Quantitative Structure-activity Relationship Methods Research Articles

Web-Based Quantitative Structure-Activity Relationship Resources Facilitate Effective Drug Discovery.

Traditional drug discovery effectively contributes to the treatment of many diseases but is limited by high costs and long cycles. Quantitative structure-activity relationship (QSAR) methods were introduced to evaluate the activity of compounds virtually, which saves the significant cost of determining the activities of the compounds experimentally. Over the past two decades, many web tools for QSAR modeling with various features have been developed to facilitate the usage of QSAR methods. These web tools significantly reduce the difficulty of using QSAR and indirectly promote drug discovery. However, there are few comprehensive summaries of these QSAR tools, and researchers may have difficulty determining which tool to use. Hence, we systematically surveyed the mainstream web tools for QSAR modeling. This work may guide researchers in choosing appropriate web tools for developing QSAR models, and may also help develop more bioinformatics tools based on these existing resources. For nonprofessionals, we also hope to make more people aware of QSAR methods and expand their use.

QSPR model for estimation of photodegradation average rate of the porphyrin-TiO2 complexes and prediction of their biodegradation activity and toxicity: Engineering of two annihilators for water/waste contaminants

4-Nitrophenol (4-NP) and 4-chlorophenol (4-CP) are classified as emerging contaminants and essential environmentally harmful waste. Due to the water solubility of the mentioned hazardous pollutants, experimental researches are widely discussed. A novel quantitative structure-property relationships (QSPR) model is presented to predict the photodegradation average rate of 4-NP and 4-CP (r͞4-NP/4-CP) by biomolecules in aqueous solutions. This QSPR model can predict the r͞4-NP/4-CP values for porphyrin-TiO2 complexes only from their molecular structures by calculation of metal interaction with ligand and fragment effects. For deriving the new model, the measured values of r͞4-NP/4-CP of 70 porphyrin complexes were collected from various references. The values of the regression coefficient (R2) for both training (56 compounds) and test (14 compounds) sets are 0.999. The calculated values of the mean squared error (MSE) for training and test sets are 0.157 and 0.053, respectively. The biodegradation activities of porphyrins are anticipated through the quantitative structure-activity relationships (QSAR) method to reveal their relevance with simple structural descriptors. All of the photocatalysts were investigated for designing novel complexes with higher r͞4-NP/4-CP and the lower ecotoxicological effect that was satisfying.

Quantitative Structure-Activity Relationships and Molecular Docking Simulation of Allicin Compounds as Inhibitors of COVID-19 Protease Enzyme

Background: Coronavirus (CoV) is a group of viruses that cause disease in humans and animals. These viruses contain crown-shaped spike glycoproteins on their surface. Objective: We conducted a quantitative structure-activity relationship (QSAR) study on a series of 36 compounds of allicin to assess their antiviral activities against the main protease of COVID-19. Methods: In the present descriptive-analytic study, the information on the structure of compounds, the COVID-19 protease enzyme, and the Allicin derivatives was obtained from the databases such as the Research Collaboratory for Structural Bioinformatics’ Protein Data Bank (PDB) and PubChem. The QSAR method, analysis of correlations and multiple linear regressions were carried out. Six molecular descriptors such as constitutional and molecular topology descriptors were selected for the model. Finally, molecular docking was performed in iGEMDOCK 2.1 software. Results: The obtained multi-parametric model reported a correlation coefficient of about 0.89, indicating that the model was able to satisfactory predict the antiviral activity of allicin compounds. Conclusion: The findings obtained can be valuable in designing, synthesizing, and developing novel antiviral agents with allicin-based scaffold.

Modeling Uptake of Polyethylenimine/Short Interfering RNA Nanoparticles in Breast Cancer Cells Using Machine Learning

Polyethylenimine (PEI) is one of the most promising nonviral vectors for delivery of short interfering RNA (siRNA) agents into cancer cells. A promising approach that increases the delivery efficiency of PEI is its modification with hydrophobic substitutions. However, the performance of modified PEIs depends on the nature and extent of substitutions. Herein, machine learning algorithms are used on the basis of quantitative structure activity relationship (QSAR) method to predict the cellular uptake of hydrophobically modified PEI/siRNA nanoparticles (NPs) into various cancer cell lines. To this end, 3 different regression models, namely, random forest (RF), multilayer perceptron (MLP), and linear regression (LR), are used. The results show that RF and MLP regression methods have a better performance than the LR method, suggesting that nonlinear models are better estimators when predicting the cellular uptake of PEI/siRNA NPs. Additionally, critical descriptors that have major contributions to cellular uptake are found to be PEI‐to‐siRNA weight ratio, type of hydrophobic substitution, as well as total numbers of Cs, unsaturated C, and thioester groups on substitutions in each PEI. This study is the first report that predicts cellular uptake with PEI‐based carriers, which provides valuable insight into the design of performance‐enhancing hydrophobic substituents on PEIs.

