Motivation: Biomedical question answering often requires evidence beyond topically retrieved literature, including gene alias resolution, database identifier normalization, and atlas-derived biological measurements. However, existing retrieval-augmented generation (RAG) systems typically follow a fixed workflow and lack an explicit mechanism for deciding when retrieved text is sufficient, when curated biomedical knowledge is required, or when executable evidence assembly over structured measurements should be invoked. This motivates a substrate-aware large language model (LLM) harness that selectively assembles sufficient evidence across literature, knowledge bases, and biological atlases. Results: We introduce BioHarness, an LLM harness for staged biomedical evidence assembly across literature retrieval, curated biomedical knowledge resources, and atlas-derived structured measurements. BioHarness first attempts to answer from reranked literature evidence and escalates through grounded cascade control to REPL-style evidence assembly only when the current evidence is uncertain, weakly grounded, or substrate-mismatched. Across 19,302 biomedical QA items spanning seven answer formats,
Observable performance is commonly used to characterize biological systems. In adaptive systems, however, similar performances may arise from distinct organizations, and configurations that appear comparable at a given time may follow different longitudinal trajectories. This limitation motivates a methodological framework for moving beyond performance-based interpretation without assuming a complete mechanistic model in advance. This article proposes a bootstrap framework for latent-space representation learning in adaptive biological systems. Here, bootstrap is used in a methodological and epistemological sense: new analytical levels are introduced when the preceding representation becomes insufficient to account for observed adaptive dynamics. The framework is organized around five levels: observable performance, dynamic organization, latent organization, longitudinal viability, and internal predictive approximation. The framework is illustrated by three previously reported gait--occlusion studies, used here only as a methodological case sequence and not as new experimental evidence. The article formalizes how performance analysis led to latent organization, how static latent or
Primates exhibit a robust deviation from canonical allometric scaling: at fixed body mass, their lifespans exceed those of non-primate mammals by factors of two to three. A rhesus macaque (8 kg) lives 25-40 years, whereas a cat of similar mass rarely exceeds 18 years. This statistically significant clade-level excess cannot be explained by standard metabolic or ecological models. We provide a thermodynamic explanation within the Principle of Biological Time Equivalence (PBTE), where lifespan is determined by a finite cycle budget governed by entropy production. We show that primates reduce entropy production per physiological cycle through increased neural energy allocation. The neural power fraction acts as a control parameter, extending the effective lifetime cycle count. Three mechanisms, predictive regulation, enhanced repair, and behavioral buffering, jointly suppress dissipation. This yields a quantitative neuro-metabolic multiplier that explains primate longevity and provides testable predictions linking brain energetics, entropy production, and lifespan.
With the growing interest in using AI and machine learning (ML) in medicine, there is an increasing number of literature covering the application and ethics of using AI and ML in areas of medicine such as clinical psychiatry. The problem is that there is little literature covering the economic aspects associated with using ML in clinical psychiatry. This study addresses this gap by specifically studying the economic implications of using ML in clinical psychiatry. In this paper, we evaluate the economic implications of using ML in clinical psychiatry through using three problem-oriented case studies, literature on economics, socioeconomic and medical AI, and two types of health economic evaluations. In addition, we provide details on fairness, legal, ethics and other considerations for ML in clinical psychiatry.
This paper surveys foundation models for AI-enabled biological design, focusing on recent developments in applying large-scale, self-supervised models to tasks such as protein engineering, small molecule design, and genomic sequence design. Though this domain is evolving rapidly, this survey presents and discusses a taxonomy of current models and methods. The focus is on challenges and solutions in adapting these models for biological applications, including biological sequence modeling architectures, controllability in generation, and multi-modal integration. The survey concludes with a discussion of open problems and future directions, offering concrete next-steps to improve the quality of biological sequence generation.
