In silico prediction of chemical-induced hematotoxicity with machine learning and deep learning methods

Hua, Yuqing; Shi, Yinping; Cui, Xueyan; Li, Xiao

doi:10.1007/s11030-021-10255-x

Cited by 23 publications

(16 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model building was performed on the online chemical database and modeling environment (OCHEM), which is a user friendly web-based platform for automatic and simple QSAR modeling ( Sushko et al, 2011 ). OCHEM supports the typical steps of QSAR modeling, and the models can be published and publicly used on the web ( Oprisiu et al, 2013 ; Cui et al, 2019 ; Pawar et al, 2019 ; Cui et al, 2021 ; Hua et al, 2021 ; Huang et al, 2021 ; Ta et al, 2021 ). Among the many state-of-the-art modeling methods available on OCHEM, we applied five widely used traditional machine learning (ML) approaches and five different deep learning (DL) algorithms.…”

Section: Methodsmentioning

confidence: 99%

In Silico Prediction and Insights Into the Structural Basis of Drug Induced Nephrotoxicity

et al. 2022

Self Cite

View full text Add to dashboard Cite

Drug induced nephrotoxicity is a major clinical challenge, and it is always associated with higher costs for the pharmaceutical industry and due to detection during the late stages of drug development. It is desirable for improving the health outcomes for patients to distinguish nephrotoxic structures at an early stage of drug development. In this study, we focused on in silico prediction and insights into the structural basis of drug induced nephrotoxicity, based on reliable data on human nephrotoxicity. We collected 565 diverse chemical structures, including 287 nephrotoxic drugs on humans in the real world, and 278 non-nephrotoxic approved drugs. Several different machine learning and deep learning algorithms were employed for in silico model building. Then, a consensus model was developed based on three best individual models (RFR_QNPR, XGBOOST_QNPR, and CNF). The consensus model performed much better than individual models on internal validation and it achieved prediction accuracy of 86.24% external validation. The results of analysis of molecular properties differences between nephrotoxic and non-nephrotoxic structures indicated that several key molecular properties differ significantly, including molecular weight (MW), molecular polar surface area (MPSA), AlogP, number of hydrogen bond acceptors (nHBA), molecular solubility (LogS), the number of rotatable bonds (nRotB), and the number of aromatic rings (nAR). These molecular properties may be able to play an important part in the identification of nephrotoxic chemicals. Finally, 87 structural alerts for chemical nephrotoxicity were mined with f-score and positive rate analysis of substructures from Klekota-Roth fingerprint (KRFP). These structural alerts can well identify nephrotoxic drug structures in the data set. The in silico models and the structural alerts could be freely accessed via https://ochem.eu/article/140251 and http://www.sapredictor.cn, respectively. We hope the results should provide useful tools for early nephrotoxicity estimation in drug development.

show abstract

Section: Methodsmentioning

confidence: 99%

In Silico Prediction and Insights Into the Structural Basis of Drug Induced Nephrotoxicity

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…To investigate the privileged fragments associated with the DITP toxicity, the IG and frequency analysis substructure of the KRFP were performed to identify SAs. Only the fragments appearing more than six times in the dataset were analyzed [ 53 , 54 ]. The distribution of IG values for each fragment is shown in Figure 6 , where the IG values of all 4860 fragments were from zero to 0.029, and the IG values of most fragments were under 0.001.…”

Section: Resultsmentioning

confidence: 99%

Drug-Induced Immune Thrombocytopenia Toxicity Prediction Based on Machine Learning

et al. 2022

View full text Add to dashboard Cite

Drug-induced immune thrombocytopenia (DITP) often occurs in patients receiving many drug treatments simultaneously. However, clinicians usually fail to accurately distinguish which drugs can be plausible culprits. Despite significant advances in laboratory-based DITP testing, in vitro experimental assays have been expensive and, in certain cases, cannot provide a timely diagnosis to patients. To address these shortcomings, this paper proposes an efficient machine learning-based method for DITP toxicity prediction. A small dataset consisting of 225 molecules was constructed. The molecules were represented by six fingerprints, three descriptors, and their combinations. Seven classical machine learning-based models were examined to determine an optimal model. The results show that the RDMD + PubChem-k-NN model provides the best prediction performance among all the models, achieving an area under the curve of 76.9% and overall accuracy of 75.6% on the external validation set. The application domain (AD) analysis demonstrates the prediction reliability of the RDMD + PubChem-k-NN model. Five structural fragments related to the DITP toxicity are identified through information gain (IG) method along with fragment frequency analysis. Overall, as far as known, it is the first machine learning-based classification model for recognizing chemicals with DITP toxicity and can be used as an efficient tool in drug design and clinical therapy.

show abstract

“…Therefore, 13 fragments could be regarded as SAs for the 12 types of toxicants. Although important fragment analysis can identify SAs for toxicants, they cannot describe the spatial arrangement of these fragments, or it is difficult to recognize the toxicants if multiple types of fragments are found simultaneously in the same compounds. − Once these SAs appear during drug design, careful analysis should be performed.…”

Section: Resultsmentioning

confidence: 99%

Multitask CapsNet: An Imbalanced Data Deep Learning Method for Predicting Toxicants

Wang

Jie

et al. 2021

ACS Omega

View full text Add to dashboard Cite

Drug development has a high failure rate, with safety properties constituting a considerable challenge. To reduce risk, in silico tools, including various machine learning methods, have been applied for toxicity prediction. However, these approaches often confront a serious problem: the training data sets are usually biased (imbalanced positive and negative samples), which would result in model training difficulty and unsatisfactory prediction accuracy. Multitask networks obtained significantly better predictive accuracies than single-task methods, and capsule neural networks showed excellent performance in sparse data sets in previous studies. In this study, we developed a new multitask framework based on a capsule neural network (multitask CapsNet) to measure 12 different toxic effects simultaneously. We found that multitask CapsNet excelled in toxicity prediction and outperformed many other computational approaches using the multitask strategy. Only after training on biased data sets did multitask CapsNet achieve significantly improved prediction accuracy on the Tox21 Data Challenge, which gave the largest ratio of highest accuracy (8/12) among compared models. Our model gave a prediction accuracy of 96.6% for the target NR.PPAR.gamma, whose ratio of negative to positive samples was up to 36:1. These results suggested that multitask CapsNet could overcome the bias problems and would provide a novel, accurate, and efficient approach for predicting the toxicities of compounds.

show abstract

In silico prediction of chemical-induced hematotoxicity with machine learning and deep learning methods

Cited by 23 publications

References 45 publications

In Silico Prediction and Insights Into the Structural Basis of Drug Induced Nephrotoxicity

In Silico Prediction and Insights Into the Structural Basis of Drug Induced Nephrotoxicity

Drug-Induced Immune Thrombocytopenia Toxicity Prediction Based on Machine Learning

Multitask CapsNet: An Imbalanced Data Deep Learning Method for Predicting Toxicants

Contact Info

Product

Resources

About