Deep imputation on large‐scale drug discovery data

AbstractMore accurate predictions of the biological properties of chemical compounds would guide the selection and design of new compounds in drug discovery and help to address the enormous cost and low success‐rate of pharmaceutical R&D. However, this domain presents a significant challenge for AI methods due to the sparsity of compound data and the noise inherent in results from biological experiments. In this paper, we demonstrate how data imputation using deep learning provides substantial improvements over quantitative structure‐activity relationship (QSAR) machine learning models that are widely applied in drug discovery. We present the largest‐to‐date successful application of deep‐learning imputation to datasets which are comparable in size to the corporate data repository of a pharmaceutical company (678 994 compounds by 1166 endpoints). We demonstrate this improvement for three areas of practical application linked to distinct use cases; (a) target activity data compiled from a range of drug discovery projects, (b) a high value and heterogeneous dataset covering complex absorption, distribution, metabolism, and elimination properties, and (c) high throughput screening data, testing the algorithm's limits on early stage noisy and very sparse data. Achieving median coefficients of determination, R2, of 0.69, 0.36, and 0.43, respectively, across these applications, the deep learning imputation method offers an unambiguous improvement over random forest QSAR methods, which achieve median R2 values of 0.28, 0.19, and 0.23, respectively. We also demonstrate that robust estimates of the uncertainties in the predicted values correlate strongly with the accuracies in prediction, enabling greater confidence in decision‐making based on the imputed values.

Development of QSAR models for evaluating pesticide toxicity against Skeletonema costatum

Nowadays, the emergence of pesticides and its application in agriculture greatly improved the crop quality and food production. However, the resulted ecological problem caused by the widespread pesticide residues attracted more and more attention since the pesticides were harmful to most living organisms. Regulatory agencies such as Environmental Protection Agency (EPA) and European Chemicals Agency (ECHA) stipulated that a comprehensive pesticides risk assessment was essential and also underscored the application of computation method in evaluating pesticides. The present study aimed to use the Quantitative Structure-Activity Relationship (QSAR) method to establish models for quantitatively and qualitatively predicting the toxicity of pesticide against Skeletonema costatum. The regression model was developed using the Genetic Algorithm plus Multiple Linear Regression method and the classification model was established based on the Random Forest algorithm, respectively. Various internal and external validation metrics suggested that the obtained regression model was of good fitness (R2=0.722), robustness (QLOO2=0.653) and external predictive ability (QFn2:0.719–0.776, CCC = 0.878). The classification could correctly predict 79.4% of pesticides in the training set and 69.7% in the validation set. The relatively high sensitivity value of the classification model indicated its good performance in identifying high-toxic pesticides. It could be concluded from the selected modelling descriptors that molecular weight and polarizability impacted the toxicity the most. The atom-type E-state descriptors generally contributed negatively to the pesticide toxicity which verified the negative influence of molecular hydrophilicity. Moreover, the lipophilic, carbon-type, charge related descriptors demonstrated the important influence of lipophilicity and polarity on pesticide toxicity. The models presented in this work could be used to pre-evaluate the toxicity of pesticides within the applicability domain, thus focusing resources on the high-toxic pesticides and assessing the environmental risk of pesticides quickly and economically.

