Hasan Ogul

• Qassi, Abdelaziz; Hallac, Ibrahim Riza & Ogul, Hasan (2026). Investigating the Relevance of NLP Benchmarks for Automated Essay Grading: A Multi-trait Evaluation of Pre-trained Transformers. Lecture Notes in Networks and Systems. ISSN 2367-3370. 1754, p. 137–151. doi: 10.1007/978-3-032-13153-9_11. Full text in Research Archive
• Tanner, Thomas; Marfurt, Andreas & Ogul, Hasan (2025). Enhancing Question Answering in Lecture Videos with a Multimodal Retrieval-Augmented Generation Framework. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 15462, p. 184–198. doi: 10.1007/978-3-031-81542-3_15. Full text in Research Archive
• Leseanu, Anda; Hallac, Ibrahim Riza; Ogul, Burcin Buket & Ogul, Hasan (2025). Revisiting Automatic Essay Assessment: A Relative Approach. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. p. 41–52. doi: 10.1007/978-3-032-08462-0_4. Full text in Research Archive Show summary

  Automatic essay assessment has remained a challenging problem in natural language processing (NLP) for over fifty years. Traditionally framed as a regression task that predicts examiner-assigned scores, this work instead adopts a relative assessment perspective. The task is redefined as pairwise ranking, where essays are compared using standard assessment criteria, but their exact grades are assumed to be unknown and ultimately unimportant. Three core contributions are presented. First, an architecture is proposed for pairwise essay ranking using labeled quality criteria, with two fusion strategies explored. Second, an experimental setup for relative ranking is redefined based on a benchmark dataset originally intended for absolute scoring. Third, empirical comparisons are reported across architectural components and design choices. Results indicate that data-level fusion using LLaMA-based embeddings and a gradient-boosted classifier achieves the highest accuracy. A model-level fusion approach with a Siamese neural network and probabilistic loss also yields competitive performance, highlighting its potential for further research. This relative assessment framework offers practical value for student progress tracking and norm-referenced grading in educational contexts.

• Surko, Arina & Ogul, Hasan (2025). Retrieving Relevant Single-Cell RNA Sequencing Profiles with Gene Expression Clustering. In Bourbakis, Nikolaos & Filipovic, Nenad (Ed.), 2025 IEEE 25th International Conference on Bioinformatics and Bioengineering (BIBE) Proceedings. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798331558994. p. 381–386. doi: 10.1109/BIBE66822.2025.00070. Full text in Research Archive Show summary

  Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful technology for analyzing cellular heterogeneity and gene expression at high resolution. With the rapid growth of publicly available scRNA-seq databases, there is a growing demand for methods that enable systematic comparison and retrieval of profiles based on gene expression patterns rather than metadata. However, no standardized workflow currently exists for retrieving relevant scRNA-seq profiles using expressionbased similarity. In this paper, we present a novel framework for comparing and retrieving scRNA-seq profiles based on gene expression. Each profile is represented as a dendrogram derived from hierarchical clustering of genes based on their expression patterns across cells. To compare profiles, we introduce a new similarity metric, Multi-Resolution Adjusted Rand Index (MRARI), which extends the traditional Adjusted Rand Index (ARI) by incorporating hierarchical information. Retrieval is performed by computing pairwise MR-ARI scores between profiles. We evaluate the method's performance using a bootstrapped distribution of the Area Under the Receiver Operating Characteristic Curve (AUROC).

