Systems Biology through complex networks, signal processing, image analysis, and artificial intelligence

Earth system models (ESMs) are our key tools for analyzing the planet's existing state and predicting its evolution in the next continuing human-caused events. However, the use of artificial intelligence (AI) approaches to augment or even replace conventional ESM functions has expanded in recent years, raising hopes that AI will be able to overcome some of the major difficulties in climate research. We address the advantages and disadvantages of neural ESM neurons, as well as the unsolved question of whether AI will eventually replace ESMs. Dynamic geophysical events are the foundation of Earth and environmental studies. Given the widespread acceptance of AI and the growing amount of Earth data, the geoscientific community may wish to seriously explore using artificial intelligence (AI) approaches at a much deeper level. Although it is a tall ambition to integrate hybrid physics and AI approaches from a fresh perspective, geology has yet to figure out how to make such methods feasible. This research is an important step towards realising the concept of combining physics and artificial intelligence to address problems with the Earth's system.

Artificial Intelligence (AI) and Machine Learning (ML) are becoming common in our daily lives. The AI-driven processes significantly affect us as individuals and as a society, spanning across ethical dimensions like discrimination, misinformation, and fraud. Several of these AI & ML approaches rely on Knowledge Graph (KG) data. Due to the large volume and complexity of today's KG-driven approaches, enormous resources are spent to utilize the complex AI approaches. Efficient usage of the resources like hardware and power consumption is essential for sustainable KG-based ML technologies. This paper introduces the ethical and sustainability considerations, challenges, and optimizations in the context of KG-based ML. We have grouped the ethical and sustainability aspects according to the typical Research & Development (R&D) lifecycle: an initial investigation of the AI approach's responsibility dimensions; technical system setup; central KG data analytics and curating; model selection, training, and evaluation; and final technology deployment. We also describe significant trade-offs and alternative options for dedicated scenarios enriched through existing and reported ethical and sustainability issues in AI-driven approaches and research. These include, e.g., efficient hardware usage guidelines; or the trade-off between transparency and accessibility compared to the risk of manipulability and privacy-related data disclosure. In addition, we propose how biased data and barely explainable AI can result in discriminating ML predictions. This work supports researchers and developers in reflecting, evaluating, and optimizing dedicated KG-based ML approaches in the dimensions of ethics and sustainability.

The primary objective of this study is to investigate various applications of artificial intelligence (AI) and statistical methodologies for analyzing and managing peritoneal metastases (PM) caused by gastrointestinal cancers. Relevant keywords and search criteria were comprehensively researched on PubMed and Google Scholar to identify articles and reviews related to the topic. The AI approaches considered were conventional machine learning (ML) and deep learning (DL) models, and the relevant statistical approaches included biostatistics and logistic models. The systematic literature review yielded nearly 30 articles meeting the predefined criteria. Analyses of these studies showed that AI methodologies consistently outperformed traditional statistical approaches. In the AI approaches, DL consistently produced the most precise results, while classical ML demonstrated varied performance but maintained high predictive accuracy. The sample size was the recurring factor that increased the accuracy of the predictions for models of the same type. AI and statistical approaches can detect PM developing among patients with gastrointestinal cancers. Therefore, if clinicians integrated these approaches into diagnostics and prognostics, they could better analyze and manage PM, enhancing clinical decision-making and patients' outcomes. Collaboration across multiple institutions would also help in standardizing methods for data collection and allowing consistent results.