QSAR and Ab Initio studies of quinolon-4(1H)-imine derivatives as antimalarial agents

Malaria is still the most dangerous disease threat in the world, including in Indonesia. In Indonesia, it is estimated that there are 20 million cases of malaria per year. Malaria resistance to conventional drugs requires the search for new antimalarial drugs. Molecular modeling can be a solution to these problems. An activity study of 22 quinolone-4 (1H) -imine derivatives as antimalarials was carried out using the QSAR Quantitative Structure-Activity Relationship method. The electronic and molecular descriptors were obtained from the Hartree-Fock HF / 6-31G ab initio calculation. The multiple linear regression (MLR) method was used to construct the QSAR model. The best QSAR models produced are: pEC50 = -4,177 + (37,902 x qC3) + (171,282 x qC8) + (9,061 x qC10) + (125,818 x qC11) + (-149,125 x qC17) + (191,623 x qC18), with statistical parameters, n = 22; r2 = 0,910; SEE = 0,171; Fhit/Ftab = 4,510 dan PRESS = 0,697. The best QSAR equation model can be used as a reference for designing and predicting the antimalarial activity of Quinolon-4 (1H) -imine derivatives which have higher activity than the previous one

Adsorption and inhibition behavior of imidazolium tetrafluoroborate derivatives as green corrosion inhibitors for carbon steel.

The adsorption and inhibition mechanism of chain length increase and group substitution of imidazole tetrafluoroborate derivatives for the corrosion inhibition of carbon steel in HCl solution was revealed in detail via the density functional theory, molecular dynamics (MD) simulation, and quantitative structure-activity relationship (QSAR) methods. The main reactive site of an ionic liquid is located on its imidazolium ring. With alkyl chain lengthening or the introduction of methyl groups onto the imidazolium ring, its molecular reactivity and electron-donating ability increase the interaction between the ionic liquid and the Fe (110) surface. Therefore, the imidazolium rings of four IL inhibitors are more likely to lie on the Fe (110) surface in parallel through chemical adsorption. The interactions between N atoms in ionic liquids and the Fe (110) surface are stronger than those between the C atoms on the imidazolium rings of the four ionic liquid, and coordination bonds can be formed between N atoms and the Fe (110) surface. Therefore, ionic liquids can hinder the interaction between corrosion particles and the Fe (110) surface, hinder the diffusion of corrosion particles, and effectively reduce the number density of corrosion particles on the Fe (110) surface. A methyl substituent on the C2 atom of the imidazolium ring can enhance the electron-donating ability and adsorption tendency much more than an increase in the alkyl chain on the N3 atom. The four inhibitors are ordered in terms of corrosion inhibition efficiency as [C12DMIM]BF4 > [C10DMIM]BF4 > [C12MIM]BF4 > [C10MIM]BF4, which agrees well with the experimental results. A good correlation between experimental inhibition efficiency, concentration and microscopic structures parameters of ILs such as energy gap ΔE, polarizability P, electronegativity χ, hardness η, softness σ, number of electrons transferred ΔN, and electrophilicity ω was achieved.

Predicting Pharmacokinetic Properties of Potential Anticancer Agents via Their Chromatographic Behavior on Different Reversed Phase Materials.

The Quantitative Structure-Activity Relationship (QSAR) methodology was used to predict biological properties, i.e., the blood–brain distribution (log BB), fraction unbounded in the brain (fu,brain), water-skin permeation (log Kp), binding to human plasma proteins (log Ka,HSA), and intestinal permeability (Caco-2), for three classes of fused azaisocytosine-containing congeners that were considered and tested as promising drug candidates. The compounds were characterized by lipophilic, structural, and electronic descriptors, i.e., chromatographic retention, topological polar surface area, polarizability, and molecular weight. Different reversed-phase liquid chromatography techniques were used to determine the chromatographic lipophilicity of the compounds that were tested, i.e., micellar liquid chromatography (MLC) with the ODS-2 column and polyoxyethylene lauryl ether (Brij 35) as the effluent component, an immobilized artificial membrane (IAM) chromatography with phosphatidylcholine column (IAM.PC.DD2) and chromatography with end-capped octadecylsilyl (ODS) column using aqueous solutions of acetonitrile as the mobile phases. Using multiple linear regression, we derived the statistically significant quantitative structure-activity relationships. All these QSAR equations were validated and were found to be very good. The investigations highlight the significance and possibilities of liquid chromatographic techniques with three different reversed-phase materials and QSARs methods in predicting the pharmacokinetic properties of our important organic compounds and reducing unethical animal testing.

Hyperbolic relational graph convolution networks plus: a simple but highly efficient QSAR-modeling method.