There are innumerable 'biological complexity measure's. While some patterns emerge from these attempts to represent biological complexity, a single measure to encompass the seemingly countless features of biological systems, still eludes the students of Biology. It is the pursuit of this paper to discuss the feasibility of finding one complete and objective measure for biological complexity. A theoretical construct (the 'Thread-Mesh model') is proposed here to describe biological reality. It segments the entire biological space-time in a series of different biological organizations before modeling the property space of each of these organizations with computational and topological constructs. Acknowledging emergence as a key biological property, it has been proved here that the quest for an objective and all-encompassing biological complexity measure would necessarily end up in failure. Since any study of biological complexity is rooted in the knowledge of biological reality, an expression for possible limit of human knowledge about ontological biological reality, in the form of an uncertainty principle, is proposed here. Two theorems are proposed to model the fundamental limitatio
Biological sequences do not come at random. Instead, they appear with particular frequencies that reflect properties of the associated system or phenomenon. Knowing how biological sequences are distributed in sequence space is thus a natural first step toward understanding the underlying mechanisms. Here we propose a new method for inferring the probability distribution from which a sample of biological sequences were drawn for the case where the sequences are composed of elements that admit a natural ordering. Our method is based on Bayesian field theory, a physics-based machine learning approach, and can be regarded as a nonparametric extension of the traditional maximum entropy estimate. As an example, we use it to analyze the aneuploidy data pertaining to gliomas from The Cancer Genome Atlas project. In addition, we demonstrate two follow-up analyses that can be performed with the resulting probability distribution. One of them is to investigate the associations among the sequence sites. This provides us a way to infer the governing biological grammar. The other is to study the global geometry of the probability landscape, which allows us to look at the problem from an evolutio
Studying psychiatric illness has often been limited by difficulties in connecting symptoms and behavior to neurobiology. Computational psychiatry approaches promise to bridge this gap by providing formal accounts of the latent information processing changes that underlie the development and maintenance of psychiatric phenomena. Models based on these theories generate individual-level parameter estimates which can then be tested for relationships to neurobiology. In this review, we explore computational modelling approaches to one key aspect of health and illness: affect. We discuss strengths and limitations of key approaches to modelling affect, with a focus on reinforcement learning, active inference, the hierarchical gaussian filter, and drift-diffusion models. We find that, in this literature, affect is an important source of modulation in decision making, and has a bidirectional influence on how individuals infer both internal and external states. Highlighting the potential role of affect in information processing changes underlying symptom development, we extend an existing model of psychosis, where affective changes are influenced by increasing cortical noise and consequent i
Many biological processes can be thought of as the result of an underlying dynamics in which the system repeatedly undergoes distinct and abortive trajectories with the dynamical process only ending when some specific process, purpose, structure or function is achieved. A classic example is the way in which microtubules attach to kinetochores as a prerequisite for chromosome segregation and cell division. In this example, the dynamics is characterized by apparently futile time histories in which microtubules repeatedly grow and shrink without chromosomal attachment. We hypothesize that for biological processes for which it is not the initial conditions that matter, but rather the final state, this kind of exploratory dynamics is biology's unique and necessary solution to achieving these functions with high fidelity. This kind of cause and effect relationship can be contrasted to examples from physics and chemistry where the initial conditions determine the outcome. In this paper, we examine the similarities of many biological processes that depend upon random trajectories starting from the initial state and the selection of subsets of these trajectories to achieve some desired func
Are biological self-organising systems more ``intelligent'' than artificial intelligence (AI)? If so, why? I address this question using a mathematical framework that defines intelligence in terms of adaptability. Systems are modelled as stacks of abstraction layers (\emph{Stack Theory}) and compared by how effectively they delegate agentic control down their stacks. I illustrate this using computational, biological, military, governmental, and economic systems. Contemporary AI typically relies on static, human-engineered stacks whose lower layers are fixed during deployment. Put provocatively, such systems resemble inflexible bureaucracies that adapt only top-down. Biological systems are more intelligent because they delegate adaptation. Formally, I prove a theorem (\emph{The Law of the Stack}) showing that adaptability at higher layers is bottlenecked by adaptability at lower layers. I further show that, under standard viability assumptions, maximising adaptability is equivalent to minimising variational free energy, implying that delegation is necessary for free-energy minimisation. Generalising bioelectric accounts of cancer as isolation from collective informational structures
Large language models (LLMs) are increasingly proposed as scalable solutions to the global mental health crisis. But their deployment in psychiatric contexts raises a distinctive ethical concern: the problem of atypicality. Because LLMs generate outputs based on population-level statistical regularities, their responses -- while typically appropriate for general users -- may be dangerously inappropriate when interpreted by psychiatric patients, who often exhibit atypical cognitive or interpretive patterns. We argue that standard mitigation strategies, such as prompt engineering or fine-tuning, are insufficient to resolve this structural risk. Instead, we propose dynamic contextual certification (DCC): a staged, reversible and context-sensitive framework for deploying LLMs in psychiatry, inspired by clinical translation and dynamic safety models from artificial intelligence governance. DCC reframes chatbot deployment as an ongoing epistemic and ethical process that prioritises interpretive safety over static performance benchmarks. Atypicality, we argue, cannot be eliminated -- but it can, and must, be proactively managed.