Praise for Computational Systems BiologyApproaches in Cancer Research: "Complex concepts are written clearly and with informative illustrations and useful links. The book is enjoyable to read yet provides sufficient depth to serve as a valuable resource for both students and faculty." — Trey Ideker, Professor of Medicine, UC Xan Diego, School of Medicine "This volume is attractive because it addresses important and timely topics for research and teaching on computational methods in cancer research. It covers a broad variety of approaches, exposes recent innovations in computational methods, and provides acces to source code and to dedicated interactive web sites." — Yves Moreau, Department of Electrical Engineering, SysBioSys Centre for Computational Systems Biology, University of Leuven With the availability of massive amounts of data in biology, the need for advanced computational tools and techniques is becoming increasingly important and key in understanding biology in disease and healthy states. This book focuses on computational systems biology approaches, with a particular lens on tackling one of the most challenging diseases - cancer. The book provides an important reference and teaching material in the field of computational biology in general and cancer systems biology in particular. The book presents a list of modern approaches in systems biology with application to cancer research and beyond. It is structured in a didactic form such that the idea of each approach can easily be grasped from the short text and self-explanatory figures. The coverage of topics is diverse: from pathway resources, through methods for data analysis and single data analysis to drug response predictors, classifiers and image analysis using machine learning and artificial intelligence approaches. Features Up to date using a wide range of approaches Applicationexample in each chapter Online resources with useful applications'

Editorial overview: Systems biology for biotechnology

This comprehensive guide offers a new approach for developing and implementing robust computational methodologies that uncover the key geometric and topological information from signals and images. With the help of detailed real-world examples and applications, readers will learn how to solve complex signal and image processing problems in fields ranging from remote sensing to medical imaging, bioinformatics, robotics, security, and defence. With an emphasis on intuitive and application-driven arguments, this text covers not only a range of methods in use today, but also introduces promising new developments for the future, bringing the reader up-to-date with the state of the art in signal and image analysis. Covering basic principles as well as advanced concepts and applications, and with examples and homework exercises, this is an invaluable resource for graduate students, researchers, and industry practitioners in a range of fields including signal and image processing, biomedical engineering, and computer graphics.

Advanced bioinformatics analysis, such as systems biology (SysBio) and artificial intelligence (AI) approaches, including machine learning (ML) and deep learning (DL), is increasingly present in stem cell (SC) research. An approximate timeline on these developments and their global impact is still lacking. We conducted a scoping review on the contribution of SysBio and AI analysis to SC research and therapy development based on literature published in PubMed between 2000 and 2024. We identified an 8 to 10-fold increase in research output related to all 3 search terms between 2000 and 2021, with a 10-fold increase in AI-related production since 2010. Use of SysBio and AI still predominates in preclinical basic research with increasing use in clinically oriented translational medicine since 2010. SysBio- and AI-related research was found all over the globe, with SysBio output led by the (US, n = 1487), (UK, n = 1094), Germany (n = 355), The Netherlands (n = 339), Russia (n = 215), and France (n = 149), while for AI-related research the US (n = 853) and UK (n = 258) take a strong lead, followed by Switzerland (n = 69), The Netherlands (n = 37), and Germany (n = 19). The US and UK are most active in SCs publications related to AI/ML and AI/DL. The prominent use of SysBio in ESC research was recently overtaken by prominent use of AI in iPSC and MSC research. This study reveals the global evolution and growing intersection among AI, SysBio, and SC research over the past 2 decades, with substantial growth in all 3 fields and exponential increases in AI-related research in the past decade.

Many of the reports created at assembly lines, where all components of an aircraft are installed, frequently indicate that errors threaten safety. The proposed methodology in this study evaluates error prediction and risk mitigation to prevent failures and their consequences. The results linked to a typical electrical harness manufacture of a military aircraft estimated reductions of 93% in time and 90% in error during the creation of engineering manufacturing processes using AI techniques. However, traditional risk assessments methods struggle to identify and mitigate errors effectively. Thus, developing an advanced methodology to ensure systems safety is needed. This paper addresses how innovative AI technology solutions can overcome these challenges, mitigate error risks, and enhance safety in aerospace. Technologies, such as artificial intelligence, predictive algorithms, machine learning, and automation, can play a key role in enhancing safety. The aim of this study is to develop a model that considers the factors that can potentially contribute to error creation, through an artificial intelligence (AI) approach. The specific AI techniques used such as support vector machine, random forest, logistic regression, K-nearest neighbor, and XGBoost (Python 3.8.5) show good performance for use in error mitigation. We have compared the modeled values obtained in this study with the experimental ones. The results confirm that the best metrics are obtained by using support vector machine and logistic regression. The smallest deviation between the measured and modeled values for these AI methods do not exceed 5%. Furthermore, using advancements in machine learning methods can enhance error mitigation in aerospace. The use of AutoML can play a key role in automatically finding an appropriate model which provides the best performance metrics and therefore the most reliable forecast for data prediction and error mitigation.