Accurate predictions of druggability and bioactivities of compounds are desirable to reduce the high cost and time of drug discovery. After more than five decades of continuing developments, quantitative structure-activity relationship (QSAR) methods have been established as indispensable tools that facilitate fast, reliable and affordable assessments of physicochemical and biological properties of compounds in drug-discovery programs. Currently, there are mainly two types of QSAR methods, descriptor-based methods and graph-based methods. The former is developed based on predefined molecular descriptors, whereas the latter is developed based on simple atomic and bond information. In this study, we presented a simple but highly efficient modeling method by combining molecular graphs and molecular descriptors as the input of a modified graph neural network, called hyperbolic relational graph convolution network plus (HRGCN+). The evaluation results show that HRGCN+ achieves state-of-the-art performance on 11 drug-discovery-related datasets. We also explored the impact of the addition of traditional molecular descriptors on the predictions of graph-based methods, and found that the addition of molecular descriptors can indeed boost the predictive power of graph-based methods. The results also highlight the strong anti-noise capability of our method. In addition, our method provides a way to interpret models at both the atom and descriptor levels, which can help medicinal chemists extract hidden information from complex datasets. We also offer an HRGCN+'s online prediction service at https://quantum.tencent.com/hrgcn/.

Novel QSAR Models for Molecular Initiating Event Modeling in Two Intersecting Adverse Outcome Pathways Based Pulmonary Fibrosis Prediction for Biocidal Mixtures.

The adverse outcome pathway (AOP) was introduced as an alternative method to avoid unnecessary animal tests. Under the AOP framework, an in silico methods, molecular initiating event (MIE) modeling is used based on the ligand-receptor interaction. Recently, the intersecting AOPs (AOP 347), including two MIEs, namely peroxisome proliferator-activated receptor-gamma (PPAR-γ) and toll-like receptor 4 (TLR4), associated with pulmonary fibrosis was proposed. Based on the AOP 347, this study developed two novel quantitative structure-activity relationship (QSAR) models for the two MIEs. The prediction performances of different MIE modeling methods (e.g., molecular dynamics, pharmacophore model, and QSAR) were compared and validated with in vitro test data. Results showed that the QSAR method had high accuracy compared with other modeling methods, and the QSAR method is suitable for the MIE modeling in the AOP 347. Therefore, the two QSAR models based on the AOP 347 can be powerful models to screen biocidal mixture related to pulmonary fibrosis.

QSAR Modelling of Peptidomimetic Derivatives towards HKU4-CoV 3CLpro Inhibitors against MERS-CoV

In this paper, we report the relationship between the anti-MERS-CoV activities of the HKU4 derived peptides for some peptidomimetic compounds and various descriptors using the quantitative structure activity relationships (QSAR) methods. The used descriptors were computed using ChemSketch, Marvin Sketch and ChemOffice software. The principal components analysis (PCA) and the multiple linear regression (MLR) methods were used to propose a model with reliable predictive capacity. The original data set of 41 peptidomimetic derivatives was randomly divided into training and test sets of 34 and 7 compounds, respectively. The predictive ability of the best MLR model was assessed by determination coefficient R2 = 0.691, cross-validation parameter Q2cv = 0.528 and the external validation parameter R2test = 0.794.

Wiener Polarity Index Calculation of Square-Free Graphs and Its Implementation to Certain Complex Materials

Molecular topology is a portion of mathematical chemistry managing the logarithmic portrayal of chemical materials, permitting a tremendous yet straightforward characterization of the compounds. Concerning the traditional physical-chemical descriptors, it is conceivable to set up direct quantitative structure-activity relationship methods to associate with such descriptors termed topological indices. In this study, we have developed the mathematical technique to study the Wiener polarity index of chemical materials without squares. We have taken the cancer treatment drugs such as lenvatinib and cabozantinib to illustrate our approach. In addition, we explored the inherent property of silicate, Sierpiński, and octahedral-related complex materials that the edge set can be decomposed in such a way that any edge in the same part of the decomposition has an equal number of neighboring vertices and applied the technique to derive the formulae for these materials.

Application of QSAR Method in the Design of Enhanced Antimalarial Derivatives of Azetidine-2-carbonitriles, their Molecular Docking, Drug-likeness, and SwissADME Properties.

