Deep exploration of random forest model boosts the interpretability of machine learning studies of complicated immune responses and lung burden of nanoparticles

Does the surface charge of the nanoparticles drive nanoparticle-cell membrane interactions?

Classical Coulombic interaction, characterized by electrostatic interactions mediated through surface charges, is often regarded as the primary determinant in nanoparticles' (NPs) cellular association and internalization. However, the intricate physicochemical properties of particle surfaces, biomolecular coronas, and cell surfaces defy this oversimplified perspective. Moreover, the nanometrological techniques employed to characterize NPs in complex physiological fluids often exhibit limited accuracy and reproducibility. A more comprehensive understanding of nanoparticle-cell membrane interactions, extending beyond attractive forces between oppositely charged surfaces, necessitates the establishment of databases through rigorous physical, chemical, and biological characterization supported by nanoscale analytics. Additionally, computational approaches, such as in silico modeling and machine learning, play a crucial role in unraveling the complexities of these interactions.

Knowledge-guided machine learning reveals pivotal drivers for gas-to-particle conversion of atmospheric nitrate

Particulate nitrate, a key component of fine particles, forms through the intricate gas-to-particle conversion process. This process is regulated by the gas-to-particle conversion coefficient of nitrate (ε(NO3-)). The mechanism between ε(NO3-) and its drivers is highly complex and nonlinear, and can be characterized by machine learning methods. However, conventional machine learning often yields results that lack clear physical meaning and may even contradict established physical/chemical mechanisms due to the influence of ambient factors. It urgently needs an alternative approach that possesses transparent physical interpretations and provides deeper insights into the impact of ε(NO3-). Here we introduce a supervised machine learning approach-the multilevel nested random forest guided by theory approaches. Our approach robustly identifies NH4+, SO42-, and temperature as pivotal drivers for ε(NO3-). Notably, substantial disparities exist between the outcomes of traditional random forest analysis and the anticipated actual results. Furthermore, our approach underscores the significance of NH4+ during both daytime (30%) and nighttime (40%) periods, while appropriately downplaying the influence of some less relevant drivers in comparison to conventional random forest analysis. This research underscores the transformative potential of integrating domain knowledge with machine learning in atmospheric studies.

Decoding Nanomaterial-Biosystem Interactions through Machine Learning

The interactions between biosystems and nanomaterials regulate most of their theranostic and nanomedicine applications. These nanomaterial-biosystem interactions are highly complex and influenced by a number of entangled factors, including but not limited to the physicochemical features of nanomaterials, the types and characteristics of the interacting biosystems, and the properties of the surrounding microenvironments. Over the years, different experimental approaches coupled with computational modeling have revealed important insights into these interactions, although many outstanding questions remain unanswered. The emergence of machine learning has provided a timely and unique opportunity to revisit nanomaterial-biosystem interactions and to further push the boundary of this field. This minireview highlights the development and use of machine learning to decode nanomaterial-biosystem interactions and provides our perspectives on the current challenges and potential opportunities in this field.

Predicting the binding configuration and release potential of heavy metals on iron (oxyhydr)oxides: A machine learning study on EXAFS

Heavy metals raise a global concern and can be easily retained by ubiquitous iron (oxyhydr)oxides in natural and engineered systems. The complex interaction between iron (oxyhydr)oxides and heavy metals results in various mineral-metal binding configurations, such as outer-sphere complexes and edge-sharing inner-sphere complexes, which determine the accumulation and release of heavy metals in the environment. However, traditional experimental approaches are time-consuming and inadequate to elucidate the complex binding relationships and configurations between iron (oxyhydr)oxides and heavy metals. Herein, a workflow that integrates the binding configuration data of 11 heavy metals on 7 iron (oxyhydr)oxides and then trains machine learning models to predict unknown binding configurations was proposed. The well-trained multi-grained cascade forest models exhibited high accuracy (> 90%) and predictive performance (R2 ∼ 0.75). The underlying effects of mineral properties, metal ion species, and environmental conditions on mineral-metal binding configurations were fully interpreted with data mining. Moreover, the metal release rate was further successfully predicted based on mineral-metal binding configurations. This work provides a method to accurately and quickly predict the binding configuration of heavy metals on iron (oxyhydr)oxides, which would provide guidance for estimating the potential release behavior of heavy metals and remediating heavy metal pollution in natural and engineered environments.

VirusPredictor: XGBoost-based software to predict virus-related sequences in human data

MOTIVATION

Discovering disease causative pathogens, particularly viruses without reference genomes, poses a technical challenge as they are often unidentifiable through sequence alignment. Machine learning prediction of patient high-throughput sequences unmappable to human and pathogen genomes may reveal sequences originating from uncharacterized viruses. Currently, there is a lack of software specifically designed for accurately predicting such viral sequences in human data.

RESULTS

We developed a fast XGBoost method and software VirusPredictor leveraging an in-house viral genome database. Our two-step XGBoost models first classify each query sequence into one of three groups: infectious virus, endogenous retrovirus (ERV) or non-ERV human. The prediction accuracies increased as the sequences became longer, i.e. 0.76, 0.93, and 0.98 for 150-350 (Illumina short reads), 850-950 (Sanger sequencing data), and 2000-5000 bp sequences, respectively. Then, sequences predicted to be from infectious viruses are further classified into one of six virus taxonomic subgroups, and the accuracies increased from 0.92 to >0.98 when query sequences increased from 150-350 to >850 bp. The results suggest that Illumina short reads should be de novo assembled into contigs (e.g. ∼1000 bp or longer) before prediction whenever possible. We applied VirusPredictor to multiple real genomic and metagenomic datasets and obtained high accuracies. VirusPredictor, a user-friendly open-source Python software, is useful for predicting the origins of patients' unmappable sequences. This study is the first to classify ERVs in infectious viral sequence prediction. This is also the first study combining virus sub-group predictions.

AVAILABILITY AND IMPLEMENTATION

www.dllab.org/software/VirusPredictor.html.

Elucidating the impacts of microplastics on soil greenhouse gas emissions through automatic machine learning frameworks

With the rise in global plastic production and agricultural demand, the released microplastics (MPs) have increasingly influenced the elemental cycles of soils, leading to notable effects on greenhouse gas emissions. Despite initial research, there remains a gap in establishing a detailed modeling approach that comprehensively explores the impacts of MPs on GHG emissions. Herein, we utilized literature mining to assemble a comprehensive dataset examining the interplays between MPs and emissions of CO2, CH4, and N2O. Five automated machine learning frameworks were employed for predictive modeling. The GAMA framework was particularly effective in predicting CO2 (Q2 = 0.946) and CH4 (Q2 = 0.991) emissions. The Autogluon framework provided the most accurate prediction for N2O emission, though it exhibited signs of overfitting. Interpretability analysis indicated that the type of MPs significantly influenced CO2 emission. Degradable MPs (i.e., polyamide) inherently led to elevated CO2 emission, and the environmental aging further exacerbated this effect. Although both linear and nonlinear correlations between MPs and CH₄ emission were not identified, the incorporation of specific MPs that elevate soil pH, augment soil water retention, and cultivate anaerobic conditions may potentially elevate soil CH₄ emission. This research underscores the profound influence of MPs on soil GHG emissions, providing vital insights for shaping agricultural policies and soil management practices in the context of escalating plastic use.

