ArXiv最新文献

{"title":"ProtoECGNet: Case-Based Interpretable Deep Learning for Multi-Label ECG Classification with Contrastive Learning.","authors":"Sahil Sethi, David Chen, Thomas Statchen, Michael C Burkhart, Nipun Bhandari, Bashar Ramadan, Brett Beaulieu-Jones","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Deep learning-based electrocardiogram (ECG) classification has shown impressive performance but clinical adoption has been slowed by the lack of transparent and faithful explanations. Post hoc methods such as saliency maps may fail to reflect a model's true decision process. Prototype-based reasoning offers a more transparent alternative by grounding decisions in similarity to learned representations of real ECG segments-enabling faithful, case-based explanations. We introduce ProtoECGNet, a prototype-based deep learning model for interpretable, multi-label ECG classification. ProtoECGNet employs a structured, multi-branch architecture that reflects clinical interpretation workflows: it integrates a 1D CNN with global prototypes for rhythm classification, a 2D CNN with time-localized prototypes for morphology-based reasoning, and a 2D CNN with global prototypes for diffuse abnormalities. Each branch is trained with a prototype loss designed for multi-label learning, combining clustering, separation, diversity, and a novel contrastive loss that encourages appropriate separation between prototypes of unrelated classes while allowing clustering for frequently co-occurring diagnoses. We evaluate ProtoECGNet on all 71 diagnostic labels from the PTB-XL dataset, demonstrating competitive performance relative to state-of-the-art black-box models while providing structured, case-based explanations. To assess prototype quality, we conduct a structured clinician review of the final model's projected prototypes, finding that they are rated as representative and clear. ProtoECGNet shows that prototype learning can be effectively scaled to complex, multi-label time-series classification, offering a practical path toward transparent and trustworthy deep learning models for clinical decision support.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12091707/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144112982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Alternative to the statistical mass confusion of testing for \"no effect\".","authors":"Josh L Morgan","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>It should not be controversial to argue that the proximate goal of measuring something is to figure out how big or small or fast or slow it is. Estimates of effect size can be used to build models of how cells work and to test quantitative predictions. Unfortunately, in cell biology, quantification is nearly synonymous with null-hypothesis significance testing. The hypothesis being tested is universally assumed to be the hypothesis that there was no effect. Framing every experiment as an attempt to reject the no-effect hypothesis is convenient but doesn't teach us about cells. In this manuscript, I walk through some of the common critiques of significance testing and how these critiques relate to experimental cell biology. I argue that careful consideration of effect size should be returned to its central position in the planning and discussion of cell biological research. To facilitate this shift in focus, I recommend replacing p-values with confidence intervals as cell biology's default statistical analysis.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12036429/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144042703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Differentiable Folding for Nearest Neighbor Model Optimization.","authors":"Ryan K Krueger, Sharon Aviran, David H Mathews, Jeffrey Zuber, Max Ward","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>The Nearest Neighbor model is the $textit{de facto}$ thermodynamic model of RNA secondary structure formation and is a cornerstone of RNA structure prediction and sequence design. The current functional form (Turner 2004) contains $approx13,000$ underlying thermodynamic parameters, and fitting these to both experimental and structural data is computationally challenging. Here, we leverage recent advances in $textit{differentiable folding}$, a method for directly computing gradients of the RNA folding algorithms, to devise an efficient, scalable, and flexible means of parameter optimization that uses known RNA structures and thermodynamic experiments. Our method yields a significantly improved parameter set that outperforms existing baselines on all metrics, including an increase in the average predicted probability of ground-truth sequence-structure pairs for a single RNA family by over 23 orders of magnitude. Our framework provides a path towards drastically improved RNA models, enabling the flexible incorporation of new experimental data, definition of novel loss terms, large training sets, and even treatment as a module in larger deep learning pipelines. We make available a new database, RNAometer, with experimentally-determined stabilities for small RNA model systems.