Amirreza Daghighi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Amirreza Daghighi has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Bakhtiyor Rasulev
Department of Coatings and Polymeric Materials, North Dakota State University, Fargo, ND 58102, USA
7 shared publications - Gerardo Maikel Casañola-Martin
Department of Coatings and Polymeric Materials, North Dakota State University, Fargo, ND 58102, USA
7 shared publications - Kweeni Iduoku
Department of Coatings and Polymeric Materials, North Dakota State University, Fargo, ND 58102, USA
4 shared publications - Marvellous Ngongang
Department of Coatings and Polymeric Materials, North Dakota State University, Fargo, ND 58102, USA
3 shared publications - Estefania Ascencio Medina
Department of Coatings and Polymeric Materials, North Dakota State University, Fargo, ND 58102, USA
2 shared publications - Humberto González-Díaz
IKERBASQUE Basque Foundation for Science 48011 Bilbao Biscay Spain
2 shared publications
Latest Publications
- Open Access
Prediction of Dielectric Constant in Series of Polymers by Quantitative Structure-Property Relationship (QSPR)
This work is devoted to the investigation of dielectric permittivity which is influenced by electronic, ionic, and dipolar polarization mechanisms, contributing to the material’s capacity to store electrical energy. In this study, an extended dataset of 86 polymers was analyzed, and two quantitative structure–property relationship (QSPR) models were developed to predict dielectric permittivity. From an initial set of 1273 descriptors, the most relevant ones were selected using a genetic algorithm, and machine learning models were built using the Gradient Boosting Regressor (GBR). In contrast to Multiple Linear Regression (MLR)- and Partial Least Squares (PLS)-based models, the gradient boosting models excel in handling nonlinear relationships and multicollinearity, iteratively optimizing decision trees to improve accuracy without overfitting. The developed GBR models showed high R2 coefficients of 0.938 and 0.822, for the training and test sets, respectively. An Accumulated Local Effect (ALE) technique was applied to assess the relationship between the selected descriptors—eight for the GB_A model and six for the GB_B model, and their impact on target property. ALE analysis revealed that descriptors such as TDB09m had a strong positive effect on permittivity, while MLOGP2 showed a negative effect. These results highlight the effectiveness of the GBR approach in predicting the dielectric properties of polymers, offering improved accuracy and interpretability.
Open AccessPrediction of Dielectric Constant in Series of Polymers by Quantitative Structure-Property Relationship (QSPR)
This work is devoted to the investigation of dielectric permittivity which is influenced by electronic, ionic, and dipolar polarization mechanisms, contributing to the material’s capacity to store electrical energy. In this study, an extended dataset of 86 polymers was analyzed, and two quantitative structure–property relationship (QSPR) models were developed to predict dielectric permittivity. From an initial set of 1273 descriptors, the most relevant ones were selected using a genetic algorithm, and machine learning models were built using the Gradient Boosting Regressor (GBR). In contrast to Multiple Linear Regression (MLR)- and Partial Least Squares (PLS)-based models, the gradient boosting models excel in handling nonlinear relationships and multicollinearity, iteratively optimizing decision trees to improve accuracy without overfitting. The developed GBR models showed high R2 coefficients of 0.938 and 0.822, for the training and test sets, respectively. An Accumulated Local Effect (ALE) technique was applied to assess the relationship between the selected descriptors—eight for the GB_A model and six for the GB_B model, and their impact on target property. ALE analysis revealed that descriptors such as TDB09m had a strong positive effect on permittivity, while MLOGP2 showed a negative effect. These results highlight the effectiveness of the GBR approach in predicting the dielectric properties of polymers, offering improved accuracy and interpretability.
- Open Access
- 13 August 2024
- Published by MDPI AG in Preprints.org
Prediction of Dielectric Constant in Series of Polymers by Quantitative Structure-Property Relationship (QSPR)
The dielectric constant (ε) reflects the ability of a material to align and orient electrical dipoles within its structure in response to an externally applied electric field; the greater the polarizability of molecules, the greater the value of dielectric constant. In this study a data set of 86 polymers was investigated to develop a structure-property quantitative relations (QSPR) model to predict the dielectric constant in polymers. An initial set of 1273 descriptors was used to select a best set of descriptors and to construct two machine learning models with Gradient Boosting Regressor (GB_A and GB_B). The best performing model (GB_A) with 8 descriptors, exhibited a performance of (R2train) = 0.938 and (R2test) = 0.802. The models were internally validated by 5 folds cross-validation, demonstrating robustness. Additionally, using the Accumulative Local Effect (ALE) technique, we analyzed the relationship between the 8 descriptors involved and the impact of these descriptors to dielectric constant of polymers.