Morphogenesis, the process of growth and shape formation in biological tissues, is driven by complex interactions between mechanical, biochemical, and genetic factors. Traditional models of biological growth often rely on the concept of homeostatic Eshelby stress, which defines an ideal target state for the growing body. Any local deviation from this state triggers growth and remodelling, aimed at restoring balance between mechanical forces and biological adaptation. Despite its relevance in the biomechanical context, the nature of homeostatic stress remains elusive, with its value and spatial distribution often chosen arbitrarily, lacking a clear biological interpretation or understanding of its connection to the lower scales of the tissue. To bring clarity on the nature of homeostatic stress, we shift the focus from Eshelby stress to growth incompatibility, a measure of geometric frustration in the tissue that is the primary source of residual stresses in the developing body. Incompatibility, measured by the Ricci tensor of the growth metric at the continuous level, can be potentially regulated at the cell level through connections with the surrounding cells, making it a more mea
The great behavioral heterogeneity observed between individuals with the same psychiatric disorder and even within one individual over time complicates both clinical practice and biomedical research. However, modern technologies are an exciting opportunity to improve behavioral characterization. Existing psychiatry methods that are qualitative or unscalable, such as patient surveys or clinical interviews, can now be collected at a greater capacity and analyzed to produce new quantitative measures. Furthermore, recent capabilities for continuous collection of passive sensor streams, such as phone GPS or smartwatch accelerometer, open avenues of novel questioning that were previously entirely unrealistic. Their temporally dense nature enables a cohesive study of real-time neural and behavioral signals. To develop comprehensive neurobiological models of psychiatric disease, it will be critical to first develop strong methods for behavioral quantification. There is huge potential in what can theoretically be captured by current technologies, but this in itself presents a large computational challenge -- one that will necessitate new data processing tools, new machine learning technique
Precision psychiatry is an ermerging field that aims to provide individualized approaches to mental health care. Multivariate analysis and machine learning are used to create outcome prediction models based on clinical data such as demographics, symptom assessments, genetic information, and brain imaging. While much emphasis has been placed on technical innovation, the complex and varied nature of mental health presents significant challenges to the successful implementation of these models. From this perspective, I review ten challenges in the field of precision psychiatry, including the need for studies on real-world populations and realistic clinical outcome definitions, consideration of treatment-related factors such as placebo effects and non-adherence to prescriptions. Fairness, prospective validation in comparison to current practice and implementation studies of prediction models are other key issues that are currently understudied. A shift is proposed from retrospective studies based on linear and static concepts of disease towards prospective research that considers the importance of contextual factors and the dynamic and complex nature of mental health.
The stochastic exploration of the configuration space and the exploitation of functional states underlie many biological processes. The evolutionary dynamics stands out as a remarkable example. Here, we introduce a novel formalism that mimics evolution and encodes a general exploration-exploitation dynamics for biological networks. We apply it to the brain wiring problem, focusing on the maturation of that of the nematode C. elegans. We demonstrate that a parsimonious maxent description of the adult brain combined with our framework is able to track down the entire developmental trajectory.