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11952582/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comprehensive Analysis of Relative Pressure Estimation Methods Utilizing 4D-Flow MRI.","authors":"Brandon Hardy, Judith Zimmermann, Vincent Lechner, Mia Bonini, Julio A Sotelo, Nicholas S Burris, Daniel B Ennis, David Marlevi, David A Nordsletten","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Magnetic resonance imaging (MRI) can estimate three-dimensional (3D) time-resolved relative pressure fields using 4D-flow MRI, thereby providing rich pressure field information. Clinical alternatives include catheterization and Doppler echocardiography, which only provide one-dimensional pressure drops. The accuracy of one-dimensional pressure drops derived from 4D-flow has been explored previously, but additional work is needed to evaluate the accuracy of 3D relative pressure field estimates. This work presents an analysis of three state-of-the-art relative pressure estimators: virtual Work-Energy Relative Pressure <math> <mrow> <mfenced><mrow><mi>v</mi> <mtext>WERP</mtext></mrow> </mfenced> </mrow> </math> , the Pressure Poisson Estimator (PPE), and the Stokes Estimator (STE). The spatiotemporal characteristics and sensitivity to noise were determined <i>in silico</i>. Estimators were then validated using a type B aortic dissection (TBAD) flow phantom with varying tear geometry and twelve catheter pressure measurements. Finally, the performance of each estimator was evaluated across eight patient cases. <i>In silico</i> pressure field errors were lower in STE compared to PPE, although PPE pressures were less noise sensitive. High velocity gradients and low spatial resolution contributed most significantly to local variations in 3D pressure field errors. Low temporal resolution lead to systematic underestimation of highly transient peak pressure events. In the flow phantom analysis, <math><mrow><mi>v</mi> <mtext>WERP</mtext></mrow> </math> was the most accurate method, followed by STE and PPE. Each pressure estimator was strongly correlated with ground truth pressure values, despite the tendency to underestimate peak pressures. Patient case results demonstrated that each pressure estimator could be feasibly integrated into a clinical workflow.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11908371/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143652570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Self-reorganization and Information Transfer in Massive Schools of Fish.","authors":"Haotian Hang, Chenchen Huang, Alex Barnett, Eva Kanso","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>The remarkable cohesion and coordination observed in moving animal groups and their collective responsiveness to threats are thought to be mediated by scale-free correlations, where changes in the behavior of one animal influence others in the group, regardless of the distance between them. But are these features independent of group size? Here, we investigate group cohesiveness and collective responsiveness in computational models of massive schools of fish of up to 50,000 individuals. We show that as the number of swimmers increases, flow interactions destabilize the school, creating clusters that constantly fragment, disperse, and regroup, similar to their biological counterparts. We calculate the spatial correlation and speed of information propagation in these dynamic clusters. Spatial correlations in cohesive and polarized clusters are indeed scale free, much like in natural animal groups, but fragmentation events are preceded by a decrease in correlation length, thus diminishing the group's collective responsiveness, leaving it more vulnerable to predation events. Importantly, in groups undergoing collective turns, the information about the change in direction propagates linearly in time among group members, thanks to the non-reciprocal nature of the visual interactions between individuals. Merging speeds up the transfer of information within each cluster by several fold, while fragmentation slows it down. Our findings suggest that flow interactions may have played an important role in group size regulation, behavioral adaptations, and dispersion in living animal groups.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12083704/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144096083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications.","authors":"Da Wu, Zhanliang Wang, Quan Nguyen, Zhuoran Xu, Kai Wang","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>The scarcity of high-quality multimodal biomedical data limits the ability to effectively fine-tune pretrained Large Language Models (LLMs) for specialized biomedical tasks. To address this challenge, we introduce MINT (Multimodal Integrated kNowledge Transfer), a framework that aligns unimodal large decoder models with domain-specific decision patterns from high-quality multimodal biomedical data through preference optimization. While MINT supports different optimization