Biology subjects

Dengel, A.

Publications and source records attributed to Dengel, A..

12 recordsLinked to original sources

bioRxiv2026

Explainable Artificial Intelligence for Cross-Dataset Generalizable Biomarker Discovery in Cardiovascular diseases (CVDs)

CVDs are heterogeneous, multifactorial disorders that remain the leading cause of global mortality from infancy to old age. It requires an early identification and treatment of risk factors to accelerate disease prevention and morbidity improvement. Advancements in transcriptomics technologies gives large pool of heterogenous gene expression data. The technical heterogeneity of gene expression data reduces ability to compare multiple cross-platform datasets at once. To bridge gap, we systematically evaluate three data harmonization techniques: Shambhala-2, TDM, and UPC to align heterogeneous data into a shared expression space while preserving biological signals. Our pipeline integrates 25 independent datasets comprising 983 samples across 23 distinct CVDs phenotypes from both RNA-seq and microarray platforms. The framework benchmarks 35 Machine learning (ML) and Deep learning (DL) classifiers, including Transformers and ResNets, across three data modalities such as RNA-seq, microarray hybridization and RNA-seq + microarray and multiple tissue types. To ensure clinical trustworthiness, we apply multiple Explainable artificial intelligence (XAI) methods, such as SHapley additive exPlanations (SHAP) and Integrated gradientss (IGs), and assess their reliability using quantitative metrics like Area over the perturbation curve (AOPC), Sensitivity, and Infidelity. Results indicate that Shambhala-2 provides superior harmonization by maximizing the biological signal-to-platform ratio. Evaluation of XAI methods reveals that Shapley-based approaches offer the highest stability for identifying influential genomic features in high-dimensional data. Functional enrichment and pathway analyses further confirmed the involvement of identified biomarkers in key cardiovascular processes, including inflammation, immune regulation, oxidative stress, and vascular remodeling. Collectively, this study provides a scalable and interpretable road-map that integrates XAI with cross-dataset biomarker discovery, supporting the transition toward precision cardiology.

bioinformatics↗

bioRxiv2025

Towards Understanding The Relationship Between Brain Disorders and the Gut Microbiome with Explainable Graph Neural Networks

MotivationThe communication between the gut microbiome and the brain, known as the microbiome-gut-brain axis (MGBA), is emerging as a critical factor in neurological and psychiatric disorders. This communication involves complex pathways including neural, hormonal, and immune interactions that enable gut microbes to modulate brain function and behavior. However, the specific mechanisms through which gut microbes influence brain function remain poorly understood, and existing computational efforts to understand these mechanisms are simplistic or have limited scope. ResultsThis work presents a comprehensive approach for elucidating the interactions that allows gut microbes to influence brain disorders. We construct a large curated biomedical knowledge graph comprising 586,318 nodes across 16 entity types and 3,573,936 edges spanning 103 relation types, integrating ontological and experimental data relevant to the MGBA. On this graph, we train GNN-GBA, a GraphSAGE-based graph neural network with a DistMult relation-aware decoder, achieving an AUC-ROC of 0.997 and an F1-score of 0.981 on link prediction, outperforming nine baseline methods across four categories. Using GNNExplainer, we extract and rank mechanistic pathways connecting gut microbes to brain disorders, and demonstrate their stability across multiple random initializations. GNN-GBA successfully identified pathways for 125 brain disorders, revealing shared metabolite hubs (including flavonoids, bile acids, and short-chain fatty acids) that mediate gut-brain communication across diverse neurological conditions. Furthermore, we show that the top pathways are consistent with existing literature for three common disorders. Lastly, we develop an interactive dashboard (GutBrainExplorer) to explore thousands of potential mechanistic pathways across 125 brain disorders, which is publicly available at https://sds-genetic-interaction-analysis.opendfki.de/gut_brain/. AvailabilityCode and data are available at https://github.com/naafey-aamer/GNN-GBA. Contactnaafey.aamer@cs.rptu.de

bioinformatics↗

bioRxiv2025

Artificial Intelligence Powered Biomarker Discovery: A Large-Scale Analysis of 236 Studies Across 19 Therapeutic Areas and 147 Diseases

