Kentaro Yamamoto, Riku Masui, Takahito Nakajima, Miwako Tsuji, Mitsuhisa Sato, Peter Schow, Lukas Heidemann, Matthew Burke, Philipp Seitz, Oliver J. Backhouse, Juan W. Pedersen, John Children, Craig Holliman, Nathan Lysne, Daichi Okuno, Seyon Sivarajah, David Muñoz Ramo, Alex Chernoguzov, Ross Duncan <<<

We develop a workflow within the ONIOM framework and demonstrate it on the hybrid computing system consisting of the supercomputer Fugaku and the Quantinuum Reimei trapped-ion quantum computer. This hybrid platform extends the layered approach for biomolecular chemical reactions to accurately treat the active site, such as a protein, and the large and often weakly correlated molecular environment. Our result marks a significant milestone in enabling scalable and accurate simulation of complex biomolecular reactions <<<

Recent advances in AI-driven drug discovery have led to widespread narratives suggesting that a single model or platform can generate viable therapeutic candidates and, when combined with automated laboratory systems, rapidly progress to clinical development. These narratives often imply that AI-driven design coupled with robotic execution can substantially compress the path to Phase I trials and accelerate the treatment of complex diseases within a few years. However, practical implementation reveals a significant gap between model-level performance and end-to-end drug development success. <<<

Abstract Millions of human genomes have been genotyped by national biobanks worldwide. Training large language models (LLM) with this data may lead to a universal model of human genome with tremendous potential. Yet the quadrillions (10 15 ) of nucleotides— resulting from genome length multiplied by population size—pose formidable challenges for modeling. In this study, we propose a novel AI framework designed to scale with this data and support diverse analytical tasks. To demonstrate this scheme, we developed SNPBag—a foundation model focusing on single nucleotide polymorphism (SNP). With 0.8 billion parameters, it is trained on one million synthesized human genomes, corresponding to a total of 6 trillion SNP tokens. SNPBag showed superior performance in benchmarking of multiple tasks. In genotype imputation, it achieves state-of-the-art (SOTA) accuracy. In haplotype phasing, it rivals the best method with a 72-fold speedup. By encoding 6 million SNPs per genome into a 0.75 MB embedding, SNPBag enables efficient storage, transfer and downstream applications. In particular, the genome embeddings facilitate rapid ancestry inference across global populations and detection of genetic relationships up to 12th-degree relatives. Collectively, SNPBag introduces a new paradigm for scalable, unified and multitask analysis of the ever-growing human variation data. <<<

Since pioneering work of Hinton et al., knowledge distillation based on Kullback-Leibler Divergence (KL-Div) has been predominant, and recently its variants have achieved compelling performance. However, KL-Div only compares probabilities of the corresponding category between the teacher and student while lacking a mechanism for cross-category comparison. Besides, KL-Div is problematic when applied to intermediate layers, as it cannot handle non-overlapping distributions and is unaware of geometry of the underlying manifold. To address these downsides, we propose a methodology of Wasserstein Distance (WD) based knowledge distillation. Specifically, we propose a logit distillation method called WKD-L based on discrete WD, which performs cross-category comparison of probabilities and thus can explicitly leverage rich interrelations among categories. Moreover, we introduce a feature distillation method called WKD-F, which uses a parametric method for modeling feature distributions and adopts continuous WD for transferring knowledge from intermediate layers. Comprehensive evaluations on image classification and object detection have shown (1) for logit distillation WKD-L outperforms very strong KL-Div variants; (2) for feature distillation WKD-F is superior to the KL-Div counterparts and state-of-the-art competitors. The source code is available at https://peihuali.org/WKD <<<

The discovery of circulating fetal and tumor cell-free DNA (cfDNA) molecules in plasma has opened up tremendous opportunities in noninvasive diagnostics such as the detection of fetal chromosomal aneuploidies and cancers and in posttransplantation monitoring. The advent of high-throughput sequencing technologies makes it possible to scrutinize the characteristics of cfDNA molecules, opening up the fields of cfDNA genetics, epigenetics, transcriptomics, and fragmentomics, providing a plethora of biomarkers. Machine learning (ML) and/or artificial intelligence (AI) technologies that are known for their ability to integrate high-dimensional features have recently been applied to the field of liquid biopsy. In this review, we highlight various AI and ML approaches in cfDNA-based diagnostics. We first introduce the biology of cell-free DNA and basic concepts of ML and AI technologies. We then discuss selected examples of ML- or AI-based applications in noninvasive prenatal testing and cancer liquid biopsy. These applications include the deduction of fetal DNA fraction, plasma DNA tissue mapping, and cancer detection and localization. Finally, we offer perspectives on the future direction of using ML and AI technologies to leverage cfDNA fragmentation patterns in terms of methylomic and transcriptional investigations. <<<