• Ogul, Hasan (2025). Language of actions: A generative model for activity recognition and next move prediction from motion sensors. Expert Systems With Applications. ISSN 0957-4174. 264. doi: 10.1016/j.eswa.2024.125947. Full text in Research Archive
• Batar, Bahadır; Serdal, Elif; Erdal, Berna & Ogul, Hasan (2024). Loss of WWOX contributes to cisplatin resistance in triple-negative breast cancer cells by modulating miR-182 and miR-214. Turkish Journal of Medical Sciences. ISSN 1300-0144. 54(5), p. 1127–1134. doi: 10.55730/1300-0144.5891. Full text in Research Archive
• Formoe, Lars; Mygind, Dan Bruun; Løkke, Espen & Ogul, Hasan (2023). Unsupervised Learning for Automatic Speech Recognition in Air Traffic Control Environment. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 14102, p. 239–248. doi: 10.1007/978-3-031-40498-6_21. Full text in Research Archive
• Ogundokun, Roseline Oluwaseun; Misra, Sanjay; Akinrotimi, Akinyemi Omololu & Ogul, Hasan (2023). MobileNet-SVM: A Lightweight Deep Transfer Learning Model to Diagnose BCH Scans for IoMT-Based Imaging Sensors. Sensors. 23(2). doi: 10.3390/s23020656. Full text in Research Archive Show summary

  Many individuals worldwide pass away as a result of inadequate procedures for prompt illness identification and subsequent treatment. A valuable life can be saved or at least extended with the early identification of serious illnesses, such as various cancers and other life-threatening conditions. The development of the Internet of Medical Things (IoMT) has made it possible for healthcare technology to offer the general public efficient medical services and make a significant contribution to patients’ recoveries. By using IoMT to diagnose and examine BreakHis v1 400× breast cancer histology (BCH) scans, disorders may be quickly identified and appropriate treatment can be given to a patient. Imaging equipment having the capability of auto-analyzing acquired pictures can be used to achieve this. However, the majority of deep learning (DL)-based image classification approaches are of a large number of parameters and unsuitable for application in IoMT-centered imaging sensors. The goal of this study is to create a lightweight deep transfer learning (DTL) model suited for BCH scan examination and has a good level of accuracy. In this study, a lightweight DTL-based model “MobileNet-SVM”, which is the hybridization of MobileNet and Support Vector Machine (SVM), for auto-classifying BreakHis v1 400× BCH images is presented. When tested against a real dataset of BreakHis v1 400× BCH images, the suggested technique achieved a training accuracy of 100% on the training dataset. It also obtained an accuracy of 91% and an F1-score of 91.35 on the test dataset. Considering how complicated BCH scans are, the findings are encouraging. The MobileNet-SVM model is ideal for IoMT imaging equipment in addition to having a high degree of precision. According to the simulation findings, the suggested model requires a small computation speed and time.

• Assidicky, Ridho; Tokat, Unal Metin; Tarman, Ibrahim Oguzhan; Saatci, Ozge; Ersan, Pelin Gulizar & Raza, Umar [Show all 10 contributors for this article] (2022). Targeting HIF1-alpha/miR-326/ITGA5 axis potentiates chemotherapy response in triple-negative breast cancer. Breast Cancer Research and Treatment. ISSN 0167-6806. 193(2), p. 331–348. doi: 10.1007/s10549-022-06569-5. Full text in Research Archive
• Bayrak, Tuncay; Çetin, Zafer; Saygılı, E. İlker & Ogul, Hasan (2022). Identifying the tumor location-associated candidate genes in development of new drugs for colorectal cancer using machine-learning-based approach. Medical and Biological Engineering and Computing. ISSN 0140-0118. 60(10), p. 2877–2897. doi: 10.1007/s11517-022-02641-w. Full text in Research Archive
• Aşuroğlu, Tunç & Ogul, Hasan (2022). A deep learning approach for parkinson’s disease severity assessment. Health and Technology. ISSN 2190-7188. 12(5), p. 943–953. doi: 10.1007/s12553-022-00698-z. Full text in Research Archive
• Şener, Duygu Dede; Ogul, Hasan & Basak, Selen (2022). Text-based experiment retrieval in genomic databases. Journal of information science. ISSN 0165-5515. 50(5), p. 1334–1344. doi: 10.1177/01655515221118670. Full text in Research Archive
• Balci, Tolgay & Ogul, Hasan (2021). Predicting Bank Return on Equity (ROE) using Neural Networks. In Kovacs, Levente (Eds.), IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728180540. p. 000279–000286. doi: 10.1109/SAMI50585.2021.9378636. Full text in Research Archive
• Paker, Ahmet & Ogul, Hasan (2021). A Deep Learning Model for MicroRNA-Target Binding. In Elloumi, Mourad (Eds.), Deep Learning for Biomedical Data Analysis: Techniques, Approaches, and Applications. Springer. ISSN 9783030716752. p. 61–79. doi: 10.1007/978-3-030-71676-9_3. Full text in Research Archive
• Chand, Dipesh & Ogul, Hasan (2021). A Framework for Lecture Video Segmentation from Extracted Speech Content. In Kovacs, Levente (Eds.), IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728180540. p. 000299–000304. doi: 10.1109/SAMI50585.2021.9378632. Full text in Research Archive Show summary

