ResNet18DNN: prediction approach of drug-induced liver injury by deep neural network with ResNet18

Deep-learning approach for developing bilayered electromagnetic interference shielding composite aerogels based on multimodal data fusion neural networks

A non-experimental approach to developing high-performance EMI shielding materials is urgently needed to reduce costs and manpower. In this investigation, a multimodal data fusion neural network model is proposed to predict the EMI shielding performances of silver-modified four-pronged zinc oxide/waterborne polyurethane/barium ferrite (Ag@F-ZnO/WPU/BF) aerogels. First, 16 Ag@F-ZnO/WPU/BF samples with varying Ag@F-ZnO and BF contents were successfully prepared using the pre-casting and directional freezing techniques. The experimental results demonstrate that these aerogels perform well in terms of averaged EMI shielding effectiveness (SET) up to 78.6 dB and absorption coefficient as high as 0.96. On the basis of composite ingredients and microstructural images, the established multimodal neural network model can effectively predict the EMI shielding performances of Ag@F-ZnO/WPU/BF aerogels. Notably, the multimodal model of fully connected neural network (FCNN) and residual neural network (ResNet) utilizing GatedFusion method yields the best root mean squared error (RMSE) and mean absolute error (MAE) values of 0.7626 and 0.4918, respectively, and correlation coefficient (R) of 0.9885. In addition, this multimodal model successfully predicts the EMI performances of four new aerogels with an average error of less than 5 %, demonstrating its strong generalization capability. The accuracy and efficiency of material property prediction based on multimodal neural network model are largely improved by integrating multiple data sources, offering new possibility for reducing experimental burdens, accelerating the development of new materials, and gaining a deeper understanding of material mechanisms.

Leveraging FDA Labeling Documents and Large Language Model to Enhance Annotation, Profiling, and Classification of Drug Adverse Events with AskFDALabel

BACKGROUND

Drug adverse events (AEs) represent a significant public health concern. US Food and Drug Administration (FDA) drug labeling documents are an essential resource for studying drug safety such as assessing a drug's likelihood to cause certain organ toxicities; however, the manual extraction of AEs is labor-intensive, requires specialized expertise, and is challenging to maintain, due to frequent updates of the labeling documents.

OBJECTIVE

To automate the extraction of AE data from FDA drug labeling documents, we developed a workflow based on AskFDALabel, a large language model (LLM)-powered framework, and its demonstration in drug safety studies.

METHODS

This framework incorporates a retrieval-augmented generation (RAG) component based on FDALabel to enhance standard LLM inference. Key steps include (1) selection of a task-specific template, (2) FDALabel database querying, and (3) content preparation for LLM processing. We evaluated the performance of the framework in three benchmark experiments, including drug-induced liver injury (DILI) classification, drug-induced cardiotoxicity (DICT) classification, and AE term recognition.

RESULTS

AskFDALabel achieved F1-scores of 0.978 for DILI, 0.931 for DICT, and 0.911 for AE annotation, outperforming other traditional methods. It also provided cited labeling content and detailed explanations, facilitating manual verification.

CONCLUSION

AskFDALabel exhibited high consistency with human AE annotation, particularly in classifying and profiling DILI and DICT. Thus, it can significantly enhance the efficiency and accuracy of AE annotation, with promising potential for advanced AE surveillance and drug safety research.

Predicting treatment response to systemic therapy in advanced gallbladder cancer using multiphase enhanced CT images

BACKGROUND

Accurate estimation of treatment response can help clinicians identify patients who would potentially benefit from systemic therapy. This study aimed to develop and externally validate a model for predicting treatment response to systemic therapy in advanced gallbladder cancer (GBC).

METHODS

We recruited 399 eligible GBC patients across four institutions. Multivariable logistic regression analysis was performed to identify independent clinical factors related to therapeutic efficacy. This deep learning (DL) radiomics signature was developed for predicting treatment response using multiphase enhanced CT images. Then, the DL radiomic-clinical (DLRSC) model was built by combining the DL signature and significant clinical factors, and its predictive performance was evaluated using area under the curve (AUC). Gradient-weighted class activation mapping analysis was performed to help clinicians better understand the predictive results. Furthermore, patients were stratified into low- and high-score groups by the DLRSC model. The progression-free survival (PFS) and overall survival (OS) between the two different groups were compared.