Bioavailability (BA)-based risk assessment of soil heavy metals in provinces of China through the predictive BA-models

The real biological effect is not generated by the total content of heavy metals (HMs), but rather by bioavailable content. A new bioavailability-based ecological risk assessment (BA-based ERA) framework was developed for deriving bioavailability-based soil quality criteria (BA-based SQC) and accurately assessing the ecological risk of soil HMs at a multi-regional scale in this study. Through the random forest (RF) models and BA-based ERA framework, the 217 BA-based SQC for HMs in 31 Chinese provinces were derived and the BA-based ERA was comprehensively assessed. This study found that bioavailable HMs extraction methods (BHEMs) and total HMs content play the predominant role in affecting HMs (As, Cd, Cr, Cu, Ni, Pb, and Zn) bioavailability by explaining 27.55-56.11% and 9.20-62.09% of the variation, respectively. The RF model had accurate and stable prediction ability for the bioavailability of soil HMs with the mean R2 and RMSE of 0.83 and 0.43 for the test set, respectively. The results of BA-based ERA showed that bioavailability could avoid the overestimation of ecological risks to some extent after reducing the uncertainty of soil differences. This study confirmed the feasibility of using bioavailability for ERA and will utilised to revise the soil environmental standards based on bioavailability for HMs.

Nanotechnology's frontier in combatting infectious and inflammatory diseases: prevention and treatment

Inflammation-associated diseases encompass a range of infectious diseases and non-infectious inflammatory diseases, which continuously pose one of the most serious threats to human health, attributed to factors such as the emergence of new pathogens, increasing drug resistance, changes in living environments and lifestyles, and the aging population. Despite rapid advancements in mechanistic research and drug development for these diseases, current treatments often have limited efficacy and notable side effects, necessitating the development of more effective and targeted anti-inflammatory therapies. In recent years, the rapid development of nanotechnology has provided crucial technological support for the prevention, treatment, and detection of inflammation-associated diseases. Various types of nanoparticles (NPs) play significant roles, serving as vaccine vehicles to enhance immunogenicity and as drug carriers to improve targeting and bioavailability. NPs can also directly combat pathogens and inflammation. In addition, nanotechnology has facilitated the development of biosensors for pathogen detection and imaging techniques for inflammatory diseases. This review categorizes and characterizes different types of NPs, summarizes their applications in the prevention, treatment, and detection of infectious and inflammatory diseases. It also discusses the challenges associated with clinical translation in this field and explores the latest developments and prospects. In conclusion, nanotechnology opens up new possibilities for the comprehensive management of infectious and inflammatory diseases.

Urbanization influences dissolved organic matter characteristics but microbes affect greenhouse gas concentrations in lakes

Recognition and prediction of dissolved organic matter (DOM) properties and greenhouse gas (GHG) emissions is critical to understanding climate change and the fate of carbon in aquatic ecosystems, but related data is challenging to interpret due to covariance in multiple natural and anthropogenic variables with high spatial and temporal heterogeneity. Here, machine learning modeling combined with environmental analysis reveals that urbanization (e.g., population density and artificial surfaces) rather than geography determines DOM composition and properties in lakes. The structure of the bacterial community is the dominant factor determining GHG emissions from lakes. Urbanization increases DOM bioavailability and decreases the DOM degradation index (Ideg), increasing the potential for DOM conversion into inorganic carbon in lakes. The traditional fossil fuel-based path (SSP5) scenario increases carbon emission potential. Land conversion from water bodies into artificial surfaces causes organic carbon burial. It is predicted that increased urbanization will accelerate the carbon cycle in lake ecosystems in the future, which deserves attention in climate models and in the management of global warming.

Machine learning coupled with causal inference to identify COVID-19 related chemicals that pose a high concern to drinking water

Various synthetic substances were utilized in large quantities during the recent coronavirus pandemic, COVID-19. Some of these chemicals could potentially enter drinking water sources. Persistent, mobile, and toxic (PMT) substances have been recognized as a threat to drinking water resources. It has not yet been assessed how many COVID-19 related substances could be considered PMT substances. One reason is the lack of high-quality experimental data for the identification of PMT substances. To solve this problem, we applied a machine learning model to identify the PMT substances among COVID-19 related chemicals. The optimal model achieved an accuracy of 90.6% based on external test data. The model interpretation and causal inference indicated that our approach understood causation between PMT properties and molecular descriptors. Notably, the screening results showed that over 60% of the COVID-19 chemicals considered are candidate PMT substances, which should be prioritized to prevent undue pollution of water resources.

Tolerogenic Nano-/Microparticle Vaccines for Immunotherapy

Autoimmune diseases, allergies, transplant rejections, generation of antidrug antibodies, and chronic inflammatory diseases have impacted a large group of people across the globe. Conventional treatments and therapies often use systemic or broad immunosuppression with serious efficacy and safety issues. Tolerogenic vaccines represent a concept that has been extended from their traditional immune-modulating function to induction of antigen-specific tolerance through the generation of regulatory T cells. Without impairing immune homeostasis, tolerogenic vaccines dampen inflammation and induce tolerogenic regulation. However, achieving the desired potency of tolerogenic vaccines as preventive and therapeutic modalities calls for precise manipulation of the immune microenvironment and control over the tolerogenic responses against the autoantigens, allergens, and/or alloantigens. Engineered nano-/microparticles possess desirable design features that can bolster targeted immune regulation and enhance the induction of antigen-specific tolerance. Thus, particle-based tolerogenic vaccines hold great promise in clinical translation for future treatment of aforementioned immune disorders. In this review, we highlight the main strategies to employ particles as exciting tolerogenic vaccines, with a focus on the particles' role in facilitating the induction of antigen-specific tolerance. We describe the particle design features that facilitate their usage and discuss the challenges and opportunities for designing next-generation particle-based tolerogenic vaccines with robust efficacy to promote antigen-specific tolerance for immunotherapy.

Fertilizer management for global ammonia emission reduction

Crop production is a large source of atmospheric ammonia (NH3), which poses risks to air quality, human health and ecosystems1-5. However, estimating global NH3 emissions from croplands is subject to uncertainties because of data limitations, thereby limiting the accurate identification of mitigation options and efficacy4,5. Here we develop a machine learning model for generating crop-specific and spatially explicit NH3 emission factors globally (5-arcmin resolution) based on a compiled dataset of field observations. We show that global NH3 emissions from rice, wheat and maize fields in 2018 were 4.3 ± 1.0 Tg N yr-1, lower than previous estimates that did not fully consider fertilizer management practices6-9. Furthermore, spatially optimizing fertilizer management, as guided by the machine learning model, has the potential to reduce the NH3 emissions by about 38% (1.6 ± 0.4 Tg N yr-1) without altering total fertilizer nitrogen inputs. Specifically, we estimate potential NH3 emissions reductions of 47% (44-56%) for rice, 27% (24-28%) for maize and 26% (20-28%) for wheat cultivation, respectively. Under future climate change scenarios, we estimate that NH3 emissions could increase by 4.0 ± 2.7% under SSP1-2.6 and 5.5 ± 5.7% under SSP5-8.5 by 2030-2060. However, targeted fertilizer management has the potential to mitigate these increases.

New Insights on the Formation of Nucleation Mode Particles in a Coastal City Based on a Machine Learning Approach

Atmospheric particles have profound implications for the global climate and human health. Among them, ultrafine particles dominate in terms of the number concentration and exhibit enhanced toxic effects as a result of their large total surface area. Therefore, understanding the driving factors behind ultrafine particle behavior is crucial. Machine learning (ML) provides a promising approach for handling complex relationships. In this study, three ML models were constructed on the basis of field observations to simulate the particle number concentration of nucleation mode (PNCN). All three models exhibited robust PNCN reproduction (R2 > 0.80), with the random forest (RF) model excelling on the test data (R2 = 0.89). Multiple methods of feature importance analysis revealed that ultraviolet (UV), H2SO4, low-volatility oxygenated organic molecules (LOOMs), temperature, and O3 were the primary factors influencing PNCN. Bivariate partial dependency plots (PDPs) indicated that during nighttime and overcast conditions, the presence of H2SO4 and LOOMs may play a crucial role in influencing PNCN. Additionally, integrating additional detailed information related to emissions or meteorology would further enhance the model performance. This pilot study shows that ML can be a novel approach for simulating atmospheric pollutants and contributes to a better understanding of the formation and growth mechanisms of nucleation mode particles.