Biomarkers are the molecular signatures that drive and reflect disease states and are indispensable for disease diagnosis, therapeutic target identification, and drug development. The landscape of biomarker discovery has undergone a transformative shift with the emergence of AI-powered predictive pipelines that can integrate complex, high-dimensional datasets. However, the field still lacks a comprehensive, cross-disciplinary foundation that unites AI pipelines with disease-specific biological insights. Together, a combined scattered knowledge of 15 review articles fails to provide a unified framework encompassing data availability, methodological trends, and disease-specific biomarker discoveries across therapeutic areas. Most prior efforts have concentrated on narrow aspects, either focusing on disease-specific AI models or individual stages of the biomarker discovery pipelines, leaving a substantial gap in translational utility. This study addresses this gap by systematically consolidating and analyzing findings from 236 AI-driven biomarker discovery studies. We systematically map the trends of datasets, data modalities, preprocessing strategies, feature engineering methods, AI models, and explainability methods across 147 diseases, which we further organize into 19 therapeutic areas. By doing so, we aim to provide a comprehensive resource that not only highlights current trends and gaps but also lays the groundwork for future advancements, including the design of multi-task learning models and multimodal AI frameworks tailored to complex biomedical data.

bioinformatics↗

bioRxiv2025

Automating AI Discovery for Biomedicine Through Knowledge Graphs And LLM Agents

The biomedical domains accelerating progress in understanding, early detection, and treatment of diseases has created an exponentially growing and overwhelming body of literature. Researchers must rely on this literature to find relevant information, but navigating this vast landscape has become increasingly challenging, especially for interdisciplinary AI-biomedicine researchers who need to stay current across both highly fast-paced fields. Despite the emergence of LLM systems, retrieving precise, domain-specific literature remains a significant challenge. This paper addresses these challenges by integrating knowledge graphs with scientific literature embedded in large language models to expedite biomedical discovery. We employ a novel strategy to discover the most relevant pathways between biomedical entities in knowledge graphs. These pathways are then leveraged by a multi-agent LLM system to formulate facts from literature, design AI predictors for understanding discovered pathways, and propose wet-lab experiments to validate AI predictions. This approach creates a comprehensive end-to-end methodology for biomedical discovery. Experiments with various biomedical entity pairs demonstrate the frameworks ability to identify highly relevant pathways and design plausible, complex AI predictors with wet lab validation experiments across diverse therapeutic areas. We developed Intelliscope, a web-based dashboard making this framework available to researchers worldwide. This first-of-its-kind platform could significantly accelerate scientific discoveries, potentially leading to breakthroughs in disease understanding, drug repurposing, and therapeutic development.

bioinformatics↗

bioRxiv2025

COMIC: Explainable Drug Repurposing via Contrastive Masking for Interpretable Connections

Many diseases worldwide remain untreated due to the slow and expensive process of drug development. Repurposing existing FDA-approved drugs offers a faster solution, especially with the assistance of artificial intelligence. Despite advancements in AI-driven drug repurposing, current approaches either have lackluster performance or fail to highlight the intricate pathways through which drugs act on diseases. The clinical utility of AI-driven drug repurposing remains constrained by these limitations, particularly for rare and undertreated diseases where data is scarce. To address the need for a precise and explainable predictor, this paper introduces COMIC (COntrastive Masking with Interpretable Connections), a predictor that employs a multi channel architecture consisting of a feature masking branch, which identifies critical drug-disease interaction patterns by extracting the most informative features, and a path masking branch, which highlights relevant biological pathways through which drugs exert their therapeutic effects. Comprehensive evaluation of the COMIC predictor on the PrimeKG knowledge graph (comprising 17,080 diseases, and 4M+ relationships) with nine distinct disease area splits demonstrated a 9.55% average performance improvement over the current state-of-the-art. The practical applicability of the proposed predictor is evaluated on a set of the most recent 30 FDA-approved repurposed drug disease pairs. The COMIC predictor successfully identified 21 of these pairs with high confidence scores. To facilitate real-time drug repurposing investigations, we have developed a publicly available web-based interface for the COMIC predictor (https://drp.opendfki.de/). This application takes disease names as input and returns a ranked list of potential repurposing candidates, along with predicted mechanistic pathways elucidating the drug-disease interactions.