RESULTS

Multivariable analysis revealed that tumor size was a significant predictor of efficacy. The DLRSC model showed great predictive performance, with AUCs of 0.86 (95% CI, 0.82-0.89) and 0.84 (95% CI, 0.80-0.87) in the internal and external test datasets, respectively. This model showed great discrimination, calibration, and clinical utility. Moreover, Kaplan-Meier survival analysis revealed that low-score group patients who were insensitive to systemic therapy predicted by the DLRSC model had worse PFS and OS.

CONCLUSION

The DLRSC model allows for predicting treatment response in advanced GBC patients receiving systemic therapy. The survival benefit provided by the DLRSC model was also assessed.

KEY POINTS

Question No effective tools exist for identifying patients who would potentially benefit from systemic therapy in clinical practice. Findings Our combined model allows for predicting treatment response to systemic therapy in advanced gallbladder cancer. Clinical relevance With the help of this model, clinicians could inform patients of the risk of potential ineffective treatment. Such a strategy can reduce unnecessary adverse events and effectively help reallocate societal healthcare resources.

Evaluating the synergistic use of advanced liver models and AI for the prediction of drug-induced liver injury

INTRODUCTION

Drug-induced liver injury (DILI) is a leading cause of acute liver failure. Hepatotoxicity typically occurs only in a subset of individuals after prolonged exposure and constitutes a major risk factor for the termination of drug development projects.

AREAS COVERED

We provide an overview of available human liver models for DILI research and discuss how they have been used to aid in early risk assessments and to mitigate the risk of project closures due to DILI in clinical stages. We summarize the different data that can be provided by such models and illustrate how these diverse data types can be interfaced with machine learning strategies to improve predictions of liver safety liabilities.

EXPERT OPINION

Advanced human liver models closely mimic human liver phenotypes and functions for many weeks, allowing for the recapitulation of hepatotoxicity events in vitro. Integration of the biochemical, histological, and toxicogenomic output data from these models with physicochemical compound properties using different machine learning architectures holds promise to enhance preclinical DILI predictions. However, to realize this aim, it is important to benchmark the available liver models on test sets of DILI positive and negative compounds and to carefully annotate and share the resulting data.

The prediction of RNA-small-molecule ligand binding affinity based on geometric deep learning

Small molecule-targeted RNA is an emerging technology that plays a pivotal role in drug discovery and inhibitor design, with widespread applications in disease treatment. Consequently, predicting RNA-small-molecule ligand interactions is crucial. With advancements in computer science and the availability of extensive biological data, deep learning methods have shown great promise in this area, particularly in efficiently predicting RNA-small molecule binding sites. However, few computational methods have been developed to predict RNA-small molecule binding affinities. Meanwhile, most of these approaches rely primarily on sequence or structural representations. Molecular surface information, vital for RNA and small molecule interactions, has been largely overlooked. To address these gaps, we propose a geometric deep learning method for predicting RNA-small molecule binding affinity, named RNA-ligand Surface Interaction Fingerprinting (RLASIF). In this study, we create RNA-ligand interaction fingerprints from the geometrical and chemical features present on molecular surface to characterize binding affinity. RLASIF outperformed other computational methods across ten different test sets from PDBbind NL2020. Compared to the second-best method, our approach improves performance by 10.01 %, 6.67 %, 2.01 % and 1.70 % on four evaluation metrics, indicating its effectiveness in capturing key features influencing RNA-ligand binding strength. Additionally, RLASIF holds potential for virtual screening of potential ligands for RNA and predicting small molecule binding nucleotides within RNA structures.

Machine Learning-Enabled Drug-Induced Toxicity Prediction

Unexpected toxicity has become a significant obstacle to drug candidate development, accounting for 30% of drug discovery failures. Traditional toxicity assessment through animal testing is costly and time-consuming. Big data and artificial intelligence (AI), especially machine learning (ML), are robustly contributing to innovation and progress in toxicology research. However, the optimal AI model for different types of toxicity usually varies, making it essential to conduct comparative analyses of AI methods across toxicity domains. The diverse data sources also pose challenges for researchers focusing on specific toxicity studies. In this review, 10 categories of drug-induced toxicity is examined, summarizing the characteristics and applicable ML models, including both predictive and interpretable algorithms, striking a balance between breadth and depth. Key databases and tools used in toxicity prediction are also highlighted, including toxicology, chemical, multi-omics, and benchmark databases, organized by their focus and function to clarify their roles in drug-induced toxicity prediction. Finally, strategies to turn challenges into opportunities are analyzed and discussed. This review may provide researchers with a valuable reference for understanding and utilizing the available resources to bridge prediction and mechanistic insights, and further advance the application of ML in drugs-induced toxicity prediction.

