ABCModeller: an automatic data mining tool based on a consistent voting method with a user-friendly graphical interface.

In order to extract useful information from a huge amount of biological data nowadays, simple and convenient tools are urgently needed for data analysis and modeling. In this paper, an automatic data mining tool, termed as ABCModeller (Automatic Binary Classification Modeller), with a user-friendly graphical interface was developed here, which includes automated functions as data preprocessing, significant feature extraction, classification modeling, model evaluation and prediction. In order to enhance the generalization ability of the final model, a consistent voting method was built here in this tool with the utilization of three popular machine-learning algorithms, as artificial neural network, support vector machine and random forest. Besides, Fibonacci search and orthogonal experimental design methods were also employed here to automatically select significant features in the data space and optimal hyperparameters of the three algorithms to achieve the best model. The reliability of this tool has been verified through multiple benchmark data sets. In addition, with the advantage of a user-friendly graphical interface of this tool, users without any programming skills can easily obtain reliable models directly from original data, which can reduce the complexity of modeling and data mining, and contribute to the development of related research including but not limited to biology. The excitable file of this tool can be downloaded from http://lishuyan.lzu.edu.cn/ABCModeller.rar.

BSA Capped gold Nanoclusters Modulated by Copper ion for Sensitive and Selective Detection of Histidine in Biological Fluid.

This research proposed a sample and environmentally sustainable technique for the synthesis of bovine serum albumin capped gold nanoclusters (BSA-AuNCs) with outstanding fluorescence. The synthesized BSA-AuNCs were investigated using various ways before being combined with Cu2+ to produce a fluorescent switch probe (BSA-AuNCs-Cu2+) for histidine determination. After adding Cu2+, the fluorescence of the BSA-AuNCs was quenched, the fluorescence intensity was enhanced after adding histidine due to good coordination between Cu2+ and histidine. The significant chelation of histidine with Cu2+ demonstrated the viability of developing a selective "switch on" probe for histidine detecting over other amino acids. Unlike existing fluorescent nanomaterial-based approaches for detecting histidine, this study promises good selectivity, high efficiency, and the avoiding of chemical solvents. The designed BSA-AuNCs-Cu2+ fluorescent probe demonstrated an acceptable linear detection range of 0 to 240 µM under optimum circumstances, with a detection limit of 0.9 µM. The BSA-AuNCs-Cu2+ system was investigated in rat serum and human urine, with recoveries ranging from 97.2 to 108.2%, demonstrating its potential applicability for histidine detection with favorable results.

Design and Screening of New Lead Compounds for Autism Based on QSAR Model and Molecular Docking Studies.

The purpose of the present study aims to develop a satisfactory model for predicting pro-social and pro-cognitive effects on azinesulfonamides of cyclic amine derivatives as potential antipsychotics. The three dimensional-quantitative structure affinity relationship (3D-QSAR) study was performed on a series of azinesulfonamides of cyclic amine derivative using comparative molecular similarity indices analysis (CoMSIA). The best statistical model of CoMSIA q2, r2, SEE and F values are 0.664, 0.973, 0.087, and 82.344, respectively. Based on the model contour maps and the highest activity structure of the 43rd compound, serial new structures were designed and the 43k1 compound was selected as the best structure. The dock results showed a good binding of 43k1 with the protein (PDB ID: 6A93). The QSAR model analysis of the contour maps can help us to provide guidelines for finding novel potential antipsychotics.

Exploring the effect of silicene monolayer on the structure and function of villin headpiece and amyloid fibrils by molecular dynamics simulations.

With the development of various nanomaterial expected to be used in biomedical fields, it is more important to evaluate and understand their potential effects on biological system. In this work, two proteins with different structure, Villin Headpiece (HP35) with α-helix structure and protofibrils Aß1-42 with five ß-strand chains, were selected and their interactions with silicene were studied by means of molecular dynamics (MD) simulation to reveal the potential effect of silicene on the structure and function of biomolecules. The obtained results indicated that silicene could rapidly attract HP35 and Aß1-42 fibrils onto the surface to form a stable binding. The adsorption strength was moderate and no significant structural distortion of HP35 and Aß1-42 fibrils was observed. Moreover, the strength of calculated the H-bonds in neighbor chain of Aß1-42 fibrils indicated that the mild interactions between silicene and fibrils could regularize the structure of Aß1-42 fibrils and stabilize the interactions between five chains of fibrils protein, which might enhance the aggregation of Aß1-42 fibrils. This study provides a new insight for understanding the interaction between nanomaterials and biomolecules and moves forward the development of silicene into biomedical fields.

