF, especially ZTF1, greatly improves the performance of the original BHOA. Comparatively speaking, ZTF, especially ZTF1, exhibits the fastest convergence behaviour of the binary algorithms. It chooses the fewest descriptors and requires the fewest iterations to achieve excellent prediction performance.
Deep beams are more susceptible to shear failure, and therefore reparation is a crucial for structural reinforcements. Shear failure is structural concrete failure in nature. It generally occurs without warning; however, it is acceptable for the beam to fail in bending but not in shear. The experimental study presented the structural behavior of the deep beams of reinforced concrete (RC) that reinforces the web openings with externally connected carbon fiber reinforced polymer (CFRP) composite in the shear zone. The structural behavior includes a failure mode, and cracking pattern, load deflection responses, stress concentration and the reinforcement factor were investigated. A total of nine reinforced concrete deep beams with openings strengthened with CFRP and one control beam without an opening have been cast and tested under static four-point bending load till failure. The experimental results showed that the increase the size of the opening causes an increase in the shear strength reduction by up to 30%. Therefore, the larger the openings, the lower the capability of load carriage, in addition to an increase in the number of CFRP layers that could enhance the load carrying capacity. Consequently, utilization of the CFRP layer wrapping technique strengthened the shear behavior of the reinforced concrete deep beams from about 10% to 40%. It was concluded that the most effective number of CFRP layers for the deep beam with opening sizes of 150 mm and 200 mm were two layers and three layers, respectively.
The concrete-filled double skin steel tube (CFDST) is a more viable option compared to a concrete-filled steel tube (CFST) due to consisting a hollow section, while degradation is enhanced simply by using carbon fiber-reinforced polymer (CFRP). Hence, the stabilization of a concrete's ductile strength needs high- performance fiber-reinforced cementitious conmposite. This study investigates the behavior of high-performance fiber-reinforced cementitious composite-filled double-skin steel tube (HPCFDST) beams strengthened longitudinally with various layers, lengths, and configurtion of CFRP sheets. The findings showed that, with increased CFRP layers, the moment capacity and flexural stiffness values of the retrofitted HPCFDST beams have significantly improved. For an instant, the moment capacity of HPCFDST beams improved by approximately 28.5% and 32.6% when they were wrapped partially along 100% with two and three layers, respectively, compared to the control beam. Moreover, the moment capacity of the HPCFDST beam using two partial layers of CFRP along 75% of its sufficient length was closed to the findings of the beam with two full CFRP layers. For energy absorption, the results showed a vast disparity. Only the two layers with a 100% full length and partial wrapping showed increasing performance over the control. Furthermore, the typical failure mode of HPCFDST beams was observed to be local buckling at the top surface near the point of loading and CFRP rapture at the bottom of effect length.
Alkali-activated concrete is an eco-friendly construction material that is used to preserve natural resources and promote sustainability in the construction industry. This emerging concrete consists of fine and coarse aggregates and fly ash that constitute the binder when mixed with alkaline activators, such as sodium hydroxide (NaOH) and sodium silicate (Na2SiO3). However, understanding its tension stiffening and crack spacing and width is of critical importance in fulfilling serviceability requirements. Therefore, this research aims to evaluate the tension stiffening and cracking performance of alkali-activated (AA) concrete. The variables considered in this study were compressive strength (fc) and concrete cover-to-bar diameter (Cc/db) ratios. After casting the specimen, they were cured before testing at ambient curing conditions for 180 days to reduce the effects of concrete shrinkage and obtain more realistic cracking results. The results showed that both AA and OPC concrete prisms develop slightly similar axial cracking force and corresponding cracking strain, but OPC concrete prisms exhibited a brittle behavior, resulting in a sudden drop in the load-strain curves at the crack location. In contrast, AA concrete prisms developed more than one crack simultaneously, suggesting a more uniform tensile strength compared to OPC specimens. The tension-stiffening factor (β) of AA concrete exhibited better ductile behavior than OPC concrete due to the strain compatibility between concrete and steel even after crack ignition. It was also observed that increasing the confinement (Cc/db ratio) around the steel bar delays internal crack formation and enhances tension stiffening in AAC. Comparing the experimental crack spacing and width with the values predicted using OPC codes of practice, such as EC2 and ACI 224R, revealed that EC2 tends to underestimate the maximum crack width, while ACI 224R provided better predictions. Thus, models to predict crack spacing and width have been proposed accordingly.