Accurate and interpretable nanoSAR models from genetic programming-based decision tree construction approaches

Converting Nanotoxicity Data to Information Using Artificial Intelligence and Simulation

Decades of nanotoxicology research have generated extensive and diverse data sets. However, data is not equal to information. The question is how to extract critical information buried in vast data streams. Here we show that artificial intelligence (AI) and molecular simulation play key roles in transforming nanotoxicity data into critical information, i.e., constructing the quantitative nanostructure (physicochemical properties)-toxicity relationships, and elucidating the toxicity-related molecular mechanisms. For AI and molecular simulation to realize their full impacts in this mission, several obstacles must be overcome. These include the paucity of high-quality nanomaterials (NMs) and standardized nanotoxicity data, the lack of model-friendly databases, the scarcity of specific and universal nanodescriptors, and the inability to simulate NMs at realistic spatial and temporal scales. This review provides a comprehensive and representative, but not exhaustive, summary of the current capability gaps and tools required to fill these formidable gaps. Specifically, we discuss the applications of AI and molecular simulation, which can address the large-scale data challenge for nanotoxicology research. The need for model-friendly nanotoxicity databases, powerful nanodescriptors, new modeling approaches, molecular mechanism analysis, and design of the next-generation NMs are also critically discussed. Finally, we provide a perspective on future trends and challenges.

Using Machine Learning to make nanomaterials sustainable

Sustainable development is a key challenge for contemporary human societies; failure to achieve sustainability could threaten human survival. In this review article, we illustrate how Machine Learning (ML) could support more sustainable development, covering the basics of data gathering through each step of the Environmental Risk Assessment (ERA). The literature provides several examples showing how ML can be employed in most steps of a typical ERA.A key observation is that there are currently no clear guidance for using such autonomous technologies in ERAs or which standards/checks are required. Steering thus seems to be the most important task for supporting the use of ML in the ERA of nano- and smart-materials. Resources should be devoted to developing a strategy for implementing ML in ERA with a strong emphasis on data foundations, methodologies, and the related sensitivities/uncertainties. We should recognise historical errors and biases (e.g., in data) to avoid embedding them during ML programming.

Could artificial intelligence revolutionize the development of nanovectors for gene therapy and mRNA vaccines?

Gene therapy enables the introduction of nucleic acids like DNA and RNA into host cells, and is expected to revolutionize the treatment of a wide range of diseases. This growth has been further accelerated by the discovery of CRISPR/Cas technology, which allows accurate genomic editing in a broad range of cells and organisms in vitro and in vivo. Despite many advances in gene delivery and the development of various viral and non-viral gene delivery vectors, the lack of highly efficient non-viral systems with low cellular toxicity remains a challenge. The application of cutting-edge technologies such as artificial intelligence (AI) has great potential to find new paradigms to solve this issue. Herein, we review AI and its major subfields including machine learning (ML), neural networks (NNs), expert systems, deep learning (DL), computer vision and robotics. We discuss the potential of AI-based models and algorithms in the design of targeted gene delivery vehicles capable of crossing extracellular and intracellular barriers by viral mimicry strategies. We finally discuss the role of AI in improving the function of CRISPR/Cas systems, developing novel nanobots, and mRNA vaccine carriers.

Versatile in silico modelling of microplastics adsorption capacity in aqueous environment based on molecular descriptor and machine learning

To comprehensively evaluate the hazards of microplastics and their coexisting organic pollutants, the sorption capacity of microplastics is a major issue that is quantified through the microplastic-aqueous sorption coefficient (K_d). Almost all quantitative structure-property relationship (QSPR) models that describe K_d apply only to narrow, relatively homogeneous groups of reactants. Herein, non-hybrid QSPR-based models were developed to predict PE-water (K_PE-w), PE-seawater (K_PE-sw), PVC-water (K_PVC-w) and PP-seawater (K_PP-sw) sorption coefficients at different temperatures, with eight machine learning algorithms. Moreover, novel hybrid intelligent models for predicting K_d more accurately were innovatively developed by applying GA, PSO and AdaBoost algorithms to optimize MLP and ELM models. The results indicated that all three optimization algorithms could improve the robustness and predictability of the standalone MLP and ELM models. In all models trained with K_PE-w, K_PE-sw, K_PVC-w and K_PP-sw data sets, GBDT-1 and XGBoost-1 models, MLP-GA-2 and MLP-PSO-2 models, MLR-3 and MLR-4 models performed better in terms of goodness of fit (R_adj²: 0.907-0.999), robustness (Q_BOOT²: 0.900-0.937) and predictability (R_ext²: 0.889-0.970), respectively. Analyzing the descriptors revealed that temperature, lipophilicity, ionization potential and molecular size were correlated closely with the adsorption capacity of microplastics to organic pollutants. The proposed QSPR models may assist in initial environmental exposure assessments without imposing heavy costs in the early experimental phase.