Integration of histopathological images and immunological analysis to predict M2 macrophage infiltration and prognosis in patients with serous ovarian cancer

Objective

Investigating the effect of M2 macrophage infiltration on overall survival and to use histopathological imaging features (HIF) to predict M2 macrophage infiltration in patients with serous ovarian cancer (SOC) is important for improving prognostic accuracy, identifying new therapeutic targets, and advancing personalized treatment approaches.

Methods

We downloaded data from 86 patients with SOC from The Cancer Genome Atlas (TCGA) and divided these patients into a training set and a validation set with a ratio of 8:2. In addition, tissue microarrays from 106 patients with SOC patients were included as an external validation set. HIF were recognized by deep multiple instance learning (MIL) to predict M2 macrophage infiltration via theResNet18 network in the training set. The final model was evaluated using the internal and external validation set.

Results

Using data acquired from the TCGA database, we applied univariate Cox analysis and determined that higher levels of M2 macrophage infiltration were associated with a poor prognosis (hazard ratio [HR]=6.8; 95% CI [confidence interval]: 1.6-28, P=0.0083). External validation revealed that M2 macrophage infiltration was an independent risk factor for the prognosis of patients with SOC (HR=3.986; 95% CI: 2.436-6.522; P<0.001). Next, we constructed four MIL strategies (Mean probability, Top-10 Mean, Top-100 Mean, and Maximum probability) to identify histopathological images that could predict M2 macrophage infiltration. The Mean Probability Method was the most suitable and was used to generate a HIF model with an AUC, recall rate, precision and F1 score of 0.7500, 0.6932, 0.600, 0.600, and 0.600, respectively.

Conclusions

Collectively, our findings indicated that M2 macrophage infiltration may increase prognostic prediction for SOC patients. Machine deep learning of pathological immunohistochemical images exhibited good potential for the direct prediction of M2 macrophage infiltration.

ConvXGB: A novel deep learning model to predict recurrence risk of early-stage cervical cancer following surgery using multiparametric MRI images

BACKGROUND

Accurate estimation of recurrence risk for cervical cancer plays a pivot role in making individualized treatment plans. We aimed to develop and externally validate an end-to-end deep learning model for predicting recurrence risk in cervical cancer patients following surgery by using multiparametric MRI images.

METHODS

The clinicopathologic data and multiparametric MRI images of 406 cervical cancer patients from three institutions were collected. We designed a novel deep learning model called "ConvXGB" for predicting recurrence risk by combining the convolutional neural network (CNN) and eXtreme Gradient Boost (XGBoost). The predictive performance of the ConvXGB model was evaluated using time-dependent area under curve (AUC), compared with the deep learning radio-clinical model, clinical model, conventional radiomics nomogram and an existing histology-specific tool. The potential of the ConvXGB model in predicting the recurrence-free survival (RFS) and overall survival (OS) was assessed.

RESULTS

The ConvXGB model outperformed other models in predicting recurrence risk, with AUCs for 1 and 3 year-RFS of 0.872(95% CI, 0.857-0.906) and 0.882(95% CI, 0.860-0.904) respectively in the test cohort. This model showed better discrimination, calibration and clinical utility. Grad-CAM analysis was adopted to help clinicians better understand the predictive results. Moreover, Kaplan-Meier survival analysis revealed that patients who were stratified into high-risk group by the ConvXGB model were significantly susceptible to higher cumulative recurrence risk rates and worse outcome.

CONCLUSION

The ConvXGB model allowed for predicting postoperative recurrence risk in cervical cancer patients and for stratifying the risk of RFS and OS.

Multi-task aquatic toxicity prediction model based on multi-level features fusion

INTRODUCTION

With the escalating menace of organic compounds in environmental pollution imperiling the survival of aquatic organisms, the investigation of organic compound toxicity across diverse aquatic species assumes paramount significance for environmental protection. Understanding how different species respond to these compounds helps assess the potential ecological impact of pollution on aquatic ecosystems as a whole. Compared with traditional experimental methods, deep learning methods have higher accuracy in predicting aquatic toxicity, faster data processing speed and better generalization ability.

OBJECTIVES

This article presents ATFPGT-multi, an advanced multi-task deep neural network prediction model for organic toxicity.