The resistance of the P. falciparum strain to some of the antimalarial drugs has been a dominant dilemma facing the treatment of this fetid disease. This necessitates the detection and development of new antimalarial agents targeting the P. falciparum. Azetidine-2-carbonitriles reported for its antimalarial activities, could provide an alternative to the customized antimalarial drugs. Leading to the use of quantitative structure-activity relationship (QSAR) studies, which relates the structures of Azetidine-2-carbonitriles with their activities to generate predictive models. The structures were optimized using density functional theory (DFT) DFT/B3LYP/6-31G* basis set to generate their molecular descriptors, where five predictive models were constructed using the generated descriptors. The models were constructed using the genetic function algorithm component of a material studio, where the model with good statistical parameters, high coefficient of determination (R2) = 0.9465, cross-validated R2 (Q2cv) = 0.8981, Q2 (L4O)cv = 0.9272, and highest external validated R2 (R2pred) = 0.6915 was selected as the best model. These statistical results show the robustness, excellent power of prediction, and validity of the selected model. The descriptor, SpMax2_Bhp (the maximum absolute eigenvalue of Barysz matrix for n = 2 was weighted by polarizability), was revealed to be the most influential in the model due to its highest mean effect. The descriptor played a role in the design of sixteen (16) theoretical derivatives of Azetidine-2-carbonitriles using compound 25 as the design template by increasing polarizability of the compounds through substitution of the various group with electron deactivating groups (F, I, Cl, SO3H, CN, NO2, etc.) at different position of the template. The designed compounds were docked with Plasmodium falciparum dihydroorotate dehydrogenase (Pf-DHODH), giving compound D9 the highest binding energy. The designed compounds were further screened for their drug-likeness, where they all pass Lipinski’s RO5. All the compounds show good skin permeability coefficient and have low Gastrointestinal absorption while few compounds D1, D2, D3, D14, and D15 inhibiting the CYP1A2.

Predictive Quantitative Structure-Activity Relationship Modeling of the Antifungal and Antibiotic Properties of Triazolothiadiazine Compounds.

Predictive models were developed using two-dimensional quantitative structure activity relationship (QSAR) methods coupled with B3LYP/6-311+G** density functional theory modeling that describe the antimicrobial properties of twenty-four triazolothiadiazine compounds against Aspergillus niger, Aspergillus flavus and Penicillium sp., as well as the bacteria Staphylococcus aureus, Bacillus subtilis, Escherichia coli, and Pseudomonas aeruginosa. B3LYP/6-311+G** density functional theory calculations indicated the triazolothiadiazine derivatives possess only modest variation between the frontier orbital properties. Genetic function approximation (GFA) analysis identified the topological and density functional theory derived descriptors for antimicrobial models using a population of 200 models with one to three descriptors that were crossed for 10,000 generations. Two or three descriptor models provided validated predictive models for antifungal and antibiotic properties with R2 values between 0.725 and 0.768 and no outliers. The best models to describe antimicrobial activities include descriptors related to connectivity, electronegativity, polarizability, and van der Waals properties. The reported method provided robust two-dimensional QSAR models with topological and density functional theory descriptors that explain a variety of antifungal and antibiotic activities for structurally related heterocyclic compounds.

M-Polynomial and Degree-Based Molecular Descriptors of Certain Classes of Benzenoid Systems

Benzenoid systems are a notable class of polycyclic aromatic compounds which have applications ranging from household materials to advanced fields like nanotechnology. Hence, the study of their fundamental properties, like observed bioactivities, carcinogenicity, toxicity, and other significant characteristics, have fascinated theoretical chemists for quite a long time. From this perspective, the topological descriptors of these networks, facilitate the prediction of their molecular properties through quantitative structure-activity (QSAR) and structure-property relationships (QSPR) methods. This article focusses on the computation of analytical expressions for nine degree-based topological descriptors using the M-polynomial, for three benzenoid structures: convex benzenoid system, hexabenzocoronene (HBC), and hexa-cata-hexabenzocoronene (cHBC). Besides, the expressions for a few recently developed indices are also calculated using edge-partition techniques. These derived indices are then compared graphically based on their numerical values. This analysis of degree-based descriptors for these structures can lay the groundwork for future researchers to discover and explore new benzenoids and their properties.

