De novo genome assembly is a relevant but computationally complex task in genomics. Although de novo assemblers have been used successfully in several genomics projects, there is still no 'best assembler', and the choice and setup of assemblers still rely on bioinformatics experts. Thus, as with other computationally complex problems, machine learning may emerge as an alternative (or complementary) way for developing more accurate and automated assemblers. Reinforcement learning has proven promising for solving complex activities without supervision - such games - and there is a pressing need to understand the limits of this approach to 'real' problems, such as the DFA problem. This study aimed to shed light on the application of machine learning, using reinforcement learning (RL), in genome assembly. We expanded upon the sole previous approach found in the literature to solve this problem by carefully exploring the learning aspects of the proposed intelligent agent, which uses the Q-learning algorithm, and we provided insights for the next steps of automated genome assembly development. We improved the reward system and optimized the exploration of the state space based on pruning and in collaboration with evolutionary computing. We tested the new approaches on 23 new larger environments, which are all available on the internet. Our results suggest consistent performance progress; however, we also found limitations, especially concerning the high dimensionality of state and action spaces. Finally, we discuss paths for achieving efficient and automated genome assembly in real scenarios considering successful RL applications - including deep reinforcement learning.

Tsallis' non-extensive entropy is extended to incorporate the dependence on affinities between the microstates of a system. At the core of our construction of the extended entropy ($\mathcal{H}$) is the concept of the effective number of dissimilar states, termed the effective diversity ($\mathitΔ$). It is a unique integrated measure derived from the probability distribution among states and the affinities between states. The effective diversity is related to the extended entropy through the Boltzmann's-equation-like relation, $\mathcal{H}=\ln_{q}\mathitΔ$, in terms of the Tsallis' $q$-logarithm. A new principle called the Nesting Principle is established, stating that the effective diversity remains invariant under an arbitrary grouping of the constituent states. It is shown that this invariance property holds only for $q=2$; however, the invariance is recovered for general $q$ in the zero-affinity limit (i.e. the Tsallis and Boltzmann-Gibbs case). Using the affinity-based extended Tsallis entropy, the microcanonical and the canonical ensembles are constructed in the presence of general between-state affinities. It is shown that the classic postulate of equal a priori probabilities no longer holds but is modified by affinity-dependent terms. As an illustration, a two-level system is investigated by the extended canonical method, which manifests that the thermal behaviours of the thermodynamic quantities at equilibrium are affected by the between-state affinity. Furthermore, some applications and implications of the affinity-based extended diversity/entropy for information theory and biodiversity theory are addressed in appendices.

Artificial Intelligence (AI) has become commonplace to solve routine everyday tasks. Because of the exponential growth in medical imaging data volume and complexity, the workload on radiologists is steadily increasing. We project that the gap between the number of imaging exams and the number of expert radiologist readers required to cover this increase will continue to expand, consequently introducing a demand for AI-based tools that improve the efficiency with which radiologists can comfortably interpret these exams. AI has been shown to improve efficiency in medical-image generation, processing, and interpretation, and a variety of such AI models have been developed across research labs worldwide. However, very few of these, if any, find their way into routine clinical use, a discrepancy that reflects the divide between AI research and successful AI translation. To address the barrier to clinical deployment, we have formed MONAI Consortium, an open-source community which is building standards for AI deployment in healthcare institutions, and developing tools and infrastructure to facilitate their implementation. This report represents several years of weekly discussions and hands-on problem solving experience by groups of industry experts and clinicians in the MONAI Consortium. We identify barriers between AI-model development in research labs and subsequent clinical deployment and propose solutions. Our report provides guidance on processes which take an imaging AI model from development to clinical implementation in a healthcare institution. We discuss various AI integration points in a clinical Radiology workflow. We also present a taxonomy of Radiology AI use-cases. Through this report, we intend to educate the stakeholders in healthcare and AI (AI researchers, radiologists, imaging informaticists, and regulators) about cross-disciplinary challenges and possible solutions.

This paper shows how C-numerical-range related new strucures may arise from practical problems in quantum control--and vice versa, how an understanding of these structures helps to tackle hot topics in quantum information. We start out with an overview on the role of C-numerical ranges in current research problems in quantum theory: the quantum mechanical task of maximising the projection of a point on the unitary orbit of an initial state onto a target state C relates to the C-numerical radius of A via maximising the trace function |\tr \{C^\dagger UAU^\dagger\}|. In quantum control of n qubits one may be interested (i) in having U\in SU(2^n) for the entire dynamics, or (ii) in restricting the dynamics to {\em local} operations on each qubit, i.e. to the n-fold tensor product SU(2)\otimes SU(2)\otimes >...\otimes SU(2). Interestingly, the latter then leads to a novel entity, the {\em local} C-numerical range W_{\rm loc}(C,A), whose intricate geometry is neither star-shaped nor simply connected in contrast to the conventional C-numerical range. This is shown in the accompanying paper (math-ph/0702005). We present novel applications of the C-numerical range in quantum control assisted by gradient flows on the local unitary group: (1) they serve as powerful tools for deciding whether a quantum interaction can be inverted in time (in a sense generalising Hahn's famous spin echo); (2) they allow for optimising witnesses of quantum entanglement. We conclude by relating the relative C-numerical range to problems of constrained quantum optimisation, for which we also give Lagrange-type gradient flow algorithms.