techniques, we primarily implement it with the Odds Ratio Preference Optimization (ORPO) framework as its backbone. This strategy enables the aligned LLMs to perform predictive tasks using text-only or image-only inputs while retaining knowledge learnt from multimodal data. MINT leverages an upstream multimodal machine learning (MML) model trained on high-quality multimodal data to transfer domain-specific insights to downstream text-only or image-only LLMs. We demonstrate MINT's effectiveness through two key applications: (1) Rare genetic disease prediction from texts, where MINT uses a multimodal encoder model, trained on facial photos and clinical notes, to generate a preference dataset for aligning a lightweight decoder-based text-only LLM (Llama 3.2-3B-Instruct). Despite relying on text input only, the MINT-derived model outperforms models trained with Supervised Fine-Tuning (SFT), Retrieval-Augmented Generation (RAG), or direct preference optimization (DPO), and even outperforms much larger foundation model (Llama 3.1-405B-Instruct). (2) Tissue type classification using cell nucleus images, where MINT uses a vision-language foundation model as the preference generator, containing knowledge learnt from both text and histopathological images to align downstream image-only models. The resulting MINT-derived model significantly improves the performance of Llama 3.2-Vision-11B-Instruct on tissue type classification. In summary, MINT provides an effective strategy to align unimodal LLMs with high-quality multimodal expertise through preference optimization. Our study also highlights a hybrid strategy that grafts the strength of encoder models in classification tasks into large decoder models to enhance reasoning, improve predictive tasks and reduce hallucination in biomedical applications.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12083703/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling the 2022 Mpox Outbreak with a Mechanistic Network Model.","authors":"Emma G Crenshaw, Jukka-Pekka Onnela","doi":"","DOIUrl":"","url":null,"abstract":"<p><strong>Background: </strong>The 2022 outbreak of mpox affected more than 80,000 individuals worldwide, most of whom were men who have sex with men (MSM) who likely contracted the disease through close contact during sex. Given the unprecedented number of mpox infections and the new route of infection, there was substantial uncertainty about how best to manage the outbreak.</p><p><strong>Methods: </strong>We implemented a dynamic agent-based network model to simulate the spread of mpox in a United States-based MSM population. This model allowed us to implement data-informed dynamic network evolution to simulate realistic disease spreading and behavioral adaptations.</p><p><strong>Results: </strong>We found that behavior change, the reduction in one-time partnerships, and widespread vaccination are effective in preventing the transmission of mpox and that earlier intervention has a greater effect, even when only a high-risk portion of the population participates. With no intervention, 16% of the population was infected (25th percentile, 75th percentiles of simulations: 15.3%, 16.6%). With vaccination and behavior change in only the 25% of individuals most likely to have a one-time partner, cumulative infections were reduced by 30%, or a total reduction in nearly 500 infections (mean: 11.3%, <math> <mrow><msub><mi>P</mi> <mrow><mn>25</mn> <mo>%</mo></mrow> </msub> </mrow> </math> and <math> <mrow><msub><mi>P</mi> <mrow><mn>75</mn> <mo>%</mo></mrow> </msub> </mrow> </math> : 9.6%, 13.5%). Earlier intervention further reduces cumulative infections; beginning vaccination a year before the outbreak results in only 5.5% of men being infected, averting 950 infections or nearly 10% of the total population in our model. We also show that sustained partnerships drive the early outbreak, while one-time partnerships drive transmission after the first initial weeks. The median effective reproductive number, <math> <mrow><msubsup><mi>R</mi> <mo>∗</mo> <mi>t</mi></msubsup> </mrow> </math> , at <math><mrow><mi>t</mi> <mo>=</mo> <mn>0</mn></mrow> </math> days is 1.30 for casual partnerships, 1.00 for main, and 0.6 for one-time. By <math><mrow><mi>t</mi> <mo>=</mo> <mn>28</mn></mrow> </math> , the median <math> <mrow><msubsup><mi>R</mi> <mo>∗</mo> <mi>t</mi></msubsup> </mrow> </math> for one-time partnerships has more than doubled to 1.48, while it decreased for casual and main partnerships: 0.46 and 0.29, respectively.</p><p><strong>Conclusion: </strong>With the ability to model individuals' behavior, mechanistic networks are particularly well suited to studying sexually transmitted infections, the spread and control of which are often governed by individual-level action. Our results contribute valuable insights into the role of different interventions and relationship types in mpox transmission dynamics.