This paper introduces ZeusAI, an artificial intelligence system developed toplay the board game 7 Wonders Duel. Inspired by the AlphaZero reinforcementlearning algorithm, ZeusAI relies on a combination of Monte Carlo Tree Searchand a Transformer Neural Network to learn the game without human supervision.ZeusAI competes at the level of top human players, develops both known andnovel strategies, and allows us to test rule variants to improve the game'sbalance. This work demonstrates how AI can help in understanding and enhancingboard games. <<<

Recent advances in computer vision and deep learning techniques have facilitated significant progress in video scene understanding, thus helping film and television practitioners achieve accurate video editing. However, so far, publicly available semantic segmentation datasets are mostly limited to indoor scenes, city streets, and natural images, often ignoring example objects in action movies, which is a research gap that needs to be urgently filled. In this paper, we introduce a large-scale, high-precision semantic segmentation dataset of props in Chinese martial arts movie clips, named ChineseMPD. Specifically, this dataset first establishes segmentation rules and general review criteria for audiovisual data, and then provides semantic segmentation annotations for six weapon props (Gun, Sword, Stick, Knife, Hook, and Arrow) with a summary of 32,992 objects.To the best of our knowledge, this dataset is the largest semantic segmentation dataset for movie props to date. ChineseMPD dataset not only significantly expands the application of traditional tasks of computer vision such as object detection and scene understanding, but also opens up new avenues for interdisciplinary research. <<<

We reliably judge locations of static objects when we walk despite the retinal images of these objects moving with every step we take. Here, we showed our brains solve this optical illusion by adopting an allocentric spatial reference frame. We measured perceived target location after the observer walked a short distance from the home base. Supporting the allocentric coding scheme, we found the intrinsic bias , which acts as a spatial reference frame for perceiving location of a dimly lit target in the dark, remained grounded at the home base rather than traveled along with the observer. The path-integration mechanism responsible for this can utilize both active and passive (vestibular) translational motion signals, but only along the horizontal direction. This asymmetric path-integration finding in human visual space perception is reminiscent of the asymmetric spatial memory finding in desert ants, pointing to nature’s wondrous and logically simple design for terrestrial creatures. <<<

Carrier screening has historically assessed a relatively small number of autosomal recessive and X-linked conditions selected based on frequency in a specific subpopulation and association with severe morbidity or mortality. Advances in genomic technologies enable simultaneous screening of individuals for several conditions. The American College of Medical Genetics and Genomics recently published a clinical practice resource that presents a framework when offering screening for autosomal recessive and X-linked conditions during pregnancy and preconception and recommends a tier-based approach when considering the number of conditions to screen for and their frequency within the US population in general. This laboratory technical standard aims to complement the practice resource and to put forth considerations for clinical laboratories and clinicians who offer preconception/prenatal carrier screening. <<<

Chenfei Wang, Dongqing Sun, Xin Huang, Changxin Wan, Ziyi Li, Ya Han, Qian Qin, Jingyu Fan, Xintao Qiu, Yingtian Xie, Clifford A Meyer, Myles Brown, Ming Tang, Henry Long, Tao Liu, X Shirley Liu <<<

We present Model-based AnalysEs of Transcriptome and RegulOme (MAESTRO), a comprehensive open-source computational workflow ( http://github.com/liulab-dfci/MAESTRO ) for the integrative analyses of single-cell RNA-seq (scRNA-seq) and ATAC-seq (scATAC-seq) data from multiple platforms. MAESTRO provides functions for pre-processing, alignment, quality control, expression and chromatin accessibility quantification, clustering, differential analysis, and annotation. By modeling gene regulatory potential from chromatin accessibilities at the single-cell level, MAESTRO outperforms the existing methods for integrating the cell clusters between scRNA-seq and scATAC-seq. Furthermore, MAESTRO supports automatic cell-type annotation using predefined cell type marker genes and identifies driver regulators from differential scRNA-seq genes and scATAC-seq peaks. <<<

Menopause eventually happens to all people with typically functioning ovaries, and almost one billion women worldwide are postmenopausal. Although the biology of typical menopause is ubiquitous, the experience varies substantially. Factors contributing to the experience include not only individual factors, such as the nature and severity of symptoms, but also psychological, social, and contextual considerations, many of which are modifiable. In this first paper in the Lancet Series on menopause, we argue for a new approach that goes beyond the treatment of specific symptoms, to encompass a broad model to support women transitioning this life stage, using the model of empowerment. WHO defines empowerment as an active process of gaining knowledge, confidence, and self-determination to self-manage health and make informed decisions about care. Rather than focusing on menopause as an endocrine deficiency, we propose an empowerment model that recognises factors modifying the experience, in which the patient is an expert in their own condition and the health-care worker supports the patient to become an equal and active partner in managing their own care. <<<