bioinformatics↗

bioRxiv2025

FROM CANCER MOLECULAR SUBTYPE TO AI HYPE: BENCHMARKING AI IN CANCER MOLECULAR SUBTYPING

BackgroundCancer molecular subtype classification is an essential component of precision oncology which provides insights into cancer prognosis and guides targeted therapy. Despite the growing applications of AI for cancer molecular subtype classification, challenges persist due to non-standardized dataset configurations, diverse omics modalities, and inconsistent evaluation measures. These issues limit the comparability, reproducibility, and generalizability of AI classifiers across different cancers and hinder the development of robust and accurate AI-driven tools. ResultsThis study benchmarks 35 unique AI classifiers across 153 datasets, covering 8 omics modalities and 20 different cancers. Particularly, it investigates 6 different research questions, and based on comprehensive performance analyses of the 35 AI classifiers it elucidates the research questions with the following answers: (i) Out of 17 different configurations for 5/8 omics modalities, RPPA (RPPA), Gistic2-all-data-by-genes (CNV), HM27 (Meth), and HiSeqV2-exon (Exon) configurations consistently yield better performance; (ii) In terms of 8 omics modalities, RNASeq, miRNA, CNV, and Exon generally achieve higher macro-accuracy compared to Meth., Array, SNP and RPPA; (iii) SNP and RPPA modalities are prone to biases due to technical noise and data imbalance; (iv) Traditional machine learning (ML) models (SVM, XGB, HGB) perform best on small and low-dimensional datasets, while deep learning (DL) models (ResNet18, CNN, NN, MLP) excel on large and high-dimensional datasets; (v) SVM achieves the highest mean macro-accuracy across all classifiers, with NN, ResNet18, DEEPGENE, and MLP also demonstrate strong performance; and (vi) DL classifiers show superior macro accuracy as compared to ML classifiers in 12 out of 20 cancers. ConclusionsThe findings offer key insights to guide the development of standardized, robust, and efficient AI-driven pipelines for cancer molecular subtype classification. This study enhances reproducibility and facilitates better comparison across AI methods, ultimately advancing precision oncology. Key PointsO_LIThis study benchmarks 35 unique AI classifiers, ranging from simpler ML models such as Support Vector Machines (SVM), Histogram-Based Gradient Boosting (HGB), and K-Nearest Neighbors (KNN), to complex DL classifiers including Convolutional Neural Networks (CNNs), computer vision models like DenseNet and ResNet, sequential models such as Recurrent Neural Networks (RNN), Gated Recurrent Units (GRU), Long Short-Term Memory networks (LSTM), and their hybrid combinations (e.g., CNN-LSTM, CNN-GRU), as well as transformer-based models, across 153 datasets spanning 8 omics modalities and 20 cancers. It identifies optimal data configurations and evaluates the performance of these classifiers in cancer molecular subtype classification. C_LIO_LIThe study highlights biases in specific omics modalities: SNP, RPPA, and Array exhibit higher variability and precision-recall imbalances, while RNASeq, miRNA, Exon, and CNV deliver more consistent and reliable results. C_LIO_LIML models (e.g., SVM, XGB, HGB) demonstrate strong performance on smaller datasets with fewer features, whereas DL models (e.g., ResNet18, CNN, NN, MLP, and DEEPGENE transformer) excel in handling high-dimensional datasets with large sample sizes. C_LIO_LIThe findings provide critical insights for developing robust, standardized AI pipelines for precision oncology, enhancing reproducibility and enabling meaningful cross-method comparisons. C_LI

bioinformatics↗

bioRxiv2025

BIND: Large-Scale Biological Interaction Network Discovery through Knowledge Graph-Driven Machine Learning

