• Korean Chemical Engineering Research
• /
• v.61 no.4
• /
• pp.523-541
• /
• 2023

As accessibility to 3D printers increases, there is a growing frequency of exposure to chemicals associated with 3D printing. However, research on the toxicity and harmfulness of chemicals generated by 3D printing is insufficient, and the performance of toxicity prediction using in silico techniques is limited due to missing molecular structure data. In this study, quantitative structure-activity relationship (QSAR) model based on data-centric AI approach was developed to predict the toxicity of new 3D printing materials by imputing missing values in molecular descriptors. First, MissForest algorithm was utilized to impute missing values in molecular descriptors of hazardous 3D printing materials. Then, based on four different machine learning models (decision tree, random forest, XGBoost, SVM), a machine learning (ML)-based QSAR model was developed to predict the bioconcentration factor (Log BCF), octanol-air partition coefficient (Log Koa), and partition coefficient (Log P). Furthermore, the reliability of the data-centric QSAR model was validated through the Tree-SHAP (SHapley Additive exPlanations) method, which is one of explainable artificial intelligence (XAI) techniques. The proposed imputation method based on the MissForest enlarged approximately 2.5 times more molecular structure data compared to the existing data. Based on the imputed dataset of molecular descriptor, the developed data-centric QSAR model achieved approximately 73%, 76% and 92% of prediction performance for Log BCF, Log Koa, and Log P, respectively. Lastly, Tree-SHAP analysis demonstrated that the data-centric-based QSAR model achieved high prediction performance for toxicity information by identifying key molecular descriptors highly correlated with toxicity indices. Therefore, the proposed QSAR model based on the data-centric XAI approach can be extended to predict the toxicity of potential pollutants in emerging printing chemicals, chemical process, semiconductor or display process.

• Applied Biological Chemistry
• /
• v.50 no.3
• /
• pp.147-153
• /
• 2007

To search for a molecular design of a new breast cancerous inhibitory active compound, 2D-QSAR and HQSAR between the substituents of flavopiridol analogues as substrates and their breast cancerous inhibitory activities against MCF-7 cell were analyzed and discussed quantitatively. It was found that the dispersion with molecule and steric hindrance with substituents will have a tremendous impact on the inhibitory activities from the 2D-QSAR model (1). Also, MR constant is better than that of MS constant as animportant factor. The inhibitory activities from 2D-QSAR model (2) were dependent upon the optimum MR constant (MR = 126 $Cm^3/mol$). Optimized HQSAR model (V) exhibited the best predictability of the inhibitory activities based on the cross-validated $r^2_{cv}$($q^2$= 0.583) and non-cross-validated conventional coefficient ($r^2_{ncv}$= 0.982). From the contribution maps, the inhibitory activity by the imino group on $C_9$ atom was higher than that of the hydroxyl group of $C_8$ atom on the A ring in molecule. Therefore, we can confirm that the dispersion by substituents in molecule is the most important factor in inhibitory activities against MCF-7 cell.

• KSBB Journal
• /
• v.15 no.3
• /
• pp.299-306
• /
• 2000

Concern for the effects of toxic chemicals on the environment leads the search for better bioassay test organisms and test procedures. Photobacterium phosphoreum was used successfully as a test organism and the luminometer detection technique was an effective and simple method for determining the concentration of toxic chemicals. With EC50 a total of 14 chlorine substituted phenols benzenes and ethanes were used for the experiments. The test results showed that the toxicity to P. phosphoreum increased in the order of phenol > benzene > ethane and the toxicity also increased with the number of chlorine substitution. Quantitative structure activity relationship (QSARO) model can be used to predict EC50 to save time and endeavor. Correlation was well established with the QSAR parameters such as log P, log S and solvatochromic parameter(Vi/100 $\pi$, ${\beta}$m and am). The QSAR modeling was used with multi-regression analysis and mono-regression analysis. These analyses resulted in the following QSAR : $log EC_{50} =2.48 + 0.914 log S(n=9 R2=85.5% RE=0.378) log EC_{50}=0.35 - 4.48 Vi/100 + 2.84 \pi^* +9.46{\beta}m-4.48am (n =14 R2=98.2% RE=0.012) log EC_{50} =2.64 -1.66 log P(n=5, R2=98.8% RE=0.16) log EC_{50}=3.44 -1.09 log P(n=9 R2= 80.8% Re=0.207)$

• The Korean Journal of Pesticide Science
• /
• v.6 no.4
• /
• pp.231-243
• /
• 2002

Starting with linear free energy relationships (LFER), drug design to mimic of the activated complexes at transition state, and hydrolysis mechanisms to control the potency and residual properties of pesticides were introduced and summarized for the necessity. In order to understand the searching or development of new agrochemicals by two dimensional quantitative structure-activity relationship (2D QSAR) methodology, a series of the various descriptors, steric constants, electronic constants including quantum pharmacological parameters and hydrophobic constants were classified and discussed for results of the several studied cases. In addition, the processes of development of new agrochemicals by QSAR techniques were introduced simply.

