Recent work indicates that low-dimensional dynamics of neural and behavioral data are often preserved across days and subjects. However, extracting these preserved dynamics remains challenging: high-dimensional neural population activity and the recorded neuron populations vary across recording sessions. While existing modeling tools can improve alignment between neural and behavioral data, they often operate on a per-subject basis or discretize behavior into categories, disrupting its natural continuity and failing to capture the underlying dynamics. We introduce $\underline{\text{C}}$ontrastive $\underline{\text{A}}$ligned $\underline{\text{N}}$eural $\underline{\text{D}}$$\underline{\text{Y}}$namics (CANDY), an end‑to‑end framework that aligns neural and behavioral data using rank-based contrastive learning, adapted for continuous behavioral variables, to project neural activity from different sessions onto a shared low-dimensional embedding space. CANDY fits a shared linear dynamical system to the aligned embeddings, enabling an interpretable model of the conserved temporal structure in the latent space. We validate CANDY on synthetic and real-world datasets spanning multiple species, behaviors, and recording modalities. Our results show that CANDY is able to learn aligned latent embeddings and preserved dynamics across neural recording sessions and subjects, and it achieves improved cross-session behavior decoding performance. We further show that the latent linear dynamical system generalizes to new sessions and subjects, achieving comparable or even superior behavior decoding performance to models trained from scratch. These advances enable robust cross‑session behavioral decoding and offer a path towards identifying shared neural dynamics that underlie behavior across individuals and recording conditions. The code and two-photon imaging data of striatal neural activity that we acquired here are available at https://github.com/schnitzer-lab/CANDY-public.git.

The human respiratory microbiome plays a crucial role in respiratory health, but there is no comprehensive respiratory genome catalogue (RGC) for studying the microbiome. In this study, we collected whole-metagenome shotgun sequencing data from 4067 samples and sequenced long reads of 124 samples, yielding 9.08 and 0.42 Tbp of short- and long-read data, respectively. By submitting these data with a novel assembly algorithm, we obtained a comprehensive human RGC. This high-quality RGC contains 190,443 contigs over 1 kbps and an N50 length exceeding 13 kbps; it comprises 159 high-quality and 393 medium-quality genomes, including 117 previously uncharacterized respiratory bacteria. Moreover, the RGC contains 209 respiratory-specific species not captured by the unified human gastrointestinal genome. Using the RGC, we revisited a study on a pediatric pneumonia dataset and identified 17 pneumonia-specific respiratory pathogens, reversing an inaccurate etiological conclusion due to the previous incomplete reference. Furthermore, we applied the RGC to the data of 62 participants with a clinical diagnosis of infection. Compared to the Nucleotide database, the RGC yielded greater specificity (0 versus 0.444, respectively) and sensitivity (0.852 versus 0.881, respectively), suggesting that the RGC provides superior sensitivity and specificity for the clinical diagnosis of respiratory diseases.

Recent advances in calcium imaging enable simultaneous recordings of up to a million neurons in behaving animals, producing datasets of unprecedented scales. Although individual neurons and their activity traces can be extracted from these videos with automated algorithms, the results often require human curation to remove false positives, a laborious process called \emph{cell sorting}. To address this challenge, we introduce ActSort, an active-learning algorithm for sorting large-scale datasets that integrates features engineered by domain experts together with data formats with minimal memory requirements. By strategically bringing outlier cell candidates near the decision boundary up for annotation, ActSort reduces human labor to about 1–3\% of cell candidates and improves curation accuracy by mitigating annotator bias. To facilitate the algorithm's widespread adoption among experimental neuroscientists, we created a user-friendly software and conducted a first-of-its-kind benchmarking study involving about 160,000 annotations. Our tests validated ActSort's performance across different experimental conditions and datasets from multiple animals. Overall, ActSort addresses a crucial bottleneck in processing large-scale calcium videos of neural activity and thereby facilitates systems neuroscience experiments at previously inaccessible scales. (\url{https://github.com/schnitzer-lab/ActSort-public})

The acquisition of a substantial volume of precisely dense pixel-annotated samples plays a crucial role in the effective training of deep learning-based change detection models. Nevertheless, in real-world scenarios, pairwise labeling of massive bitemporal remote sensing images is often laborious and time-consuming, resulting in the lack of labeled samples. In this article, we propose a novel point-based weakly supervised learning approach, called as the consistency-aligned regional growth network (CARGNet), for remote sensing change detection. Unlike pixel-level labels, point labels are easy to label and usually sparse, which leads to a lack of boundary information, making it difficult for the model to accurately capture the details of the changed objects. Therefore, learning directly from them may mislead the training of the network. To address these problems, we introduce a point-based changed regional growth (PCRG) module and consistency alignment (CA) constraint into CARGNet, which breaks the limitation of point labels in losing important target details. Specifically, our CARGNet contains two branches: a base decoder branch and an expanded decoder branch. First, we utilize the PCRG module to generate the expanded annotations from the point annotations. Then, the base decoder is supervised by the original point annotations, while the expanded decoder is supervised by the expanded annotations. Finally, the CA constraint is thereby achieved by minimizing the discrepancy between the predictions from both the base and the expanded decoders, which greatly improves the performance of the model. Experimental results on LEVIR-CD-Point and DSIFN-CD-Point datasets demonstrate that our proposed CARGNet can achieve highly competitive results compared with state-of-the-art fully-supervised methods. Code and datasets are available athttps://github.com/Wanderlust717/CARGNet.