Urban land use change is a complex and dynamic process. It is therefore important to understand the complexity involved with system dynamics and choose appropriate modelling approaches. For this purpose, this paper firstly reviews how artificial intelligence (AI) approaches provide solutions to aid urban land dynamics modelling. The three dimensions that are considered pivotal for the understanding of urban dynamic processes – urban land dynamics, planning support and AI infrastructure – are defined. Once these three dimensions are clarified, it is possible to propose the different solution spaces provided by AI approaches using a graphic representation of a cube and its associated mathematical formulation. It is therefore possible to understand and define the best data model to represent the complexity of different phenomena in urban systems.

This study introduces an improved artificial intelligence (AI) approach called intelligence optimized support vector regression (IO-SVR) for estimating the compressive strength of high-performance concrete (HPC). The nonlinear functional mapping between the HPC materials and compressive strength is conducted using the AI approach. A dataset with 1,030 HPC experimental tests is used to train and validate the prediction model. Depending on the results of the experiments, the forecast outcomes of the IO-SVR model are of a much higher quality compared to the outcomes of other AI approaches. Additionally, because of the high-quality learning capabilities, the IO-SVR is highly recommended for calculating HPC strength.

There is an old saying (at least in English) that what you don't know can't hurt you. In science it is the reverse. So how much are we thinking about the deep unknowns in the life sciences, compared with gathering data? The European Commission set the tone for research with its launch of the “Information Society,” and proclamation (made in 2000 and known as the “Lisbon Agenda”) to make Europe the world-leading knowledge-based economy by 2010. With the rapid technological advances in molecular biology (particularly genome sequencing), some of this knowledge was practically in the bag, so it seemed. It was a “known” entity with predictable growth prospects. Thinking about what we already know, and know how to do, enables us to build on knowledge in an evolutionary, incremental, sense. Thinking about what we don't know, and don't know how to do, on the other hand, raises the truly fascinating questions in biology that are likely to culminate in revolutions in understanding. But at a more practical level, carefully thinking about what we don't know can help us make the right decision as to which data to gather, how to interpret them, and which other advances we need to support this endeavor. It is not necessarily easy to get the concept across these days, because large sectors of the life sciences are concerned with massive data collecting and interpretation projects. It might very well have been more implicitly understood 50 years ago, for instance, when we had but a fraction of the biological data to ponder that we do today. How to sequence (this has been known, in principle, for a very long time) How to decode the sequence (this has also been known for a very long time) But the ambitious aim of understanding the data needed to be matched by ambitious thinking about the unknowns. What we did not know was how to embed the knowledge of the sequence into the model of gene interactions as complex networks with phenotypic outputs that tend to be unpredictable. However, network biology as a discipline had been around for quite some time already. Now we tend to call it systems biology, and systems biology has been a defined discipline for probably more than 40 years: Mihajlo Mesarovic defined it as a research field in 1966 with an international symposium “Systems Theory and Biology” (though Ludwig von Bertalanffy's book “General Systems Theory in Physics and Biology” was published in 1950). Concerted funding for systems biology only really started in the late 1990s. If discovery of information advances faster than the rate at which we are developing the means to understand that information, it is inevitable that we will start misunderstanding it, and – even worse – misapplying it. A hackneyed example is the concept that the human genome sequence would give us the “genes for X, Y, Z”. Unfortunately, this worked against a positive trend in perception that individual genes were not determinants of phenotype.