  Increasing demand for lecture videos in digital libraries has raised the challenge of automatic annotation of lecture content for effective navigation of lectures by users. One direction is the prior segmentation of lecture videos to simplify several applications such as indexing, keyword spotting, and targeted search. In this study, we present a lecture video segmentation framework based on the speech content of the instructors. The framework is built upon a model that extracts textual and acoustic features from speech and uses them to identify topical segment boundaries of the lecture video. To evaluate our proposed model, we collected our own dataset containing a diverse set of 37 lecture videos and also manually created ground truth. The performance was measured by using metrics like Precision, Recall, and F1 Score and obtained 0.69, 0.58, and 0.63 respectively. We also compared our model with some previously known similar models where our model outperformed others. The overall results of the study are presented as a lecture video segmentation model, integrating various tools and techniques, and showing promising performance. Findings can be used further for research in content-based search and retrieval using speech content.

• Bayrak, Tuncay & Ogul, Hasan (2021). Computer-aided diagnosis of sleep apnea using gene expression. Health and Technology. ISSN 2190-7188. 11, p. 941–952. doi: 10.1007/s12553-021-00557-3. Full text in Research Archive
• Aşuroğlu, Tunç & Ogul, Hasan (2021). A Deep Learning Approach for Sepsis Monitoring via Severity Score Estimation. Computer Methods and Programs in Biomedicine. ISSN 0169-2607. 198. doi: 10.1016/j.cmpb.2020.105816. Full text in Research Archive
• Chand, Dipesh & Ogul, Hasan (2020). Content-Based Search in Lecture Video: A Systematic Literature Review. In Huang, May; Gokhale, Anu & Zhang, Sen (Ed.), 3rd International Conference on Information and Computer Technologies (ICICT). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728172835. p. 169–176. doi: 10.1109/ICICT50521.2020.00034. Full text in Research Archive
• Cabıoğlu, Çağrı & Ogul, Hasan (2020). Computer-Aided Breast Cancer Diagnosis from Thermal Images Using Transfer Learning. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 12108, p. 716–726. doi: 10.1007/978-3-030-45385-5_64. Full text in Research Archive Show summary

  Breast cancer is one of the prevalent types of cancer. Early diagnosis and treatment of breast cancer have vital importance for patients. Various imaging techniques are used in the detection of cancer. Thermal images are obtained by using the temperature difference of regions without giving radiation by the thermal camera. In this study, we present methods for computer aided diagnosis of breast cancer using thermal images. To this end, various Convolutional Neural Networks (CNNs) have been designed by using transfer learning methodology. The performance of the designed nets was evaluated on a benchmarking dataset considering accuracy, precision, recall, F1 measure, and Matthews Correlation coefficient. The results show that an architecture holding pre-trained convolutional layers and training newly added fully connected layers achieves a better performance compared with others. We have obtained an accuracy of 94.3%, a precision of 94.7% and a recall of 93.3% using transfer learning methodology with CNN.

