Experimental Biology and Medicine

Causality assessment is vital in patient safety and pharmacovigilance (PSPV) for safety signal detection, adverse reaction management, and regulatory submission. Large language models (LLMs), especially those designed with transformer architecture, are revolutionizing various fields, including PSPV. While attempts to utilize Bidirectional Encoder Representations from Transformers (BERT)-like LLMs for causal inference in PSPV are underway, a detailed evaluation of “fit-for-purpose” BERT-like model selection to enhance causal inference performance within PSPV applications remains absent. This study conducts an in-depth exploration of BERT-like LLMs, including generic pre-trained BERT LLMs, domain-specific pre-trained LLMs, and domain-specific pre-trained LLMs with safety knowledge-specific fine-tuning, for causal inference in PSPV. Our investigation centers around (1) the influence of data complexity and model architecture, (2) the correlation between the BERT size and its impact, and (3) the role of domain-specific training and fine-tuning on three publicly accessible PSPV data sets. The findings suggest that (1) BERT-like LLMs deliver consistent predictive power across varied data complexity levels, (2) the predictive performance and causal inference results do not directly correspond to the BERT-like model size, and (3) domain-specific pre-trained LLMs, with or without safety knowledge-specific fine-tuning, surpass generic pre-trained BERT models in causal inference. The findings are valuable to guide the future application of LLMs in a broad range of application.

Tumor mutational burden (TMB), when at a high level, is an emerging indicative factor of sensitivity to immune checkpoint inhibitors. Previous studies have shown that the more affordable and accurate targeted panels can be used to measure TMB as a substitute for whole exome sequencing (WES). However, additional processes, such as hotspot mutations exclusion and TMB adjustment, are usually required to deal with the effect of the limited panel sizes. A comprehensive investigation of the effective factors is needed for accurate TMB estimation by targeted panels. In this study, we quantitatively evaluated the variances of TMB values calculated by WES and targeted panels using 10,000 simulated targeted panels with panel sizes ranging from 0.2 to 3.1 million bases. With The Cancer Genome Atlas (TCGA) cancer samples and mutation profiles, we fixed regressions on WES-TMBs and panel-TMBs to assess the performance of a given targeted panel. Panel size was found as one of the major effective factors of TMB estimation. Meanwhile, by investigating the well-performing small panels that reported TMB values similar to those of WES, we demonstrated the evidence of the cancer type–specific impacts of genes on TMB estimation and identified high-impact gene sets for different cancer types based on the TCGA data. This study revealed the quantitative correlations between TMB variance and panel size, and the potential impacts of individual genes on TMB estimation. Our results suggested that for cancer patients diagnosed using targeted panels, it would be highly beneficial to have the capability to directly measure TMB from the targeted sequencing data. This would greatly assist in making decisions regarding the use of immunotherapies.

The coronavirus disease 2019 (COVID-19) global pandemic resulted in millions of people becoming infected with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus and close to seven million deaths worldwide. It is essential to further explore and design effective COVID-19 treatment drugs that target the main protease of SARS-CoV-2, a major target for COVID-19 drugs. In this study, machine learning was applied for predicting the SARS-CoV-2 main protease binding of Food and Drug Administration (FDA)-approved drugs to assist in the identification of potential repurposing candidates for COVID-19 treatment. Ligands bound to the SARS-CoV-2 main protease in the Protein Data Bank and compounds experimentally tested in SARS-CoV-2 main protease binding assays in the literature were curated. These chemicals were divided into training (516 chemicals) and testing (360 chemicals) data sets. To identify SARS-CoV-2 main protease binders as potential candidates for repurposing to treat COVID-19, 1188 FDA-approved drugs from the Liver Toxicity Knowledge Base were obtained. A random forest algorithm was used for constructing predictive models based on molecular descriptors calculated using Mold2 software. Model performance was evaluated using 100 iterations of fivefold cross-validations which resulted in 78.8% balanced accuracy. The random forest model that was constructed from the whole training dataset was used to predict SARS-CoV-2 main protease binding on the testing set and the FDA-approved drugs. Model applicability domain and prediction confidence on drugs predicted as the main protease binders discovered 10 FDA-approved drugs as potential candidates for repurposing to treat COVID-19. Our results demonstrate that machine learning is an efficient method for drug repurposing and, thus, may accelerate drug development targeting SARS-CoV-2.