Nanoparticle-protein corona complex: understanding multiple interactions between environmental factors, corona formation, and biological activity

The surfaces of pristine nanoparticles become rapidly coated by proteins in biological fluids, forming the so-called protein corona. The corona modifies key physicochemical characteristics of nanoparticle surfaces that modulate its biological and pharmacokinetic activity, biodistribution, and safety. In the two decades since the protein corona was identified, the importance of nanoparticles surface properties in regulating biological responses have been recognized. However, there is still a lack of clarity about the relationships between physiological conditions and corona composition over time, and how this controls biological activities/interactions. Here we review recent progress in characterizing the structure and composition of protein corona as a function of biological fluid and time. We summarize the influence of nanoparticle characteristics on protein corona composition and discuss the relevance of protein corona to the biological activity and fate of nanoparticles. The aim is to provide a critical summary of the key factors that affect protein corona formation (e.g. characteristics of nanoparticles and biological environment) and how the corona modulates biological activity, cellular uptake, biodistribution, and drug delivery. In addition to a discussion on the importance of the characterization of protein corona adsorbed on nanoparticle surfaces under conditions that mimic relevant physiological environment, we discuss the unresolved technical issues related to the characterization of nanoparticle-protein corona complexes during their journey in the body. Lastly, the paper offers a perspective on how the existing nanomaterial toxicity data obtained from in vitro studies should be reconsidered in the light of the presence of a protein corona, and how recent advances in fields, such as proteomics and machine learning can be integrated into the quantitative analysis of protein corona components.

Machine learning-integrated omics for the risk and safety assessment of nanomaterials

With the advancement in nanotechnology, we are experiencing transformation in world order with deep insemination of nanoproducts from basic necessities to advanced electronics, health care products and medicines. Therefore, nanoproducts, however, can have negative side effects and must be strictly monitored to avoid negative outcomes. Future toxicity and safety challenges regarding nanomaterial incorporation into consumer products, including rapid addition of nanomaterials with diverse functionalities and attributes, highlight the limitations of traditional safety evaluation tools. Currently, artificial intelligence and machine learning algorithms are envisioned for enhancing and improving the nano-bio-interaction simulation and modeling, and they extend to the post-marketing surveillance of nanomaterials in the real world. Thus, hyphenation of machine learning with biology and nanomaterials could provide exclusive insights into the perturbations of delicate biological functions after integration with nanomaterials. In this review, we discuss the potential of combining integrative omics with machine learning in profiling nanomaterial safety and risk assessment and provide guidance for regulatory authorities as well.

Interaction of nanoparticles with biological macromolecules: a review of molecular docking studies

The high frequency of using engineered nanoparticles in various medical applications entails a deep understanding of their interaction with biological macromolecules. Molecular docking simulation is now widely used to study the binding of different types of nanoparticles with proteins and nucleic acids. This helps not only in understanding the mechanism of their biological action but also in predicting any potential toxicity. In this review, the computational techniques used in studying the nanoparticles interaction with biological macromolecules are covered. Then, a comprehensive overview of the docking studies performed on various types of nanoparticles will be offered. The implication of these predicted interactions in the biological activity and/or toxicity is also discussed for each type of nanoparticles.

Understanding Nanoparticle Toxicity to Direct a Safe-by-Design Approach in Cancer Nanomedicine

Nanomedicine is a rapidly growing field that uses nanomaterials for the diagnosis, treatment and prevention of various diseases, including cancer. Various biocompatible nanoplatforms with diversified capabilities for tumor targeting, imaging, and therapy have materialized to yield individualized therapy. However, due to their unique properties brought about by their small size, safety concerns have emerged as their physicochemical properties can lead to altered pharmacokinetics, with the potential to cross biological barriers. In addition, the intrinsic toxicity of some of the inorganic materials (i.e., heavy metals) and their ability to accumulate and persist in the human body has been a challenge to their translation. Successful clinical translation of these nanoparticles is heavily dependent on their stability, circulation time, access and bioavailability to disease sites, and their safety profile. This review covers preclinical and clinical inorganic-nanoparticle based nanomaterial utilized for cancer imaging and therapeutics. A special emphasis is put on the rational design to develop non-toxic/safe inorganic nanoparticle constructs to increase their viability as translatable nanomedicine for cancer therapies.