• Erdogan, Burak & Ogul, Hasan (2020). Objective Pain Assessment Using Vital Signs. Procedia Computer Science. 170, p. 947–952. doi: 10.1016/j.procs.2020.03.103. Full text in Research Archive Show summary

  Pain is considered as an emotional experience and unrestful feeling associated with tissue damage. The feeling of pain occurs when the interpretation starts in brain; as a signal is sent through nerve fiber to the brain. Pain allows the body to prevent further tissue damage. Since there are different ways of expressing and feeling pain, the experience of pain is unique for everybody. In this respect, objective pain assessment is a key step and a major challenge in proper management of pain in different individuals. In this study, we offer a computational solution for objective assessment of pain using vital signs. To this end, we have reported the prediction for existence of pain by calculating the performances of several computational methods that take the sequence of vital signs acquired until pain observation as input. We claim that the use of computational intelligence methods can encourage computer-aided monitoring of pain in a hospitalized environment to a certain degree.

• Agziyagli, Veysel Sercan & Ogul, Hasan (2020). Multi-level lecture video classification using text content. In Adamov, Abzetdin (Eds.), 2020 IEEE 14th International Conference on Application of Information and Communication Technologies (AICT): Conference proceedings. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728173863. doi: 10.1109/AICT50176.2020.9368692. Full text in Research Archive
• Baldominos, Alejandro; Ogul, Hasan; Colomo-Palacios, Ricardo; Sanz-Moreno, José & Gómez-Pulido, José Manuel (2020). Infection Prediction using Physiological and Social Data in Social Environments. Information Processing & Management. ISSN 0306-4573. 57(3). doi: 10.1016/j.ipm.2020.102213. Full text in Research Archive Show summary

  The ability of detecting infections at an early stage in clinical environments is an important clinical problem. When an infection is not diagnosed on time, it may not only affect the health of the infected patient, but also spread and infect other people. In this paper, we propose the development of a clinical decision support system (CDSS) for diagnosing infections using clinical signals from patients. This system is designed to be able to cope with small amounts of data (a single record per day and patient), making it convenient for environments under strict constraints (such as low resources or bad connectivity). Additionally, we have incorporated data from external sources, in order to enrich the quality of the models. In particular, we have considered social data arising from web searches, retrieved from Google Trends, as well as weather data.

• Baldominos, Alejandro; Puello, Adrián; Ogul, Hasan; Aşuroğlu, Tunç & Colomo-Palacios, Ricardo (2020). Predicting infections using computational intelligence – A systematic review. IEEE Access. 8, p. 31083–31102. doi: 10.1109/ACCESS.2020.2973006. Full text in Research Archive Show summary

  Infections encompass a set of medical conditions of very diverse kinds that can pose a significant risk to health, and even death. As with many other diseases, early diagnosis can help to provide patients with proper care to minimize the damage produced by the disease, or to isolate them to avoid the risk of spread. In this context, computational intelligence can be useful to predict the risk of infection in patients, raising early alarms that can aid medical teams to respond as quick as possible. In this paper, we survey the state of the art on infection prediction using computer science by means of a systematic literature review. The objective is to find papers where computational intelligence is used to predict infections in patients using physiological data as features. We have posed one major research question along with nine specific subquestions. The whole review process is thoroughly described, and eight databases are considered which index most of the literature published in different scholarly formats. A total of 101 relevant documents have been found in the period comprised between 2003 and 2019, and a detailed study of these documents is carried out to classify the works and answer the research questions posed, resulting to our best knowledge in the most comprehensive study of its kind. We conclude that the most widely addressed infection is by far sepsis, followed by Clostridium difficile infection and surgical site infections. Most works use machine learning techniques, from which logistic regression, support vector machines, random forest and naive Bayes are the most common. Some machine learning works provide some ideas on the problems of small data and class imbalance, which can be of interest. The current systematic literature review shows that automatic diagnosis of infectious diseases using computational intelligence is well documented in the medical literature.