Adsorption Behaviors of Typical Proteins on BP, GR, and C2N Surfaces.

The biotoxicity of nanomaterials is very important for the application of nanomaterials in biomedical systems. In this study, proteins with varying secondary structures (α-helices, ß-sheets, and mixed α/ß structures) were employed to investigate the biological properties of three representative two-dimensional (2D) nanomaterials; these nanomaterials consisted of black phosphorus (BP), graphene (GR), and nitrogenized graphene (C2N) and were studied using molecular dynamics simulations. The results showed that the α-helix motif underwent a slight structural change on the BP surface and little structural change on the C2N surface. In contrast, the structure of the ß-sheet motif remained fairly intact on both the BP and C2N surfaces. The α-helix and ß-sheet motifs were able to freely migrate on the BP surface, but they were anchored to the C2N surface. In contrast to BP and C2N, GR severely disrupted the structures of the α-helix and ß-sheet motifs. BBA protein with mixed α/ß structures adsorbed on the BP and C2N surfaces and exhibited biological behaviors that were consistent with those of the α-helix and ß-sheet motifs. In summary, C2N may possess better biocompatibility than BP and GR and is expected to have applications in the biomedical field. This study not only comprehensively evaluated the biological characteristics of nanomaterials but also provided a theoretical strategy to explore and distinguish the surface characteristics of nanomaterials.

Development of a facile and sensitive method for detecting alkaline phosphatase activity in serum with fluorescent gold nanoclusters based on the inner filter effect.

In this work, a simple and sensitive method based on the inner filter effect (IFE) of p-nitrophenol (PNP) on the fluorescence of gold nanoclusters (AuNCs) has been developed for detecting alkaline phosphatase (ALP) activity. Bright orange fluorescent AuNCs were synthesized by one-pot synthesis and used directly as IFE fluorophores. p-Nitrophenyl phosphate (PNPP) is hydrolyzed by ALP to PNP, which quenches the fluorescence of AuNCs by the IFE. In the presence of ALP, PNPP was converted to PNP, and the absorption band shifted from 310 nm to 405 nm, which resulted in a certain degree of overlap between the absorption of PNP and the excitation of AuNCs. Due to the competitive absorption between AuNCs and PNP, the excitation of AuNCs was clearly diminished, leading to the quenching of the fluorescence of AuNCs. The IFE detection method exhibited a good linear relationship between 0.01 and 7.0 U L-1 (R2 = 0.9990) with the lowest detection limit of 0.003 U L-1 (the signal-to-noise ratio is 3). The proposed detection method was successfully applied for detecting ALP in serum samples and studying ALP inhibitors.

Investigation on Adsorption Mechanism of Peptides with Surface-Modified Super-Macroporous Resins.

Macroporous adsorption resins (MARs) have experienced rapid growth because of their unique properties and applications. Recently, it was discovered that a series of MARs with super-macroporous and diverse functional groups were synthesized to adsorb and enrich peptides; however, the detailed change mechanism of pore diameter and element composition and peptide adsorption mechanism have not yet been established. In this study, MARs and modified MARs were prepared by the surfactant reverse micelles swelling method and Friedel-Crafts reaction, and the pore diameter and element changes of these super-macroporous resin particles were accurately determined to elucidate formation processes of modified MARs. The adsorption mechanism of four peptides on different MARs was investigated. Sieving effect, electrostatic, hydrophobic, and hydrogen bonds interactions were found to play a major role in the adsorption process of peptides. Compared to that of the traditional resins, the adsorption capacity of super-macroporous MARs for peptides enormously increased. Electrostatic interactions have been explained perfectly by determining the isoelectric point. The molecular docking technology proved that the hydrogen-bonding receptor in MARs was a crucial factor for the adsorption capacity by autodock 4.26 and gromacs 5.14. These findings will enable selective adsorption of peptides by MARs, which also provides a theoretical basis for the construction of specific resin to adsorb different peptides.

