Nature Machine Intelligence自然·机器智能
Nature Machine Intelligence(英文缩写 NAT MACH INTELL),ISSN 2522-5839,eISSN 2522-5839,中文译名:自然·机器智能 是一本学术期刊。本页汇总该期刊的最新影响因子、分区信息以及最新收录于 PubMed 的文献,帮助您快速了解期刊全貌。
发文量统计区间：2025-09-27 至 2026-09-27，按本站收录文献的发表日期统计。
期刊介绍
Nature Machine Intelligence 最新收录文献
-
1. Empowering biomedical evidence exploration and synthesis with deep knowledge graph research.
PMID:日期:2026-07-01Compared with generic artificial intelligence agents, deep research agents perform longer-horizon reasoning and deeper literature exploration to investigate complex questions. Here we present DeepEvidence, a deep research agent for evidence exploration and synthesis across heterogeneous biomedical knowledge sources. DeepEvidence advances deep research through coordinated multi-agent collaboration combining breadth-first and depth-first research strategies to search, explore and aggregate evidence from multiple biomedical knowledge bases and literature. It also incrementally constructs an evidence graph of key entities and observations to support transparent tracking, attribution and validation of the research process. DeepEvidence substantially outperforms generic artificial intelligence agents across four open benchmarks. We further establish seven benchmark tasks spanning major stages of biomedical discovery, including drug discovery, preclinical experimentation, clinical trial development and evidence-based medicine. DeepEvidence demonstrates substantial improvements in systematic evidence exploration and synthesis. These results highlight the potential of deep research agents to accelerate biomedical discovery and translational research.
-
3. LLMs displaying less cognitive bias are not necessarily better decision makers.
PMID:日期:2026-03-17该文献暂无摘要。
-
4. Large language models as uncertainty-calibrated optimizers for experimental discovery.
PMID:日期:2026-01-01From reaction optimization to molecular design, experimental discovery poses the same expensive question: which candidate to test next under time and resource constraints. Bayesian optimization provides principled answers but depends on domain expertise that rarely transfers. Large language models (LLMs) contain rich scientific knowledge but lack the calibrated uncertainty estimates crucial for high-stakes decisions. Here we show how training language models through Bayesian objectives enables their use as reliable optimizers guided by natural language. Our approach, GOLLuM (Gaussian process Optimized LLMs), teaches LLMs from experimental outcomes under uncertainty, transforming their overconfidence from a fundamental flaw into a precise learning signal. This signal reshapes the LLM embeddings so that experiments with similar outcomes cluster together, revealing structure in the design space. Starting from only ten low-performing experiments, GOLLuM generalizes across 23 tasks in organic synthesis, materials science, process chemistry and molecular design, ranking first on average among all competing methods. It matches traditional Bayesian optimization with over 40% fewer experiments and nearly doubles the discovery of high-performing Buchwald-Hartwig reactions over expert quantum-chemical descriptors and state-of-the-art LLMs (43% versus 24-25%). More broadly, GOLLuM points to a different paradigm for specializing foundation models: not through more data but through richer, uncertainty-guided information.
-
5. Inferring spatial single-cell-level interactions through interpreting cell state and niche correlations learned by self-supervised graph transformer.
PMID:日期:2026-01-01Cell-cell interactions (CCI), driven by distance-dependent signaling, are important for tissue development and organ function. While imaging-based spatial transcriptomics (ST) offers unprecedented opportunities to unravel CCI at single-cell resolution, current analyses face challenges such as limited ligand-receptor pairs measured, insufficient spatial encoding, and low interpretability. We present GITIII, a lightweight, interpretable, self-supervised graph transformer-based model that conceptualizes cells as words and their surrounding cellular neighborhood as context that shapes the meaning or state of the central cell. GITIII infers CCI by examining the correlation between a cell's state and its niche, enabling us to understand how sender cells influence the gene expression of receiver cells, visualize spatial CCI patterns, perform CCI-informed cell clustering, and construct CCI networks. Applied to four ST datasets across multiple species, organs, and platforms, GITIII effectively identified and statistically interpreted CCI patterns in the brain and tumor microenvironments.
-
6. A dexterous soft hand exoskeleton restores intentional grasping in individuals with severe hand impairment.
6. 灵巧柔软的手外骨骼可以恢复严重手部损伤患者的有意抓握PMID:日期:2026-01-01Soft hand exoskeletons have emerged as promising assistive devices for individuals with impaired hand function. However, most existing systems provide limited dexterity and primarily target users with moderate hand ability, leaving individuals with severe hand paralysis without effective solutions for reliable grasping of diverse objects. Here we report the translational development of a lightweight, textile-based soft robotic exoskeleton glove with wrist dorsiflexion and an active opposable and abductable thumb, designed to restore hand function in a patient with severe right-hand impairment due to amyotrophic lateral sclerosis. We followed a co-creation approach, enhancing dexterity by increasing hand articulations based on patient needs. Furthermore, to enhance the patient's sense of control, a non-invasive surface electromyography-based grasp predictor (97% sensitivity) was combined with motion data and machine learning-based error correction to compensate for weak, noisy muscle signals, compared with healthy controls ( = 15). The exoskeleton enabled the patient to grasp objects, achieve a Box-and-Blocks Test score of 5 and perform meaningful tasks, including feeding himself. We further validated the exoskeleton in patients with stroke ( = 6). While exoskeleton assistance on average reduced Action Research Arm Test scores of moderately impaired patients by 9, severely impaired patients scored 17 points higher when using the exoskeleton. These results indicate that the dexterous soft hand exoskeleton is particularly effective for individuals with severe to near-complete hand paralysis, while its utility for patients with moderate residual function is limited and task dependent.