• Bayrak, Tuncay & Ogul, Hasan (2019). A New Approach for Predicting the Value of Gene Expression: Two-way Collaborative Filtering. Current Bioinformatics. ISSN 1574-8936. 14(6), p. 480–490. doi: 10.2174/1574893614666190126144139. Full text in Research Archive
• Acici, Koray; Asuroglu, Tunc; Erdas, Cagatay Berke & Ogul, Hasan (2019). T4SS Effector Protein Prediction with Deep Learning. Data. 4(1). doi: 10.3390/data4010045. Full text in Research Archive Show summary

  Extensive research has been carried out on bacterial secretion systems, as they can pass effector proteins directly into the cytoplasm of host cells. The correct prediction of type IV protein effectors secreted by T4SS is important, since they are known to play a noteworthy role in various human pathogens. Studies on predicting T4SS effectors involve traditional machine learning algorithms. In this work we included a deep learning architecture, i.e., a Convolutional Neural Network (CNN), to predict IVA and IVB effectors. Three feature extraction methods were utilized to represent each protein as an image and these images fed the CNN as inputs in our proposed framework. Pseudo proteins were generated using ADASYN algorithm to overcome the imbalanced dataset problem. We demonstrated that our framework predicted all IVA effectors correctly. In addition, the sensitivity performance of 94.2% for IVB effector prediction exhibited our framework’s ability to discern the effectors in unidentified proteins.

• Paker, Ahmet & Ogul, Hasan (2019). mirLSTM: A Deep Sequential Approach to MicroRNA Target Binding Site Prediction. Communications in Computer and Information Science (CCIS). ISSN 1865-0929. 1062, p. 38–44. doi: 10.1007/978-3-030-27684-3_6. Full text in Research Archive
• Haberal, Ismail & Ogul, Hasan (2019). Prediction of Protein Metal Binding Sites Using Deep Neural Networks. Molecular Informatics. ISSN 1868-1743. 38(7). doi: 10.1002/minf.201800169. Full text in Research Archive
• Ogul, Hasan; Baldominos, Alejandro; Aşuroğlu, Tunç & Colomo-Palacios, Ricardo (2019). On Computer-Aided Prognosis of Septic Shock from Vital Signs. In Rodriguez, Alejandro (Eds.), 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS): Proceedings of a meeting held 5-7 June 2019, Cordoba, Spain. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728122861. p. 87–92. doi: 10.1109/CBMS.2019.00028. Full text in Research Archive Show summary

  Sepsis is a life-threatening condition due to the reaction to an infection. With certain changes in circulatory system, sepsis may progress to septic shock if it is left untreated. Therefore, early prognosis of septic shock may facilitate implementing correct treatment and prevent more serious complications. In this study, we assess the feasibility of applying a computer-aided prognosis system for septic shock. The system is envisaged as a tool to predict septic shock at the time of sepsis onset using only vital signs which are collected routinely in intensive care units (ICUs). To this end, we evaluate the performances of computational methods that take the sequence of vital signs acquired until sepsis onset as input and report the possibility of progressing to a septic shock before any further clinical analysis is performed. Results show that an adaptation of multivariate dynamic time warping can reveal higher accuracy than other known time-series classification methods on a new dataset built from a public ICU database. We argue that the use of computational intelligence methods can promote computer-aided prognosis of septic shock in hospitalized environment to a certain degree.

• Baldominos, Alejandro; Ogul, Hasan & Colomo-Palacios, Ricardo (2019). Infection diagnosis using biomedical signals in small data scenarios. IEEE International Symposium on Computer-Based Medical Systems. p. 38–43. doi: 10.1109/CBMS.2019.00018. Full text in Research Archive Show summary

  Being able to detect an infection at an early stage is a clinical problem of the utmost importance. An infection not diagnosed on time might not only severely affect the infected patient's health, but also to spread and start a focus of contagion to other people. In this paper, we propose a clinical decision support system to automatically diagnose infections using physiological signals from the patients. The focus of the system is put on being able to deal with very small amounts of data (one aggregated record per patient and day), which eases the potential of the system in environments with low resources. Data has been acquired between April 2018 and January 2019 in two nursing homes in Spain, where nurses had also tested patients for infections. Machine learning models have then been created by aggregating measurements from days prior to the infection (lead) and after the infection started (lag) in order to generate features. The best model attained reports an AUROC of 0.722, using data from up to two days after the infection started. Interestingly, an AUROC of up to 0.692 is achieved when infection prognosis is considered; i.e., using only measurements prior to the manual recording of the infection to compose the dataset.