In silico toxicity evaluation of dioxins using structure-activity relationship (SAR) and two-dimensional quantitative structure-activity relationship (2D-QSAR).

Prediction of pEC50 values of dioxins binding with the aryl hydrocarbon receptor (AhR) is of great significance for exploring how dioxins induce toxicity in human body and evaluating their environmental behaviors and risks. To reveal the factors that influence the toxicity of dioxins, provide more accurate mathematical models for predicting the pEC50 values of dioxins, and supplement the toxicity database of persistent organic pollutants, qualitative structure-activity relationship (SAR) and two-dimensional quantitative structure-activity relationship (2D-QSAR) were used in this study. The research objects in this study were 60 organic compounds with pEC50 values and 162 compounds without pEC50 values, which included polychlorinated dibenzofurans (PCDFs), polychlorinated dibenzo-p-dioxins (PCDDs), and polybrominated dibenzo-p-dioxins (PBDDs). The qualitative structure-activity relationship (SAR) was performed first and concluded that halogen substitutions at any of the 2, 3, 7, and 8 sites increased the pEC50 value of the compound. Moreover, two-dimensional quantitative structure-activity relationship (2D-QSAR) models were established by employing multiple linear regression (MLR) method and artificial neural network (ANN) algorithm to investigate the factors affecting the pEC50 values of dioxins molecules. MLR was used to establish the well-understood linear model and ANN was used to establish a more accurate non-linear model. Both models have good fitting, robustness, and predictive ability. Importantly, the ability of dioxins binding to AhR is mainly determined by molecular descriptors including E1m, SM09_AEA (dm), RDF065u, F05 [Cl-Cl], and Neoplastic-80. In addition, the pEC50 values of the 162 dioxins without toxicity data were predicted by MLR and ANN models, respectively.

3D-QSAR modeling and molecular docking study on Mer kinase inhibitors of pyridine-substituted pyrimidines.

Mer kinase is a novel therapeutic target for many cancers, and overexpression of Mer receptor tyrosine kinase has been observed in several kinds of tumors. To deeply understand the structure-activity correlation of a series of pyridine/pyrimidine analogs as potent Mer inhibitors, a combined molecular docking and three-dimensional quantitative structure-activity relationship modeling was carried out. A comparative molecular similarity indices analysis model was developed based on the maximum common substructure alignment. The optimum model exhibited statistically significant results: the cross-validated correlation coefficient q2 was 0.599, and non-cross-validated r2 value was 0.984. Furthermore, the results of internal validation such as bootstrapping, Y-randomization as well as external validation (the external predictive correlation coefficient r2 ext = 0.728) confirmed the rationality and good predictive ability of the model. Using the crystal structure of Mer kinase, the selected pyridine/pyrimidine compounds were docked into the enzyme active site. Some key amino acid residues were determined, and hydrogen bonding and hydrophobic interactions between Mer kinase and inhibitors were identified. The satisfactory results from this study may aid in the research and development of novel potent Mer kinase inhibitors.

A novel fluorescence sensor based on Al3+-mediated aggregation of gold nanoclusters for determination of citric acid in beverages.

This paper revealed a new strategy for citric acid (CA) detection using aggregation-induced emission (AIE)-based fluorescent gold nanoclusters (AuNCs). AuNCs was synthesized using glutathione (GSH) as the template and reducing agent and used as the fluorescent probe to detect CA under aluminum ion (Al3+) mediation. The fluorescence intensity of AuNCs increased about 4 times with the addition of Al3+, but the enhanced fluorescence was quenched after the addition of CA. Based on this fluorescence phenomenon, an "on-off" fluorescence strategy was designed for the sensitive determination of CA and a linear detection range for CA was achieved within 0-80.0 µM. In addition, the developed probe exhibited high selectivity and accuracy for determination of CA. The mechanism of fluorescence enhancement and quenching of AuNCs was explored in detail. The established probe was used successfully for CA detection in beverages. The spiked recoveries from 97.50% to 103.67% were gratifying, which indicated the probe had potential prospects for detecting CA in food.