- 13 August 2024
- Published by MDPI AG in Preprints.org
Open AccessPrediction of Dielectric Constant in Series of Polymers by Quantitative Structure-Property Relationship (QSPR)
The dielectric constant (ε) reflects the ability of a material to align and orient electrical dipoles within its structure in response to an externally applied electric field; the greater the polarizability of molecules, the greater the value of dielectric constant. In this study a data set of 86 polymers was investigated to develop a structure-property quantitative relations (QSPR) model to predict the dielectric constant in polymers. An initial set of 1273 descriptors was used to select a best set of descriptors and to construct two machine learning models with Gradient Boosting Regressor (GB_A and GB_B). The best performing model (GB_A) with 8 descriptors, exhibited a performance of (R2train) = 0.938 and (R2test) = 0.802. The models were internally validated by 5 folds cross-validation, demonstrating robustness. Additionally, using the Accumulative Local Effect (ALE) technique, we analyzed the relationship between the 8 descriptors involved and the impact of these descriptors to dielectric constant of polymers.
- Open Access
Phenolic Acid–β-Cyclodextrin Complexation Study to Mask Bitterness in Wheat Bran: A Machine Learning-Based QSAR Study
The need to solvate and encapsulate hydro-sensitive molecules drives noticeable trends in the applications of cyclodextrins in the pharmaceutical industry, in foods, polymers, materials, and in agricultural science. Among them, β-cyclodextrin is one of the most used for the entrapment of phenolic acid compounds to mask the bitterness of wheat bran. In this regard, there is still a need for good data and especially for a robust predictive model that assesses the bitterness masking capabilities of β-cyclodextrin for various phenolic compounds. This study uses a dataset of 20 phenolic acids docked into the β-cyclodextrin cavity to generate three different binding constants. The data from the docking study were combined with topological, topographical, and quantum-chemical features from the ligands in a machine learning-based structure–activity relationship study. Three different models for each binding constant were computed using a combination of the genetic algorithm (GA) and multiple linear regression (MLR) approaches. The developed ML/QSAR models showed a very good performance, with high predictive ability and correlation coefficients of 0.969 and 0.984 for the training and test sets, respectively. The models revealed several factors responsible for binding with cyclodextrin, showing positive contributions toward the binding affinity values, including such features as the presence of six-membered rings in the molecule, branching, electronegativity values, and polar surface area.
Open AccessPhenolic Acid–β-Cyclodextrin Complexation Study to Mask Bitterness in Wheat Bran: A Machine Learning-Based QSAR Study
The need to solvate and encapsulate hydro-sensitive molecules drives noticeable trends in the applications of cyclodextrins in the pharmaceutical industry, in foods, polymers, materials, and in agricultural science. Among them, β-cyclodextrin is one of the most used for the entrapment of phenolic acid compounds to mask the bitterness of wheat bran. In this regard, there is still a need for good data and especially for a robust predictive model that assesses the bitterness masking capabilities of β-cyclodextrin for various phenolic compounds. This study uses a dataset of 20 phenolic acids docked into the β-cyclodextrin cavity to generate three different binding constants. The data from the docking study were combined with topological, topographical, and quantum-chemical features from the ligands in a machine learning-based structure–activity relationship study. Three different models for each binding constant were computed using a combination of the genetic algorithm (GA) and multiple linear regression (MLR) approaches. The developed ML/QSAR models showed a very good performance, with high predictive ability and correlation coefficients of 0.969 and 0.984 for the training and test sets, respectively. The models revealed several factors responsible for binding with cyclodextrin, showing positive contributions toward the binding affinity values, including such features as the presence of six-membered rings in the molecule, branching, electronegativity values, and polar surface area.