Abstract The automation of science is a long-standing ambition in artificial intelligence (AI) research 1,2 . Although the community has made substantial progress in automating individual components of the scientific process, a system that autonomously navigates the entire research life cycle—from conception to publication—has remained out of reach. Here we present a pipeline for automating the entire scientific process end to end. We present The AI Scientist, which creates research ideas, writes code, runs experiments, plots and analyses data, writes the entire scientific manuscript, and performs its own peer review. Its ideas, execution and presentation are of sufficient quality that the manuscript generated by this AI system passed the first round of peer review for a workshop of a top-tier machine learning conference. The workshop had an acceptance rate of 70%. Our system leverages modern foundation models 3–5 within a complex agentic system. We evaluate The AI Scientist in two settings: a focused mode using human-provided code templates as an initial scaffold for conducting research on a specific topic and a template-free, open-ended mode that leverages agentic search for wider scientific exploration 6,7 . Both settings produce diverse ideas and automatically test, report on and evaluate them. This achievement demonstrates the growing capacity of AI for making scientific contributions and signifies a potential paradigm shift in how research is conducted. As with any impactful new technology, there could be important risks, including taxing overwhelmed review systems and adding noise to the scientific literature. However, if developed responsibly, such autonomous systems could greatly accelerate scientific discovery. <<<

AbstractAstrocytes are a direct target of neuromodulators and can influence neuronal activity on broad spatial and temporal scales in response to a rise in cytosolic calcium. However, our knowledge about how astrocytes are recruited during different animal behaviors remains limited. To measure astrocyte activity calcium in vivo during normative behaviors, we utilize a high-resolution, long working distance multicore fiber optic imaging system that allows visualization of individual astrocyte calcium transients in the cerebral cortex of freely moving mice. We define the spatiotemporal dynamics of astrocyte calcium changes during diverse behaviors, ranging from sleep-wake cycles to the exploration of novel objects, showing that their activity is more variable and less synchronous than apparent in head-immobilized imaging conditions. In accordance with their molecular diversity, individual astrocytes often exhibit distinct thresholds and activity patterns during explorative behaviors, allowing temporal encoding across the astrocyte network. Astrocyte calcium events were induced by noradrenergic and cholinergic systems and modulated by internal state. The distinct activity patterns exhibited by astrocytes provides a means to vary their neuromodulatory influence in different behavioral contexts and internal states. <<<

严耕望是享誉世界的史学家,在中国政治制度史和中国历史地理学方面卓有成就。他以学问为生命,一生以做"坚强纯净的学术人"自守,深受学界尊敬。他的巨大学术成就,体现出鲜明的治学风格。其主要表现:在学术路径上是通过专精以达博通;在研究旨趣上,倾向于做实在具体的研究,不做抽象理论的研究;在资料运用上,主张把研究建立在基本资料上;在研究方法上,主要是通过对史料的考辨、归纳、统计而得出结论,而不倚重新奇的理论和方法。作为一个著名史学家,他提出的中国现代史学"四大家"观点,对二陈、吕思勉、傅斯年、唯物史观等所作的评论,均有其独到的视角和价值。 <<<

Yusong Wang, Youjun Xu, Wentao Li, Haoyu Yu, Wenjuan Tan, Shaoning Li, Qiaojing Huang, Nanjun Chen, Xuan Wu, Qilong Wu, Kai Liu <<<

Abstract Biomolecular functions are governed by dynamic conformational ensembles rather than static structures. While models like AlphaFold have revolutionized static structure prediction, accurately capturing the equilibrium distribution of all-atom biomolecular interactions remains a significant challenge due to the high computational cost of molecular dynamics (MD). We present AnewSampling, a transferable generative foundation framework designed for the high-fidelity sampling of all-atom equilibrium distributions, which is the first model to faithfully reproduce MD at the all-atom level. It uses a novel quotient-space generative framework to ensure mathematical consistency and leverages the largest self-curated database of protein-ligand trajectories to date, with over 15 million conformations. Statistically, AnewSampling consistently outperforms all prior generative methods on the ATLAS monomer benchmark, and the all-atom capabilities of AnewSampling enable close statistical alignment with ground-truth MD for evaluating atomic biomolecular interactions in protein-ligand dynamics. Furthermore, AnewSampling successfully recovers coupled ligand and side-chain motions in CDK2 systems, overcoming a major sampling hurdle inherent to conventional MD. AnewSampling enables rapid exploration of conformational landscapes prior to intensive simulations, elucidating fundamental biophysical mechanisms and accelerating the broader design of functional biomolecules. <<<