QSAR Study of Novel 1, 8-Naphthimide Derivatives Targeting Nuclear DNA.

BACKGROUND: 1, 8-naphthimide is a novel tumor inhibitor targeting nuclear DNA, which can be used to design and develop anti-osteosarcoma drugs. OBJECTIVE: Quantitative structure-activity relationship (QSAR) model was established to predict the physical properties of compounds. METHODS: In this study, gene expression programming (GEP) was used to build a nonlinear quantitative structureactivity relationship (QSAR) model with descriptors and to predict the activity of a serials novel DNA-targeted chemotherapeutic agents. These descriptors were calculated in CODESSA software and selected from the descriptor pool based on heuristics. Three descriptors were selected to establish a multiple linear regression model. The best nonlinear QSAR model with a correlation coefficient of 0.89 and 0.82 and mean error of 0.02 and 0.06 for the training and test sets were obtained. RESULTS: The results showed that the model established by GEP had better stability and predictive ability. The small molecular docking experiment of 32 compounds was carried out in SYBYL software, and it was found that compound 7A had reliable molecular docking ability. CONCLUSION: The established model reveals the factors affecting the activity of DNA inhibitors and provides direction and guidance for the further design of highly effective DNA-targeting drugs for osteosarcoma.

Tit Structure-activity Relationship Study and Design of Novel 1, 8- Naphthimide Derivatives as Potential DNA-targeting Chemotherapeutic Agents for Osteosarcoma.

BACKGROUND: 1, 8-naphthimide is a novel tumor inhibitor targeting nuclear DNA, which makes it applicable to the design and development of anti-osteosarcoma drugs. OBJECTIVE: The aim of this study is to establish a satisfactory model based on 1, 8-naphthimide derivatives that makes reliable prediction as DNA-targeted chemotherapy agents for osteosarcoma. METHODS: All compounds are constructed using ChemDraw software and subsequently optimized using Sybyl software. COMSIA method is used to construct QSAR model with the optimized compound in Sybyl software package. A series of new 1, 8-naphthalimide derivatives are designed and their IC50 values are predicted using the QSAR model. Finally, the newly designed compounds are screened according to IC50 values, and molecular docking experiments are conducted on the top ten compounds of IC50. RESULTS: The COMSIA model shows that q2 is 0.529 and the optimum number of components is 6. The model has a high r2 value of 0.993 and a low SEE of 0.033, with the F value and the r2 predicted to be 495.841 and 0.996 respectively. The statistical results and verification results of the model are satisfactory. In addition, analyzing the contour maps is conducive to finding the structural requirements. CONCLUSION: The results of this study can provide guidance for medical chemists and other related workers to develop targeted chemotherapy drugs for osteosarcoma.

Potential of vibrational spectroscopy coupled with machine learning as a non-invasive diagnostic method for COVID-19.

BACKGROUND AND OBJECTIVE: Efforts to alleviate the ongoing coronavirus disease 2019 (COVID-19) crisis showed that rapid, sensitive, and large-scale screening is critical for controlling the current infection and that of ongoing pandemics. METHODS: Here, we explored the potential of vibrational spectroscopy coupled with machine learning to screen COVID-19 patients in its initial stage. Herein presented is a hybrid classification model called grey wolf optimized support vector machine (GWO-SVM). The proposed model was tested and comprehensively compared with other machine learning models via vibrational spectroscopic fingerprinting including saliva FTIR spectra dataset and serum Raman scattering spectra dataset. RESULTS: For the unknown vibrational spectra, the presented GWO-SVM model provided an accuracy, specificity and F1_score value of 0.9825, 0.9714 and 0.9778 for saliva FTIR spectra dataset, respectively, while an overall accuracy, specificity and F1_score value of 0.9085, 0.9552 and 0.9036 for serum Raman scattering spectra dataset, respectively, which showed superiority than those of state-of-the-art models, thereby suggesting the suitability of the GWO-SVM model to be adopted in a clinical setting for initial screening of COVID-19 patients. CONCLUSIONS: Prospectively, the presented vibrational spectroscopy based GWO-SVM model can facilitate in screening of COVID-19 patients and alleviate the medical service burden. Therefore, herein proof-of-concept results showed the chance of vibrational spectroscopy coupled with GWO-SVM model to help COVID-19 diagnosis and have the potential be further used for early screening of other infectious diseases.