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12083702/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"scDrugMap: Benchmarking Large Foundation Models for Drug Response Prediction.","authors":"Qing Wang, Yining Pan, Minghao Zhou, Zijia Tang, Yanfei Wang, Guangyu Wang, Qianqian Song","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Drug resistance remains a significant barrier to improving the effectiveness of cancer therapies. To better understand the biological mechanisms driving resistance, single-cell profiling has emerged as a powerful tool for characterizing cellular heterogeneity. Recent advancements in large-scale foundation models have demonstrated potential in enhancing single-cell analysis, yet their performance in drug response prediction remains underexplored. In this study, we developed scDrugMap, an integrated framework for drug response prediction that features both a Python command-line tool and an interactive web server. scDrugMap supports the evaluation of a wide range of foundation models, including eight single-cell foundation models and two large language models (LLMs), using large-scale single-cell datasets across diverse tissue types, cancer types, and treatment regimens. The framework incorporates a curated data resource consisting of a primary collection of 326,751 cells from 36 datasets across 23 studies, and a validation collection of 18,856 cells from 17 datasets across 6 studies. Using scDrugMap, we conducted comprehensive benchmarking under two evaluation scenarios: pooled-data evaluation and cross-data evaluation. In both settings, we implemented two model training strategies-layer freezing and fine-tuning using Low-Rank Adaptation (LoRA) of foundation models. In the pooled-data evaluation, scFoundation outperformed all others, while most models achieved competitive performance. Specifically, scFoundation achieved the highest mean F1 scores of 0.971 and 0.947 using layer-freezing and fine-tuning, outperforming the lowest-performing model by 54% and 57%, respectively. In the cross-data evaluation, UCE achieved the highest performance (mean F1 score: 0.774) after fine-tuning on tumor tissue, while scGPT demonstrated superior performance (mean F1 score: 0.858) in a zero-shot learning setting. Together, this study presents the first comprehensive benchmarking of large-scale foundation models for drug response prediction in single-cell data and introduces a user-friendly, flexible platform to support drug discovery and translational research.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12083700/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144096079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rodent Breathing Waveforms in ApoE Rats: Statistical and Entropic Differentiation.","authors":"Stephen E Wormald, Nicholas J Napoli, Gordon S Mitchell, Alexandria B Marciante","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Apolipoprotein E (ApoE) gene variations are involved in lipid metabolism and cholesterol transport, with the ApoE4 allele being a known risk factor associated with neurodegenerative conditions later in life. Emerging evidence suggests these genetic variations may also influence respiratory function and vitality. However, the specific impact of different ApoE genotypes on breathing patterns remains largely unexplored. This work investigates differences in breathing waveform characteristics and entropy statistics derived from plethysmography (PLETH) data between rat models possessing two distinct ApoE genotypes (referred to herein as gene59 and gene95). Findings reveal significant distributional differences in common plethysmography metrics and approximate entropy between the two genotypes, observed during both active and resting states. Additionally, the study examines the transient impact of sighs (deep breaths) on these breathing metrics, demonstrating that entropy and other measures are altered in the breaths immediately following a sigh.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12097682/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144129757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparing CPU and GPU compute of PERMANOVA on MI300A.","authors":"Igor Sfiligoi","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Comparing the tradeoffs of CPU and GPU compute for memory-heavy algorithms is often challenging, due to the drastically different memory subsystems on host CPUs and discrete GPUs. The AMD MI300A is an exception, since it sports both CPU and GPU cores in a single package, all backed by the same type of HBM memory. In this paper we analyze the performance of Permutational Multivariate Analysis of Variance (PERMANOVA), a non-parametric method that tests whether two or more groups of objects are significantly different based on a categorical factor. This method is memory-bound and has been recently optimized for CPU cache locality. Our tests show that GPU cores on the MI300A prefer the brute force approach instead, significantly outperforming the CPU-based implementation. The significant benefit of Simultaneous Multithreading (SMT) was also a pleasant surprise.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12083706/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}