Machine Learning Elucidates Design Features of Plasmid DNA Lipid Nanoparticles for Cell Type-Preferential Transfection

For cell and gene therapies to become more broadly accessible, it is critical to develop and optimize non-viral cell type-preferential gene carriers such as lipid nanoparticles (LNPs). Despite the effectiveness of high throughput screening (HTS) approaches in expediting LNP discovery, they are often costly, labor-intensive, and often do not provide actionable LNP design rules that focus screening efforts on the most relevant chemical and formulation parameters. Here we employed a machine learning (ML) workflow using well-curated plasmid DNA LNP transfection datasets across six cell types to maximize chemical insights from HTS studies and has achieved predictions with 5-9% error on average depending on cell type. By applying Shapley additive explanations to our ML models, we unveiled composition-function relationships dictating cell type-preferential LNP transfection efficiency. Notably, we identified consistent LNP composition parameters that enhance in vitro transfection efficiency across diverse cell types, such as ionizable to helper lipid ratios near 1:1 or 10:1 and the incorporation of cationic/zwitterionic helper lipids. In addition, several parameters were found to modulate cell type-preferentiality, including the ionizable and helper lipid total molar percentage, N/P ratio, cholesterol to PEGylated lipid ratio, and the chemical identity of the helper lipid. This study leverages HTS of compositionally diverse LNP libraries and ML analysis to understand the interactions between lipid components in LNP formulations; and offers fundamental insights that contribute to the establishment of unique sets of LNP compositions tailored for cell type-preferential transfection.

Machine Learning Models for Inverse Design of the Electrochemical Oxidation Process for Water Purification

In this study, a machine learning (ML) framework is developed toward target-oriented inverse design of the electrochemical oxidation (EO) process for water purification. The XGBoost model exhibited the best performances for prediction of reaction rate (k) based on training the data set relevant to pollutant characteristics and reaction conditions, indicated by Rext2 of 0.84 and RMSEext of 0.79. Based on 315 data points collected from the literature, the current density, pollutant concentration, and gap energy (Egap) were identified to be the most impactful parameters available for the inverse design of the EO process. In particular, adding reaction conditions as model input features allowed provision of more available information and an increase in the sample size of the data set to improve the model accuracy. The feature importance analysis was performed for revealing the data pattern and feature interpretation by using Shapley additive explanations (SHAP). The ML-based inverse design for the EO process was generalized to a random case for tailoring the optimum conditions with phenol and 2,4-dichlorophenol (2,4-DCP) serving as model pollutants. The resulting predicted k values were close to the experimental k values by experimental verification, accounting for the relative error lower than 5%. This study provides a paradigm shift from conventional trial-and-error mode to data-driven mode for advancing research and development of the EO process by a time-saving, labor-effective, and environmentally friendly target-oriented strategy, which makes electrochemical water purification more efficient, more economic, and more sustainable in the context of global carbon peaking and carbon neutrality.

Deep-Learning-Based Automated Tracking and Counting of Living Plankton in Natural Aquatic Environments

Plankton are widely distributed in the aquatic environment and serve as an indicator of water quality. Monitoring the spatiotemporal variation in plankton is an efficient approach to forewarning environmental risks. However, conventional microscopy counting is time-consuming and laborious, hindering the application of plankton statistics for environmental monitoring. In this work, an automated video-oriented plankton tracking workflow (AVPTW) based on deep learning is proposed for continuous monitoring of living plankton abundance in aquatic environments. With automatic video acquisition, background calibration, detection, tracking, correction, and statistics, various types of moving zooplankton and phytoplankton were counted at a time scale. The accuracy of AVPTW was validated with conventional counting via microscopy. Since AVPTW is only sensitive to mobile plankton, the temperature- and wastewater-discharge-induced plankton population variations were monitored online, demonstrating the sensitivity of AVPTW to environmental changes. The robustness of AVPTW was also confirmed with natural water samples from a contaminated river and an uncontaminated lake. Notably, automated workflows are essential for generating large amounts of data, which are a prerequisite for available data set construction and subsequent data mining. Furthermore, data-driven approaches based on deep learning pave a novel way for long-term online environmental monitoring and elucidating the correlation underlying environmental indicators. This work provides a replicable paradigm to combine imaging devices with deep-learning algorithms for environmental monitoring.

Advancing Computational Toxicology by Interpretable Machine Learning

Chemical toxicity evaluations for drugs, consumer products, and environmental chemicals have a critical impact on human health. Traditional animal models to evaluate chemical toxicity are expensive, time-consuming, and often fail to detect toxicants in humans. Computational toxicology is a promising alternative approach that utilizes machine learning (ML) and deep learning (DL) techniques to predict the toxicity potentials of chemicals. Although the applications of ML- and DL-based computational models in chemical toxicity predictions are attractive, many toxicity models are "black boxes" in nature and difficult to interpret by toxicologists, which hampers the chemical risk assessments using these models. The recent progress of interpretable ML (IML) in the computer science field meets this urgent need to unveil the underlying toxicity mechanisms and elucidate the domain knowledge of toxicity models. In this review, we focused on the applications of IML in computational toxicology, including toxicity feature data, model interpretation methods, use of knowledge base frameworks in IML development, and recent applications. The challenges and future directions of IML modeling in toxicology are also discussed. We hope this review can encourage efforts in developing interpretable models with new IML algorithms that can assist new chemical assessments by illustrating toxicity mechanisms in humans.

Using Machine Learning to Predict Adverse Effects of Metallic Nanomaterials to Various Aquatic Organisms

The wide production and use of metallic nanomaterials (MNMs) leads to increased emissions into the aquatic environments and induces high potential risks. Experimentally evaluating the (eco)toxicity of MNMs is time-consuming and expensive due to the multiple environmental factors, the complexity of material properties, and the species diversity. Machine learning (ML) models provide an option to deal with heterogeneous data sets and complex relationships. The present study established an in silico model based on a machine learning properties-environmental conditions-multi species-toxicity prediction model (ML-PEMST) that can be applied to predict the toxicity of different MNMs toward multiple aquatic species. Feature importance and interaction analysis based on the random forest method indicated that exposure duration, illumination, primary size, and hydrodynamic diameter were the main factors affecting the ecotoxicity of MNMs to a variety of aquatic organisms. Illumination was demonstrated to have the most interaction with the other features. Moreover, incorporating additional detailed information on the ecological traits of the test species will allow us to further optimize and improve the predictive performance of the model. This study provides a new approach for ecotoxicity predictions for organisms in the aquatic environment and will help us to further explore exposure pathways and the risk assessment of MNMs.

Environmental tipping points for global soil carbon fixation microorganisms

Carbon fixation microorganisms (CFMs) are important components of the soil carbon cycle. However, the global distribution of CFMs and whether they will exceed the environmental tipping points remain unclear. According to the machine learning models, total carbon content, nitrogen fertilizer, and precipitation play dominant roles in CFM abundance. Obvious stimulation and inhibition effects on CFM abundance only happened at low levels of total carbon and precipitation, where the tipping points were 6.1 g·kg-1 and 22.38 mm, respectively. The abundance of CFMs in response to nitrogen fertilizer changed from positive to negative (tipping point at 9.45 kg ha-1·y-1). Approximately 46% of CFM abundance decline happened in cropland at 2100. Our work presents the distribution of carbon-fixing microorganisms on a global scale and then points out the sensitive areas with significant abundance changes. The previously described information will provide references for future soil quality prediction and policy decision-making.