The US drug labeling document contains essential information on drug efficacy and safety, making it a crucial regulatory resource for Food and Drug Administration (FDA) drug reviewers. Due to its extensive volume and the presence of free-text, conventional text mining analysis have encountered challenges in processing these data. Recent advances in artificial intelligence (AI) for natural language processing (NLP) have provided an unprecedented opportunity to identify key information from drug labeling, thereby enhancing safety reviews and support for regulatory decisions. We developed RxBERT, a Bidirectional Encoder Representations from Transformers (BERT) model pretrained on FDA human prescription drug labeling documents for an enhanced application of drug labeling documents in both research and drug review. RxBERT was derived from BioBERT with further training on human prescription drug labeling documents. RxBERT was demonstrated in several tasks using regulatory datasets, including those involved in the National Institutes of Technology Text Analysis Challenge Dataset (NIST TAC dataset), the FDA Adverse Drug Event Evaluation Dataset (ADE Eval dataset), and the classification of texts from submission packages into labeling sections (US Drug Labeling dataset). For all these tasks, RxBERT reached 86.5 F1-scores in both TAC and ADE Eval classification, respectively, and prediction accuracy of 87% for the US Drug Labeling dataset. Overall, RxBERT was shown to be as competitive or have better performance compared to other NLP approaches such as BERT, BioBERT, etc. In summary, we developed RxBERT, a transformer-based model specific for drug labeling that outperformed the original BERT model. RxBERT has the potential to be used to assist research scientists and FDA reviewers to better process and utilize drug labeling information toward the advancement of drug effectiveness and safety for public health. This proof-of-concept study also demonstrated a potential pathway to customized large language models (LLMs) tailored to the sensitive regulatory documents for internal application.

The opioid epidemic has become a serious national crisis in the United States. An indepth systematic analysis of opioid-related adverse events (AEs) can clarify the risks presented by opioid exposure, as well as the individual risk profiles of specific opioid drugs and the potential relationships among the opioids. In this study, 92 opioids were identified from the list of all Food and Drug Administration (FDA)-approved drugs, annotated by RxNorm and were classified into 13 opioid groups: buprenorphine, codeine, dihydrocodeine, fentanyl, hydrocodone, hydromorphone, meperidine, methadone, morphine, oxycodone, oxymorphone, tapentadol, and tramadol. A total of 14,970,399 AE reports were retrieved and downloaded from the FDA Adverse Events Reporting System (FAERS) from 2004, Quarter 1 to 2020, Quarter 3. After data processing, Empirical Bayes Geometric Mean (EBGM) was then applied which identified 3317 pairs of potential risk signals within the 13 opioid groups. Based on these potential safety signals, a comparative analysis was pursued to provide a global overview of opioid-related AEs for all 13 groups of FDA-approved prescription opioids. The top 10 most reported AEs for each opioid class were then presented. Both network analysis and hierarchical clustering analysis were conducted to further explore the relationship between opioids. Results from the network analysis revealed a close association among fentanyl, oxycodone, hydrocodone, and hydromorphone, which shared more than 22 AEs. In addition, much less commonly reported AEs were shared among dihydrocodeine, meperidine, oxymorphone, and tapentadol. On the contrary, the hierarchical clustering analysis further categorized the 13 opioid classes into two groups by comparing the full profiles of presence/absence of AEs. The results of network analysis and hierarchical clustering analysis were not only consistent and cross-validated each other but also provided a better and deeper understanding of the associations and relationships between the 13 opioid groups with respect to their adverse effect profiles.

The ever-increasing number of chemicals has raised public concerns due to their adverse effects on human health and the environment. To protect public health and the environment, it is critical to assess the toxicity of these chemicals. Traditional in vitro and in vivo toxicity assays are complicated, costly, and time-consuming and may face ethical issues. These constraints raise the need for alternative methods for assessing the toxicity of chemicals. Recently, due to the advancement of machine learning algorithms and the increase in computational power, many toxicity prediction models have been developed using various machine learning and deep learning algorithms such as support vector machine, random forest, k-nearest neighbors, ensemble learning, and deep neural network. This review summarizes the machine learning- and deep learning-based toxicity prediction models developed in recent years. Support vector machine and random forest are the most popular machine learning algorithms, and hepatotoxicity, cardiotoxicity, and carcinogenicity are the frequently modeled toxicity endpoints in predictive toxicology. It is known that datasets impact model performance. The quality of datasets used in the development of toxicity prediction models using machine learning and deep learning is vital to the performance of the developed models. The different toxicity assignments for the same chemicals among different datasets of the same type of toxicity have been observed, indicating benchmarking datasets is needed for developing reliable toxicity prediction models using machine learning and deep learning algorithms. This review provides insights into current machine learning models in predictive toxicology, which are expected to promote the development and application of toxicity prediction models in the future.

Early de-risking of drug targets and chemistry is essential to provide drug projects with the best chance of success. Target safety assessments (TSAs) use target biology, gene and protein expression data, genetic information from humans and animals, and competitor compound intelligence to understand the potential safety risks associated with modulating a drug target. However, there is a vast amount of information, updated daily that must be considered for each TSA. We have developed a data science–based approach that allows acquisition of relevant evidence for an optimal TSA. This is built on expert-led conventional and artificial intelligence–based mining of literature and other bioinformatics databases. Potential safety risks are identified according to an evidence framework, adjusted to the degree of target novelty. Expert knowledge is necessary to interpret the evidence and to take account of the nuances of drug safety, the modality, and the intended patient population for each TSA within each project. Overall, TSAs take full advantage of the most recent developments in data science and can be used within drug projects to identify and mitigate risks, helping with informed decision-making and resource management. These approaches should be used in the earliest stages of a drug project to guide decisions such as target selection, discovery chemistry options, in vitro assay choice, and end points for investigative in vivo studies.