METHODS

The model integrates molecular fingerprints and molecule graphs to characterize molecules, enabling the simultaneous prediction of acute toxicity for the same organic compound across four distinct fish species. Furthermore, to validate the advantages of multi-task learning, we independently construct prediction models, named ATFPGT-single, for each fish species. We employ cross-validation in our experiments to assess the performance and generalization ability of ATFPGT-multi.

RESULTS

The experimental results indicate, first, that ATFPGT-multi outperforms ATFPGT-single on four fish datasets with AUC improvements of 9.8%, 4%, 4.8%, and 8.2%, respectively, demonstrating the superiority of multi-task learning over single-task learning. Furthermore, in comparison with previous algorithms, ATFPGT-multi outperforms comparative methods, emphasizing that our approach exhibits higher accuracy and reliability in predicting aquatic toxicity. Moreover, ATFPGT-multi utilizes attention scores to identify molecular fragments associated with fish toxicity in organic molecules, as demonstrated by two organic molecule examples in the main text, demonstrating the interpretability of ATFPGT-multi.

CONCLUSION

In summary, ATFPGT-multi provides important support and reference for the further development of aquatic toxicity assessment. All of codes and datasets are freely available online at https://github.com/zhaoqi106/ATFPGT-multi.

NBCR-ac4C: A Deep Learning Framework Based on Multivariate BERT for Human mRNA N4-Acetylcytidine Sites Prediction

N4-acetylcytidine (ac4C) plays a crucial role in regulating cellular biological processes, particularly in gene expression regulation and disease development. However, experiments to identify ac4C in a wet lab are time-consuming and costly, and the learning-based methods struggle to capture the underlying semantic knowledge and relations within sequences. To address this, we propose a deep learning approach called NBCR-ac4C based on pretrained models. Specifically, we employ Nucleotide Transformer and DNABERT2 to construct contextual embedding of nucleotide sequences, which effectively mine and express context relations between different features in the sequence. Convolutional neural network (CNN) and ResNet18 are then applied to further extract shallow and deep knowledge from context embedding. Depending on extensive experiments for the prediction of ac4C sites in nucleotide sequences, we observe that NBCR-ac4C outperforms general learning-based models. It achieves the highest accuracy (ACC) of 83.51% and an Area Under the Receiver Operating Characteristic Curve (AUROC) of 89.58% on an independent test set. Moreover, the proposed model, compared to the current state-of-the-art (SOTA) model LSA-ac4C, demonstrates higher ACC and AUROC by 0.81-3.7% and 0.05-1.58%, respectively. The data set and code are available on https://github.com/2103374200/NBCR to facilitate further discussion on NBCR-ac4C.

Deep learning-assisted diagnosis of benign and malignant parotid gland tumors based on automatic segmentation of ultrasound images: a multicenter retrospective study

Objectives

To construct deep learning-assisted diagnosis models based on automatic segmentation of ultrasound images to facilitate radiologists in differentiating benign and malignant parotid tumors.

Methods

A total of 582 patients histopathologically diagnosed with PGTs were retrospectively recruited from 4 centers, and their data were collected for analysis. The radiomics features of six deep learning models (ResNet18, Inception_v3 etc) were analyzed based on the ultrasound images that were obtained under the best automatic segmentation model (Deeplabv3, UNet++, and UNet). The performance of three physicians was compared when the optimal model was used and not. The Net Reclassification Index (NRI) and Integrated Discrimination Improvement (IDI) were utilized to evaluate the clinical benefit of the optimal model.

Results

The Deeplabv3 model performed optimally in terms of automatic segmentation. The ResNet18 deep learning model had the best prediction performance, with an area under the receiver-operating characteristic curve of 0.808 (0.694-0.923), 0.809 (0.712-0.906), and 0.812 (0.680-0.944) in the internal test set and external test sets 1 and 2, respectively. Meanwhile, the optimal model-assisted clinical and overall benefits were markedly enhanced for two out of three radiologists (in internal validation set, NRI: 0.259 and 0.213 [p = 0.002 and 0.017], IDI: 0.284 and 0.201 [p = 0.005 and 0.043], respectively; in external test set 1, NRI: 0.183 and 0.161 [p = 0.019 and 0.008], IDI: 0.205 and 0.184 [p = 0.031 and 0.045], respectively; in external test set 2, NRI: 0.297 and 0.297 [p = 0.038 and 0.047], IDI: 0.332 and 0.294 [p = 0.031 and 0.041], respectively).

Conclusions

The deep learning model constructed for automatic segmentation of ultrasound images can improve the diagnostic performance of radiologists for PGTs.