-
7. Neural sampling from cognitive maps enables goal-directed imagination and planning.
PMID:日期:2026-01-01Artificial intelligence systems are becoming more intelligent, but at a very high cost in terms of energy consumption and training requirements. By contrast, our brains only require 20 W of energy, they learn online and they can instantly adjust to changing contingencies. This begs the question what data structures, algorithms and learning methods enable brains to achieve that, and whether these can be ported into artificial devices. We are addressing this question for a core feature of intelligence: the capacity to plan and solve problems, including new problems that involve states that were never encountered before. Here we examine three tools that brains are likely to use for achieving that: cognitive maps, stochastic computing and compositional coding. We integrate these tools into a transparent neural network model, and demonstrate its power for flexible planning and problem-solving. Importantly, this approach is suitable for implementation by in-memory computing and other energy-efficient neuromorphic hardware. In particular, it only requires self-supervised local synaptic plasticity that is suited for on-chip learning. Hence, a core feature of brain intelligence-the capacity to generate solutions to problems that were never encountered before-does not require deep neural networks or large language models, and can be implemented in energy-efficient edge devices.
-
8. Algorithm-hardware co-design of neuromorphic networks with dual memory pathways.
PMID:日期:2026-01-01Spiking neural networks excel at event-driven sensing. Yet, maintaining task-relevant context over long timescales both algorithmically and in hardware, while respecting both tight energy and memory budgets, remains a core challenge in the field. Here we address this challenge through an algorithm-hardware co-design effort. At the algorithm level, inspired by the cortical fast-slow organization in the brain, we introduce a neural network with an explicit slow memory pathway that, combined with fast spiking activity, enables a dual memory pathway architecture in which each layer maintains a compact low-dimensional state that summarizes recent activity and modulates spiking dynamics. This explicit memory stabilizes learning while preserving event-driven sparsity, achieving competitive accuracy on long-sequence benchmarks with 40-60% fewer parameters than equivalent state-of-the-art spiking neural networks. At the hardware level, we introduce a near-memory-compute architecture that fully leverages the advantages of the dual memory pathway architecture by retaining its compact shared state while optimizing data flow, across heterogeneous sparse-spike and dense-memory pathways. We show experimental results that demonstrate more than a fourfold increase in throughput and over a fivefold improvement in energy efficiency compared with state-of-the-art implementations. Together, these contributions demonstrate that biological principles can guide functional abstractions that are both algorithmically effective and hardware-efficient, establishing a scalable co-design framework for real-time neuromorphic computation and learning.
-
9. Platonic representation of foundation machine learning interatomic potentials.
PMID:日期:2026-01-01Foundation machine learning interatomic potentials (MLIPs) have emerged as powerful tools for atomistic simulation, yet different models encode chemical environments in incompatible latent spaces, limiting direct comparison and interoperability. The platonic representation hypothesis suggests that sufficiently capable models converge towards a shared statistical representation of reality. Here, motivated by this hypothesis, we show that independently developed MLIPs exhibit statistically consistent geometric organization of atomic environments. By projecting embeddings relative to a set of atomic anchors, we unify the latent spaces of seven MLIPs-spanning equivariant, non-equivariant, conservative and non-conservative architectures-into a common latent space that preserves chemical periodicity and structural invariants. This unified framework enables cross-model optimal transport, interpretable embedding arithmetic and the detection of representational biases. Furthermore, we show that deviation in this space provides a ground-truth-free measure for atypical structures, and signals physical prediction failures. Our results suggest that the platonic representation offers a practical route towards interoperable, comparable and interpretable foundation models for materials science.
-
10. Immunotherapy drug target identification using machine learning and patient-derived tumour explant validation.
PMID:日期:2026-01-01Immunotherapy has revolutionized cancer treatment, yet only a minority of individuals respond clinically, necessitating alternative strategies that can benefit these patients. Novel immuno-oncology targets may achieve this through bypassing resistance mechanisms to standard therapies. We introduce Mining Immunotherapy Drug tArgetS (MIDAS), a multimodal graph neural network system for immuno-oncology target discovery. MIDAS leverages gene interactions, multi-omic patient profiles, immune cell biology, antigen processing, disease associations and phenotypic consequences of genetic perturbations. It generalizes to time-sliced data, outcompetes state-of-the-art baselines (including OpenTargets) and ranks approved targets above those in clinical development. Moreover, MIDAS recovers immunotherapy-response-associated genes in unseen patients, thereby capturing immunotherapy response determinants. Interpretability analyses reveal a reliance on autoimmunity, regulatory networks and immuno-oncology pathways. Functionally perturbing oncostatin M-oncostatin M receptor signalling, a proposed MIDAS target, in TRACERx melanoma-patient-derived explants yielded reduced dysfunctional CD8 T cells, which associate with immunotherapy response, and reduced CCL4 levels. Furthermore, oncostatin M and oncostatin M receptor expression is associated with altered T cell and macrophage profiles in bulk transcriptomic data from patient samples. These data are consistent with a role for oncostatin M-oncostatin M in modulating the tumour microenvironment towards immunosuppressive, tumour-promoting phenotypes. Our results present a machine learning framework for analysing multimodal data for immuno-oncology target discovery.