As the emerging field of predictive analytics in psychiatry generated and continues to generate massive interest overtime with its major promises to positively change and revolutionize clinical psychiatry, health care and medical professionals are greatly looking forward to its integration and application into psychiatry. However, by directly applying predictive analytics to the practice of psychiatry, this could cause detrimental damage to those that use predictive analytics through creating or worsening existing medical issues. In both cases, medical ethics issues arise, and need to be addressed. This paper will use literature to provide descriptions of selected stages in the treatment of mental disorders and phases in a predictive analytics project, approach mental disorder diagnoses using predictive models that rely on neural networks, analyze the complexities in clinical psychiatry, neural networks and predictive analytics, and conclude with emphasizing and elaborating on limitations and medical ethics issues of applying neural networks and predictive analytics to clinical psychiatry.
Computational psychiatry is a field aimed at developing formal models of information processing in the human brain, and how alterations in this processing can lead to clinical phenomena. Despite significant progress in the development of tasks and how to model them, computational psychiatry methodologies have yet to be incorporated into large-scale research projects or into clinical practice. In this viewpoint, we explore some of the barriers to incorporation of computational psychiatry tasks and models into wider mainstream research directions. These barriers include the time required for participants to complete tasks, test-retest reliability, limited ecological validity, as well as practical concerns, such as lack of computational expertise and the expense and large sample sizes traditionally required to validate tasks and models. We then discuss solutions, such as the redesigning of tasks with a view toward feasibility, and the integration of tasks into more ecologically valid and standardized game platforms that can be more easily disseminated. Finally, we provide an example of how one task, the conditioned hallucinations task, might be translated into such a game. It is our h
In light of the NIMH's Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of the ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. Additionally, we review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We further discuss explainable AI (XAI) and causality testing in a closed-human-in-the-loop manner, and highlight the ML potential in multimedia information extraction and multimodal data fusion. Finally, we disc
Monocular depth estimation (MDE) aims to transform an RGB image of a scene into a pixelwise depth map from the same camera view. It is fundamentally ill-posed due to missing information: any single image can have been taken from many possible 3D scenes. Part of the MDE task is, therefore, to learn which visual cues in the image can be used for depth estimation, and how. With training data limited by cost of annotation or network capacity limited by computational power, this is challenging. In this work we demonstrate that explicitly injecting visual cue information into the model is beneficial for depth estimation. Following research into biological vision systems, we focus on semantic information and prior knowledge of object sizes and their relations, to emulate the biological cues of relative size, familiar size, and absolute size. We use state-of-the-art semantic and instance segmentation models to provide external information, and exploit language embeddings to encode relational information between classes. We also provide a prior on the average real-world size of objects. This external information overcomes the limitation in data availability, and ensures that the limited cap
We review the trade-offs between speed, fluctuations, and thermodynamic cost involved with biological processes in nonequilibrium states, and discuss how optimal these processes are in light of the universal bound set by the thermodynamic uncertainty relation (TUR). The values of the uncertainty product $\mathcal{Q}$ of TUR, which can be used as a measure of the precision of enzymatic processes realized for a given thermodynamic cost, are suboptimal when the substrate concentration $[S]$ is at the Michaelis constant ($K_\text{M}$), and some of the key biological processes are found to work around this condition. We illustrate the utility of $\mathcal{Q}$ in assessing how close the molecular motors and biomass producing machineries are to the TUR bound, and for the cases of biomass production (or biological copying processes) we discuss how their optimality quantified in terms of $\mathcal{Q}$ is balanced with the error rate in the information transfer process. We also touch upon the trade-offs in other error-minimizing processes in biology, such as gene regulation and chaperone-assisted protein folding. A spectrum of $\mathcal{Q}$ recapitulating the biological processes surveyed he