Application of Bayesian networks in determining nanoparticle-induced cellular outcomes using transcriptomics

Abstract

Inroads have been made in our understanding of the risks posed to human health and the environment by nanoparticles (NPs) but this area requires continuous research and monitoring. Machine learning techniques have been applied to nanotoxicology with very encouraging results. This study deals with bridging physicochemical properties of NPs, experimental exposure conditions and in vitro characteristics with biological effects of NPs on a molecular cellular level from transcriptomics studies. The bridging is done by developing and implementing Bayesian Networks (BNs) with or without data preprocessing. The BN structures are derived either automatically or methodologically and compared. Early stage nanotoxicity measurements represent a challenge, not least when attempting to predict adverse outcomes and modeling is critical to understanding the biological effects of exposure to NPs. The preprocessed data-driven BN showed improved performance over automatically structured BN and the BN with unprocessed datasets. The prestructured BN captures inter relationships between NP properties, exposure condition and in vitro characteristics and links those with cellular effects based on statistic correlation findings. Information gain analysis showed that exposure dose, NP and cell line variables were the most influential attributes in predicting the biological effects. The BN methodology proposed in this study successfully predicts a number of toxicologically relevant cellular disrupted biological processes such as cell cycle and proliferation pathways, cell adhesion and extracellular matrix responses, DNA damage and repair mechanisms etc., with a success rate >80%. The model validation from independent data shows a robust and promising methodology for incorporating transcriptomics outcomes in a hazard and, by extension, risk assessment modeling framework by predicting affected cellular functions from experimental conditions.

Practices and Trends of Machine Learning Application in Nanotoxicology

“…Furthermore, 8% of the studies mention that their dataset had equal outcome classes, while, on the other hand, 4% of studies tackled the imbalance issue by resampling the training dataset. Resampling can be done by applying the Synthetic Minority Oversampling Technique (SMOTE), which is a supervised instance algorithm that oversamples the minority instances using the k-nearest-neighbor (kNN) [60,67,77]. This method balances the dataset by generating more data points.…”

“…Different models that use measured p-chem properties and experimental data, including biological data, exploit all the features since those properties are nano-specific [60,77]. QSAR-perturbation models, in addition to classical QSARs, make use of all available descriptors by generating several pairs of variables using the moving average approach [122,125].…”

“…MCC is equivalent to the Pearson Correlation Coefficient for binary variables [147] and has been selected as an evaluation metric for micro-array-based predictive models by the MicroArray Quality Control (MAQC) Consortium [148]. From the gathered studies, only six used MCC as a performance metric [77,118,121,122,124,126]. Table 10 presents the studies that, in compliance with OECD principles, applied measures of robustness and predictivity validation, and estimated the applicability domain.…”

“…Bayes can be restructured as new scientific data becomes available and contemporary research grows, which enhances underlying assumptions in the construction of the initial model [77]. BNs provide the capacity to merge different common (i.e., experimental data) and non-traditional (i.e., expert judgment, simulated data) knowledge bases into the BN parameterization process.…”

Predicting In Vitro Neurotoxicity Induced by Nanoparticles Using Machine Learning

“…ML does not require deterministic insights; bypassing in depth comprehension of the interactions within a system, it constructs a computational predictor bridging input data directly to the outcome. Furthermore, those tools are fast and cheap, and as they rely on information inputs rather than physical test materials, can be used to predict the impact of materials not yet synthesized, thereby contributing to safe-by-design approaches [20].…”