• Reproductive and Developmental Biology
• /
• v.33 no.3
• /
• pp.119-123
• /
• 2009

The two dimensional quantitative structure-activity relationships (2D-QSARs) models concerning the binding affinity constants ($p[Od.]_{50}$) between 2-cyclohexyltetrahydropyrane and 2-cyclohexyltetrahydrofurane analogues as substrates, and bovine odorant binding protein (bOBP) as receptor were derived by multiple regression analyses method and discussed. The statistical quality of the optimized 2D-QSAR model (5) was good (r=0.907). From the model, the binding affinity constants ($p[Od.]_{50}$) were dependent upon the optimal value ($(TL)_{opt.}$=2.737) of total lipole (TL) of substrate molecules. Based on these findings, the high active compounds predicted by optimized 2D-QSAR model (5) were 2-(dimethylcyclohexyl)tetrahydropyrane molecule and their isomer molecules. The binding affinity constants regarding bOBP of the tetrahydrofuryl-2-yl family compounds were dependent upon the hydrophobicity (logP) of whole substrate molecules. In any case of porcine odorant-binding proteins (pOBP), the constants were dependent upon the hydrophobicity (${\pi}x={\log}P_X-{\log}P_H$) of substituents (R) in substrate molecules. Also, from the optimal values of hydrophobic constant, the hydrophobicity for bOBP influenced ca. twice time bigger (bOBP>pOBP) than that for pOBP.

• Proceedings of the PSK Conference
• /
• 2003.04a
• /
• pp.249.2-250
• /
• 2003

3D-QSAR analyses by CoMFA and CoMSIA were conducted on a series of thiazole and triazole analogues with respect to their antifungal activities against Microsporum gypseum. A total of twenty analogues were used for the derivation of the 3D-QSAR models (training set). Thesuperposition of the compounds was performed by applying the FlexS with shape-based screening method. (omitted)

• 한국생물공학회:학술대회논문집
• /
• 2000.11a
• /
• pp.479-479
• /
• 2000

• Journal of the Korean Chemical Society
• /
• v.57 no.1
• /
• pp.99-103
• /
• 2013

The present communication deals with the Pharmacophore modeling, 3D QSAR and docking analysis on series of Pyrimidine derivatives as potential calcium channel blockers. The computational studies showed hydrogen bond donor, hydrogen bond acceptor, and hydrophobic group are important features for calcium channel blocking activity. These studies showed that Pyrimidine scaffold can be utilized for designing of novel calcium channels blockers for CVS disorders.

• Bulletin of the Korean Chemical Society
• /
• v.22 no.4
• /
• pp.388-394
• /
• 2001

Quantitative Structure-Activity Relationship (QSAR) have been established of 57 fluorovinyloxyacetamides compounds to correlate and predict EC50 values. Genetic algorithm (GA) and multiple linear regression analysis were used to select the descriptors and to generate the equations that relate the structural features to the biological activities. This equation consists of three descriptors calculated from the molecular structures with molecular mechanics and quantum-chemical methods. The results of MLR and GA show that dipole moment of z-axis, radius of gyration and logP play an important role in growth inhibition of barnyard grass.

• Food Science and Biotechnology
• /
• v.17 no.3
• /
• pp.501-507
• /
• 2008

The quantitative structure-activity relationships (QSAR) study of antioxidative anthocyanidins and their glycosides were evaluated using 4 different assays of Trolox equivalent antioxidant capacity (TEAC), superoxide radical ($O_2^{{\cdot}-}$), hydrogen peroxide ($H_2O_2$), and peroxynitrite radical ($ONOO^-$) scavenging with TSAR software. Four models were developed with significant predictive values ($r^2$ and p value), which indicated that the antioxidant activities were mainly governed by the 3-dimensional structural energy (torsional energy), constitutional properties (the number of hydroxyl and methyl groups), and electrostatic properties (heat of formation, and dipole, quadrupole, and octupole components). This QSAR approach could contribute to a better understanding of structural properties of anthocyanidins and their glycosides that are responsible for their antioxidant activities. It might also be useful in predicting the antioxidant activities of other anthocyanins.