Qian You, Ze Peng, Zhiliang Li, Yaolan Jiang, Penglong Wan, Yahui Zhao, Wei Zhao, Songyuan Zhang, Hefen Cheng, Chengjie Chen, Zhou Heng, Ming Hu, Yongfeng Zhou, Brandon S. Gaut, Baojuan Sun, Tao Li, Yi Liao <<<

Abstract Eggplant ( Solanum melongena L.) is a globally important Solanaceae crop, yet trait-relevant genomic variants remain poorly characterized. Here, we perform population genomic analyses of 226 eggplant accessions sampled mainly from a major domestication center spanning Southeast Asia and South China, and find that genetic relationships closely track geographic origin. We generate chromosome-scale assemblies for 11 representative accessions using long-read sequencing and integrate six published genomes to build a pangenome resource. Using this resource, association scans identify a 12.4 Mb inversion on chromosome 10 segregating at 50.44% frequency that is strongly associated with fruit color, likely through hitchhiking with SmMYB1 . We also detect variants associated with bacterial wilt resistance, including a premature stop codon in SmCYP82D47 and copy number variations in SmEPS1 and SmRoq1 homologs. Together, our results illuminate the evolution and phenotypic impact of large structural variants and provide genomic resources for eggplant genetics and breeding. <<<

Abstract Epigenetic clocks derived from DNA methylation patterns are among the most promising biomarkers of biological aging 1–7 , as they capture molecular signatures that predict morbidity and mortality beyond chronological age. Although cross-sectional assessments of epigenetic age have been linked consistently to health outcomes and lifespan, it remains unclear whether the rate of change in these clocks over time provides additional insight into aging trajectories. In this longitudinal study of 699 adults from the InCHIANTI cohort followed for up to 24 years, we evaluated whether temporal acceleration of several epigenetic clocks—including first-, second- and third-generation epigenetic clocks—was associated with mortality. We found that faster increases in several clocks were linked robustly to higher risk of death, independent of baseline epigenetic age and other confounders. These findings suggest that dynamic changes in epigenetic aging reflect evolving health status and may serve as sensitive indicators for interventions aimed at extending healthspan and longevity. <<<

Abstract Objectives To train and validate a machine learning model to distinguish paper mill publications from genuine cancer research articles, and to screen the cancer research literature to assess the prevalence of papers that have textual similarities to paper mill papers. Design Methodological and cross sectional study applying a BERT (bidirectional encoder representations from transformers) based, text classification model to article titles and abstracts. Setting Retracted paper mill publications listed in the Retraction Watch database were used for model training. The cancer research corpus was screened by the model using the PubMed database restricted to original cancer research articles published between 1999 and 2024. Population The model was trained on 2202 retracted paper mill papers and validated on independent data collected by image integrity experts. 2.6 million cancer research papers were screened. Main outcome measures Classification performance of the model. Prevalence of papers flagged as similar to retracted paper mill publications with 95% confidence intervals and their distribution over time, by country, publisher, cancer type, research area, and within high impact journals (top 10%). Results The model achieved an accuracy of 0.91. When applied to the cancer research literature, it flagged 261 245 of 2 647 471 papers (9.87%, 95% confidence interval 9.83 to 9.90) and revealed a large increase in flagged papers from 1999 to 2024, both across the entire corpus and in the top 10% of journals by impact factor. More than 170 000 papers affiliated with Chinese institutions were flagged, accounting for 36% of Chinese cancer research articles. Most publishers had published substantial numbers of flagged papers. Flagged papers were overrepresented in fundamental research and in gastric, bone, and liver cancer. Conclusions Paper mills are a large and growing problem in the cancer literature and are not restricted to low impact journals. Collective awareness and action will be crucial to address the problem of paper mill publications. <<<

A. Coutrot, E. Manley, S. Goodroe, C. Gahnstrom, G. Filomena, D. Yesiltepe, R. C. Dalton, J. M. Wiener, C. Hölscher, M. Hornberger, H. J. Spiers <<<

Board games have long served as complex decision-making benchmarks in artificial intelligence. In this field, search-based reinforcement learning methods such as AlphaZero have achieved remarkable success. However, their significant computational demands have been pointed out as barriers to their reproducibility. In this study, we propose a model-free reinforcement learning algorithm designed for board games to achieve more efficient learning. To validate the efficiency of the proposed method, we conducted comprehensive experiments on five board games: Animal Shogi, Gardner Chess, Go, Hex, and Othello. The results demonstrate that the proposed method achieves more efficient learning than existing methods across these environments. In addition, our extensive ablation study shows the importance of core techniques used in the proposed method. We believe that our efficient algorithm shows the potential of model-free reinforcement learning in domains traditionally dominated by search-based methods. <<<