IntroductionIn a series of 5 studies, Lam and Buehler found that first-year university students felt closer to a target event (the day they learned that they were accepted into university) when they recalled a stream of related events in a backward direction (a reverse-chronological order ending with the target event) than when they recalled those events in a forward direction (a forward-chronological order beginning with the target event).MethodsIn a conceptual replication of their Study 2, we asked participants how close they felt to the first day that lockdowns were imposed in response to the Covid-19 pandemic in the U.S. (federally mandated on March 13, 2020) following either backward or forward recall of a stream of related events.ResultsThe results of the present study ran directly counter to those of Lam and Buehler: participants rated the first day of lockdowns as feeling closer following forward recall than following backward recall.DiscussionPotential explanations for this reversal of Lam and Buehler's effect are discussed that focus on the temporal distortions that people have been found to experience when they think about autobiographical events that occurred at the beginning of the pandemic. <<<

This paper introduces the Stoch BiRo, a cost-effective bipedal robot designedwith a modular mechanical structure having point feet to navigate uneven andunfamiliar terrains. The robot employs proprioceptive actuation in abduction,hips, and knees, leveraging a Raspberry Pi4 for control. Overcomingcomputational limitations, a Learning-based Linear Policy controller managesbalance and locomotion with only 3 degrees of freedom (DoF) per leg, distinctfrom the typical 5DoF in bipedal systems. Integrated within a modular controlarchitecture, these controllers enable autonomous handling of unforeseenterrain disturbances without external sensors or prior environment knowledge.The robot's policies are trained and simulated using MuJoCo, transferringlearned behaviors to the Stoch BiRo hardware for initial walking validations.This work highlights the Stoch BiRo's adaptability and cost-effectiveness inmechanical design, control strategies, and autonomous navigation, promisingdiverse applications in real-world robotics scenarios. <<<

The abundance of distractors in the world poses a major challenge to our brain's limited processing capacity, but little is known about how selective attention modulates stimulus representations in the brain to reduce interference and support durable target memory. Here, we collected functional magnetic resonance imaging (fMRI) data in a selective attention task in which target and distractor pictures of different visual categories were simultaneously presented. Participants were asked to selectively process the target according to the effective cue, either before the encoding period (i.e., perceptual attention) or the maintenance period (i.e., reflective attention). On the next day, participants were asked to perform a memory recognition task in the scanner in which the targets, distractors, and novel items were presented in a pseudorandom order. Behavioral results showed that perceptual attention was better at enhancing target memory and reducing distractor memory than reflective attention, although the overall memory capacity (memory for both target and distractor) was comparable. Using multiple-voxel pattern analysis of the neural data, we found more robust target representation and weaker distractor representation in working memory for perceptual attention than for reflective attention. Interestingly, perceptual attention partially shifted the regions involved in maintaining the target representation from the visual cortex to the parietal cortex. Furthermore, the targets and distractors simultaneously presented in the perceptual attention condition showed reduced pattern similarity in the parietal cortex during retrieval compared to items not presented together. This neural pattern repulsion positively correlated with individuals' recognition of both targets and distractors. These results emphasize the critical role of selective attention in transforming memory representations to reduce interference and improve long-term memory performance. <<<

Sheng-Kai Lai, Allen Chilun Luo, I-Hsuan Chiu, Hui-Wen Chuang, Ting-Hsuan Chou, Tsung-Kai Hung, Jacob Shujui Hsu, Chien-Yu Chen, Wei-Shiung Yang, Ya-Chien Yang, Pei-Lung Chen <<<

Human leukocyte antigen (HLA) genes play pivotal roles in numerous immunological applications. Given the immense number of polymorphisms, achieving accurate high-throughput HLA typing remains challenging. This study aimed to harness the human pan-genome reference consortium (HPRC) resources as a potential benchmark for HLA reference materials. We meticulously annotated specific four field-resolution alleles for 11 HLA genes (HLA, , , , , , , , , and ) from 44 high-quality HPRC personal genome assemblies. For sequencing, we crafted HLA-specific probes and conducted capture-based targeted sequencing of the genomic DNA of the HPRC cohort, ensuring focused and comprehensive coverage of the HLA region of interest. We used publicly available short-read whole-genome sequencing (WGS) data from identical samples to offer a comparative perspective. To decipher the vast amount of sequencing data, we employed seven distinct software tools: OptiType, HLA-VBseq, HISAT genotype, SpecHLA, T1K, QzType, and DRAGEN. Each tool offers unique capabilities and algorithms for HLA genotyping, allowing comprehensive analysis and validation of the results. We then compared these results with benchmarks derived from personal genome assemblies. Our findings present a comprehensive four-field-resolution HLA allele annotation for 44 HPRC samples. Significantly, our innovative targeted next-generation sequencing (NGS) approach for HLA genes showed superior accuracy compared with conventional short-read WGS. An integrated analysis involving QzType, T1K, and DRAGEN was developed, achieving 100% accuracy for all 11 HLA genes. In conclusion, our study highlighted the combination of targeted short-read sequencing and astute computational analysis as a robust approach for HLA genotyping. Furthermore, the HPRC cohort has emerged as a valuable assembly-based reference in this realm. <<<