Enhancing RABASAR for Multi-Temporal SAR Image Despeckling through Directional Filtering and Wavelet Transform

The presence of speckle noise severely hampers the interpretability of synthetic aperture radar (SAR) images. While research on despeckling single-temporal SAR images is well-established, there remains a significant gap in the study of despeckling multi-temporal SAR images. Addressing the limitations in the acquisition of the "superimage" and the generation of ratio images within the RABASAR despeckling framework, this paper proposes an enhanced framework. This enhanced framework proposes a direction-based segmentation approach for multi-temporal SAR non-local means filtering (DSMT-NLM) to obtain the "superimage". The DSMT-NLM incorporates the concept of directional segmentation and extends the application of the non-local means (NLM) algorithm to multi-temporal images. Simultaneously, the enhanced framework employs a weighted averaging method based on wavelet transform (WAMWT) to generate superimposed images, thereby enhancing the generation process of ratio images. Experimental results demonstrate that compared to RABASAR, Frost, and NLM, the proposed method exhibits outstanding performance. It not only effectively removes speckle noise from multi-temporal SAR images and reduces the generation of false details, but also successfully achieves the fusion of multi-temporal information, aligning with experimental expectations.

Interpretable XGBoost-SHAP Model Predicts Nanoparticles Delivery Efficiency Based on Tumor Genomic Mutations and Nanoparticle Properties

Understanding the complex interaction between nanoparticles (NPs) and tumors in vivo and how it dominates the delivery efficiency of NPs is critical for the translation of nanomedicine. Herein, we proposed an interpretable XGBoost-SHAP model by integrating the information on NPs physicochemical properties and tumor genomic profile to predict the delivery efficiency. The correlation coefficients were 0.66, 0.75, and 0.54 for the prediction of maximum delivery efficiency, delivery efficiency at 24 and 168 h postinjection for test sets. The analysis of the feature importance revealed that the tumor genomic mutations and their interaction with NPs properties played important roles in the delivery of NPs. The biological pathways of the NP-delivery-related genes were further explored through gene ontology enrichment analysis. Our work provides a pipeline to predict and explain the delivery efficiency of NPs to heterogeneous tumors and highlights the power of simultaneously using omics data and interpretable machine learning algorithms for discovering interactions between NPs and individual tumors, which is important for the development of personalized precision nanomedicine.

Identifying potential biomarkers of idiopathic pulmonary fibrosis through machine learning analysis

Idiopathic pulmonary fibrosis (IPF) is the most common and serious type of idiopathic interstitial pneumonia, characterized by chronic, progressive, and low survival rates, while unknown disease etiology. Until recently, patients with idiopathic pulmonary fibrosis have a poor prognosis, high mortality, and limited treatment options, due to the lack of effective early diagnostic and prognostic tools. Therefore, we aimed to identify biomarkers for idiopathic pulmonary fibrosis based on multiple machine-learning approaches and to evaluate the role of immune infiltration in the disease. The gene expression profile and its corresponding clinical data of idiopathic pulmonary fibrosis patients were downloaded from Gene Expression Omnibus (GEO) database. Next, the differentially expressed genes (DEGs) with the threshold of FDR < 0.05 and |log2 foldchange (FC)| > 0.585 were analyzed via R package "DESeq2" and GO enrichment and KEGG pathways were run in R software. Then, least absolute shrinkage and selection operator (LASSO) logistic regression, support vector machine-recursive feature elimination (SVM-RFE) and random forest (RF) algorithms were combined to screen the key potential biomarkers of idiopathic pulmonary fibrosis. The diagnostic performance of these biomarkers was evaluated through receiver operating characteristic (ROC) curves. Moreover, the CIBERSORT algorithm was employed to assess the infiltration of immune cells and the relationship between the infiltrating immune cells and the biomarkers. Finally, we sought to understand the potential pathogenic role of the biomarker (SLAIN1) in idiopathic pulmonary fibrosis using a mouse model and cellular model. A total of 3658 differentially expressed genes of idiopathic pulmonary fibrosis were identified, including 2359 upregulated genes and 1299 downregulated genes. FHL2, HPCAL1, RNF182, and SLAIN1 were identified as biomarkers of idiopathic pulmonary fibrosis using LASSO logistic regression, RF, and SVM-RFE algorithms. The ROC curves confirmed the predictive accuracy of these biomarkers both in the training set and test set. Immune cell infiltration analysis suggested that patients with idiopathic pulmonary fibrosis had a higher level of B cells memory, Plasma cells, T cells CD8, T cells follicular helper, T cells regulatory (Tregs), Macrophages M0, and Mast cells resting compared with the control group. Correlation analysis demonstrated that FHL2 was significantly associated with the infiltrating immune cells. qPCR and western blotting analysis suggested that SLAIN1 might be a signature for the diagnosis of idiopathic pulmonary fibrosis. In this study, we identified four potential biomarkers (FHL2, HPCAL1, RNF182, and SLAIN1) and evaluated the potential pathogenic role of SLAIN1 in idiopathic pulmonary fibrosis. These findings may have great significance in guiding the understanding of disease mechanisms and potential therapeutic targets in idiopathic pulmonary fibrosis.

Knowledge Gaps in Generating Cell-Based Drug Delivery Systems and a Possible Meeting with Artificial Intelligence

Cell-based drug delivery systems are new strategies in targeted delivery in which cells or cell-membrane-derived systems are used as carriers and release their cargo in a controlled manner. Recently, great attention has been directed to cells as carrier systems for treating several diseases. There are various challenges in the development of cell-based drug delivery systems. The prediction of the properties of these platforms is a prerequisite step in their development to reduce undesirable effects. Integrating nanotechnology and artificial intelligence leads to more innovative technologies. Artificial intelligence quickly mines data and makes decisions more quickly and accurately. Machine learning as a subset of the broader artificial intelligence has been used in nanomedicine to design safer nanomaterials. Here, how challenges of developing cell-based drug delivery systems can be solved with potential predictive models of artificial intelligence and machine learning is portrayed. The most famous cell-based drug delivery systems and their challenges are described. Last but not least, artificial intelligence and most of its types used in nanomedicine are highlighted. The present Review has shown the challenges of developing cells or their derivatives as carriers and how they can be used with potential predictive models of artificial intelligence and machine learning.

Harnessing Hafnium-Based Nanomaterials for Cancer Diagnosis and Therapy

With the rapid development of nanotechnology and nanomedicine, there are great interests in employing nanomaterials to improve the efficiency of disease diagnosis and treatment. The clinical translation of hafnium oxide (HfO2 ), commercially namedas NBTXR3, as a new kind of nanoradiosensitizer for radiotherapy (RT) of cancers has aroused extensive interest in researches on Hf-based nanomaterials for biomedical application. In the past 20 years, Hf-based nanomaterials have emerged as potential and important nanomedicine for computed tomography (CT)-involved bioimaging and RT-associated cancer treatment due to their excellent electronic structures and intrinsic physiochemical properties. In this review, a bibliometric analysis method is employed to summarize the progress on the synthesis technology of various Hf-based nanomaterials, including HfO2 , HfO2 -based compounds, and Hf-organic ligand coordination hybrids, such as metal-organic frameworks or nanoscaled coordination polymers. Moreover, current states in the application of Hf-based CT-involved contrasts for tissue imaging or cancer diagnosis are reviewed in detail. Importantly, the recent advances in Hf-based nanomaterials-mediated radiosensitization and synergistic RT with other current mainstream treatments are also generalized. Finally, current challenges and future perspectives of Hf-based nanomaterials with a view to maximize their great potential in the research of translational medicine are also discussed.

