VAVenkat Ayyalasomayajula

Venkat Ayyalasomayajula

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Venkat Ayyalasomayajula has a total of 45 co-authors. Here are the top co-authors by number of shared publications:

  • Baptiste Pierrat

    Mines Saint-Étienne, CIS-EMSE, F-42023 Saint-Étienne, France; INSERM, U1059, SAINBIOSE, F-42023 Saint-Étienne, France; Université de Lyon, F-69000 Lyon, France

    4 shared publications
  • Kak Khee Yeung

    4 shared publications
  • Pierre Badel

    Mines Saint-Étienne, CIS-EMSE, F-42023 Saint-Étienne, France; INSERM, U1059, SAINBIOSE, F-42023 Saint-Étienne, France; Université de Lyon, F-69000 Lyon, France

    4 shared publications
  • Bjørn Skallerud

    Department of Structural Engineering, Norwegian University of Science and Technology, Trondheim, 7052, Norway

    3 shared publications
  • Juliette Raffort

    2 shared publications
  • Aleksandra Stankovic

    Laboratory for Radiobiology and Molecular Genetics, VINCA Institute of Nuclear Sciences—National Institute of the Republic of Serbia, University of Belgrade, Belgrade, Serbia

    1 shared publication

Latest Publications

  • Open Access

    Future directions in aorto-iliac aneurysm repair and integration of artificial intelligence

    by Fabien Lareyre, Juliette Raffort, Sébastien Goffart, Venkat Ayyalasomayajula, Kak Khee Yeung

  • Open Access

    Uncertainty-aware graph representation learning with positive-unlabeled classification for biomarker discovery in peripheral artery disease

    by Venkat Siva Radha Krishna Ayyalasomayajula, Max L. Senders, Jelmer M. Wolterink, Kak Khee Yeung

    Peripheral artery disease (PAD) is a complex vascular disorder characterized by heterogeneous molecular mechanisms and incomplete functional annotation, limiting systematic biomarker discovery. Network-based learning approaches provide a powerful framework for disease gene prioritization; however, most existing methods produce overconfident predictions without explicitly accounting for model uncertainty or structural novelty. Here, we present an uncertainty-aware framework for PAD biomarker discovery that integrates unsupervised graph representation learning, positive–unlabeled (PU) classification, ensemble prediction, and mechanistic explainability. Node embeddings were learned using multiple unsupervised graph neural network (GNN) objectives and combined with heterogeneous classifiers to generate ensemble-averaged probability estimates and epistemic uncertainty. By jointly modeling predictive confidence and embedding-space novelty, we stratified candidates into high-confidence rediscoveries and structurally novel hypotheses under explicit uncertainty control. Across eight embedding objectives and five classifiers, ensemble aggregation produced stable, well-calibrated predictions and enabled prioritization of 100 candidate PAD-associated proteins. Probability-heavy candidates clustered tightly with known PAD proteins and were enriched for established vascular and hemostatic pathways, including extracellular matrix organization, integrin signaling, coagulation, and fibrinolysis. In contrast, novelty-heavy candidates occupied distinct embedding-space regions and partitioned into multiple coherent clusters enriched for upstream regulatory and signaling processes, including G protein-coupled receptor, ephrin receptor, kinase-driven, and NF-κB-associated pathways. Five-fold cross-validated comparison with established PU learning baselines demonstrated consistent improvement across all evaluation metrics (AUC 0.916 ± 0.019 vs. 0.821 ± 0.030 for the best baseline), and external validity was confirmed by significant enrichment of top candidates for related cardiovascular disease annotations (5.7× above background). Together, these results demonstrate that integrating uncertainty, novelty, and explainability enables calibrated and biologically grounded biomarker prioritization, with broad applicability to PAD and other complex diseases.

  • Open Access

    Developing Trustworthy Artificial Intelligence Models to Predict Vascular Disease Progression: the VASCUL-AID-RETRO Study Protocol

    by Lotte Rijken, Sabrina Zwetsloot, Stefan Smorenburg, Jelmer Wolterink, Ivana Išgum, Henk Marquering, Jan van Duivenvoorde, Corrette Ploem, Roosmarie Jessen, Fabio Catarinella, et al.

