J Med Syst. 2025 Apr 10;49(1):47. doi: 10.1007/s10916-025-02182-3.

ABSTRACT

Drug response prediction (DRP) is a central task in the era of precision medicine. Over the past decade, the emergence of deep learning (DL) has greatly contributed to addressing DRP challenges. Notably, the prediction of DRP for cancer cell lines benefits significantly from data availability for model development. However, an effective predictive model is still challenging due to issues with data quality, high-dimensional data, and multi-omics data integration. In this study, we introduce MLG2Net, a deep-learning model inspired by graph neural networks designed to predict DRP in lung cancer cell lines based on pharmacogenomics data. Our model comprises two key components: drug SMILES described by local and global graph networks and cell line genomics are illustrated as a map. Our results show that MLG2Net outperforms three reference graph networks. MLG2Net performance reached a Pearson coefficient correlation ( $C{C}_p$ ) of 0.8616 and a root mean square error (RMSE) of 2.94e-6 in predicting drug responses for Lung Adenocarcinoma (LUAD) cell lines. Subsequent testing on the Lung Squamous Cell Carcinoma (LUSC) dataset reveals lower performance ( $C{C}_p$ : 0.7999, RMSE: 4.08e-6), attributed to the dataset's smaller size influencing model capacity. Moreover, we assessed the model's architecture by isolating its components, with results indicating that the global network is particularly effective in this task. In conclusion, MLG2Net exhibited promising applications in DRP for cancer cell lines, with potential advancements by incorporating larger datasets.

PMID:40208442 | DOI:10.1007/s10916-025-02182-3

J Med Syst. 2025 Apr 10;49(1):47. doi: 10.1007/s10916-025-02182-3.

ABSTRACT

Drug response prediction (DRP) is a central task in the era of precision medicine. Over the past decade, the emergence of deep learning (DL) has greatly contributed to addressing DRP challenges. Notably, the prediction of DRP for cancer cell lines benefits significantly from data availability for model development. However, an effective predictive model is still challenging due to issues with data quality, high-dimensional data, and multi-omics data integration. In this study, we introduce MLG2Net, a deep-learning model inspired by graph neural networks designed to predict DRP in lung cancer cell lines based on pharmacogenomics data. Our model comprises two key components: drug SMILES described by local and global graph networks and cell line genomics are illustrated as a map. Our results show that MLG2Net outperforms three reference graph networks. MLG2Net performance reached a Pearson coefficient correlation ( $C{C}_p$ ) of 0.8616 and a root mean square error (RMSE) of 2.94e-6 in predicting drug responses for Lung Adenocarcinoma (LUAD) cell lines. Subsequent testing on the Lung Squamous Cell Carcinoma (LUSC) dataset reveals lower performance ( $C{C}_p$ : 0.7999, RMSE: 4.08e-6), attributed to the dataset's smaller size influencing model capacity. Moreover, we assessed the model's architecture by isolating its components, with results indicating that the global network is particularly effective in this task. In conclusion, MLG2Net exhibited promising applications in DRP for cancer cell lines, with potential advancements by incorporating larger datasets.

PMID:40208442 | DOI:10.1007/s10916-025-02182-3

ACS Sens. 2025 Apr 25;10(4):3101-3111. doi: 10.1021/acssensors.5c00314. Epub 2025 Apr 7.

ABSTRACT

Early screening of individuals with high-risk lung nodules can significantly improve the prognosis of lung cancer patients, and accurate identification of lung nodule subtypes can provide guidance for medical treatment. Exhaled breath (EB) analysis via eNoses offers a quick and noninvasive approach, but current eNose technology lacks quality control and solid validation in large population studies. Herein, an eNose platform integrated with a metal ion-decorated graphene sensor array and a breath sampling accessory was established. EB samples from 427 healthy subjects and 2586 subjects with lung nodules, including various benign and malignant subtypes, were collected through the breath sampling accessory for quality control. The large-cohort clinical EB samples were analyzed by the eNose platform to acquire the cross-reactive resistance response. Breathprint analysis for high-risk lung nodules using SVM and age-matched training sets yielded strong and robust performance. Combined with baseline data, the model achieved an AUC of 0.93 (95% CI, 0.89-0.96) on the external test set, with 97% sensitivity and 73% specificity. Moreover, dimensionality reduction analysis of breathprints demonstrated separability across different lung nodule subtypes. This study demonstrates the reliability of the graphene eNose platform to identify high-risk lung nodules and classify lung nodule subtypes in a noninvasive and rapid method.

PMID:40193324 | DOI:10.1021/acssensors.5c00314

Cytopathology. 2025 Apr 11. doi: 10.1111/cyt.13485. Online ahead of print.

ABSTRACT

The advent of personalised and precision medicine has radically modified the management and the clinical outcome of cancer patients. However, the expanding number of predictive, prognostic, and diagnostic biomarkers has raised the need for simple, noninvasive, quicker, but equally efficient tests for molecular profiling. In this complex scenario, the adoption of liquid biopsy, particularly circulating tumour DNA (ctDNA), has been a real godsend for many cancer patients who would otherwise have been denied the benefits of targeted treatments. Undeniably, ctDNA analysis has several advantages over conventional tissue-based analysis. One advantage is that it can guide treatment decision making, especially when tissue samples are scarce or totally unavailable. Indeed, a simple blood test can inform clinicians on patients' response or resistance to targeted therapies, help them monitor minimal residual disease (MRD) after surgical resections, and facilitate them with early cancer detection and interception. Finally, an equally important advantage is that ctDNA analysis can help decipher temporal and spatial tumour heterogeneity, a mechanism highly responsible for therapeutic resistance. In this review, we gathered and analysed current evidence on the clinical usefulness of ctDNA analysis in solid tumours.

PMID:40219616 | DOI:10.1111/cyt.13485

Tuberc Respir Dis (Seoul). 2025 Apr 8. doi: 10.4046/trd.2024.0146. Online ahead of print.

ABSTRACT

Molecular profiling of tumours from patients plays a crucial role in precision oncology. While tumour tissue-based genomic testing remains the gold standard in clinical management of patients with non-small cell lung cancer, advances in genomic technologies, the analysis of various bodily fluids, mainly blood but also saliva, pleural/ pericardial effusions, urine, and cerebrospinal fluid is now feasible and readily available. In this review, we will focus on the clinical application of circulating tumour DNA in patients with non-small cell lung cancer in the setting of early-stage disease, locally advanced disease with attention to the potential of ctDNA in prognostication, risk stratification, minimal residual disease, and in advanced disease, its role in the detection of genomic markers and mechanisms of acquired resistance. The role of ctDNA and liquid biopsies in lung cancer screening will also be discussed.

PMID:40195729 | DOI:10.4046/trd.2024.0146