- Open Access
- 24 June 2024
- Published by American Chemical Society (ACS) in ChemRxiv
In Silico Prediction of the Biodegradability of Chlorinated Com-pounds: Application of Quantitative Structure-Biodegradability Relationship Approach
Chlorinated compounds are generally known to be non-readily biodegradable. The insight into the structural features that allow chlorinated compounds to readily biodegrade is crucial information that needs to be unveiled. Combined in silico modeling and machine learning approach to predict desirable compound properties has proven to be an effective tool, enabling chemists to save time and resources compared to web lab experimentation. Here we present two machine learning-based quantitative structure – biodegradability relationship (QSBR) models, one for predicting biodegradability values of chlorinated compounds, and the other one for classifying chlorinated compounds as biodegradable or non-biodegradable. The regression models were generated using the Support Vector Regression (SVR) machine learning method. The optimal regression model was a 10 descriptor SVR model with R2 = 0.925 and R2test = 0.881. The optimal classification model was a logistic regression classifier model with 5 descriptors. It has a Matthew’s Correlation Coefficient of 0.59 for training and 0.55 for test, as well as accuracy of 0.79 for training set, 0.77 for test set. For validation purposes the models were tested on an external data set of chlorinated compounds. In addition, models were further applied to an external test set of monomeric units representing polymers to assess the capability of the model to estimate the biodegradability of polymers, where the models showed statistical robustness. The developed SVR model could be used for accurate prediction of biodegradability of various organic molecules, as well as materials based on organic compounds. The analysis of the influence of descriptors on biodegradability is performed. The classification model showed that the biodegradability of chlorinated compounds is heavily correlated with descriptors that relate to electrotopological descriptors, position of oxygen relative to chlorine.
- 24 June 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessIn Silico Prediction of the Biodegradability of Chlorinated Com-pounds: Application of Quantitative Structure-Biodegradability Relationship Approach
Chlorinated compounds are generally known to be non-readily biodegradable. The insight into the structural features that allow chlorinated compounds to readily biodegrade is crucial information that needs to be unveiled. Combined in silico modeling and machine learning approach to predict desirable compound properties has proven to be an effective tool, enabling chemists to save time and resources compared to web lab experimentation. Here we present two machine learning-based quantitative structure – biodegradability relationship (QSBR) models, one for predicting biodegradability values of chlorinated compounds, and the other one for classifying chlorinated compounds as biodegradable or non-biodegradable. The regression models were generated using the Support Vector Regression (SVR) machine learning method. The optimal regression model was a 10 descriptor SVR model with R2 = 0.925 and R2test = 0.881. The optimal classification model was a logistic regression classifier model with 5 descriptors. It has a Matthew’s Correlation Coefficient of 0.59 for training and 0.55 for test, as well as accuracy of 0.79 for training set, 0.77 for test set. For validation purposes the models were tested on an external data set of chlorinated compounds. In addition, models were further applied to an external test set of monomeric units representing polymers to assess the capability of the model to estimate the biodegradability of polymers, where the models showed statistical robustness. The developed SVR model could be used for accurate prediction of biodegradability of various organic molecules, as well as materials based on organic compounds. The analysis of the influence of descriptors on biodegradability is performed. The classification model showed that the biodegradability of chlorinated compounds is heavily correlated with descriptors that relate to electrotopological descriptors, position of oxygen relative to chlorine.
- Open Access
- 6 June 2024
- Published by MDPI AG in Preprints.org
Phenolic Acid – β-cyclodextrin Complexation Study to Mask Bitterness in Wheat Bran: A Machine-Learning-based QSAR Study
The need for solvating and encapsulating hydro-sensitive molecules drives noticeable trends in the applications of cyclodextrins in pharmaceutical industry, food, polymer, materials, and agricultural science. Among them, β-cyclodextrin is one of the most used for the entrapment of phenolic acid compounds to mask the bitterness of wheat bran. In this regard, there is still a need for a good predictive model that assesses β-cyclodextrin bitterness masking capabilities for various phenolic compounds. This study uses a dataset of 20 phenolic acids docked to the β-cyclodextrin cavity to generate three different binding constants. The data from docking study were combined with topological, topographical and quantum-chemical features from the ligands in a machine learning-based structure-activity relationship study. Three different models for each binding constant were computed using a combination of Genetic Algorithm (GA) and Multiple Linear Regression (MLR) approaches. The developed ML/QSAR models showed a very good performance, with high predictive ability and correlation coefficients of 0.969 and 0.984, for training and test sets, respectively. The models revealed several factors responsible for a binding with cyclodextrin, showing positive contributions toward the binding affinity values, including such features as presence of six-membered rings in the molecule, branching, electronegativity values, and polar surface area.