Risk Management Framework for Nano-Biomaterials Used in Medical Devices and Advanced Therapy Medicinal Products

The convergence of nanotechnology and biotechnology has led to substantial advancements in nano-biomaterials (NBMs) used in medical devices (MD) and advanced therapy medicinal products (ATMP). However, there are concerns that applications of NBMs for medical diagnostics, therapeutics and regenerative medicine could also pose health and/or environmental risks since the current understanding of their safety is incomplete. A scientific strategy is therefore needed to assess all risks emerging along the life cycles of these products. To address this need, an overarching risk management framework (RMF) for NBMs used in MD and ATMP is presented in this paper, as a result of a collaborative effort of a team of experts within the EU Project BIORIMA and with relevant inputs from external stakeholders. The framework, in line with current regulatory requirements, is designed according to state-of-the-art approaches to risk assessment and management of both nanomaterials and biomaterials. The collection/generation of data for NBMs safety assessment is based on innovative integrated approaches to testing and assessment (IATA). The framework can support stakeholders (e.g., manufacturers, regulators, consultants) in systematically assessing not only patient safety but also occupational (including healthcare workers) and environmental risks along the life cycle of MD and ATMP. The outputs of the framework enable the user to identify suitable safe(r)-by-design alternatives and/or risk management measures and to compare the risks of NBMs to their (clinical) benefits, based on efficacy, quality and cost criteria, in order to inform robust risk management decision-making.

Role of Artificial Intelligence and Machine Learning in Nanosafety

Robotics and automation provide potentially paradigm shifting improvements in the way materials are synthesized and characterized, generating large, complex data sets that are ideal for modeling and analysis by modern machine learning (ML) methods. Nanomaterials have not yet fully captured the benefits of automation, so lag behind in the application of ML methods of data analysis. Here, some key developments in, and roadblocks to the application of ML methods are reviewed to model and predict potentially adverse biological and environmental effects of nanomaterials. This work focuses on the diverse ways a range of ML algorithms are applied to understand and predict nanomaterials properties, provides examples of the application of traditional ML and deep learning methods to nanosafety, and provides context and future perspectives on developments that are likely to occur, or need to occur in the near future that allow artificial intelligence to make a deeper contribution to nanosafety.

Artificial Intelligence and Machine Learning in Computational Nanotoxicology: Unlocking and Empowering Nanomedicine

Advances in nanomedicine, coupled with novel methods of creating advanced materials at the nanoscale, have opened new perspectives for the development of healthcare and medical products. Special attention must be paid toward safe design approaches for nanomaterial-based products. Recently, artificial intelligence (AI) and machine learning (ML) gifted the computational tool for enhancing and improving the simulation and modeling process for nanotoxicology and nanotherapeutics. In particular, the correlation of in vitro generated pharmacokinetics and pharmacodynamics to in vivo application scenarios is an important step toward the development of safe nanomedicinal products. This review portrays how in vitro and in vivo datasets are used in in silico models to unlock and empower nanomedicine. Physiologically based pharmacokinetic (PBPK) modeling and absorption, distribution, metabolism, and excretion (ADME)-based in silico methods along with dosimetry models as a focus area for nanomedicine are mainly described. The computational OMICS, colloidal particle determination, and algorithms to establish dosimetry for inhalation toxicology, and quantitative structure-activity relationships at nanoscale (nano-QSAR) are revisited. The challenges and opportunities facing the blind spots in nanotoxicology in this computationally dominated era are highlighted as the future to accelerate nanomedicine clinical translation.

Nanotoxicology data for in silico tools: a literature review

The exercise of non-testing approaches in nanoparticles (NPs) hazard assessment is necessary for the risk assessment, considering cost and time efficiency, to identify, assess, and classify potential risks. One strategy for investigating the toxicological properties of a variety of NPs is by means of computational tools that decode how nano-specific features relate to toxicity and enable its prediction. This literature review records systematically the data used in published studies that predict nano (eco)-toxicological endpoints using machine learning models. Instead of seeking mechanistic interpretations this review maps the pathways followed, involving biological features in relation to NPs exposure, their physico-chemical characteristics and the most commonly predicted outcomes. The results, derived from published research of the last decade, are summarized visually, providing prior-based data mining paradigms to be readily used by the nanotoxicology community in computational studies.