• Acici, Koray; Asuroglu, Tunc; Ogul, Hasan & Erdas, Cagatay Berke (2018). HANDY: A benchmark dataset for context-awareness via wrist-worn motion sensors. Data. 3(3). doi: 10.3390/data3030024. Full text in Research Archive Show summary

  Being aware of a personal context is a promising task for various applications, such as biometry, human-computer interactions, telemonitoring, remote care, mobile marketing and security. The task can be formally defined as the classification of a person being considered into one of predefined labels, which may correspond to his/her identity, gender, physical properties, the activity that he/she performs or any other attribute related to the environment being involved. Here, we offer a solution to the problem with a set of multiple motion sensors worn on the wrist. We first provide an annotated and publicly accessible benchmark set for context-awareness through wrist-worn sensors, namely, accelerometers, magnetometers and gyroscopes. Second, we present an evaluation of recent computational methods for two relevant tasks: activity recognition and person identification from hand movements. Finally, we show that fusion of two motion sensors (i.e., accelerometers and magnetometers), leads to higher accuracy for both tasks, compared with the individual use of each sensor type.

• Ogul, Hasan (2018). ALoT: A Time-Series Similarity Measure Based on Alignment of Textures. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 11314 LNCS, p. 576–585. doi: 10.1007/978-3-030-03493-1_60. Full text in Research Archive Show summary

  Inferring the similarity between two time-series signals is a key step in several data analysis tasks for a variety of engineering applications. In this paper, we introduce a novel elastic similarity measure (ALoT) based on the alignment of textures, instead of observed values, extracted from input time-series signals. To obtain the texture information, Local Binary Patterns are adapted for one-dimensional signals. According to experiments performed on a large number of benchmark time-series classification datasets, the proposed method achieves higher accuracy than current pairwise similarity measures for several cases in a 1-Nearest Neighbor classification setup.

View all works in NVA

• Ogul, Hasan & Moræus, Jonas Aamodt (2024). 2024 4th International Conference on Applied Artificial Intelligence (ICAPAI). IEEE (Institute of Electrical and Electronics Engineers). ISBN 9798350349764. 240 p. Full text in Research Archive
• Ogul, Hasan; Aamodt, Jonas Moræus; Misra, Sanjay & Kjølerbakken, Kai Morgan (2024). 2024 4th International Conference on Applied Artificial Intelligence (ICAPAI). IEEE (Institute of Electrical and Electronics Engineers). ISBN 9798350349764. 300 p. Full text in Research Archive

View all works in NVA

• Surko, Arina & Ogul, Hasan (2025). Retrieving Relevant Single-Cell RNA Sequencing Profiles with Gene Expression Clustering. doi: https:/easyconferences.eu/bibe2025/detailed-program/. Full text in Research Archive Show summary

  Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful technology for analyzing cellular heterogeneity and gene expression at high resolution. With the rapid growth of publicly available scRNA-seq databases, there is a growing demand for methods that enable systematic comparison and retrieval of profiles based on gene expression patterns rather than metadata. However, no standardized workflow currently exists for retrieving relevant scRNA-seq profiles using expressionbased similarity. In this paper, we present a novel framework for comparing and retrieving scRNA-seq profiles based on gene expression. Each profile is represented as a dendrogram derived from hierarchical clustering of genes based on their expression patterns across cells. To compare profiles, we introduce a new similarity metric, Multi-Resolution Adjusted Rand Index (MRARI), which extends the traditional Adjusted Rand Index (ARI) by incorporating hierarchical information. Retrieval is performed by computing pairwise MR-ARI scores between profiles. We evaluate the method's performance using a bootstrapped distribution of the Area Under the Receiver Operating Characteristic Curve (AUROC).