Prediction of Drug-Induced Liver Injury: From Molecular Physicochemical Properties and Scaffold Architectures to Machine Learning Approaches

The process of developing new drugs is widely acknowledged as being time-intensive and requiring substantial financial investment. Despite ongoing efforts to reduce time and expenses in drug development, ensuring medication safety remains an urgent problem. One of the major problems involved in drug development is hepatotoxicity, specifically known as drug-induced liver injury (DILI). The popularity of new drugs often poses a significant barrier during development and frequently leads to their recall after launch. In silico methods have many advantages compared with traditional in vivo and in vitro assays. To establish a more precise and reliable prediction model, it is necessary to utilize an extensive and high-quality database consisting of information on drug molecule properties and structural patterns. In addition, we should also carefully select appropriate molecular descriptors that can be used to accurately depict compound characteristics. The aim of this study was to conduct a comprehensive investigation into the prediction of DILI. First, we conducted a comparative analysis of the physicochemical properties of extensively well-prepared DILI-positive and DILI-negative compounds. Then, we used classic substructure dissection methods to identify structural pattern differences between these two different types of chemical molecules. These findings indicate that it is not feasible to establish property or substructure-based rules for distinguishing between DILI-positive and DILI-negative compounds. Finally, we developed quantitative classification models for predicting DILI using the naïve Bayes classifier (NBC) and recursive partitioning (RP) machine learning techniques. The optimal DILI prediction model was obtained using NBC, which combines 21 physicochemical properties, the VolSurf descriptors and the LCFP_10 fingerprint set. This model achieved a global accuracy (GA) of 0.855 and an area under the curve (AUC) of 0.704 for the training set, while the corresponding values were 0.619 and 0.674 for the test set, respectively. Moreover, indicative substructural fragments favorable or unfavorable for DILI were identified from the best naïve Bayesian classification model. These findings may help prioritize lead compounds in the early stage of drug development pipelines.

Advancing Drug Safety in Drug Development: Bridging Computational Predictions for Enhanced Toxicity Prediction

The attrition rate of drugs in clinical trials is generally quite high, with estimates suggesting that approximately 90% of drugs fail to make it through the process. The identification of unexpected toxicity issues during preclinical stages is a significant factor contributing to this high rate of failure. These issues can have a major impact on the success of a drug and must be carefully considered throughout the development process. These late-stage rejections or withdrawals of drug candidates significantly increase the costs associated with drug development, particularly when toxicity is detected during clinical trials or after market release. Understanding drug-biological target interactions is essential for evaluating compound toxicity and safety, as well as predicting therapeutic effects and potential off-target effects that could lead to toxicity. This will enable scientists to predict and assess the safety profiles of drug candidates more accurately. Evaluation of toxicity and safety is a critical aspect of drug development, and biomolecules, particularly proteins, play vital roles in complex biological networks and often serve as targets for various chemicals. Therefore, a better understanding of these interactions is crucial for the advancement of drug development. The development of computational methods for evaluating protein-ligand interactions and predicting toxicity is emerging as a promising approach that adheres to the 3Rs principles (replace, reduce, and refine) and has garnered significant attention in recent years. In this review, we present a thorough examination of the latest breakthroughs in drug toxicity prediction, highlighting the significance of drug-target binding affinity in anticipating and mitigating possible adverse effects. In doing so, we aim to contribute to the development of more effective and secure drugs.

Image-based molecular representation learning for drug development: a survey

Artificial intelligence (AI) powered drug development has received remarkable attention in recent years. It addresses the limitations of traditional experimental methods that are costly and time-consuming. While there have been many surveys attempting to summarize related research, they only focus on general AI or specific aspects such as natural language processing and graph neural network. Considering the rapid advance on computer vision, using the molecular image to enable AI appears to be a more intuitive and effective approach since each chemical substance has a unique visual representation. In this paper, we provide the first survey on image-based molecular representation for drug development. The survey proposes a taxonomy based on the learning paradigms in computer vision and reviews a large number of corresponding papers, highlighting the contributions of molecular visual representation in drug development. Besides, we discuss the applications, limitations and future directions in the field. We hope this survey could offer valuable insight into the use of image-based molecular representation learning in the context of drug development.

