Predicting Environmental Chemical Toxicity using a New Hybrid Deep Machine Learning Method

Limbu, Sarita; Zakka, Cyril; Dakshanamurthy, Sivanesan

doi:10.26434/chemrxiv.13726258.v2

Cited by 3 publications

(13 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the HNN models, we used the modified version of the 3D array representation of 1D SMILES to use it in the convolutional neural network (CNN) from our previous model 17 . The SMILES processing method here included a vocabulary of 94 characters in the ASCII table not to miss any possible characters of SMILES in any format.…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…To determine the chemical carcinogenicity, we have developed carcinogenicity prediction models based on the hybrid neural network (HNN) architecture that we reported previously for toxicity prediction 17 . In this study, we used the modified version of the 3D array representation of 1D SMILES to use it in the convolutional neural network (CNN) model 17 . Other machine learning methods used were Random Forest (RF), Bootstrap Aggregating (Bagging) and Adaptive Boosting (AdaBoost) for binary classification and multiclass classification.…”

Section: Introductionmentioning

confidence: 99%

“…Tokenizer class in python is used to encode the SMILES string. The SMILES preprocessing method that we used while predicting toxicity17 created the index for the set of unique characters of SMILES from the training set only. Here, we have created unique index for 94 characters in the ASCII table so that there is no possibility of missing out creating index of any character in the SMILES string represented in any format.…”

mentioning

confidence: 99%

“…As the length of the SMILES vary depending on the length and properties of the compound, the length of the encoding results also varies. The resulting vector for the SMILES of every input compound is thus padded with 0s or truncated so that they are of uniform length, L. The SMILES for the input compounds are converted to a 2-D matrix of size K x L where K is the number of input SMILES and L = 325 is the allowed maximum length of the SMILES string used in the model.Our previous method17 mapped the SMILES for the K number of chemicals to a one-hot encoded matrix of size KxLxM where M is the number of the possible characters in the SMILES.Machine Learning ModelsHybrid Neural Network ModelHybrid Neural Network (HNN) model17 that we developed for chemical toxicity prediction was used here by modifying the SMILES vectorization method and then the method by which the vectorized SMILES input is processed by Convolutional Neural Network (CNN) of the model. The model is developed in python using the Keras API with Tensorflow in the backend.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Predicting Environmental Chemical Carcinogenicity using a Hybrid Machine-Learning Approach

Limbu

Dakshanamurthy

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Determining environmental chemical carcinogenicity is an urgent need as humans are increasingly exposed to these chemicals. In this study, we determined the carcinogenicity of wide variety real-life exposure chemicals in large scale. To determine chemical carcinogenicity, we have developed carcinogenicity prediction models based on the hybrid neural network (HNN) architecture. In the HNN model, we included new SMILES feature representation method, by modifying our previous 3D array representation of 1D SMILES simulated by the convolutional neural network (CNN). We used 653 molecular descriptors modeled by feed forward neural network (FFNN), and SMILES as chemical features to train the models. We have developed three types of machine learning models: binary classification models to predict chemical is a carcinogenic or non-carcinogenic, multiclass classification models to predict severity of the chemical carcinogenicity, and regression models to predict median toxic dose of the chemicals. Along with the hybrid neural network (HNN) model that we developed, Random Forest (RF), Bootstrap Aggregating (Bagging) and Adaptive Boosting (AdaBoost) methods were also used for binary and multiclass classification. Regression models were developed using HNN, RF, Support Vector Regressor (SVR), Gradient Boosting (GB), Kernel Ridge (KR), Decision Tree with AdaBoost (DT), KNeighbors (KN), and a consensus method. For binary classification, our HNN model predicted with an average accuracy of 74.33% and an average AUC of 0.806, for multiclass classification, the HNN model predicted with an average accuracy of 50.58% and an average micro-AUC of 0.68, and for regression model, the consensus method achieved R2 of 0.40. The predictive performance of our models based on a highly diverse chemicals is comparable to the literature reported models that included the similar and less diverse molecules. Our models can be used in identifying the potentially carcinogenic chemicals for a wide variety of chemical classes