• Surko, Arina & Ogul, Hasan (2025). Transfer retrieval: A new paradigm for person-alised medicine through AI-driven genomic database search. doi: 10.5617/nmi.12551. Full text in Research Archive Show summary

  Genetic diseases can differ significantly among patientsdue to the variations in the human genome. Personalisedmedicine aims to facilitate the treatment’s efficacyby tailoring it to each patient based on their uniquegenetic profile. Transfer retrieval is a novel concept forpersonalised medicine, based on assessing the similaritybetween patients’ profiles to enable the content-basedsearch of relevant genomic profiles in large, clinicallyannotated databases. A challenge in developing transferretrieval is the presence of a variety of technologiesand data modalities of gene expression profiles. Thisdiversity complicates the similarity assessment betweenthe profiles. To address this issue, transfer retrieval willenable the similarity assessment by transforming eachraw measurement data into a common and biologicallyinterpretable concept. This approach will increasethe possibilities of transfer retrieval and, also, keep itagile for future discoveries. More advanced sequencingtechnologies are emerging, such as single-cell RNAsequencing (sc-RNAseq), which allows analysing each cellfrom the sample individually. Currently, we are buildingand testing the transfer retrieval models for the sc-RNAseq data. As for today, two transfer retrieval modelsare tested. The first model was built as a baseline, and it isbased on the average expression per gene across all cells ofthe sample, imitating bulk RNAseq data. The second oneis based on the differential expression data for a cancerdataset. The tested distance metrics include Euclideanand MSE distances, Cosine and Jaccard similarities. Theretrieval results are assessed via the Area Under Curve(AUC) metric.

• Surko, Arina & Ogul, Hasan (2025). Transfer Retrieval: A new paradigm for personalised medicine through AI-driven genomic database search. doi: https:/mmiv.no/wp-content/uploads/2025/11/PRESIMAL_Abstract_Book_2025.pdf. Full text in Research Archive
• Surko, Arina & Ogul, Hasan (2025). Retrieving Relevant Single-Cell RNA Sequencing Profiles with Gene Expression Clustering. doi: https:/www.nora.ai/resources/pdf-files/naim_2025_poster_sessions_abstracts.pdf. Full text in Research Archive Show summary

  Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful technology for analyzing cellular heterogeneity and gene expression at high resolution. With the rapid growth of publicly available scRNA-seq databases, there is a growing demand for methods that enable systematic comparison and retrieval of profiles based on gene expression patterns rather than metadata. However, no standardized workflow currently exists for retrieving relevant scRNA-seq profiles using expression-based similarity. In this work, we present a novel framework for comparing and retrieving scRNA-seq profiles based on gene expression. Each profile is represented as a dendrogram derived from hierarchical clustering of genes based on their expression patterns across cells. To compare profiles, we introduce a new similarity metric, Multi-Resolution Adjusted Rand Index (MR-ARI), which extends the traditional Adjusted Rand Index (ARI) by incorporating hierarchical information. Retrieval is performed by computing pairwise MR-ARI scores between profiles. We evaluate the method's performance using a bootstrapped distribution of the Area Under the Receiver Operating Characteristic Curve (AUROC).

• Halnes, Geir; Javaid, Anam; Solvang, Michael; Nichele, Stefano; Riegler, Michael & Singstad, Bjørn-Jostein [Show all 82 contributors for this article] (2025). Proceedings of NORA’s annual conference 2025. Nordic Machine Intelligence (NMI). 5(3), p. 1–14. doi: 10.5617/nmi.12551. Full text in Research Archive
• Gunel, A; Guler, U; Erkan, B; Idrisoglu, H; Mazlum, V & Salih, B [Show all 8 contributors for this article] (2022). Benchmarking proteome of extracellular vesicles from plasma of fALS-associated SOD1 mutant patients and SOD1 mutant healthy controls. Amyotrophic Lateral Sclerosis and Frontotemporal Degeneration. ISSN 2167-8421. 23, p. 102–102. doi: 10.1080/21678421.2022.2120682. Full text in Research Archive

View all works in NVA