Zero-shot action recognition (ZSAR) aims to recognize unseen action categories in the test set without corresponding training examples. Most existing zero-shot methods follow the feature generation framework to transfer knowledge from seen action categories to model the feature distribution of unseen categories. However, due to the complexity and diversity of actions, it remains challenging to generate unseen feature distribution, especially for the cross-dataset scenario when there is a potentially larger domain shift. This article proposes aDeconfoundingCaUSAlGAN (DeCalGAN) for generating unseen action video features with the following technical contributions: 1) Our model unifies compositional ZSAR with traditional visual-semantic models to incorporate local object information with global semantic information for feature generation. 2) A GAN-based architecture is proposed for causal inference and unseen distribution discovery. 3) A deconfounding module is proposed to refine representations of local objects and global semantic information confounder in the training data. Action descriptions and random object features after causal inference are then used to discover unseen distributions of novel actions in different datasets. Our extensive experiments onCross-DatasetZero-ShotActionRecognition (CD-ZSAR) demonstrate substantial improvement over the UCF101 and HMDB51 standard benchmarks for this problem.

Robotic applications often involve working in environments that are uncertain, dynamic, and partially observable. Recently, diffusion models have been proposed for learning trajectory prediction models trained from expert demonstrations, which can be used for planning in robot tasks. Such models have demonstrated a strong ability to overcome challenges such as multi-modal action distributions, high-dimensional output spaces, and training instability. It is crucial to quantify the uncertainty of these dynamics models when using them for planning. In this paper, we quantify the uncertainty of diffusion dynamics models using Conformal Prediction (CP). Given a finite number of exchangeable expert trajectory examples (called the “calibration set”), we use CP to obtain a set in the trajectory space (called the “coverage region”) that is guaranteed to contain the output of the diffusion model with a user-defined probability (called the “coverage level”). In PlanCP, inspired by concepts from conformal prediction, we modify the loss function for training the diffusion model to include a quantile term to encourage more robust performance across the variety of training examples. At test time, we then calibrate PlanCP with a conformal prediction process to obtain coverage sets for the trajectory prediction with guaranteed coverage level. We evaluate our algorithm on various planning tasks and model-based offline reinforcement learning tasks and show that it reduces the uncertainty of the learned trajectory prediction model. As a by-product, our algorithm PlanCP outperforms prior algorithms on existing offline RL benchmarks and challenging continuous planning tasks. Our method can be combined with most model-based planning approaches to produce uncertainty estimates of the closed-loop system.

Recently, GAN based method has demonstrated strong effectiveness in generating augmentation data for person re-identification (ReID), on account of its ability to bridge the gap between domains and enrich the data variety in feature space. However, most of the ReID works pick all the GAN generated data as additional training samples or evaluate the quality of GAN generation at the entire data set level, ignoring the image-level essential feature of data in ReID task. In this paper, we analyze the in-depth characteristics of ReID sample and solve the problem of "What makes a GAN-generated image good for ReID''. Specifically, we propose to examine each data sample with id-consistency and diversity constraints by mapping image onto different spaces. With a metric-based sampling method, we demonstrate that not every GAN-generated data is beneficial for augmentation. Models trained with data filtered by our quality evaluation outperform those trained with the full augmentation set by a large margin. Extensive experiments show the effectiveness of our method on both supervised ReID task and unsupervised domain adaptation ReID task.

MOTIVATION: The microbial community plays an essential role in human diseases and physiological activities. The functions of microbes can differ due to strain-level differences in the genome sequences. Shotgun metagenomic sequencing allows us to profile the strains in microbial communities practically. However, current methods are underdeveloped due to the highly similar sequences among strains. We observe that strains genotypes at the same single nucleotide variant (SNV) locus can be speculated by the genotype frequencies. Also, the variants in different loci covered by the same reads can provide evidence that they reside on the same strain. RESULTS: These insights inspire us to design PStrain, an optimization method that utilizes genotype frequencies and the reads which cover multiple SNV loci to profile strains iteratively based on SNVs in a set of MetaPhlAn2 marker genes. Compared to the state-of-art methods, PStrain, on average, improved the performance of inferring strains abundances and genotypes by 87.75% and 59.45%, respectively. We have applied the PStrain package to the dataset with two cohorts of colorectal cancer (CRC) and found that the sequences of Bacteroides coprocola strains are significantly different between CRC and control samples, which is the first time to report the potential role of B.coprocola in the gut microbiota of CRC. AVAILABILITYAND IMPLEMENTATION: https://github.com/wshuai294/PStrain. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Horizontal Gene Transfer (HGT) refers to the transfer of genetic materials between organisms through mechanisms other than parent-offspring inheritance. HGTs may affect human health through a large number of microorganisms, especially the gut microbiomes which the human body harbors. The transferred segments may lead to complicated local genome structural variations. Details of the local genome structure can elucidate the effects of the HGTs. RESULTS: In this work, we propose a graph-based method to reconstruct the local strains from the gut metagenomics data at the HGT sites. The method is implemented in a package named LEMON. The simulated results indicate that the method can identify transferred segments accurately on reference sequences of the microbiome. Simulation results illustrate that LEMON could recover local strains with complicated structure variation. Furthermore, the gene fusion points detected in real data near HGT breakpoints validate the accuracy of LEMON. Some strains reconstructed by LEMON have a replication time profile with lower standard error, which demonstrates HGT events recovered by LEMON is reliable. CONCLUSIONS: Through LEMON we could reconstruct the sequence structure of bacteria, which harbors HGT events. This helps us to study gene flow among different microbial species.