Computational models for predicting liver toxicity in the deep learning era

Drug-induced liver injury (DILI) is a severe adverse reaction caused by drugs and may result in acute liver failure and even death. Many efforts have centered on mitigating risks associated with potential DILI in humans. Among these, quantitative structure-activity relationship (QSAR) was proven to be a valuable tool for early-stage hepatotoxicity screening. Its advantages include no requirement for physical substances and rapid delivery of results. Deep learning (DL) made rapid advancements recently and has been used for developing QSAR models. This review discusses the use of DL in predicting DILI, focusing on the development of QSAR models employing extensive chemical structure datasets alongside their corresponding DILI outcomes. We undertake a comprehensive evaluation of various DL methods, comparing with those of traditional machine learning (ML) approaches, and explore the strengths and limitations of DL techniques regarding their interpretability, scalability, and generalization. Overall, our review underscores the potential of DL methodologies to enhance DILI prediction and provides insights into future avenues for developing predictive models to mitigate DILI risk in humans.

Predicting drug-induced liver injury using graph attention mechanism and molecular fingerprints

Drug-induced liver injury (DILI) is a significant issue in drug development and clinical treatment due to its potential to cause liver dysfunction or damage, which, in severe cases, can lead to liver failure or even fatality. DILI has numerous pathogenic factors, many of which remain incompletely understood. Consequently, it is imperative to devise methodologies and tools for anticipatory assessment of DILI risk in the initial phases of drug development. In this study, we present DMFPGA, a novel deep learning predictive model designed to predict DILI. To provide a comprehensive description of molecular properties, we employ a multi-head graph attention mechanism to extract features from the molecular graphs, representing characteristics at the level of compound nodes. Additionally, we combine multiple fingerprints of molecules to capture features at the molecular level of compounds. The fusion of molecular fingerprints and graph features can more fully express the properties of compounds. Subsequently, we employ a fully connected neural network to classify compounds as either DILI-positive or DILI-negative. To rigorously evaluate DMFPGA's performance, we conduct a 5-fold cross-validation experiment. The obtained results demonstrate the superiority of our method over four existing state-of-the-art computational approaches, exhibiting an average AUC of 0.935 and an average ACC of 0.934. We believe that DMFPGA is helpful for early-stage DILI prediction and assessment in drug development.

Review of human risk factors for idiosyncratic drug-induced liver injury: latest advances and future goals

INTRODUCTION

Idiosyncratic drug-induced liver injury (DILI) is a common cause of acute liver injury and can lead to death from acute liver failure or require liver transplantation. Although the total burden of liver injury is high, the frequency of DILI caused by specific agents is often low. As the liver injury is by per definition idiosyncratic, the prediction of which patients will develop liver injury from specific drugs is currently a very difficult challenge.

AREAS COVERED

The current paper highlights the most important studies on prediction of DILI published in 2019-2023, including studies on genetic, metabolomic, and demographic risk factors, concomitant medication, and the role of comorbid liver diseases. Risk stratification using demographic, metabolomic, and multigenetic risk factors is discussed.

EXPERT OPINION

Great advances have been made in identifying genetic risk factors for DILI. Combining these risk factors with demographic information and other biomarkers into multigenetic risk models might become highly useful in risk stratifying patients exposed to DILI. However, a more detailed mapping of genetic risk factors is needed. Results of these studies need to be validated in the selected ethnic groups before applicability and cost-effectiveness can be determined.

GeoDILI: A Robust and Interpretable Model for Drug-Induced Liver Injury Prediction Using Graph Neural Network-Based Molecular Geometric Representation

Drug-induced liver injury (DILI) is a significant cause of drug failure and withdrawal due to liver damage. Accurate prediction of hepatotoxic compounds is crucial for safe drug development. Several DILI prediction models have been published, but they are built on different data sets, making it difficult to compare model performance. Moreover, most existing models are based on molecular fingerprints or descriptors, neglecting molecular geometric properties and lacking interpretability. To address these limitations, we developed GeoDILI, an interpretable graph neural network that uses a molecular geometric representation. First, we utilized a geometry-based pretrained molecular representation and optimized it on the DILI data set to improve predictive performance. Second, we leveraged gradient information to obtain high-precision atomic-level weights and deduce the dominant substructure. We benchmarked GeoDILI against recently published DILI prediction models, as well as popular GNN models and fingerprint-based machine learning models using the same data set, showing superior predictive performance of our proposed model. We applied the interpretable method in the DILI data set and derived seven precise and mechanistically elucidated structural alerts. Overall, GeoDILI provides a promising approach for accurate and interpretable DILI prediction with potential applications in drug discovery and safety assessment. The data and source code are available at GitHub repository (https://github.com/CSU-QJY/GeoDILI).