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Predicting Environmental Chemical Carcinogenicity using a Hybrid Machine-Learning Approach

Limbu

Dakshanamurthy

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives

Tran

Wibowo

Tayara

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Toxicity prediction is a critical step in the drug discovery process that helps identify and prioritize compounds with the greatest potential for safe and effective use in humans, while also reducing the risk of costly late-stage failures. It is estimated that over 30% of drug candidates are discarded owing to toxicity. Recently, artificial intelligence (AI) has been used to improve drug toxicity prediction as it provides more accurate and efficient methods for identifying the potentially toxic effects of new compounds before they are tested in human clinical trials, thus saving time and money. In this review, we present an overview of recent advances in AI-based drug toxicity prediction, including the use of various machine learning algorithms and deep learning architectures, of six major toxicity properties and Tox21 assay end points. Additionally, we provide a list of public data sources and useful toxicity prediction tools for the research community and highlight the challenges that must be addressed to enhance model performance. Finally, we discuss future perspectives for AI-based drug toxicity prediction. This review can aid researchers in understanding toxicity prediction and pave the way for new methods of drug discovery.

show abstract

Predicting Chemical Carcinogens Using a Hybrid Neural Network Deep Learning Method

Limbu

Dakshanamurthy

2022

Sensors

Self Cite

View full text Add to dashboard Cite

Determining environmental chemical carcinogenicity is urgently needed as humans are increasingly exposed to these chemicals. In this study, we developed a hybrid neural network (HNN) method called HNN-Cancer to predict potential carcinogens of real-life chemicals. The HNN-Cancer included a new SMILES feature representation method by modifying our previous 3D array representation of 1D SMILES simulated by the convolutional neural network (CNN). We developed binary classification, multiclass classification, and regression models based on diverse non-congeneric chemicals. Along with the HNN-Cancer model, we developed models based on the random forest (RF), bootstrap aggregating (Bagging), and adaptive boosting (AdaBoost) methods for binary and multiclass classification. We developed regression models using HNN-Cancer, RF, support vector regressor (SVR), gradient boosting (GB), kernel ridge (KR), decision tree with AdaBoost (DT), KNeighbors (KN), and a consensus method. The performance of the models for all classifications was assessed using various statistical metrics. The accuracy of the HNN-Cancer, RF, and Bagging models were 74%, and their AUC was ~0.81 for binary classification models developed with 7994 chemicals. The sensitivity was 79.5% and the specificity was 67.3% for the HNN-Cancer, which outperforms the other methods. In the case of multiclass classification models with 1618 chemicals, we obtained the optimal accuracy of 70% with an AUC 0.7 for HNN-Cancer, RF, Bagging, and AdaBoost, respectively. In the case of regression models, the correlation coefficient (R) was around 0.62 for HNN-Cancer and RF higher than the SVM, GB, KR, DTBoost, and NN machine learning methods. Overall, the HNN-Cancer performed better for the majority of the known carcinogen experimental datasets. Further, the predictive performance of HNN-Cancer on diverse chemicals is comparable to the literature-reported models that included similar and less diverse molecules. Our HNN-Cancer could be used in identifying potentially carcinogenic chemicals for a wide variety of chemical classes.

show abstract

Predicting Environmental Chemical Toxicity using a New Hybrid Deep Machine Learning Method

Cited by 3 publications

References 21 publications

Predicting Environmental Chemical Carcinogenicity using a Hybrid Machine-Learning Approach

Predicting Environmental Chemical Carcinogenicity using a Hybrid Machine-Learning Approach

Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives

Predicting Chemical Carcinogens Using a Hybrid Neural Network Deep Learning Method

Contact Info

Product

Resources

About