Quantitative Structure-Activity Relationship (QSAR) Model for the Severity Prediction of Drug-Induced Rhabdomyolysis by Using Random Forest

Advancing Adverse Drug Reaction Prediction with Deep Chemical Language Model for Drug Safety Evaluation

The accurate prediction of adverse drug reactions (ADRs) is essential for comprehensive drug safety evaluation. Pre-trained deep chemical language models have emerged as powerful tools capable of automatically learning molecular structural features from large-scale datasets, showing promising capabilities for the downstream prediction of molecular properties. However, the performance of pre-trained chemical language models in predicting ADRs, especially idiosyncratic ADRs induced by marketed drugs, remains largely unexplored. In this study, we propose MoLFormer-XL, a pre-trained model for encoding molecular features from canonical SMILES, in conjunction with a CNN-based model to predict drug-induced QT interval prolongation (DIQT), drug-induced teratogenicity (DIT), and drug-induced rhabdomyolysis (DIR). Our results demonstrate that the proposed model outperforms conventional models applied in previous studies for predicting DIQT, DIT, and DIR. Notably, an analysis of the learned linear attention maps highlights amines, alcohol, ethers, and aromatic halogen compounds as strongly associated with the three types of ADRs. These findings hold promise for enhancing drug discovery pipelines and reducing the drug attrition rate due to safety concerns.

Rhabdomyolysis associated with newer-generation anti-seizure medications (ASMs): a real-world retrospective and pharmacovigilance study

Objective: Rhabdomyolysis is a potentially fatal adverse reaction mostly triggered by certain medications. Few real-world studies have shown a clear association between newer-generation anti-seizure medications (ASMs) and rhabdomyolysis. We sought to quantify the risk and evaluate the clinical features and management of rhabdomyolysis associated with newer-generation ASMs. Methods: Data were retrieved from the US FDA Adverse Event Reporting System database (FAERS) from 2018 to 2022 on newer-generation ASMs to identify rhabdomyolysis events, and disproportionality analyses were conducted by estimating the reporting odds ratios (RORs) and corresponding 95% confidence intervals (CIs). Furthermore, case reports from 2012 to 31 December 2022 on newer-generation ASMs-induced rhabdomyolysis were retrieved for retrospective analysis. Results: A total of 1,130 rhabdomyolysis reports from the FAERS database were considered. Levetiracetam had the greatest proportion and the highest positive signal values of rhabdomyolysis. The RORs (95% CIs) for newer-generation ASMs were, in descending order, levetiracetam 8.01 (7.26-8.84), lamotrigine 3.78 (3.25-4.40), oxcarbazepine 3.47 (2.53-4.75), pregabalin 2.75 (2.43-3.12), lacosamide 1.85 (1.29-2.65), topiramate 1.64 (1.25-2.15), and gabapentin 1.32 (1.13-1.55). Twenty-six case reports showed evidence of rhabdomyolysis, and levetiracetam (65.4%) was the most frequently reported agent. The median age was 32 years; typical initial symptoms included muscle weakness (34.8%), myalgia (34.8%), backache (17.4%), fatigue (13.0%) and leg pain (8.7%). The median time to onset of rhabdomyolysis was 2 days. All cases had elevated creatine phosphokinase (CPK), and some cases were accompanied by elevated creatinine (57.1%) and myoglobinuria (53.8%). Cessation of ASMs could lead to complete clinical remission. The median time for creatine phosphokinase (CPK) normalization was 8 days. Conclusion: This study identified 7 newer-generation ASMs with significant rhabdomyolysis reporting associations. Prescribers should be more aware of this risk and teach patients to recognize rhabdomyolysis signs/symptoms early.

Machine Learning for the Prediction of Antiviral Compounds Targeting Avian Influenza A/H9N2 Viral Proteins

Avian influenza subtype A/H9N2—which infects chickens, reducing egg production by up to 80%—may be transmissible to humans. In humans, this virus is very harmful since it attacks the respiratory system and reproductive tract, replicating in both. Previous attempts to find antiviral candidates capable of inhibiting influenza A/H9N2 transmission were unsuccessful. This study aims to better characterize A/H9N2 to facilitate the discovery of antiviral compounds capable of inhibiting its transmission. The Symmetry of this study is to apply several machine learning methods to perform virtual screening to identify H9N2 antivirus candidates. The parameters used to measure the machine learning model’s quality included accuracy, sensitivity, specificity, balanced accuracy, and receiver operating characteristic score. We found that the extreme gradient boosting method yielded better results in classifying compounds predicted to be suitable antiviral compounds than six other machine learning methods, including logistic regression, k-nearest neighbor analysis, support vector machine, multilayer perceptron, random forest, and gradient boosting. Using this algorithm, we identified 10 candidate synthetic compounds with the highest scores. These high scores predicted that the molecular fingerprint may involve strong bonding characteristics. Thus, we were able to find significant candidates for synthetic H9N2 antivirus compounds and identify the best machine learning method to perform virtual screenings.