Fructose as a novel nutraceutical for acetaminophen (APAP)-induced hepatotoxicity

Acetaminophen (APAP) is the most widely used analgesic in the world. APAP overdose can cause severe hepatotoxicity and therefore is the most common cause of drug-induced liver injury. The only approved treatment for APAP overdose is N-acetyl-cysteine (NAC) supplementation. However, the narrow efficacy window of the drug severely limits its clinical use, prompting the search for other therapeutic options to counteract APAP toxicity. Recent research has pointed to fructose as a novel nutraceutical for APAP-induced liver injury. This review summarizes the current understanding of the molecular mechanisms underlying APAP-induced liver injury, introduces how fructose supplementation could prevent and treat APAP liver toxicity with a focus on the ChREBPα-FGF21 pathway, and proposes possible future directions of study.

Advances in the study of acetaminophen-induced liver injury

Acetaminophen (APAP) overdose is a significant cause of drug-induced liver injury and acute liver failure. The diagnosis, screening, and management of APAP-induced liver injury (AILI) is challenging because of the complex mechanisms involved. Starting from the current studies on the mechanisms of AILI, this review focuses on novel findings in the field of diagnosis, screening, and management of AILI. It highlights the current issues that need to be addressed. This review is supposed to summarize the recent research progress and make recommendations for future research.

Prediction of functional characteristics of gari (cassava flakes) using near-infrared reflectance spectrometry

Gari is a creamy, granular flour obtained from roasting fermented cassava mash. Its preparation involves several unit operations, including fermentation, which is essential in gari production. Fermentation brings about specific biochemical changes in cassava starch due to the actions of lactic acid bacteria. Consequently, it gives rise to organic acids and a significant reduction in the pH. Consumer preferences for gari are influenced by these changes and impact specific functional characteristics, which are often linked to cassava genotypes. Measurement of these functional characteristics is time-consuming and expensive. Therefore, this study aimed to develop high-throughput and less expensive prediction models for water absorption capacity, swelling power, bulk density, and dispersibility using Near-Infrared Reflectance Spectroscopy (NIRS). Gari was produced from 63 cassava genotypes using the standard method developed in the RTB foods project. The prediction model was developed by dividing the gari samples into two sets of 48 samples for calibration and 15 samples as the validation set. The gari samples were transferred into a ring cell cup and scanned on the NIRS machine within the Vis-NIR range of 400-2,498 nm wavelength, though only the NIR range of 800-2,400 nm was used to build the model. Calibration models were developed using partial least regression algorithms after spectra pre-processing. Also, the gari samples were analysed in the laboratory for their functional properties to generate reference data. Results showed an excellent coefficient of determination in calibrations (R² _Cal) of 0.99, 0.97, 0.97, and 0.89 for bulk density, swelling power, dispersibility, and water absorption capacity, respectively. Also, the performances of the prediction models were tested using an independent set of 15 gari samples. A good prediction coefficient (R² pred) and low standard error of prediction (SEP) was obtained as follows: Bulk density (0.98), Swelling power (0.93), WAC (0.68), Dispersibility (0.65), and solubility index (0.62), respectively. Therefore, NIRS prediction models in this study could provide a rapid screening tool for cassava breeding programs and food scientists to determine the food quality of cassava granular products (Gari).

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

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

Rapid identification of salmonella serovars by using Raman spectroscopy and machine learning algorithm

A widespread and escalating public health problem worldwide is foodborne illness, and foodborne Salmonella infection is one of the most common causes of human illness.For the three most pathogenic Salmonella serotypes, Raman spectroscopy was employed to acquire spectral data.As machine learning offers high efficiency and accuracy, we have chosen the convolutional neural network(CNN), which is suitable for solving multi-classification problems, to do in-depth mining and analysis of Raman spectral data.To optimize the instrument parameters, we compared three laser wavelengths: 532, 638, and 785 nm.Ultimately, the 532 nm wavelength was chosen as the most effective for detecting Salmonella.A pre-processing step is necessary to remove interference from the background noise of the Raman spectrum.Our study compared the effects of five spectral preprocessing methods, Savitzky-Golay smoothing (SG), Multivariate Scatter Correction (MSC), Standard Normal Variate (SNV), and Hilbert Transform (HT), on the predictive power of CNN models.Accuracy(ACC), Precision, Recall, and F1-score 4 machine learning evaluation indicators are used to evaluate the model performance under different preprocessing methods.In the results, SG combined with SNV was found to be the most accurate spectral pre-processing method for predicting Salmonella serotypes using Raman spectroscopy, achieving an accuracy of 98.7% for the training set and over 98.5% for the test set in CNN model.Pre-processing spectral data using this method yields higher accuracy than other methods.As a conclusion, the results of this study demonstrate that Raman spectroscopy when used in conjunction with a convolutional neural network model enables the rapid identification of three Salmonella serotypes at the single-cell level, and that the model has a great deal of potential for distinguishing between different serotypes of pathogenic bacteria and closely related bacterial species.This is vital to preventing outbreaks of foodborne illness and the spread of foodborne pathogens.