3D,2D-QSAR study and docking of novel quinazolines as potential target drugs for osteosarcoma.

Background: Quinazolines are an important class of benzopyrimidine heterocyclic compounds with a promising antitumor activity that can be used for the design and development of osteosarcoma target compounds. Objective: To predict the compound activity of quinazoline compounds by constructing 2D- and 3D-QSAR models, and to design new compounds according to the main influencing factors of compound activity in the two models. Methods: First, heuristic method and GEP (gene expression programming) algorithm were used to construct linear and non-linear 2D-QSAR models. Then a 3D-QSAR model was constructed using CoMSIA method in SYBYL software package. Finally, new compounds were designed according to molecular descriptors of 2D-QSAR model and contour maps of 3D-QSAR model. Several compounds with optimal activity were used for docking experiments with osteosarcoma related targets (FGFR4). Results: The non-linear model constructed by GEP algorithm was more stable and predictive than the linear model constructed by heuristic method. A 3D-QSAR model with high Q2 (0.63) and R 2 (0.987) values and low error values (0.05) was obtained in this study. The success of the model fully passed the external validation formula, proving that the model is very stable and has strong predictive power. 200 quinazoline derivatives were designed according to molecular descriptors and contour maps, and docking experiments were carried out for the most active compounds. Compound 19g.10 has the best compound activity with good target binding capability. Conclusion: To sum up, the two novel QSAR models constructed were very reliable. The combination of descriptors in 2D-QSAR with COMSIA contour maps provides new design ideas for future compound design in osteosarcoma.

QSAR and molecular docking studies on designing potent inhibitors of SARS-CoVs main protease.

Background: Severe acute respiratory syndrome coronavirus (SARS-CoVs) have emerged as a global health threat, which had caused a high rate of mortality. There is an urgent need to find effective drugs against these viruses. Objective: This study aims to predict the activity of unsymmetrical aromatic disulfides by constructing a QSAR model, and to design new compounds according to the structural and physicochemical attributes responsible for higher activity towards SARS-CoVs main protease. Methods: All molecules were constructed in ChemOffice software and molecular descriptors were calculated by CODESSA software. A regression-based linear heuristic method was established by changing descriptors datasets and calculating predicted IC50 values of compounds. Then, some new compounds were designed according to molecular descriptors from the heuristic method model. The compounds with predicted values smaller than a set point were constantly screened out. Finally, the properties analysis and molecular docking were conducted to further understand the structure-activity relationships of these finalized compounds. Results: The heuristic method explored the various descriptors responsible for bioactivity and gained the best linear model with R2 0.87. The success of the model fully passed the testing set validation, proving that the model has both high statistical significance and excellent predictive ability. A total of 5 compounds with ideal predicted IC50 were found from the 96 newly designed derivatives and their properties analyze was carried out. Molecular docking experiments were conducted for the optimal compound 31a, which has the best compound activity with good target protein binding capability. Conclusion: The heuristic method was quite reliable for predicting IC50 values of unsymmetrical aromatic disulfides. The present research provides meaningful guidance for further exploration of the highly active inhibitors for SARS-CoVs.

Network Pharmacology Integrated Molecular Docking to Reveal the Autism and Mechanism of Baohewan Heshiwei Wen Dan Tang.