    Introduction: Abdominal aortic aneurysms (AAAs) and peripheral artery disease (PAD) are two vascular diseases with a significant risk of major adverse cardiovascular events and mortality. A challenge in current disease management is the unpredictable disease progression in individual patients. The VASCUL-AID-RETRO study aims to develop trustworthy multimodal predictive artificial intelligence (AI) models for multiple tasks including risk stratification of disease progression and cardiovascular events in patients with AAA and PAD. Methods: The VASCUL-AID-RETRO study will collect data from 5000 AAA and 6000 PAD patients across multiple European centers of the VASCUL-AID consortium using electronic health records from 2015 to 2024. This retrospectively-collected data will be enriched with additional data from existing biobanks and registries. Multimodal data, including clinical records, radiological imaging, proteomics, and genomics, will be collected to develop AI models predicting disease progression and cardiovascular risks. This will be done while integrating the international ethics guidelines and legal standards for trustworthy AI, to ensure a socially-responsible data integration and analysis. Proposed Analyses: A consensus-based variable list of clinical parameters and core outcome set for both diseases will be developed through meetings with key opinion leaders. Blood, plasma, and tissue samples from existing biobanks will be analyzed for proteomic and genomic variations. AI models will be trained on segmented AAA and PAD artery geometries for estimation of hemodynamic parameters to quantify disease progression. Initially, risk prediction models will be developed for each modality separately, and subsequently, all data will be combined to be used as input to multimodal prediction models. During all processes, data security, data quality, and ethical guidelines and legal standards will be carefully considered. As a next step, the developed models will be further adjusted with prospective data and internally validated in a prospective cohort (VASCUL-AID-PRO study). Conclusion: The VASCUL-AID-RETRO study will utilize advanced AI techniques and integrate clinical, imaging, and multi-omics data to predict AAA and PAD progression and cardiovascular events. Clinical Trial Registration: The VASCUL-AID-RETRO study is registered at www.clinicaltrials.gov under the identification number NCT06206369. Clinical Impact: The VASCUL-AID-RETRO study aims to improve clinical practice of vascular surgery by developing artificial intelligence-driven multimodal predictive models for patients with abdominal aortic aneurysms or peripheral artery disease, enhancing personalized medicine. By integrating comprehensive data sets including clinical, imaging, and multi-omics data, these models have the potential to provide accurate risk stratification for disease progression and cardiovascular events. An innovation lies in the extensive European data set in combination with multimodal analyses approaches, which enables the development of advanced models to facilitate better understanding of disease mechanisms and progression. For clinicians, this means that more precise, individualized treatment plans can be established, ultimately aiming to improve patient outcomes.


  • Open Access

    Evaluation of a multi-scale discrete fiber model for analyzing arterial failure

    by Venkat Ayyalasomayajula, Baptiste Pierrat, Pierre Badel


  • Open Access

    Potential of computational models in personalized treatment of obstructive sleep apnea: a patient-specific 3-d finite element study

    by Venkat Ayyalasomayajula, Mads H S Moxeness, Bjørn Skallerud

    The upper airway experiences mechanical loads during breathing. Obstructive sleep apnea is a very common sleep disorder, in which the normal function of the airway is compromised, enabling its collapse. Its treatment remains unsatisfactory with variable efficacy in the case of many surgeries. Finite element models of the upper airway to simulate the effects of various anatomic and physiologic manipulations on its mechanics could be helpful in predicting surgical success. Partial 3-D finite element models based on patient-specific CT-scans are generated. The pharyngeal wall, the soft palate, the tongue, and their interactions are aimed at. Anatomic and physiologic operations are then conducted on the generated models to reflect commonly employed surgical techniques. Our results showed that maxillo-mandibular advancement(MAD) surgery of just 1 cm improved the critical closing pressure by atleast 212.2%. Following MAD, the best improvement was seen via uvulopalatopharyngoplasty (UPPP), with an improvement of at least 19.12%. Palatal and tongue implants also offered a certain degree of improvement. Further, we observed possible interacting mechanisms which suggested simultaneous implementation of UPPP and tongue stiffening; and palatal and tongue stiffening could be beneficial. Our results suggest that computational modeling is a useful tool for analyzing the influence of anatomic and physiological manipulations on upper airway mechanics. The goal of personalized treatment in the case of OSA could be achieved with the use of computational modeling.


  • Open Access

    Failure properties and microstructure of porcine aortic adventitia: fiber level damage vs tissue failure

    by Venkat Ayyalasomayajula, Baptiste Pierrat, Pierre Badel

    Aortic aneurysm rupture is a sudden local event with high mortality. It is generally accepted that the adventitia acts as the final barrier protecting the aorta from over-expansion. Currently, the knowledge of microscopic structural determinants of the tissue’s mechanical response and failure is very limited. The purpose of this study is to provide data on the directional failure properties of the adventitia, combined with micro-structural imaging and structure based constitutive modeling to quantify fiber-scale rupture criteria. Eleven healthy porcine aortas were used in this study. Cylindrical portions of the abdominal section were excised, cut-open longitudinally, the medial and adventitial layers separated methodically. Picrosirius red staining was used to image the collagen fiber morphology via an optical microscope. Subsequently, dog-bone shaped specimens were subjected to uniaxial testing until failure while being recorded by a Nikon digital camera. A fiber-scale damage model was utilized to explain the tissue-scale failure. The ultimate tensile stress in the circumferential and longitudinal directions were recorded to be 0.96 ± 0.29 MPa and 0.85 ± 0.36 MPa respectively. Meanwhile, the ultimate stretch to failure in the circumferential and longitudinal directions were recorded to be 1.72 ± 0.16 and 1.88 ± 0.13 respectively. Further, correlation between the failure properties of the tissue and mean fiber orientation have been reported. Finally, the critical fiber stretch for damage initiation and eventual tissue failure were identified to be 1.19 ± 0.07 and 1.24 ± 0.05 for circumferential and longitudinal specimens respectively. Our approach provides valuable insight into the (patho)physiological mechanical role of collagen fibers at different loading states. This study is useful in enhancing the utilization of structurally motivated material models for predicting arterial tissue failure.