Best practice and reproducible science are required to advance artificial intelligence in real-world applications

Drug-induced liver injury (DILI) is one of the most significant concerns in medical practice but yet it still cannot be fully recapitulated with existing in vivo, in vitro and in silico approaches. To address this challenge, Chen et al. [ 1] developed a deep learning-based DILI prediction model based on chemical structure information alone. The reported model yielded an outstanding prediction performance (i.e. 0.958, 0.976, 0.935, 0.947, 0.926 and 0.913 for AUC, accuracy, recall, precision, F1-score and specificity, respectively, on a test set), far outperforming all publicly available and similar in silico DILI models. This extraordinary model performance is counter-intuitive to what we know about the underlying biology of DILI and the principles and hypothesis behind this type of in silico approach. In this Letter to the Editor, we raise awareness of several issues concerning data curation, model validation and comparison practices, and data and model reproducibility.

The prediction approach of drug-induced liver injury: response to the issues of reproducible science of artificial intelligence in real-world applications

In the previous study, we developed the generalized drug-induced liver injury (DILI) prediction model—ResNet18DNN to predict DILI based on multi-source combined DILI dataset and achieved better performance than that of previously published described DILI prediction models. Recently, we were honored to receive the invitation from the editor to response the Letter to Editor by Liu Zhichao, et al. We were glad that our research has attracted the attention of Liu’s team and they has put forward their opinions on our research. In this response to Letter to the Editor, we will respond to these comments.

Segmentation of liver tumors with abdominal computed tomography using fully convolutional networks

BACKGROUND

Dividing liver organs or lesions depicting on computed tomography (CT) images could be applied to help tumor staging and treatment. However, most existing image segmentation technologies use manual or semi-automatic analysis, making the analysis process costly and time-consuming.

OBJECTIVE

This research aims to develop and apply a deep learning network architecture to segment liver tumors automatically after fine tuning parameters.

METHODS AND MATERIALS

The medical imaging is obtained from the International Symposium on Biomedical Imaging (ISBI), which includes 3D abdominal CT scans of 131 patients diagnosed with liver tumors. From these CT scans, there are 7,190 2D CT images along with the labeled binary images. The labeled binary images are regarded as gold standard for evaluation of the segmented results by FCN (Fully Convolutional Network). The backbones of FCN are extracted from Xception, InceptionresNetv2, MobileNetv2, ResNet18, ResNet50 in this study. Meanwhile, the parameters including optimizers (SGDM and ADAM), size of epoch, and size of batch are investigated. CT images are randomly divided into training and testing sets using a ratio of 9:1. Several evaluation indices including Global Accuracy, Mean Accuracy, Mean IoU (Intersection over Union), Weighted IoU and Mean BF Score are applied to evaluate tumor segmentation results in the testing images.

RESULTS

The Global Accuracy, Mean Accuracy, Mean IoU, Weighted IoU, and Mean BF Scores are 0.999, 0.969, 0.954, 0.998, 0.962 using ResNet50 in FCN with optimizer SGDM, batch size 12, and epoch 9. It is important to fine tuning the parameters in FCN model. Top 20 FNC models enable to achieve higher tumor segmentation accuracy with Mean IoU over 0.900. The occurred frequency of InceptionresNetv2, MobileNetv2, ResNet18, ResNet50, and Xception are 9, 6, 3, 5, and 2 times. Therefore, the InceptionresNetv2 has higher performance than others.

CONCLUSIONS

This study develop and test an automated liver tumor segmentation model based on FCN. Study results demonstrate that many deep learning models including InceptionresNetv2, MobileNetv2, ResNet18, ResNet50, and Xception have high potential to segment liver tumors from CT images with accuracy exceeding 90%. However, it is still difficult to accurately segment tiny and small size tumors by FCN models.