Iron (Fe) deficiency remains widespread among people in developing countries. To help solve this problem, breeders have been attempting to develop maize cultivars with high yields and high Fe concentrations in the kernels. We conducted a genome-wide association study and identified a gene, (), that regulates Fe concentrations in maize kernels. We cultivated maize varieties with both high yield and high Fe concentrations in their kernels by using a molecular marker developed from a 42-base pair insertion or deletion (indel) in the promoter of . expression is enriched in the basal endosperm transfer layer of kernels, and the ZmNAC78 protein directly regulates messenger RNA abundance of Fe transporters. Our results thus provide an approach to develop maize varieties with Fe-enriched kernels. <<<

Lei Chang, Yang Xie, Brett Taylor, Zhaoning Wang, Jiachen Sun, Tuyet R Tan, Rafael Bejar, Clark C Chen, Frank B Furnari, Ming Hu, Bing Ren <<<

Comprehensive analysis of chromatin architecture is crucial for understanding the gene regulatory programs during development and in disease pathogenesis, yet current methods often inadequately address the unique challenges presented by analysis of heterogeneous tissue samples. Here, we introduce Droplet Hi-C, which employs a commercial microfluidic device for high-throughput, single-cell chromatin conformation profiling in droplets. Using Droplet Hi-C, we mapped the chromatin architecture at single-cell resolution from the mouse cortex and analyzed gene regulatory programs in major cortical cell types. Additionally, we used this technique to detect copy number variation (CNV), structural variations (SVs) and extrachromosomal DNA (ecDNA) in cancer cells, revealing clonal dynamics and other oncogenic events during treatment. We further refined this technique to allow for joint profiling of chromatin architecture and transcriptome in single cells, facilitating a more comprehensive exploration of the links between chromatin architecture and gene expression in both normal tissues and tumors. Thus, Droplet Hi-C not only addresses critical gaps in chromatin analysis of heterogeneous tissues but also emerges as a versatile tool enhancing our understanding of gene regulation in health and disease. <<<

Transformers achieve remarkable performance in several tasks but due to theirquadratic complexity, with respect to the input's length, they areprohibitively slow for very long sequences. To address this limitation, weexpress the self-attention as a linear dot-product of kernel feature maps andmake use of the associativity property of matrix products to reduce thecomplexity from $\mathcal{O}\left(N^2\right)$ to $\mathcal{O}\left(N\right)$,where $N$ is the sequence length. We show that this formulation permits aniterative implementation that dramatically accelerates autoregressivetransformers and reveals their relationship to recurrent neural networks. Ourlinear transformers achieve similar performance to vanilla transformers andthey are up to 4000x faster on autoregressive prediction of very longsequences. <<<

AbstractThe rational targeting of RNA with small molecules is hampered by our still limited understanding of RNA structural and dynamic properties. Mostin silicotools for binding site identification rely on static structures and therefore cannot face the challenges posed by the dynamic nature of RNA molecules. Here, we present SHAMAN, a computational technique to identify potential small-molecule binding sites in RNA structural ensembles. SHAMAN enables exploring the conformational landscape of RNA with atomistic molecular dynamics and at the same time identifying RNA pockets in an efficient way with the aid of probes and enhanced-sampling techniques. In our benchmark composed of large, structured riboswitches as well as small, flexible viral RNAs, SHAMAN successfully identified all the experimentally resolved pockets and ranked them among the most favorite probe hotspots. Overall, SHAMAN sets a solid foundation for future drug design efforts targeting RNA with small molecules, effectively addressing the long-standing challenges in the field. <<<

AbstractStable diffusion revolutionized image creation from descriptive text. GPT-2 (ref. 1), GPT-3(.5) (ref. 2) and GPT-4 (ref. 3) demonstrated high performance across a variety of language tasks. ChatGPT introduced such language models to the public. It is now clear that generative artificial intelligence (AI) such as large language models (LLMs) is here to stay and will substantially change the ecosystem of online text and images. Here we consider what may happen to GPT-{n} once LLMs contribute much of the text found online. We find that indiscriminate use of model-generated content in training causes irreversible defects in the resulting models, in which tails of the original content distribution disappear. We refer to this effect as ‘model collapse’ and show that it can occur in LLMs as well as in variational autoencoders (VAEs) and Gaussian mixture models (GMMs). We build theoretical intuition behind the phenomenon and portray its ubiquity among all learned generative models. We demonstrate that it must be taken seriously if we are to sustain the benefits of training from large-scale data scraped from the web. Indeed, the value of data collected about genuine human interactions with systems will be increasingly valuable in the presence of LLM-generated content in data crawled from the Internet. <<<