- 6 June 2024
- Published by MDPI AG in Preprints.org
Open AccessPhenolic Acid – β-cyclodextrin Complexation Study to Mask Bitterness in Wheat Bran: A Machine-Learning-based QSAR Study
The need for solvating and encapsulating hydro-sensitive molecules drives noticeable trends in the applications of cyclodextrins in pharmaceutical industry, food, polymer, materials, and agricultural science. Among them, β-cyclodextrin is one of the most used for the entrapment of phenolic acid compounds to mask the bitterness of wheat bran. In this regard, there is still a need for a good predictive model that assesses β-cyclodextrin bitterness masking capabilities for various phenolic compounds. This study uses a dataset of 20 phenolic acids docked to the β-cyclodextrin cavity to generate three different binding constants. The data from docking study were combined with topological, topographical and quantum-chemical features from the ligands in a machine learning-based structure-activity relationship study. Three different models for each binding constant were computed using a combination of Genetic Algorithm (GA) and Multiple Linear Regression (MLR) approaches. The developed ML/QSAR models showed a very good performance, with high predictive ability and correlation coefficients of 0.969 and 0.984, for training and test sets, respectively. The models revealed several factors responsible for a binding with cyclodextrin, showing positive contributions toward the binding affinity values, including such features as presence of six-membered rings in the molecule, branching, electronegativity values, and polar surface area.
- Open Access
- 13 May 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Development of QSAR Models on the Fouling-Release Performance of Silicone Oil-modified Siloxane Polyurethane Coatings
Polymer coatings with a fouling release activity is an effective method to prevent marine biological fouling caused by large number of marine organisms (over 4000) and ensure stability and safety of marine facilities. In this study, a novel cheminformatics-based approach was employed to investigate the fouling-release performance of siloxane-PU coating system. The structure-fouling release activity relationship was modeled for a set of 18 siloxane PU coatings by incorporation phenylmethyl silicones oils (PMM-1025, PMM-1043, PMM-5021, PMM-6025, PMM-0021, PMM-0025 of 1, 2 and 5 wt%). A specific structural descriptors encoding approach was applied for these systems, based on a mixture-based encoding, to feed the complex polymeric systems in machine learning algorithms. Several predictive quantitative structure-fouling release relationships models were developed using machine learning techniques, from multiple linear regression to nonlinear random forest methods, followed by scoring them based on high performance accuracy and validation with rigorous internal fit R2 train values between 0.73 to 0.95 and external predictivity R2ext between 0.68 to 0.88. Random Forest method was the best nonlinear one for predicting diatom removal activity. This work indicates that both linear and nonlinear machine learning-based modeling can be beneficial to predict fouling release properties of polymer coatings with an effective fouling release performance.
- 13 May 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessDevelopment of QSAR Models on the Fouling-Release Performance of Silicone Oil-modified Siloxane Polyurethane Coatings
Polymer coatings with a fouling release activity is an effective method to prevent marine biological fouling caused by large number of marine organisms (over 4000) and ensure stability and safety of marine facilities. In this study, a novel cheminformatics-based approach was employed to investigate the fouling-release performance of siloxane-PU coating system. The structure-fouling release activity relationship was modeled for a set of 18 siloxane PU coatings by incorporation phenylmethyl silicones oils (PMM-1025, PMM-1043, PMM-5021, PMM-6025, PMM-0021, PMM-0025 of 1, 2 and 5 wt%). A specific structural descriptors encoding approach was applied for these systems, based on a mixture-based encoding, to feed the complex polymeric systems in machine learning algorithms. Several predictive quantitative structure-fouling release relationships models were developed using machine learning techniques, from multiple linear regression to nonlinear random forest methods, followed by scoring them based on high performance accuracy and validation with rigorous internal fit R2 train values between 0.73 to 0.95 and external predictivity R2ext between 0.68 to 0.88. Random Forest method was the best nonlinear one for predicting diatom removal activity. This work indicates that both linear and nonlinear machine learning-based modeling can be beneficial to predict fouling release properties of polymer coatings with an effective fouling release performance.
- Open Access
A Novel Machine-Learning Framework Based on a Hierarchy of Dispute Models for the Identification of Fish Species Using Multi-Mode Spectroscopy
Seafood mislabeling rates of approximately 20% have been reported globally. Traditional methods for fish species identification, such as DNA analysis and polymerase chain reaction (PCR), are expensive and time-consuming, and require skilled technicians and specialized equipment. The combination of spectroscopy and machine learning presents a promising approach to overcome these challenges. In our study, we took a comprehensive approach by considering a total of 43 different fish species and employing three modes of spectroscopy: fluorescence (Fluor), and reflectance in the visible near-infrared (VNIR) and short-wave near-infrared (SWIR). To achieve higher accuracies, we developed a novel machine-learning framework, where groups of similar fish types were identified and specialized classifiers were trained for each group. The incorporation of global (single artificial intelligence for all species) and dispute classification models created a hierarchical decision process, yielding higher performances. For Fluor, VNIR, and SWIR, accuracies increased from 80%, 75%, and 49% to 83%, 81%, and 58%, respectively. Furthermore, certain species witnessed remarkable performance enhancements of up to 40% in single-mode identification. The fusion of all three spectroscopic modes further boosted the performance of the best single mode, averaged over all species, by 9%. Fish species mislabeling not only poses health-related risks due to contaminants, toxins, and allergens that could be life-threatening, but also gives rise to economic and environmental hazards and loss of nutritional benefits. Our proposed method can detect fish fraud as a real-time alternative to DNA barcoding and other standard methods. The hierarchical system of dispute models proposed in this work is a novel machine-learning tool not limited to this application, and can improve accuracy in any classification problem which contains a large number of classes.