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.

Comparative study of lipid nanoparticle-based mRNA vaccine bioprocess with machine learning and combinatorial artificial neural network-design of experiment approach

To develop a combinatorial artificial-neural-network design-of-experiment (ANN-DOE) model, the effect of ionizable lipid, an ionizable lipid-to-cholesterol ratio, N/P ratio, flow rate ratio (FRR), and total flow rate (TFR) on the outcome responses of mRNA-LNP vaccine were evaluated using a definitive screening design (DSD) and machine learning (ML) algorithms. Particle size (PS), PDI, zeta potential (ZP), and encapsulation efficiency (EE) of mRNA-LNP were optimized within a defined constraint (PS 40-100 nm, PDI≤0.30, ZP≥(±)0.30 mV, EE≥70%), fed to ML algorithms (XGBoost, bootstrap forest, support vector machines, k-nearest neighbors, generalized regression-Lasso, ANN) and prediction was compared to ANN-DOE model. Increased FRR decreased the PS and increased ZP, while increased TFR increased PDI and ZP. Similarly, DOTAP and DOTMA produced higher ZP and EE. Particularly, a cationic ionizable lipid with an N/P ratio ≥6 provided a higher EE. ANN showed better predictive ability (R²=0.7269-0.9946), while XGBoost demonstrated better RASE (0.2833-2.9817). The ANN-DOE model outperformed both optimized ML models by R²=1.21% and RASE=43.51% (PS prediction), R²=0.23% and RASE=3.47% (PDI prediction), R²=5.73% and RASE=27.95% (ZP prediction), and R²=0.87% and RASE=36.95% (EE prediction), respectively, which demonstrated that ANN-DOE model was superior in predicting the bioprocess compared to independent models.

A New Method for Ecological Risk Assessment of Combined Contaminated Soil

Ecological risk assessment of combined polluted soil has been conducted mostly on the basis of the risk screening value (RSV) of a single pollutant. However, due to its defects, this method is not accurate enough. Not only were the effects of soil properties neglected, but the interactions among different pollutants were also overlooked. In this study, the ecological risks of 22 soils collected from four smelting sites were assessed by toxicity tests using soil invertebrates (Eisenia fetida, Folsomia candida, Caenorhabditis elegans) as subjects. Besides a risk assessment based on RSVs, a new method was developed and applied. A toxicity effect index (EI) was introduced to normalize the toxicity effects of different toxicity endpoints, rendering assessments comparable based on different toxicity endpoints. Additionally, an assessment method of ecological risk probability (RP), based on the cumulative probability distribution of EI, was established. Significant correlation was found between EI-based RP and the RSV-based Nemerow ecological risk index (NRI) (p < 0.05). In addition, the new method can visually present the probability distribution of different toxicity endpoints, which is conducive to aiding risk managers in establishing more reasonable risk management plans to protect key species. The new method is expected to be combined with a complex dose-effect relationship prediction model constructed by machine learning algorithm, providing a new method and idea for the ecological risk assessment of combined contaminated soil.

Algal community structure prediction by machine learning

The algal community structure is vital for aquatic management. However, the complicated environmental and biological processes make modeling challenging. To cope with this difficulty, we investigated using random forests (RF) to predict phytoplankton community shifting based on multi-source environmental factors (including physicochemical, hydrological, and meteorological variables). The RF models robustly predicted the algal communities composed by 13 major classes (Bray-Curtis dissimilarity = 9.2 ± 7.0%, validation NRMSE mostly <10%), with accurate simulations to the total biomass (validation R² > 0.74) in Norway's largest lake, Lake Mjosa. The importance analysis showed that the hydro-meteorological variables (Standardized MSE and Node Purity mostly >0.5) were the most influential factors in regulating the phytoplankton. Furthermore, an in-depth ecological interpretation uncovered the interactive stress-response effect on the algal community learned by the RF models. The interpretation results disclosed that the environmental drivers (i.e., temperature, lake inflow, and nutrients) can jointly pose strong influence on the algal community shifts. This study highlighted the power of machine learning in predicting complex algal community structures and provided insights into the model interpretability.

Application of Computing as a High-Practicability and -Efficiency Auxiliary Tool in Nanodrugs Discovery

Research and development (R&D) of nanodrugs is a long, complex and uncertain process. Since the 1960s, computing has been used as an auxiliary tool in the field of drug discovery. Many cases have proven the practicability and efficiency of computing in drug discovery. Over the past decade, computing, especially model prediction and molecular simulation, has been gradually applied to nanodrug R&D, providing substantive solutions to many problems. Computing has made important contributions to promoting data-driven decision-making and reducing failure rates and time costs in discovery and development of nanodrugs. However, there are still a few articles to examine, and it is necessary to summarize the development of the research direction. In the review, we summarize application of computing in various stages of nanodrug R&D, including physicochemical properties and biological activities prediction, pharmacokinetics analysis, toxicological assessment and other related applications. Moreover, current challenges and future perspectives of the computing methods are also discussed, with a view to help computing become a high-practicability and -efficiency auxiliary tool in nanodrugs discovery and development.

Predicting the toxicity of nanoparticles using artificial intelligence tools: a systematic review

Nanoparticles have been used extensively in different scientific fields. Due to the possible destructive effects of nanoparticles on the environment or the biological systems, their toxicity evaluation is a crucial phase for studying nanomaterial safety. In the meantime, experimental approaches for toxicity assessment of various nanoparticles are expensive and time-consuming. Thus, an alternative technique, such as artificial intelligence (AI), could be valuable for predicting nanoparticle toxicity. Therefore, in this review, the AI tools were investigated for the toxicity assessment of nanomaterials. To this end, a systematic search was performed on PubMed, Web of Science, and Scopus databases. Articles were included or excluded based on pre-defined inclusion and exclusion criteria, and duplicate studies were excluded. Finally, twenty-six studies were included. The majority of the studies were conducted on metal oxide and metallic nanoparticles. In addition, Random Forest (RF) and Support Vector Machine (SVM) had the most frequency in the included studies. Most of the models demonstrated acceptable performance. Overall, AI could provide a robust, fast, and low-cost tool for the evaluation of nanoparticle toxicity.

Graph Neural Tree: A novel and interpretable deep learning-based framework for accurate molecular property predictions

Determining various properties of molecules is a critical step in drug discovery. Recently, with the improvement of large heterogeneous datasets and the development of deep learning approaches, more and more scientists have turned their attention to neural network-based virtual preliminary screening to reduce the time and monetary cost of drug discovery. However, the poor interpretability of deep learning masks causality, so models' conclusions are often beyond the comprehension of human users, which reduces the credibility of the model and makes it difficult for chemists to further narrow the huge chemical space based on models' results. Thus, this study develops a novel framework consisting of Graph Neural Networks for feature extraction, Curriculum-Based Learning Strategies for optimization, and a Learning Binary Neural Tree (LBNT) for prediction, to improve the performance of neural networks and reveal their decision-making process to chemists. The framework encodes molecular graph data with graph neural networks (GNNs), then retrains the encoder with curriculum-based learning strategies to reduce uncertainty and improve accuracy, and finally uses LBNT as the predictor, which joint retrains with the encoder after independently training, for prediction and visualization. The framework is validated on the public datasets and compared to single GNNs with normal training strategies as well as GNN encoders with common machine learning predictors instead of the LBNT predictor. The result reveals that the proposed framework enhances the point prediction accuracy of the completely trained GNN and reduces its uncertainty through curriculum-based learning, and further improves the accuracy by combining LBNT. Besides, compared with common machine learning tools, the LBNT predictor generally has the best performance because of joint retraining with the GNN encoder. The decision-making process of LBNT is also better and easier to explain than that of other models.

