Deep learning models have emerged as rapid, accurate, and effective approaches for clinical decisions. Through a combination of drug screening and deep learning models, drugs that may benefit patients before and after surgery can be discovered to reduce the risk of complications or speed recovery. However, most existing drug prediction methods have high data requirements and lack interpretability, which has a limited role in adjuvant surgical treatment. To address these limitations, the authors propose the attention-based convolution transpositional interfusion network (ACTIN) for flexible and efficient drug discovery. ACTIN leverages the graph convolution and the transformer mechanism, utilizing drug and transcriptome data to assess the impact of chemical pharmacophores containing certain elements on gene expression. Remarkably, just with only 393 training instances, only one-tenth of the other models, ACTIN achieves state-of-the-art performance, demonstrating its effectiveness even with limited data. By incorporating chemical element embedding disparity and attention mechanism-based parameter analysis, it identifies the possible pharmacophore containing certain elements that could interfere with specific cell lines, which is particularly valuable for screening useful pharmacophores for new drugs tailored to adjuvant surgical treatment. To validate its reliability, the authors conducted comprehensive examinations by utilizing transcriptome data from the lung tissue of fatal COVID-19 patients as additional input for ACTIN, the authors generated novel lead chemicals that align with clinical evidence. In summary, ACTIN offers insights into the perturbation biases of elements within pharmacophore on gene expression, which holds the potential for guiding the development of new drugs that benefit surgical treatment.

Hearing loss (HL) is an otolaryngology disease susceptible to environmental pollutants. Volatile organic compounds (VOCs), as a class of chemical pollutants with evaporation propensity, pose a great threat to human health. However, the association between VOCs and HL remains unclear. This study aimed to explore the association between urinary-specific VOC metabolites and HL. It included 1048 participants from the National Health and Nutrition Examination Survey (NHANES) from 2011 to 2012. Multivariate linear regression models, smooth curve analysis, and stratified analysis were employed to investigate the relationship between urinary-specific VOC metabolite concentrations and pure tone audiometry (PTA) across three different frequencies. A two-piecewise linear regression model was employed to analyze the threshold effects of urinary-specific VOC metabolites on hearing threshold changes. Furthermore, a comparative toxicogenomics database (CTD) and functional gene enrichment were constructed. An interaction network of transcription factors, genes, and non-coding RNA was constructed to further confirm the upstream and downstream regulatory relationships. Molecular docking analyses were conducted to explore the potential binding modes and critical docking sites. Additionally, a moderation analysis was conducted to investigate the role of oxidative stress in moderating the influence of VOC metabolites on hearing. Multivariate linear regression model discerned a significant correlation between cyanide 2-aminothiazoline-4-carboxylic acid (ATCA) with speech-frequency PTA and N-acetyl-S-(3,4-dihydroxybutyl)-L-cysteine (DHBMA) with high-frequency PTA. The smoothed curve and threshold effect analysis corroborated a positive linear relationship between cyanide ATCA and speech-frequency PTA without a threshold effect only in the 20–34 age group. Additionally, the bioinformatics analysis discovered pathogenic genes related to cyanide-induced HL and suggested that oxidative stress responses play a critical role in this biological process. Furthermore, the moderation effect of total bilirubin (TB), an oxidative stress-associated molecule, was ascertained on the effects of ATCA on hearing. Our findings suggest a potential link between VOC metabolites and hearing and indicate the crucial role of oxidative stress responses in this association.

An abstract is unavailable. This article is available as a PDF only.