The complex interactions between biological entities provide valuable insights into fundamental life processes, which pave the way to a deeper understanding of disease mechanisms for the development of innovative therapeutic strategies. To enable large-scale predictions of biological interactions, multifarious AI-driven predictors have been developed. However, most of these are developed by leveraging information from only a limited subset of interaction types, and the broader interaction types landscape could facilitate AI algorithms to learn more informative patterns to predict unknown interactions. To address the need of a robust and precise interaction predictor, we introduce BIND (Biological Interaction Network Discovery), a predictor that leverages simultaneous learning across 10 biological entities and 30 interaction types. To develop BIND, we first evaluate 11 distinct Knowledge Graph Embedding Methods on the largest public biomedical interaction dataset namely PrimeKG. For each relation type, we extracted entity embeddings from the top 5 performing Knowledge Graph Embedding Models (KGEMs) and input them into 7 distinct machine learning classifiers. Rigorous evaluation of 1,050 predictive pipelines demonstrated that specific combinations of KGEMs and classifiers achieved F1 scores of 90% to 99% across various interaction types. Comprehensive evaluation across each relation type identified the top-performing predictive pipelines, which became the foundation of the BIND web application. To reveal the practical utility of our web application in identifying novel biological interactions, we conducted a case study on drug-phenotype interactions. The application gave 1,355 high confidence predictions, from which potential interactions were subsequently validated by scientific evidence found within the existing literature (Table 5). We believe BINDs web applications public access will serve as a valuable tool for biologists to identify unknown interactions that can be subsequently validated through wet-lab experiments. O_TBL View this table: org.highwire.dtl.DTLVardef@18666a0org.highwire.dtl.DTLVardef@bbb608org.highwire.dtl.DTLVardef@1ac062borg.highwire.dtl.DTLVardef@c90ea1org.highwire.dtl.DTLVardef@1df9369_HPS_FORMAT_FIGEXP M_TBL O_FLOATNOTable 5.C_FLOATNO O_TABLECAPTIONPredicted Drug-Phenotype Associations with Strong Literature Support C_TABLECAPTION C_TBL

bioinformatics↗

bioRxiv2023

iLEC-DNA: Identifying Long Extra-chromosomalCircular DNA by Fusing Sequence-derived Featuresof Physicochemical Properties and NucleotideDistribution Patterns

Long extrachromosomal circular DNA (leccDNA) regulates several biological processes such as genomic instability, gene amplification, and oncogenesis. The identification of leccDNA holds significant importance to investigate its potential associations with cancer, autoimmune, cardiovascular, and neurological diseases. In addition, understanding these associations can provide valuable insights about disease mechanisms and potential therapeutic approaches. Conventionally, wet lab-based methods are utilized to identify leccDNA, which are hindered by the need for prior knowledge, and resource-intensive processes, potentially limiting their broader applicability. To empower the process of leccDNA identification across multiple species, the paper in hand presents the very first computational predictor. The proposed iLEC-DNA predictor makes use of SVM classifier along with sequence-derived nucleotide distribution patterns and physicochemical properties-based features. In addition, the study introduces a set of 12 benchmark leccDNA datasets related to three species, namely HM, AT, and YS. It performs large-scale experimentation across 12 benchmark datasets under different experimental settings using the proposed predictor and more than 140 baseline predictors. The proposed predictor outperforms baseline predictors across diverse leccDNA datasets by producing average performance values of 80.699%, 61.45% and 80.7% in terms of ACC, MCC and AUC-ROC across all the datasets. The source code of the proposed and baseline predictors is available at https://github.com/FAhtisham/Extrachrosmosomal-DNA-Prediction.

bioinformatics↗

bioRxiv2023

Generative adversarial networks in cell microscopy for image augmentation. A systematic review

Cell microscopy is the main tool that allows researchers to study microorganisms and plays a key role in observing and understanding the morphology, interactions, and development of microorganisms. However, there exist limitations in both the techniques and the samples that impair the amount of available data to study. Generative adversarial networks (GANs) are a deep learning alternative to alleviate the data availability limitation by generating nonexistent samples that resemble the probability distribution of the real data. The aim of this systematic review is to find trends, common practices, popular datasets, and analyze the impact of GANs in image augmentation of cell microscopy images. We used ScienceDirect, IEEE Xplore, PubMed, bioRxiv, and arXiv to select English research articles that employed GANs to generate any kind of cell microscopy images independently of the main objective of the study. We conducted the data collection using 15 selected features from each study, which allowed us to analyze the results from different perspectives using tables and histograms. 32 studies met the legibility criteria, where 18 had image augmentation as the main task. Moreover, we retrieved 21 publicly available datasets. The results showed a lack of consensus with performance metrics, baselines, and datasets. Additionally, we evidenced the relevance of popular architectures such as StyleGAN and losses including Vanilla and Wasserstein adversarial loss. This systematic review presents the most popular configurations to perform image augmentation. It also highlights the importance of design good practices and gold standards to guarantee comparability and reproducibility. This review implemented the ROBIS tool to assess the risk of bias, and it was not registered in PROSPERO.