Environmental behavior, human health effect, and pollution control of heavy metal(loid)s toward full life cycle processes

Heavy metal(loid)s (HMs) have caused serious environmental pollution and health risks. Although the past few years have witnessed the achievements of studies on environmental behavior of HMs, the related toxicity mechanisms, and pollution control, their relationship remains a mystery. Researchers generally focused on one topic independently without comprehensive considerations due to the knowledge gap between environmental science and human health. Indeed, the full life cycle control of HMs is crucial and should be reconsidered with the combination of the occurrence, transport, and fate of HMs in the environment. Therefore, we started by reviewing the environmental behaviors of HMs which are affected by a variety of natural factors as well as their physicochemical properties. Furthermore, the related toxicity mechanisms were discussed according to exposure route, toxicity mechanism, and adverse consequences. In addition, the current state-of-the-art of available technologies for pollution control of HMs wastewater and solid wastes were summarized. Finally, based on the research trend, we proposed that advanced in-operando characterizations will help us better understand the fundamental reaction mechanisms, and big data analysis approaches will aid in establishing the prediction model for risk management.

Trichloroethylene remediation using zero-valent iron with kaolin clay, activated carbon and bacteria

Nanoscale particles of zero-valent iron were used to form a permeable reactive barrier whose performance in dechlorinating a solution of trichloroethylene was compared with that of a barrier formed from limestone. The iron was combined with kaolin by calcination. The test liquid contained sewage sludge, and also added NH₄Cl and KH₂PO₄. The average removal rates of trichloroethylene and phosphorus over 365 days both exceeded 94%. Chemical oxygen demand was reduced by 92% and ammonium nitrogen by 43.6%. All were significantly greater than the removals with the limestone barrier. The ceramsite barrier retained 85% of its effectiveness even after 365 days of use. Dechloromonas sp. was the main dechlorinating bacterium, but its removal ability is limited. The removal of trichloroethylene in such a barrier mainly depends on reduction by the zero-valent iron and biodegradation. The results show that the prepared ceramsite is stable and effective in removing trichloroethylene from water. It is a promising in-situ remediation material for groundwater.

Mapping of machine learning approaches for description, prediction, and causal inference in the social and health sciences

Machine learning (ML) methodology used in the social and health sciences needs to fit the intended research purposes of description, prediction, or causal inference. This paper provides a comprehensive, systematic meta-mapping of research questions in the social and health sciences to appropriate ML approaches by incorporating the necessary requirements to statistical analysis in these disciplines. We map the established classification into description, prediction, counterfactual prediction, and causal structural learning to common research goals, such as estimating prevalence of adverse social or health outcomes, predicting the risk of an event, and identifying risk factors or causes of adverse outcomes, and explain common ML performance metrics. Such mapping may help to fully exploit the benefits of ML while considering domain-specific aspects relevant to the social and health sciences and hopefully contribute to the acceleration of the uptake of ML applications to advance both basic and applied social and health sciences research.

Machine learning in the identification, prediction and exploration of environmental toxicology: Challenges and perspectives

Over the past few decades, data-driven machine learning (ML) has distinguished itself from hypothesis-driven studies and has recently received much attention in environmental toxicology. However, the use of ML in environmental toxicology remains in the early stages, with knowledge gaps, technical bottlenecks in data quality, high-dimensional/heterogeneous/small-sample data analysis and model interpretability, and a lack of an in-depth understanding of environmental toxicology. Given the above problems, we review the recent progress in the literature and highlight state-of-the-art toxicological studies using ML (such as learning and predicting toxicity in complicated biosystems and multiple-factor environmental scenarios of long-term and large-scale pollution). Beyond predicting simple biological endpoints by integrating untargeted omics and adverse outcome pathways, ML development should focus on revealing toxicological mechanisms. The integration of data-driven ML with other methods (e.g., omics analysis and adverse outcome pathway frameworks) endows ML with widely promising application in revealing toxicological mechanisms. High-quality databases and interpretable algorithms are urgently needed for toxicology and environmental science. Addressing the core issues and future challenges for ML in this review may narrow the knowledge gap between environmental toxicity and computational science and facilitate the control of environmental risk in the future.

Development, Validation, and Application of a Human Reproductive Toxicity Prediction Model Based on Adverse Outcome Pathway

A growing number of environmental contaminants have been proved to have reproductive toxicity to males and females. However, the unclear toxicological mechanism of reproductive toxicants limits the development of virtual screening methods. By consolidating androgen (AR)-/estrogen receptors (ERs)-mediated adverse outcome pathways (AOPs) with more than 8000 chemical substances, we uncovered relationships between chemical features, a series of pathway-related effects, and reproductive apical outcomes─changes in sex organ weights. An AOP-based computational model named RepTox was developed and evaluated to predict and characterize chemicals' reproductive toxicity for males and females. Results showed that RepTox has three outstanding advantages. (I) Compared with the traditional models (37 and 81% accuracy, respectively), AOP significantly improved the predictive robustness of RepTox (96.3% accuracy). (II) Compared with the application domain (AD) of models based on small in vivo datasets, AOP expanded the ADs of RepTox by 1.65-fold for male and 3.77-fold for female, respectively. (III) RepTox implied that hydrophobicity, cyclopentanol substructure, and several topological indices (e.g., hydrogen-bond acceptors) were important, unbiased features associated with reproductive toxicants. Finally, RepTox was applied to the inventory of existing chemical substances of China and identified 2100 and 7281 potential toxicants to the male and female reproductive systems, respectively.

Machine learning predicts ecological risks of nanoparticles to soil microbial communities

With the rapid development of nanotechnology in agriculture, there is increasing urgency to assess the impacts of nanoparticles (NPs) on the soil environment. This study merged raw high-throughput sequencing (HTS) data sets generated from 365 soil samples to reveal the potential ecological effects of NPs on soil microbial community by means of metadata analysis and machine learning methods. Metadata analysis showed that treatment with nanoparticles did not have a significant impact on the alpha diversity of the microbial community, but significantly altered the beta diversity. Unfortunately, the abundance of several beneficial bacteria, such as Dyella, Methylophilus, Streptomyces, which promote the growth of plants, and improve pathogenic resistance, was reduced under the addition of synthetic nanoparticles. Furthermore, metadata demonstrated that nanoparticles treatment weakened the biosynthesis ability of cofactors, carriers, and vitamins, and enhanced the degradation ability of aromatic compounds, amino acids, etc. This is unfavorable for the performance of soil functions. Besides the soil heterogeneity, machine learning uncovered that a) the exposure time of nanoparticles was the most important factor to reshape the soil microbial community, and b) long-term exposure decreased the diversity of microbial community and the abundance of beneficial bacteria. This study is the first to use a machine learning model and metadata analysis to investigate the relationship between the properties of nanoparticles and the hazards to the soil microbial community from a macro perspective. This guides the rational use of nanoparticles for which the impacts on soil microbiota are minimized.

Multiple factors drive imbalance in the global microbial assemblage in soil

Soil microbial assemblages play a critical role in biogeochemical cycling processes in terrestrial ecosystems. Dynamic global information for these assemblages considering multiple factors is critical for predicting ecological safety concerns but remains unpredictable. Here, we collected microbial data from soil datasets worldwide and used a feature-explicable machine learning (FEML) approach to address this problem. Multiple-factor and factor interaction network analysis based on FEML can be used to visualize the restrictive relationships among multiple factors (e.g., fertilizer application, land use, and changing global climate and natural environments), which are difficult to explore based on limited experimental data and traditional machine learning methods. The FEML approach predicted that areas of bacterial hotspots in South America and Africa will expand by approximately 27% and 83%, respectively, in scenario RCP8.5 in 2100. In contrast, the areas of fungal hotspots in Asia and North America will decline by approximately 34% and 62%, respectively, under RCP8.5. The unbalanced ratios of bacteria to fungi affect the soil ecosystem, and bacterial-dominated communities contribute to the reduction of easily decomposing nutrients, the growth of the bacterivore community and a high proportion of microaggregates in the soil. Therefore, mitigating climate change is critical to reduce the remarkable imbalance between soil bacteria and fungi and predict risks to soil microbial assemblages based on multiple factors.