Open AccessA Novel Machine-Learning Framework Based on a Hierarchy of Dispute Models for the Identification of Fish Species Using Multi-Mode Spectroscopy
Seafood mislabeling rates of approximately 20% have been reported globally. Traditional methods for fish species identification, such as DNA analysis and polymerase chain reaction (PCR), are expensive and time-consuming, and require skilled technicians and specialized equipment. The combination of spectroscopy and machine learning presents a promising approach to overcome these challenges. In our study, we took a comprehensive approach by considering a total of 43 different fish species and employing three modes of spectroscopy: fluorescence (Fluor), and reflectance in the visible near-infrared (VNIR) and short-wave near-infrared (SWIR). To achieve higher accuracies, we developed a novel machine-learning framework, where groups of similar fish types were identified and specialized classifiers were trained for each group. The incorporation of global (single artificial intelligence for all species) and dispute classification models created a hierarchical decision process, yielding higher performances. For Fluor, VNIR, and SWIR, accuracies increased from 80%, 75%, and 49% to 83%, 81%, and 58%, respectively. Furthermore, certain species witnessed remarkable performance enhancements of up to 40% in single-mode identification. The fusion of all three spectroscopic modes further boosted the performance of the best single mode, averaged over all species, by 9%. Fish species mislabeling not only poses health-related risks due to contaminants, toxins, and allergens that could be life-threatening, but also gives rise to economic and environmental hazards and loss of nutritional benefits. Our proposed method can detect fish fraud as a real-time alternative to DNA barcoding and other standard methods. The hierarchical system of dispute models proposed in this work is a novel machine-learning tool not limited to this application, and can improve accuracy in any classification problem which contains a large number of classes.
- Open Access
In Silico Prediction of the Toxicity of Nitroaromatic Compounds: Application of Ensemble Learning QSAR Approach
In this work, a dataset of more than 200 nitroaromatic compounds is used to develop Quantitative Structure–Activity Relationship (QSAR) models for the estimation of in vivo toxicity based on 50% lethal dose to rats (LD50). An initial set of 4885 molecular descriptors was generated and applied to build Support Vector Regression (SVR) models. The best two SVR models, SVR_A and SVR_B, were selected to build an Ensemble Model by means of Multiple Linear Regression (MLR). The obtained Ensemble Model showed improved performance over the base SVR models in the training set (R2 = 0.88), validation set (R2 = 0.95), and true external test set (R2 = 0.92). The models were also internally validated by 5-fold cross-validation and Y-scrambling experiments, showing that the models have high levels of goodness-of-fit, robustness and predictivity. The contribution of descriptors to the toxicity in the models was assessed using the Accumulated Local Effect (ALE) technique. The proposed approach provides an important tool to assess toxicity of nitroaromatic compounds, based on the ensemble QSAR model and the structural relationship to toxicity by analyzed contribution of the involved descriptors.
Open AccessIn Silico Prediction of the Toxicity of Nitroaromatic Compounds: Application of Ensemble Learning QSAR Approach
In this work, a dataset of more than 200 nitroaromatic compounds is used to develop Quantitative Structure–Activity Relationship (QSAR) models for the estimation of in vivo toxicity based on 50% lethal dose to rats (LD50). An initial set of 4885 molecular descriptors was generated and applied to build Support Vector Regression (SVR) models. The best two SVR models, SVR_A and SVR_B, were selected to build an Ensemble Model by means of Multiple Linear Regression (MLR). The obtained Ensemble Model showed improved performance over the base SVR models in the training set (R2 = 0.88), validation set (R2 = 0.95), and true external test set (R2 = 0.92). The models were also internally validated by 5-fold cross-validation and Y-scrambling experiments, showing that the models have high levels of goodness-of-fit, robustness and predictivity. The contribution of descriptors to the toxicity in the models was assessed using the Accumulated Local Effect (ALE) technique. The proposed approach provides an important tool to assess toxicity of nitroaromatic compounds, based on the ensemble QSAR model and the structural relationship to toxicity by analyzed contribution of the involved descriptors.