Otitis media (OM) is a common inflammatory condition, particularly in children, and poses significant diagnostic and treatment challenges. It also significantly affects adults, especially those with atopic conditions. OM can lead to complications such as hearing loss and speech delays. The advent of electronic health records, big data, and artificial intelligence (AI) offers transformative opportunities in OM diagnosis. AI plays a crucial role in enabling early detection and enhancing diagnostic precision through advanced image analysis and predictive modeling. This review paper explores modern techniques used for the diagnosis of OM, with an emphasis on both traditional and machine learning approaches. A wide range of studies has been evaluated, demonstrating the application of AI in improving diagnostic accuracy and treatment planning. Notably, AI approaches—particularly deep neural networks—have shown remarkable success in otoscopy image analysis. Additionally, recently developed hybrid models that combine multiple techniques have outperformed individual approaches. Despite these advancements, challenges remain, including limited dataset standardization and issues with image quality.

The new trend toward modern earthquake-resistant design of buildings based on nonlinear dynamic analysis accounting for peak and energy demands requires efficient ground motion record selection procedures. For this reason, in the present work, two record selection strategies based on acceleration and input energy spectrum considering the spectral shape via Np are presented. Furthermore, both record selection strategies are optimized by means of four artificial intelligence (AI) techniques: Genetic Algorithms (GA), Harmony Search (HS), Particle Swarm Optimization (PSO) and Vibrating Particle System (VPS). In particular, the effectiveness of each AI approach toward the best set of ground motion records for nonlinear dynamic analysis is compared. For this aim, spectral acceleration and input energy design spectra were considered, as well as 1024 seismic records obtained from the Pacific Earthquake Engineering Research Center. For all the AI or meta-heuristic approaches, the fitness function used is focused on minimizing the difference between the average spectrum of eleven ground motion records and the design spectrum using the well-known parameter Np, which represents the spectral shape in a range of periods. In addition, a penalization is included for those spectra with very large or low demands. Thus, 24 sets of eleven seismic records that can be used for nonlinear dynamic analysis of structures with a fundamental period of vibration of 0.6, 1.2 and 1.8 seconds were obtained and purposes. The results demonstrate the ability of the two records selection strategies analyzed and the four meta-heuristic procedures, achieving results quickly and simply regardless of the type of demands, intensities and periods considered. Finally, it is concluded that the VPS algorithm is better in comparison with GA, HS, and PSO since it obtains superior results in almost all the selected cases.

Physiology: alone at the bottom, alone at the top

The gut microbiome plays a fundamental role in host metabolism, immune regulation, and disease development. With the rapid accumulation of multi-omics and literature data, the microbiome field now faces the challenge of efficiently extracting scientific insights from massive, heterogeneous datasets. Artificial intelligence (AI) and large language models (LLMs) provide promising tools to address this complexity by enabling integrative analysis and knowledge synthesis across diverse biological sources. In this study, we developed METABOLISM, a microbiome-specialized LLM fine-tuned on 160,000 scientific abstracts to enhance literature-based contextual understanding of microbiome-liver interactions and related biological mechanisms. Using LoRA-based parameter-efficient training, METABOLISM was optimized for domain-specific reasoning and response generation. Model performance was evaluated through both automated Phi-4 scoring (a large language model-based evaluator for relevance, informativeness, and fluency) and structured human expert rubric assessments involving 20 domain specialists. The fine-tuned METABOLISM achieved superior relevance and clarity scores (mean > 7.5 ± 0.06) compared with general-purpose LLMs such as Gemma-3-12B-IT and ChatGPT-4o. Correlation analysis revealed weak to moderate negative relationships (R = -0.65, p < 0.0001) between traditional NLP metrics (BLEU, ROUGE) and human expert rubric scores, with a similar trend observed for correlations with Phi-4-based automated evaluation scores, indicating the limitations of surface-level similarity measures in biomedical contexts. Overall, our findings demonstrate that microbiome-adapted LLMs can effectively distill high-volume scientific data into biologically meaningful insights, supporting more efficient and interpretable research in microbiology and systems biology.