bioinformatics↗

bioRxiv2023

Segment Anything for Microscopy

We present Segment Anything for Microscopy, a tool for interactive and automatic segmentation and tracking of objects in multi-dimensional microscopy data. Our method is based on Segment Anything, a vision foundation model for image segmentation. We extend it by training specialized models for microscopy data that significantly improve segmentation quality for a wide range of imaging conditions. We also implement annotation tools for interactive (volumetric) segmentation and tracking, that speed up data annotation significantly compared to established tools. Our work constitutes the first application of vision foundation models to microscopy, laying the groundwork for solving image analysis problems in these domains with a small set of powerful deep learning architectures.

bioinformatics↗

bioRxiv2023

NTpred: A robust and precise machine learningframework for in-silico identification of Tyrosine nitration sites in protein sequences

Post-translational modifications (PTMs) either enhance a proteins activity in various sub-cellular processes, or degrade their activity which leads towards failure of intracellular processes. Tyrosine nitration (NT) modification degrades proteins activity that initiate and propagate various diseases including Neurodegenerative, Cardiovascular, Autoimmune diseases, and Carcinogenesis. Identification of NT modification support development of novel therapies and drug discoveries for associated diseases. Identification of NT modification in biochemical labs is expensive, time consuming, and error-prone. To supplement this process, several computational approaches have been proposed. However these approaches remain fail to precisely identify NT modification, due to the extraction of irrelevant, redundant and less discriminative features from protein sequences. The paper in hand presents NTpred framework competent in extracting comprehensive features from raw protein sequences using four different sequence encoders. To reap the benefits of different encoders, it generates four additional feature spaces by fusing different combinations of individual encodings. Furthermore, it eradicates irrelevant and redundant features from eight different feature spaces through a Recursive Feature Elimination process. Selected features of four individual encodings and four feature fusion vectors are used to train eight different Gradient Boosted Tree classifiers. The probability scores from the trained classifiers are utilized to generate a new probabilistic feature space, that is utilized to train a Logistic Regression classifier. On BD1 benchmark dataset, the proposed framework outperform existing best performing predictor in 5-fold cross validation and independent test evaluation with combined improvement of 13.7% in MCC and 20.1% in AUC. Similarly, on BD2 benchmark dataset, the proposed framework outperform existing best performing predictor with combined improvement of 5.3% in MCC and 1.0% in AUC.

bioinformatics↗

bioRxiv2020

A convNet based multi-label microRNA subcellular location predictor, by incorporating k-mer positional encoding

MicroRNAs are special RNA sequences containing 22 nucleotides and are capable of regulating almost 60% of highly complex mammalian transcriptome. Presently, there exists very limited approaches capable of visualizing miRNA locations inside cell to reveal the hidden pathways, and mechanisms behind miRNA functionality, transport, and biogenesis. State-of-the-art miRNA sub-cellular location prediction MIRLocatar approach makes use of sequence to sequence model along with pre-train k-mer embeddings. Existing pre-train k-mer embedding generation methodologies focus on the extraction of semantics of k-mers. In RNA sequences, rather than semantics, positional information of nucleotides is more important because distinct positions of four basic nucleotides actually define the functionality of RNA molecules. Considering the dynamicity and importance of nucleotides positions, instead of learning representation on the basis of k-mers semantics, we propose a novel kmerRP2vec feature representation approach that fuses positional information of k-mers to randomly initialized neural k-mer embeddings. Effectiveness of proposed feature representation approach is evaluated with two deep learning based convolutional neural network CNN and recurrent neural network RNN methodologies using 8 evaluation measures. Experimental results on a public benchmark miRNAsubloc dataset prove that proposed kmerRP2vec approach along with a simple CNN model outperforms state-of-the-art MirLocator approach with a significant margin of 18% and 19% in terms of precision and recall.

genomics↗