UV-light promoted formation of boron nitride-fullerene composite and its photodegradation performance for antibiotics under visible light irradiation

A series of C60/BN composites have been synthesized, which can efficiently photodegrade TC under visible-light irradiation. Compared with C60/BN-D6 and C60/BN-V6 synthesized under dark and visible-light irradiation, C60/BN-U6 synthesized under UV-light irradiation has the largest adsorption and photodegradation performance for TC under visible-light irradiation. FTIR and XPS characterizations suggest that C60/BN composite is most likely the charge transfer composite, in which C60 acts as electron acceptor and BN acts as electron donor. UV-light has the best promotion effect for the formation of C60/BN. The adsorption quantity of TC by C60/BN-U6 is 2.77 times higher than that of BN (131.05 mg g−1 vs. 47.27 mg g−1), being due to that C60/BN-U6 has higher surface area than BN (135.7 m2 g−1 vs. 18.8 m2 g−1). The photodegradation of C60/BN-U6 for TC follows Z-scheme heterojunction mechanism, as well as the photo-induced ·O2- and h+ are the dominant photoactive species. Quantitative structure-activity relationship (QSAR) method is applied to evaluate the toxicity of TC and its photodegradation intermediates. The photodegradation rate of C60/BN-U6 for TC is 19.19 times, 10.06 times, 5.83 times, 2.73 times and 1.84 times higher than that of TiO2 (P25), g-C3N4, BNPA, BCNPA, and BN/TiO2, respectively, implying that C60/BN-U is a good metal-free photocatalyst.

Allelopathic effects of phenolic acids on germination of watermelon(Citrullus lanatus Thunb): Dose-effect relationship and quantitative structure-activity relationship

To determine the allelopathic potential of phenolic acids on watermelon (Citrullus lanatus Thunb), we studied the inhibitory activities of 21 phenolic acids on watermelon seeds germination. The quantitative structure-activity relationship (QSAR) method using the comparative molecular field analysis and comparative molecular similarity index analysis was used to elucidate the relationships between the inhibitory activities and structural characteristics. The results showed that half-maximal inhibitory concentrations (IC50) were in ~µg/mL. The QSAR calculations suggested that the allelopathic inhibitory activities were increased when substituents had large moieties at 1/2/3/4-positions, negative charge at 1/3-position, a H-bond donor at 4-position and a H-bond acceptor at 2-position.

Cysteine focused covalent inhibitors against the main protease of SARS-CoV-2

In viral replication and transcription, the main protease (Mpro) of SARS-CoV-2 plays an important role and appears to be a vital target for drug design. In Mpro, there is a Cys–His catalytic dyad, and ligands that interact with the Cys145 assumed to be an effective approach to inhibit the Mpro. In this study, approximately 1400 cysteine-focused ligands were screened to identify the best candidates that can act as potent inhibitors against Mpro. Our results show that the selected ligands strongly interact with the key Cys145 and His41 residues. Covalent docking was performed for the selected candidates containing the acrylonitrile group, which can form a covalent bond with Cys145. All atoms molecular dynamics (MD) simulation was performed on the selected four inhibitors including L1, L2, L3 and L4 to validate the docking interactions. Our results were also compared with a control ligand, α-ketoamide (11r). Principal component analysis on structural and energy data obtained from the MD trajectories shows that L1, L3, L4 and α-ketoamide (11r) have structural similarity with the apo-form of the Mpro. Quantitative structure-activity relationship method was employed for pattern recognition of the best ligands, which discloses that ligands containing acrylonitrile and amide warheads can show better performance. ADMET analysis displays that our selected candidates appear to be safer inhibitors. Our combined studies suggest that the best cysteine focused ligands can help to design an effective lead drug for COVID-19 treatment. Communicated by Ramaswamy H. Sarma

Mathematical Modeling Approaches for Assessing the Joint Toxicity of Chemical Mixtures Based on Luminescent Bacteria: A Systematic Review.

Developments in industrial applications inevitably accelerate the discharge of enormous substances into the environment, whereas multi-component mixtures commonly cause joint toxicity which is distinct from the simple sum of independent effect. Thus, ecotoxicological assessment, by luminescent bioassays has recently brought increasing attention to overcome the environmental risks. Based on the above viewpoint, this review included a brief introduction to the occurrence and characteristics of toxic bioassay based on the luminescent bacteria. In order to assess the environmental risk of mixtures, a series of models for the prediction of the joint effect of multi-component mixtures have been summarized and discussed in-depth. Among them, Quantitative Structure-Activity Relationship (QSAR) method which was widely applied in silico has been described in detail. Furthermore, the reported potential mechanisms of joint toxicity on the luminescent bacteria were also overviewed, including the Trojan-horse type mechanism, funnel hypothesis, and fishing hypothesis. The future perspectives toward the development and application of toxicity assessment based on luminescent bacteria were proposed.