BACKGROUND: In recent years, the prevalence and mortality of autism spectrum disorder (ASD) have been increasing. The clinical features are different with different cases, so the treatment ways are different for each one. OBJECTIVE: Baohewan Heshiwei Wen Dan Tang (BHWDT) has been recommended for treating autistic spectrum disorder. To investigate the mechanism of action and how the compounds interact with ASD targets, network pharmacology and molecular docking methods were used in this study. METHODS: Traditional Chinese Medicine Systems Pharmacology (TCMSP) was used to screen the active components according to index of oral bio-activity and drug-likeness. Then, TCMSP and Swiss Target Prediction databases were used to screen potential target genes of active components. The related target genes of ASD were obtained from the Gene Cards database. Matescape database was utilized to get gene ontology (GO) function enrichment and Kyoto Encyclopedia of Genes and Genomes pathway annotation of gene targets. Composition- target-pathway (C-T-P) and a protein-protein interaction (PPI) networks were built with Cytoscape 3.8.2 software. RESULTS: The interaction of the main active components of BHWDT was verified by molecular docking. The key targets of MAPK1, IL6, CXCL8 and TP53 of BHWDT were obtained. The key active components Quercetin, Kaempferol and Iuteolin of BHWDT could bind with MAPK1, IL6, CXCL8 and TP53 of BHWDT, respectively. CONCLUSION: BHWDT can be highly effective for treating ASD and this study can help us to understand multiple targets and multiple pathways mechanism.

Novel quantitative structure-activity relationship model to predict activities of natural products against COVID-19.

Currently, COVID-19 is spreading in a large scale while no efficient vaccine has been produced. A high-effective drug for COVID-19 is very necessary now. We established a satisfied quantitative structure-activity relationship model by gene expression programming to predict the IC50 value of natural compounds. A total of 27 natural products were optimized by heuristic method in CODESSA program to build a liner model. Based on it, only two descriptors were selected and utilized to build a nonlinear model in gene expression programming. The square of correlation coefficient and s2 of heuristic method were 0.80 and 0.10, respectively. In gene expression programming, the square of correlation coefficient and mean square error for training set were 0.91 and 0.04. The square of correlation coefficient and mean square error for test set are 0.86 and 0.1. This nonlinear model has stronger predictive ability to develop the targeted drugs of COVID-19.

Prediction of the inhibitory concentrations of chloroquine derivatives using deep neural networks models.

In recent years, deep neural networks have begun to receive much attention, which has obvious advantages in feature extraction and modeling. However, in the using of deep neural networks for the QSAR modeling process, the selection of various parameters (number of neurons, hidden layers, transfer functions, data set partitioning, number of iterations, etc.) becomes difficult. Thus, we proposed a new and easy method for optimizing the model and selecting Deep Neural Networks (DNN) parameters through uniform design ideas and orthogonal design methods. By using this approach, 222 chloroquine (CQ) derivatives with half maximal inhibitory concentration values reported in different kinds of literature were selected to establish DNN models and a total number of 128,000 DNN models were built to determine the optimized parameters for selecting the better models. Comparing with linear and Artificial Neural Network (ANN) models, we found that DNN models showed better performance.Communicated by Ramaswamy H. Sarma.

Study on novel PtNP-sorafenib and its interaction with VEGFR2.

With the developments of nanodrugs, some drugs have combined with nanoparticles (NPs) to reduce their side-effects and increase their therapeutic activities. Here, a novel nanodrug platinum nanoparticle-sorafenib (PtNP-SOR) was proposed for the first time. By means of molecular dynamics simulation, the stability and biocompatibility of PtNP-SOR were investigated. Then, the interaction mechanism between PtNP-SOR and vascular endothelial growth factor receptor 2 (VEGFR2) was explored and compared with that of the peptide 2a coated PtNPs. The results showed that PtNP-SOR could bind to VEGFR2 more stably, which was driven by the Coulombic and strong dispersion interaction between PtNP-SOR and VEGFR2. According to their contributions obtained from the decomposition of binding free energies, the key residues in VEGFR2 were identified to form the specific space, which increased the affinity with PtNP-SOR. This study provided useful insights to the design of PtNP-drugs as well as important theoretical proofs to the interaction between PtNP-SOR and VEGFR2 at a molecular level, which can be of large help during the development and optimization of novel nanodrugs.