bioRxiv Science⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2021.10.19.465019

Novel graph theoretic biological pathway network analytics methods for analyzing and discovering Alzheimer's disease related genes

Saha, S.·Soliman, A.·Rajasekaran, S.
View original source ↗Export metadata ↓

Abstract

BackgroundAlzheimers disease (AD) is the most common form of dementia among older people. It is a complex disease and the genetics and environmental factors behind it are not conclusive yet. Traditional statistical analyses are inadequate to identify variants, genes, or pathways capable of explaining AD as a unit. In this context, pathway network analysis based on a set of curated AD-specific genes identified in the literature can elucidate biological mechanisms underneath AD. Through the network, we can infer influential pathways that can together explain AD. Consequently, we can target those pathways and corresponding genes for further analysis to develop new drugs, discover novel AD-related genes, combine multiple hypotheses, and so forth. MethodsWe have developed a novel graph theoretic algorithm that can elucidate complex biology from a given set of disease-related genes. It constructs a weighted network of enriched pathways where similarity score between a pair of pathways is defined in a context-specific manner. To make the network robust, we employ topological overlap techniques on top of the raw similarity measure. We then provide the importance of each pathway with respect to the entire network, functional modules and importance of each pathway in a specific module, gene clusters, and so forth. We also provide a method to identify a set of novel genes that can further explain the disease-related genes and the disease itself. ResultsWe have employed our algorithms onto a set of AD-specific genes. It identified three distinct functional modules that are related to metabolism, cancer, and infectious disease related pathways. These findings are matched with three recognized hypotheses in Alzheimers disease, e.g. "metabolism hypothesis," "cell cycle hypothesis," and "infectious disease hypothesis." By analyzing the curated genes common among those functional modules, we can attain more understanding about this fateful disease. We have also identified 24 novel AD-related genes of which at least 14 genes are known to be involved in AD. ConclusionsWe developed a computational framework for analyzing biological pathways in a context-specific manner. It can be used in any sets of disease-related genes. We manifest its efficacy, reliability, and accuracy by employing a set of AD-specific genes.

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Saha, S., Soliman, A., Rajasekaran, S.. 2021-10-20. Novel graph theoretic biological pathway network analytics methods for analyzing and discovering Alzheimer's disease related genes. https://doi.org/10.1101/2021.10.19.465019

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

PHATE-Derived Ancestry Coordinates Capture Continuous Population Structure in Human Genomic Data

Population genetic data are increasingly visualized using low-dimensional embeddings as ancestry coordinates, yet how these methods represent population structure can depend strongly on sampling and construction choices. Principal component analysis (PCA), when visualized using only leading components, can obscure fine-scale structure, while nonlinear neighbor-based methods such as uniform manifold approximation and projection (UMAP) often fragment geographic and admixture gradients into discrete clusters. Here, we introduce a framework for constructing ancestry coordinates using potential of heat-diffusion for affinity-based trajectory embedding (PHATE), a diffusion-based method that preserves relationships across scales. Across synthetic benchmarks and large genomic datasets, we show that appropriate scale tuning and population balancing allow PHATE to recover geographic organization and admixture gradients. We show that incorrectly tuned neighborhood scale and population imbalance can distort the resulting representations of population structure. These results therefore provide a methodological framework and practical guidance for constructing ancestry visualizations that better reflect continuous human genetic diversity.

bioinformatics↗
bioRxiv2026

FedEpitope: Parameter-Efficient Federated Protein Language Models for Linear B-Cell Epitope Prediction

Linear B-cell epitopes are antigenic regions recognised by antibodies that play crucial roles in vaccine development, antibody production, and other therapeutic applications.Their prediction can support peptide-based vaccine candidate screening and diagnostic assay development, but the experimental data required for model development may be distributed across institutions that cannot freely pool their records. We present FedEpitope, a federated framework that adapts the ESM-2 protein language model for peptide-level linear B-cell epitope prediction using Low-Rank Adaptation (LoRA), keeping client-partitioned data local and restricting the communicated trainable model state to approximately 1.11 MB. Simulated benchmarks of FedAvg and FedProx algorithms, evaluated using homology-aware data splits of five biologically heterogeneous, organism-partitioned clients, achieve promising global test performance without centralising training data, with FedAvg outperforming all single-client models in mean AP, F1, and MCC. Additional experiments characterise post-federation personalisation, record-level differential privacy, sensitivity to controlled client heterogeneity, LoRA rank, and generalisation to the independent BCPreds and NetBCE benchmarks, demonstrating the feasibility of parameter-efficient federated protein language model adaptation for data-localised B-cell epitope prediction and the associated trade-offs among predictive performance, personalisation, privacy, communication efficiency, and distribution shift.

bioinformatics↗
bioRxiv2026

Parameter-Efficient Adaptation of Protein Language Models for Dual-Target Antimicrobial Peptide Discovery Under Strict Homology Constraints

The worldwide escalation of antimicrobial resistance (AMR) poses a severe challenge to modern public health, necessitating novel classes of therapeutic agents. Antimicrobial peptides (AMPs) represent highly promising alternatives to small-molecule antibiotics due to their co-evolutionary resilience and rapid membrane disruption dynamics. However, translating computational AMP leads into clinical drug candidates remains bottlenecked by off-target cytotoxicity, predominantly hemolytic activity against mammalian erythrocytes. Although pretrained foundational protein language models (PLMs) have rapidly advanced molecular property prediction, current architectures frequently isolate antibacterial potency and cytotoxicity into disconnected single-task pipelines or succumb to catastrophic performance drops under strict homology-controlled evaluations. Recently, the Quantitative Mapping of Antimicrobial Peptides (QMAP) benchmark proposed that frozen PLM embeddings show weak linearly accessible features for hemolytic activity (HC50) resulting in poor rank correlation ({rho} < 0.25) on out-of-distribution sequence splits. In this work, we introduce an end-to-end multi-task parameter-efficient transfer learning framework designed to simultaneously optimize antibacterial potency and minimize mammalian cytotoxicity without sequence leakage. Built upon ESM-2 (150M), our architecture incorporates Low-Rank Adaptation (LoRA) into self-attention projections, fine-tuning approx 0.70% of model weights. To restore gradient interference originating from disparate membrane lysis mechanisms, we implement an adaptive multi-task loss guided by Kendall homoscedastic uncertainty weighting. Evaluated across predefined QMAP benchmark splits enforcing a 60% maximal sequence identity threshold, our joint architecture remarkably outperforms conventional linear probes, tree-based regressors, and frozen foundational models. The framework achieves an E. coli potency rank correlation of {rho} = 0.6132 (r = 0.6816) and successfully elevates hemolytic toxicity correlation to {rho} = 0.5374 (r = 0.5541). To establish real world utility, we deploy the optimized joint network to screen a curated in silico library of 749 de-novo designed peptides, successfully isolating selective cationic-amphipathic candidates possessing Therapeutic Indices (TI = HC50/MIC) up to 144.03 while effectively deprioritizing broadly lytic motifs (TI < 2.0). These findings demonstrate that parameter-efficient adaptation unlocks fine-grained bioactive structural semantics in foundational PLMs, providing an accurate, scalable framework for therapeutic peptide engineering.

bioinformatics↗