Carbon quantum dots have become attractive in various applications, such as drug delivery, biological sensing, photocatalysis, and solar cells. Among these, pH sensing via luminescence lifetime measurements of surface-functionalised carbon dots is one application currently investigated for their long lifetime and autonomous operation. In this manuscript, we explore the theoretical connection between excitation lifetimes and the pH value of the surrounding liquid via the protonation and deprotonation of functional groups. Example calculations applied to m-phenylenediamine, phloroglucinol and tethered disperse blue 1 are shown by applying a separation approach treating the electronic wavefunction of functional groups separately from the internal electronic structure of the (large) carbon dot. The bulk of the carbon dot is treated as an environment characterised by its optical spectrum that shifts the transition rates of the functional group. A simple relationship between pH, pKa and mixed fluorescence lifetime is derived from transition rates of the protonated and deprotonated states. pH sensitivity improves when the difference in transition rates is greatest between protonated and deprotonated species, with the greatest sensitivity found where the pKa is close to the pH region of interest. The introduced model can directly be extended to consider multicomponent liquids and multiple protonation states.

The pH dependence of emission from graphene oxide is believed to be due to the protonation of surface functional groups. In this study we use transient absorption spectroscopy to study the sub-picosecond charge dynamics in graphene oxide over a range of pH values, observing dynamics consistent with an excited state protonation step for pH < 9.3. The timescale of this process is ~ 1.5 ps, and a corresponding change in recombination dynamics follows. A broad photo-induced absorption peak centred at 530 nm associated with excited state protonation is also observed.

Gene regulatory relationships can be abstracted as a gene regulatory network (GRN), which plays a key role in characterizing complex cellular processes and pathways. Recently, graph neural networks (GNNs), as a class of deep learning models, have emerged as a useful tool to infer gene regulatory relationships from gene expression data. However, deep learning models have been found to be vulnerable to noise, which greatly hinders the adoption of deep learning in constructing GRNs, because high noise is often unavoidable in the process of gene expression measurement. Can we preferably prototype a robust GNN for constructing GRNs? In this paper, we give a positive answer by proposing a Quadratic Graph Attention Network (Q-GAT) with a dual attention mechanism. We study the changes in the predictive accuracy of Q-GAT and 9 state-of-the-art baselines by introducing different levels of adversarial perturbations. Experiments in the E. coli and S. cerevisiae datasets suggest that Q-GAT outperforms the state-of-the-art models in robustness. Lastly, we dissect why Q-GAT is robust through the signal-to-noise ratio (SNR) and interpretability analyses. The former informs that nonlinear aggregation of quadratic neurons can amplify useful signals and suppress unwanted noise, thereby facilitating robustness, while the latter reveals that Q-GAT can leverage more features in prediction thanks to the dual attention mechanism, which endows Q-GAT with the ability to confront adversarial perturbation. We have shared our code in https://github.com/Minorway/Q-GAT_for_Robust_Construction_of_GRN for readers' evaluation.

Model-free learning for multi-agent stochastic games is an active area of research. Existing reinforcement learning algorithms, however, are often restricted to zero-sum games, and are applicable only in small state-action spaces or other simplified settings. Here, we develop a new data efficient Deep-Q-learning methodology for model-free learning of Nash equilibria for general-sum stochastic games. The algorithm uses a local linear-quadratic expansion of the stochastic game, which leads to analytically solvable optimal actions. The expansion is parametrized by deep neural networks to give it sufficient flexibility to learn the environment without the need to experience all state-action pairs. We study symmetry properties of the algorithm stemming from label-invariant stochastic games and as a proof of concept, apply our algorithm to learning optimal trading strategies in competitive electronic markets.

Recently, we demonstrated the existence of nonextensivity in neuromuscular transmission [Phys. Rev. E 84, 041925 (2011)]. In the present letter, we propose a general criterion based on the q-calculus foundations and nonextensive statistics to estimate the values for both scale factor and q-index using the maximum likelihood q-estimation method (MLqE). We next applied our theoretical findings to electrophysiological recordings from neuromuscular junction (NMJ) where spontaneous miniature end plate potentials (MEPP) were analyzed. These calculations were performed in both normal and high extracellular potassium concentration, [K+]o. This protocol was assumed to test the validity of the q-index in electrophysiological conditions closely resembling physiological stimuli. Surprisingly, the analysis showed a significant difference between the q-index in high and normal [K+]o, where the magnitude of nonextensivity was increased. Our letter provides a general way to obtain the best q-index from the q-Gaussian distribution function. It also expands the validity of Tsallis statistics in a more realistic stimulus condition. Physical and physiological implications of these findings are discussed in detail.

Quantifying the neural signatures of consciousness remains a major challenge in neuroscience and AI. Although many theories link consciousness to rich, multiscale, and flexible neural organisation, robust quantitative measures are still lacking. This paper presents a theory-neutral framework that characterises consciousness-related dynamics through three properties: hierarchical integration (H), cross-frequency complexity (D), and metastability (M). Candidate subsystems are identified using predictive information, temporal complexity, and state-space exploration to distinguish structured from unstructured activity. We provide mathematical definitions for all components and implement the framework in a generative model of synthetic EEG, simulating nine brain states ranging from psychedelic and wakeful to dreaming, non-REM sleep, minimally conscious, anaesthetised, and seizure-like regimes. Across single trials and Monte Carlo ensembles, the composite index reliably separates high-consciousness from impaired or non-conscious states. We further validate the framework using real EEG from the Sleep-EDF dataset alongside matched synthetic EEG designed to reproduce state-dependent oscillatory structure. Across Wake, N2, and REM sleep, synthetic data recapitulate the empirical ordering and magnitude of the index, indicating that the index captures stable and biologically meaningful distinctions. This approach provides a principled and empirically grounded tool for quantifying consciousness-related neural organisation with potential applications to both biological and artificial systems.