International Journal of Molecular Sciences

Journal Browser

► Journal Browser

Special Issue Editor

Dr. Andra Valentina Krauze

E-Mail Website
Guest Editor

Radiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Building 10, Bethesda, MD 20892, USA
Interests: rare tumors; data science and computational biology; brain and spine cancer; head and neck cancer; genitourinary tumors; re-irradiation

Special Issue Information

Dear Colleagues,

Machine learning and artificial intelligence have transformed our lives at an unprecedented pace. However, while the application of computational approaches to medicine has now reached virtually every medical specialty and been considered in efforts to address most critical scenarios faced in the clinic, the implementation of bioinformatic tools and the success of novel biomedicines has been slow to arrive. The reasons for this are multifactorial including limited validation and transferability in part secondary to data sharing, privacy and curation barriers. While data-related barriers are difficult to overcome, bioinformatics can be the solution to many data problems when employed with clinical expertise and computational knowhow. The transition of novel biomedicines to the clinic, meanwhile, hinges on the ability to collect, curate and analyse data to improve the understanding of many structural and functional linkages between clinical outcomes and biological mechanisms of action to enhance the interpretability of results. Biomolecular markers have been emerging and their implementation into clinical care is critical; however, as yet, few patients are able to harness the potential benefits that such markers promise to deliver. Machine-learning-based bioinformatics and biomedicine successes therefore serve as templates for ongoing research and improvement in this space, as guidelines for actionable, responsible and transferable approaches evolve. This Special Issue will focus on progress made with respect to machine learning and artificial intelligence as applied to the identification, validation and directions towards clinical implementation of biomolecular markers highlighting successes and allowing learning from failures. The articles featured here share the unified goal of enhancing our understanding of molecules to get us closer to a resolution on the concepts that enable successful applications with the ability to improve the outcomes of patients.

Dr. Andra Valentina Krauze
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. International Journal of Molecular Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. There is an Article Processing Charge (APC) for publication in this open access journal. For details about the APC please see here. Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

machine learning
artificial intelligence
biomarkers
data collection
data curation
prognostic
predictive

Published Papers (2 papers)

Download All Papers

Research

24 pages, 3154 KiB

Open AccessArticle

MGMT ProFWise: Unlocking a New Application for Combined Feature Selection and the Rank-Based Weighting Method to Link MGMT Methylation Status to Serum Protein Expression in Patients with Glioblastoma

by Erdal Tasci, Yajas Shah, Sarisha Jagasia, Ying Zhuge, Jason Shephard, Margaret O. Johnson, Olivier Elemento, Thomas Joyce, Shreya Chappidi, Theresa Cooley Zgela, Mary Sproull, Megan Mackey, Kevin Camphausen and Andra Valentina Krauze

Int. J. Mol. Sci. 2024, 25(7), 4082; https://doi.org/10.3390/ijms25074082 - 6 Apr 2024

Viewed by 1842

Abstract

Glioblastoma (GBM) is a fatal brain tumor with limited treatment options. O6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation status is the central molecular biomarker linked to both the response to temozolomide, the standard chemotherapy drug employed for GBM, and to patient survival. However, MGMT status is captured on tumor tissue which, given the difficulty in acquisition, limits the use of this molecular feature for treatment monitoring. MGMT protein expression levels may offer additional insights into the mechanistic understanding of MGMT but, currently, they correlate poorly to promoter methylation. The difficulty of acquiring tumor tissue for MGMT testing drives the need for non-invasive methods to predict MGMT status. Feature selection aims to identify the most informative features to build accurate and interpretable prediction models. This study explores the new application of a combined feature selection (i.e., LASSO and mRMR) and the rank-based weighting method (i.e., MGMT ProFWise) to non-invasively link MGMT promoter methylation status and serum protein expression in patients with GBM. Our method provides promising results, reducing dimensionality (by more than 95%) when employed on two large-scale proteomic datasets (7k SomaScan^® panel and CPTAC) for all our analyses. The computational results indicate that the proposed approach provides 14 shared serum biomarkers that may be helpful for diagnostic, prognostic, and/or predictive operations for GBM-related processes, given further validation. Full article

(This article belongs to the Special Issue Machine Learning and Bioinformatics Applications for Biomarkers)

► Show Figures

Figure 1

12 pages, 2355 KiB

Open AccessArticle

Graph Neural Network Model for Prediction of Non-Small Cell Lung Cancer Lymph Node Metastasis Using Protein–Protein Interaction Network and ¹⁸F-FDG PET/CT Radiomics

by Hyemin Ju, Kangsan Kim, Byung Il Kim and Sang-Keun Woo

Int. J. Mol. Sci. 2024, 25(2), 698; https://doi.org/10.3390/ijms25020698 - 5 Jan 2024

Cited by 2 | Viewed by 1142

Abstract

The image texture features obtained from ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) images of non-small cell lung cancer (NSCLC) have revealed tumor heterogeneity. A combination of genomic data and radiomics may improve the prediction of tumor prognosis. This study aimed to predict NSCLC metastasis using a graph neural network (GNN) obtained by combining a protein–protein interaction (PPI) network based on gene expression data and image texture features. ¹⁸F-FDG PET/CT images and RNA sequencing data of 93 patients with NSCLC were acquired from The Cancer Imaging Archive. Image texture features were extracted from ¹⁸F-FDG PET/CT images and area under the curve receiver operating characteristic curve (AUC) of each image feature was calculated. Weighted gene co-expression network analysis (WGCNA) was used to construct gene modules, followed by functional enrichment analysis and identification of differentially expressed genes. The PPI of each gene module and genes belonging to metastasis-related processes were converted via a graph attention network. Images and genomic features were concatenated. The GNN model using PPI modules from WGCNA and metastasis-related functions combined with image texture features was evaluated quantitatively. Fifty-five image texture features were extracted from ¹⁸F-FDG PET/CT, and radiomic features were selected based on AUC (n = 10). Eighty-six gene modules were clustered by WGCNA. Genes (n = 19) enriched in the metastasis-related pathways were filtered using DEG analysis. The accuracy of the PPI network, derived from WGCNA modules and metastasis-related genes, improved from 0.4795 to 0.5830 (p < 2.75 × 10⁻¹²). Integrating PPI of four metastasis-related genes with ¹⁸F-FDG PET/CT image features in a GNN model elevated its accuracy over a without image feature model to 0.8545 (95% CI = 0.8401–0.8689, p-value < 0.02). This model demonstrated significant enhancement compared to the model using PPI and ¹⁸F-FDG PET/CT derived from WGCNA (p-value < 0.02), underscoring the critical role of metastasis-related genes in prediction model. The enhanced predictive capability of the lymph node metastasis prediction GNN model for NSCLC, achieved through the integration of comprehensive image features with genomic data, demonstrates promise for clinical implementation. Full article

(This article belongs to the Special Issue Machine Learning and Bioinformatics Applications for Biomarkers)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Machine Learning and Bioinformatics Applications for Biomarkers

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (2 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI