reviewed by three experts in the area of the presented study. The candidates for acceptance had to undergo one or more thorough revisions. In the remainder of this editorial, we briefly describe the contribution made by each accepted paper.

The paper "DiaDeL: An Accurate Deep Learning-Based Model with Mutational Signatures for Predicting Metastasis Stage and Cancer Types" by Sina Abdollahi, Peng-Chan Lin, and Jung-Hsien Chiang investigated the trinucleotide mutational pattern of cancers and proposed a deep learning-based binary classifier that uses mutational signatures as input features and distinct a cancer type from the others. The proposed model outperforms six state-of-the-art methods with better accuracy and AUC.

The paper "Construction and Evaluation of Robust Interpretation Models for Breast Cancer Metastasis Prediction" by Nahim Adnan, Maryam Zand, Tim H. M. Huang, and Jianhua Ruan proposed a breast cancer metastasis prediction model using a very small number of biologically interpretable features, and a simple yet novel model interpretation approach that can provide personalized interpretations. It is the first method to quantitatively compare different interpretation algorithms. Experimental results show that the proposed model achieved competitive prediction accuracy and higher inter-classifier interpretation consistency than stateof-the-art interpretation methods.

The paper "Unsupervised Feature Selection Using an Integrated Strategy of Hierarchical Clustering with Singular Value Decomposition: An Integrative Biomarker Discovery Method with Application to Acute Myeloid Leukemia" by Tapas Bhadra, Saurav Mallik, Amir Sohel, and Zhongming Zhao developed a novel unsupervised feature selection by combining hierarchical feature clustering with singular value decomposition. The experimental results demonstrated that the proposed algorithm performed well against state-of-the-art methods of feature selection in terms of various evaluation criteria through the analysis of Acute Myeloid Leukemia multi-omics data.

The paper "Heterogeneity in Blood Biomarker Trajectories After Mild TBI Revealed by Unsupervised Learning" by Lien A. Bui, Dacosta Yeboah, Louis Steinmeister, Sima Azizi, Daniel B. Hier, Donald C. Wunsch II, Gayla R. Olbricht, and Tayo Obafemi-Ajayi applied a Locality-Sensitive Hashing model enhanced by varied statistical methods to cluster blood biomarker level trajectories acquired over multiple time points. Additional features derived from demographics, injury context, neurocognitive assessment, and postural stability assessment were extracted using an autoencoder to augment the model. The ability to cluster blood biomarker trajectories enhances the possibilities for precision medicine approaches to mTBI.

The paper "Genetic Analysis of Coronary Artery Disease Using Tree-Based Automated Machine Learning Informed by Biology-Based Feature Selection" by Elisabetta Manduchi, Trang Le, Weixuan Fu, and Jason H. Moore assessed the applicability of Tree-based Pipeline Optimization Tool to genomics and identified combinations of single nucleotide polymorphisms (SNPs) associated with coronary artery disease (CAD). Importance analysis uncovered functional relevance of the identified SNPs to genes whose association with CAD is supported by other resources.

The paper "An Ensemble of U-Net Models for Kidney Tumor Segmentation with CT images" by Jason Causey, Jonathan Stubblefield, Jake Qualls, Jennifer Fowler, Lingrui Cai, Karl Walker, Yuanfang Guan, and Xiuzhen Huang summarized the Arkansas AI-Campus solution method for the 2019 Kidney Tumor Segmentation Challenge (KiTS19). The proposed solution is an ensemble of U-Net models developed after testing many model variations. The model achieved Dice scores 0.9470 and 0.6099 kidney and tumor segmentation in the final competition test.

The paper "Age Prediction by DNA Methylation in Neural Networks" by Lechuan Li , Chonghao Zhang, Shiyu Liu, Hannah Guan, and Yu Zhang proposed a Correlation Pre-Filtered Neural Network (CPFNN) that uses Spearman Correlation to pre-filter the input features before feeding them into neural networks. CPFNN outperformed state-of-the-art models by at least 1 year in term of Mean Absolute Error (MAE), with a MAE of 2.7 years.

We would like to thank the external reviewers for volunteering their time to review the submissions. We would like to thank Yi Pan, the editor-in-chief of this TCBB special section, for offering this opportunity for wider dissemination of the research in genomics and precision medicine. Last but not least, we would like to thank the authors of these seven articles for their time and effort in submitting their high-quality work to TCBB.