Convolutional neural network-based applied research on the enrichment of heavy metals in the soil-rice system in China

The enrichment of heavy metals in the soil-rice system is affected by various factors, which hampers the prediction of heavy metal concentrations. In this research, a prediction model (CNN-HM) of heavy metal concentrations in rice was constructed based on convolutional neural network (CNN) technology and 17 environmental factors. For comparison, other machine learning models, such as multiple linear regression, Bayesian ridge regression, support vector machine, and backpropagation neural networks, were applied. Furthermore, the LH-OAT method was used to evaluate the sensitivity of CNN-HM to each environmental factor. The results showed that the R² values of CNN-HM for Cd, Pb, Cr, As, and Hg were 0.818, 0.709, 0.688, 0.462, and 0.816, respectively, and both the MAE and RMAE values were acceptable. The sensitivity analysis showed that the concentrations of Cd and Pb, mechanical composition, soil pH, and altitude were the main sensitive features for CNN-HM. Compared with CNN-HM based on all input features, the performance of the quick prediction model that was based on the sensitive features did not degrade significantly, thereby indicating that CNN-HM has stronger stability and robustness. The quick prediction model has extensive application value for timely prediction of the enrichment of heavy metals in emergencies. This study demonstrated the effectiveness and practicability of CNNs in predicting heavy metal enrichment in the soil-rice system and provided a new perspective and solution for heavy metal prediction.

Machine learning may accelerate the recognition and control of microplastic pollution: Future prospects

Microplastics (MPs, sizes <5 mm) have been found to be widely distributed in various environments, such as marine, freshwater, terrestrial and atmospheric systems. Machine learning provides a potential solution for evaluating the ecological risks of MPs based on big data. Compared with traditional models, data-driven machine learning can accelerate the realization of the control of hazardous MPs and reduce the impact of MPs at both local and global scales. However, there are some urgent issues that should be resolved. For example, lack of MP databases and incomparable literatures causing the current MP data cannot fully support big data research. Therefore, it is imperative to formulate a set of standard and universal MP collection and testing protocols. For machine learning, predictions of large-scale MP distribution and the corresponding environmental risks remain lacking. To accelerate studies of MPs in the future, the methods and theories achieved for other particle pollutants, such as nanomaterials and aerosols, can be referenced. Beyond predication alone, the improvement of causality and interpretability of machine learning deserves attention in the studies of MP risks. Overall, this perspective paper provides insights for the development of machine learning methods in research on the environmental risks of MPs.

Intelligent control of nanoparticle synthesis through machine learning

The synthesis of nanoparticles is affected by many reaction conditions, and their properties are usually determined by factors such as their size, shape and surface chemistry. In order for the synthesized nanoparticles to have functions suitable for different fields (for example, optics, electronics, sensor applications and so on), precise control of their properties is essential. However, with the current technology of preparing nanoparticles on a microreactor, it is time-consuming and laborious to achieve precise synthesis. In order to improve the efficiency of synthesizing nanoparticles with the expected functionality, the application of machine learning-assisted synthesis is an intelligent choice. In this article, we mainly introduce the typical methods of preparing nanoparticles on microreactors, and explain the principles and procedures of machine learning, as well as the main ways of obtaining data sets. We have studied three types of representative nanoparticle preparation methods assisted by machine learning. Finally, the current problems in machine learning-assisted nanoparticle synthesis and future development prospects are discussed.

Artificial intelligence to bring nanomedicine to life

The technology of drug delivery systems (DDSs) has demonstrated an outstanding performance and effectiveness in production of pharmaceuticals, as it is proved by many FDA-approved nanomedicines that have an enhanced selectivity, manageable drug release kinetics and synergistic therapeutic actions. Nonetheless, to date, the rational design and high-throughput development of nanomaterial-based DDSs for specific purposes is far from a routine practice and is still in its infancy, mainly due to the limitations in scientists' capabilities to effectively acquire, analyze, manage, and comprehend complex and ever-growing sets of experimental data, which is vital to develop DDSs with a set of desired functionalities. At the same time, this task is feasible for the data-driven approaches, high throughput experimentation techniques, process automatization, artificial intelligence (AI) technology, and machine learning (ML) approaches, which is referred to as The Fourth Paradigm of scientific research. Therefore, an integration of these approaches with nanomedicine and nanotechnology can potentially accelerate the rational design and high-throughput development of highly efficient nanoformulated drugs and smart materials with pre-defined functionalities. In this Review, we survey the important results and milestones achieved to date in the application of data science, high throughput, as well as automatization approaches, combined with AI and ML to design and optimize DDSs and related nanomaterials. This manuscript mission is not only to reflect the state-of-art in data-driven nanomedicine, but also show how recent findings in the related fields can transform the nanomedicine's image. We discuss how all these results can be used to boost nanomedicine translation to the clinic, as well as highlight the future directions for the development, data-driven, high throughput experimentation-, and AI-assisted design, as well as the production of nanoformulated drugs and smart materials with pre-defined properties and behavior. This Review will be of high interest to the chemists involved in materials science, nanotechnology, and DDSs development for biomedical applications, although the general nature of the presented approaches enables knowledge translation to many other fields of science.

Multifeature superposition analysis of the effects of microplastics on microbial communities in realistic environments

Microplastic (MP) contamination has become an increasingly serious environmental problem. However, the risks of MP contamination in complex global climatic and geographic scenarios remain unclear. We established a multifeature superposition analysis boosting (MFAB) machine learning (ML) approach to address the above knowledge gap. MFAB-ML identified and predicted the importance, interaction networks and superposition effects of multiple features, including 34 characteristic variables (e.g., MP contamination and climatic and geographic variables), from 1354 samples distributed globally. MFAB-ML analysis achieved realistic and significant results, in some cases even opposite to those obtained using a single or a few features, revealing the importance of considering complicated scenarios. We found that the microbial diversity in East Asian seas will continually decrease due to the superposition effects of MPs with ocean warming; for example, the Chao1 index will decrease by 10.32% by 2065. The present work provides a powerful approach to identify and predict the multifeature superposition effects of pollutants on realistic environments in complicated climatic and geographic scenarios, overcoming the bias from general studies.

Merging data curation and machine learning to improve nanomedicines

Nanomedicine design is often a trial-and-error process, and the optimization of formulations and in vivo properties requires tremendous benchwork. To expedite the nanomedicine research progress, data science is steadily gaining importance in the field of nanomedicine. Recently, efforts have explored the potential to predict nanomaterials synthesis and biological behaviors via advanced data analytics. Machine learning algorithms process large datasets to understand and predict various material properties in nanomedicine synthesis, pharmacologic parameters, and efficacy. "Big data" approaches may enable even larger advances, especially if researchers capitalize on data curation methods. However, the concomitant use of data curation processes needed to facilitate the acquisition and standardization of large, heterogeneous data sets, to support advanced data analytics methods such as machine learning has yet to be leveraged. Currently, data curation and data analytics areas of nanotechnology-focused data science, or 'nanoinformatics', have been proceeding largely independently. This review highlights the current efforts in both areas and the potential opportunities for coordination to advance the capabilities of data analytics in nanomedicine.

Predicting Nanoparticle Delivery to Tumors Using Machine Learning and Artificial Intelligence Approaches

Background

Low delivery efficiency of nanoparticles (NPs) to the tumor is a critical barrier in the field of cancer nanomedicine. Strategies on how to improve NP tumor delivery efficiency remain to be determined.

Methods

This study analyzed the roles of NP physicochemical properties, tumor models, and cancer types in NP tumor delivery efficiency using multiple machine learning and artificial intelligence methods, using data from a recently published Nano-Tumor Database that contains 376 datasets generated from a physiologically based pharmacokinetic (PBPK) model.

Results

The deep neural network model adequately predicted the delivery efficiency of different NPs to different tumors and it outperformed all other machine learning methods; including random forest, support vector machine, linear regression, and bagged model methods. The adjusted determination coefficients (R2) in the full training dataset were 0.92, 0.77, 0.77 and 0.76 for the maximum delivery efficiency (DEmax), delivery efficiency at 24 h (DE24), at 168 h (DE168), and at the last sampling time (DETlast). The corresponding R2 values in the test dataset were 0.70, 0.46, 0.33 and 0.63, respectively. Also, this study showed that cancer type was an important determinant for the deep neural network model in predicting the tumor delivery efficiency across all endpoints (19-29%). Among all physicochemical properties, the Zeta potential and core material played a greater role than other properties, such as the type, shape, and targeting strategy.

Conclusion

This study provides a quantitative model to improve the design of cancer nanomedicine with greater tumor delivery efficiency. These results help to improve our understanding of the causes of low NP tumor delivery efficiency. This study demonstrates the feasibility of integrating artificial intelligence with PBPK modeling approaches to study cancer nanomedicine.

Combinatorial Polycation Synthesis and Causal Machine Learning Reveal Divergent Polymer Design Rules for Effective pDNA and Ribonucleoprotein Delivery

The development of polymers that can replace engineered viral vectors in clinical gene therapy has proven elusive despite the vast portfolios of multifunctional polymers generated by advances in polymer synthesis. Functional delivery of payloads such as plasmids (pDNA) and ribonucleoproteins (RNP) to various cellular populations and tissue types requires design precision. Herein, we systematically screen a combinatorially designed library of 43 well-defined polymers, ultimately identifying a lead polycationic vehicle (P38) for efficient pDNA delivery. Further, we demonstrate the versatility of P38 in codelivering spCas9 RNP and pDNA payloads to mediate homology-directed repair as well as in facilitating efficient pDNA delivery in ARPE-19 cells. P38 achieves nuclear import of pDNA and eludes lysosomal processing far more effectively than a structural analogue that does not deliver pDNA as efficiently. To reveal the physicochemical drivers of P38's gene delivery performance, SHapley Additive exPlanations (SHAP) are computed for nine polyplex features, and a causal model is applied to evaluate the average treatment effect of the most important features selected by SHAP. Our machine learning interpretability and causal inference approach derives structure-function relationships underlying delivery efficiency, polyplex uptake, and cellular viability and probes the overlap in polymer design criteria between RNP and pDNA payloads. Together, combinatorial polymer synthesis, parallelized biological screening, and machine learning establish that pDNA delivery demands careful tuning of polycation protonation equilibria while RNP payloads are delivered most efficaciously by polymers that deprotonate cooperatively via hydrophobic interactions. These payload-specific design guidelines will inform further design of bespoke polymers for specific therapeutic contexts.

Effectively Increasing Pt Utilization Efficiency of the Membrane Electrode Assembly in Proton Exchange Membrane Fuel Cells through Multiparameter Optimization Guided by Machine Learning

Although proton exchange membrane fuel cells have received attention, the high costs associated with Pt-based catalysts in membrane electrode assemblies (MEAs) remain a huge obstacle for large-scale applications. To solve this urgent problem, the utilization efficiency of Pt in MEAs must be increased. Facing numerous interacting parameters in an attempt to keep experimental costs as low as possible, we innovatively introduce machine learning (ML) to achieve this goal. Nine different ML algorithms are trained on the experimental dataset from our laboratory to precisely predict the performance and Pt utilization (maximum R² = 0.973/0.968). To determine the best synthesis conditions, black-box interpretation methods are applied to provide reliable insights from both qualitative and quantitative perspectives. The optimized choices of ionomer/catalyst ratio, water content, organic solvent, catalyst loading, stirring method, solid content, and ultrasonic spraying flow rate are properly made with few experimental attempts under ML results' guidance. Promising Pt utilization of 0.147 gPt kW^-1 and a power density of 1.02 W cm^-2 are achieved at 0.6 V in a single cell (H₂/air) at an ultralow total loading of 0.15 mg Pt cm^-2. Therefore, this work contributes to the economy of hydrogen energy by paving the way for MEA optimization with complex parameters by ML.

Evaluating the capability of municipal solid waste separation in China based on AHP-EWM and BP neural network

With the increase in municipal solid waste (MSW), most cities face solid waste management issues. In this study, the analytic hierarchy process (AHP) and artificial neural network (ANN) models were improved to assess the MSW separation capability based on 18 selected indicators of solid waste separation in 15 cities in China. The entropy weight method (EWM) was used in AHP to optimize and determine the indicators and then evaluate their weights, which showed that the general public budget expenditure had the highest weight (0.5239). This implied that the MSW separation capability could be mainly influenced by government financial support. ANN based on scan optimization and machine learning methods were established (R² = 0.9992) to predict the missing indicators. The mapping relationship between MSW separation indicators and capabilities was also significantly improved from R² = 0.5317 to R² = 0.9993, thereby increasing the prediction accuracy of MSW separation capabilities to 95.15%. Thus, this research provides a new avenue for MSW separation and establishes a combined model to predict the separation capability in practical applications.

Usefulness of Random Forest Algorithm in Predicting Severe Acute Pancreatitis

BACKGROUND AND AIMS

This study aimed to develop an interpretable random forest model for predicting severe acute pancreatitis (SAP).

METHODS

Clinical and laboratory data of 648 patients with acute pancreatitis were retrospectively reviewed and randomly assigned to the training set and test set in a 3:1 ratio. Univariate analysis was used to select candidate predictors for the SAP. Random forest (RF) and logistic regression (LR) models were developed on the training sample. The prediction models were then applied to the test sample. The performance of the risk models was measured by calculating the area under the receiver operating characteristic (ROC) curves (AUC) and area under precision recall curve. We provide visualized interpretation by using local interpretable model-agnostic explanations (LIME).

RESULTS

The LR model was developed to predict SAP as the following function: -1.10-0.13×albumin (g/L) + 0.016 × serum creatinine (μmol/L) + 0.14 × glucose (mmol/L) + 1.63 × pleural effusion (0/1)(No/Yes). The coefficients of this formula were utilized to build a nomogram. The RF model consists of 16 variables identified by univariate analysis. It was developed and validated by a tenfold cross-validation on the training sample. Variables importance analysis suggested that blood urea nitrogen, serum creatinine, albumin, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, calcium, and glucose were the most important seven predictors of SAP. The AUCs of RF model in tenfold cross-validation of the training set and the test set was 0.89 and 0.96, respectively. Both the area under precision recall curve and the diagnostic accuracy of the RF model were higher than that of both the LR model and the BISAP score. LIME plots were used to explain individualized prediction of the RF model.

CONCLUSIONS

An interpretable RF model exhibited the highest discriminatory performance in predicting SAP. Interpretation with LIME plots could be useful for individualized prediction in a clinical setting. A nomogram consisting of albumin, serum creatinine, glucose, and pleural effusion was useful for prediction of SAP.