Research and Reviews : Journal of Computational Biology
Volume 15, Issue 2 (2026)
Table of contents
-
Genomic Selection for Grain Yield in Wheat Using Machine Learning on DArT Molecular Markers: A Comparative Evaluation Across Multi-Environment Trials
Abstract: Genomic selection (GS) predicts complex quantitative traits directly from genome-wide molecular markers, bypassing the need for extensive phenotypic trials and accelerating plant breeding cycles. We conducted a comparative evaluation of seven regression approaches — ridge regression (the machine-learning equivalent of RR-BLUP), Lasso, Elastic Net, Partial Least Squares, linear Support Vector Regression, Random Forest, and Gradient Boosting — for predicting grain yield from 1,279 Diversity Array Technology (DArT) molecular markers genotyped …
Published in Research and Reviews : Journal of Computational Biology · Vol. 15, Issue 2, 2026 Read article
-
Comparative Evaluation of Pedigree-Based and Genomic BLUP Models for Wheat Grain Yield Prediction
Abstract: Before genome-wide molecular markers became affordable, plant and animal breeding relied on pedigree-based prediction (P-BLUP), using the expected additive relationship matrix (A) derived from recorded ancestry. Genomic selection replaced or augmented this with a marker-derived genomic relationship matrix (G; GBLUP), and single-step methods combining A and G are now standard when only a subset of a breeding population is genotyped. It is less clear whether pedigree information retains any predictive …
Published in Research and Reviews : Journal of Computational Biology · Vol. 15, Issue 2, 2026 · pp. 1–9 Read article
-
A Smart Framework that Combines Data Mining and Optimization for Different Applications
Abstract: Blending predictive data mining with metaheuristic optimization has become essential for tackling tough, real-world problems across all kinds of fields. Most existing methods stick to fixed algorithms, each focused on a tiny slice of the puzzle, barely budging when new variables or unpredictability show up—especially with messy, human-generated data. So, here’s the idea: a Unified Metaheuristic and Predictive Data Mining (UMPDM) framework that finally connects adaptive search methods with powerful …
Published in Research and Reviews : Journal of Computational Biology · Vol. 15, Issue 2, 2026 · pp. 10–14 Read article
-
Neuro-Symbolic Agentic AI for Autonomous Scientific Discovery: Integrating Deep Reinforcement Learning, Quantum Simulation, and XAI-Audited LLM Hypothesis Generation in Drug Target Identification
Abstract: The exponential growth of multi-omics data and the increasing complexity of disease-associated protein interactomes have rendered conventional drug target identification pipelines computationally and epistemologically inadequate. This paper presents the Neuro-Symbolic Agentic AI for Scientific Discovery (NS-AASD) framework, a unified architecture that cohesively integrates deep reinforcement learning (DRL) exploration strategies, variational quantum simulation (VQS) of protein conformational dynamics, and XAI-audited large language model (LLM) hypothesis generation within an autonomous scientific discovery …
Published in Research and Reviews : Journal of Computational Biology · Vol. 15, Issue 2, 2026 · pp. 15–24 Read article
-
A Factorial Investigation of Hyperparameter Tuning Strategies for Lasso- Based Genomic Prediction
Abstract: In an earlier comparative study of machine-learning methods for genomic prediction of wheat grain yield, we reported a counter-intuitive result: automated nested-cross-validation tuning of the Lasso regularization penalty reduced mean predictive ability relative to a fixed, arbitrarily chosen penalty (mean Pearson r falling from 0.408 to 0.349 across four environments), the opposite of the expected effect of hyperparameter tuning. We hypothesized two possible explanations at the time — high-variance penalty …
Published in Research and Reviews : Journal of Computational Biology · Vol. 15, Issue 2, 2026 · pp. 42–51 Read article
-
Unveiling Actionable Pathogenic Genes for Precision Oncology in Brain Cancers: Glioblastoma and Astrocytoma
Abstract: Glioblastoma (GBM) and astrocytoma are aggressive primary brain tumors characterized by significant molecular heterogeneity, complicating effective treatment. This study employed targeted next-generation sequencing of 529 cancer-associated genes on matched tumor-normal pairs from GBM and astrocytoma patients. Somatic variants were identified using a rigorous bioinformatic pipeline adhering to GATK Best Practices, with variant allele frequencies (VAF) calculated to assess clonal dominance. Functional annotation and driver mutation classification were performed using Ensemble …
Published in Research and Reviews : Journal of Computational Biology · Vol. 15, Issue 2, 2026 · pp. 43–59 Read article