Practices and Trends of Machine Learning Application in Nanotoxicology

Machine Learning (ML) techniques have been applied in the field of nanotoxicology with very encouraging results. Adverse effects of nanoforms are affected by multiple features described by theoretical descriptors, nano-specific measured properties, and experimental conditions. ML has been proven very helpful in this field in order to gain an insight into features effecting toxicity, predicting possible adverse effects as part of proactive risk analysis, and informing safe design. At this juncture, it is important to document and categorize the work that has been carried out. This study investigates and bookmarks ML methodologies used to predict nano (eco)-toxicological outcomes in nanotoxicology during the last decade. It provides a review of the sequenced steps involved in implementing an ML model, from data pre-processing, to model implementation, model validation, and applicability domain. The review gathers and presents the step-wise information on techniques and procedures of existing models that can be used readily to assemble new nanotoxicological in silico studies and accelerates the regulation of in silico tools in nanotoxicology. ML applications in nanotoxicology comprise an active and diverse collection of ongoing efforts, although it is still in their early steps toward a scientific accord, subsequent guidelines, and regulation adoption. This study is an important bookend to a decade of ML applications to nanotoxicology and serves as a useful guide to further in silico applications.

Fermented mulberry leaf meal as fishmeal replacer in the formulation of feed for carp Labeo rohita and catfish Heteropneustes fossilis-optimization by mathematical programming

Search for cost-effective, eco-friendly and sustainable plant resources as potential feedstuff to replace fishmeal in the formulation of feed for fish has been in the forefront of aquaculture researches since the last few years. In this study, experiments were conducted to evaluate if replacement of fishmeal by the fermented leaf meal of mulberry (Morus indica) was viable in the formulation of feed for carp fish Labeo rohita and catfish Heteropneustes fossilis. Four iso-proteinous, iso-lipidic and iso-energetic experimental feed were formulated by replacing 0, 25, 50 and 75% of fishmeal by the fermented mulberry leaf meal (FMLM), and both species were grown on these feeds for 8 weeks. Since the results revealed differences in response to fishmeal replacement level between parameters, we determined optimum fishmeal replacement level (OFRL) for each parameter from the polynomial curve equation. While maximum weight gain and specific growth rate and minimum feed conversion ratio was found at 30-32% OFRL for L. rohita and at 52-53% OFRL for H. fossilis, other parameters responded differently in both fish. Therefore, we applied a two-phase fuzzy goal programming technique using all parameters, which showed overall OFRL for L. rohita and H. fossilis as 30.95% and 52%, respectively. We also applied the concept of 'decision tree' to identify the key factor behind utilization of FMLM. It was concluded that activity of amylase and subsequent utilization of carbohydrate was the key factor in utilizing FMLM. Interestingly, H. fossilis was found more efficient in utilizing carbohydrate of FMLM than L. rohita.

Importance of Choosing Relevant Biological End Points To Predict Nanoparticle Toxicity with Computational Approaches for Human Health Risk Assessment

Because it is impossible to assess in vitro or in vivo the toxicity of all nanoparticles available on the market on a case-by-case basis, computational approaches have been proposed as useful alternatives to predict in silico the hazard potential of engineered nanoparticles. Despite promising results, a major issue associated with these mathematical models lies in the a priori choice of the physicochemical descriptors and the biological end points. We performed a thorough bibliographic survey on the biological end points used for nanotoxicology purposes and compared them between experimental and computational approaches. They were found to be disparate: while conventional in vitro nanotoxicology assays usually investigate a large array of biological effects using eukaryotic cells (cytotoxicity, pro-inflammatory response, oxidative stress, genotoxicity), computational studies mostly focus on cell viability and also include studies on prokaryotic cells. We may thus wonder the relevance of building complex mathematical models able to predict accurately a biological end point if this latter is not the most relevant to support human health risk assessment. The choice of biological end points clearly deserves to be more carefully discussed. This could bridge the gap between experimental and computational nanotoxicology studies and allow in silico predictive models to reach their full potential.

Computational models for the assessment of manufactured nanomaterials: Development of model reporting standards and mapping of the model landscape

Different types of computational models have been developed for predicting the biokinetics, environmental fate, exposure levels and toxicological effects of chemicals and manufactured nanomaterials (MNs). However, these models are not described in a consistent manner in the scientific literature, which is one of the barriers to their broader use and acceptance, especially for regulatory purposes. Quantitative structure-activity relationships (QSARs) are in silico models based on the assumption that the activity of a substance is related to its chemical structure. These models can be used to provide information on (eco)toxicological effects in hazard assessment. In an environmental risk assessment, environmental exposure models can be used to estimate the predicted environmental concentration (PEC). In addition, physiologically based kinetic (PBK) models can be used in various ways to support a human health risk assessment. In this paper, we first propose model reporting templates for systematically and transparently describing models that could potentially be used to support regulatory risk assessments of MNs, for example under the REACH regulation. The model reporting templates include (a) the adaptation of the QSAR Model Reporting Format (QMRF) to report models for MNs, and (b) the development of a model reporting template for PBK and environmental exposure models applicable to MNs. Second, we show the usefulness of these templates to report different models, resulting in an overview of the landscape of available computational models for MNs.

On the prediction of cytotoxicity of diverse chemicals for topminnow (Poeciliopsis lucida) hepatoma cell line, PLHC-1$

Two data sets on the cytotoxicity of diverse chemicals to topminnow (Poeciliopsis lucida) hepatoma cell line (PLHC-1) were modelled with quantitative structure-toxicity relationship (QSTR). The data sets are based on 3-amino-7-dimethylamino-2-methylphenazine hydrochloride (NR) and 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyl tetrazolium bromide (MTT) assays representing lysosomal damage and metabolic impairment, respectively. The descriptors were calculated with DRAGON 6 and SPARTAN 10 software packages. Descriptor selection was made by 'all subset' and genetic algorithm-based features implemented in QSARINS software. The proposed QSTR models were validated both internally and externally. For both endpoints, statistically satisfactory QSTR models were generated with n_Tr = 39; r²_Tr = 0.782; RMSE_Tr = 0.466; n_Test = 18; r²_Test = 0.799; RMSE_Test = 0.360 for NR-based model and n_Tr = 32; r²_Tr = 0.775; RMSE_Tr = 0.460; n_Test = 10; r²_Test = 0.864; RMSE_Test = 0.290 for MTT-based model. Additionally, the QSTR models generated for NR and MTT endpoints were used to predict the cytotoxicity of an external set of 657 and 652 diverse chemicals with structural coverage of 98.6% and 98.3%, respectively. A moderate correlation was observed between the experimental in vivo and predicted in vitro values for external set chemicals. The QSTR models may provide an initial, rapid screening and prioritization of these diverse chemicals for the acute fish toxicity assessment and reduce the need for extensive in vivo toxicity testing.

What if the number of nanotoxicity data is too small for developing predictive Nano-QSAR models? An alternative read-across based approach for filling data gaps

Over the past decade, computational nanotoxicology, in particular Quantitative Structure-Activity Relationship models (Nano-QSAR) that help in assessing the biological effects of nanomaterials, have received much attention. In effect, a solid basis for uncovering the relationships between the structure and property/activity of nanoparticles has been created. Nonetheless, six years after the first pioneering computational studies focusing on the investigation of nanotoxicity were commenced, these computational methods still suffer from many limitations. These are mainly related to the paucity of widely available, systematically varied, libraries of experimental data necessary for the development and validation of such models. This results in the still-low acceptance of these methods as valuable research tools for nanosafety and raises the query as to whether these methods could gain wide acceptance of regulatory bodies as alternatives for traditional in vitro methods. This study aimed to give an answer to the following question: How to remedy the paucity of experimental nanotoxicity data and thereby, overcome key roadblock that hinders the development of approaches for data-driven modeling of nanoparticle properties and toxicities? Here, a simple and transparent read-across algorithm for a pre-screening hazard assessment of nanomaterials that provides reasonably accurate results by making the best use of existing limited set of observations will be introduced.

In silico prediction of toxicity of phenols to Tetrahymena pyriformis by using genetic algorithm and decision tree-based modeling approach

Risk assessment of chemicals is an important issue in environmental protection; however, there is a huge lack of experimental data for a large number of end-points. The experimental determination of toxicity of chemicals involves high costs and time-consuming process. In silico tools such as quantitative structure-toxicity relationship (QSTR) models, which are constructed on the basis of computational molecular descriptors, can predict missing data for toxic end-points for existing or even not yet synthesized chemicals. Phenol derivatives are known to be aquatic pollutants. With this background, we aimed to develop an accurate and reliable QSTR model for the prediction of toxicity of 206 phenols to Tetrahymena pyriformis. A multiple linear regression (MLR)-based QSTR was obtained using a powerful descriptor selection tool named Memorized_ACO algorithm. Statistical parameters of the model were 0.72 and 0.68 for R_training² and R_test², respectively. To develop a high-quality QSTR model, classification and regression tree (CART) was employed. Two approaches were considered: (1) phenols were classified into different modes of action using CART and (2) the phenols in the training set were partitioned to several subsets by a tree in such a manner that in each subset, a high-quality MLR could be developed. For the first approach, the statistical parameters of the resultant QSTR model were improved to 0.83 and 0.75 for R_training² and R_test², respectively. Genetic algorithm was employed in the second approach to obtain an optimal tree, and it was shown that the final QSTR model provided excellent prediction accuracy for the training and test sets (R_training² and R_test² were 0.91 and 0.93, respectively). The mean absolute error for the test set was computed as 0.1615.