Digital Commons Network^™

Divergent Floral And Vegetative Trait Responses To Abiotic Factors Drive Phenotypic Diversity In Platanthera Dilatata (Orchidaceae) Across Alaska, Marlin L. Bowles, Lisa E. Wallace

Biological Sciences Faculty Publications

Multiple traits make up an integrated phenotype, but traits may be shaped by differing drivers. It is often assumed that selection by biotic agents drives floral variation, but abiotic factors are also known to influence floral traits. Understanding trait covariations and their association with diverse environmental factors is a central question in evolution and ecology. Here, we studied covariation in floral and vegetative traits in relation to climate and topo-edaphic variation in the orchid Platanthera dilatata. In Platanthera, nectar spur length is associated with pollinator tongue length, but much variation exists in other traits too, likely to be …

The Role Of Tgf-Beta Superfamily Members In Immune Homeostasis And Disease, Natalie Eva Nieuwenhuizen, Ioannis Eleftherianos, Piotr Jan Kraj, Maria Semitekolou

Biological Sciences Faculty Publications

[Introduction] The Transforming Growth Factor beta (TGF-beta) superfamily, encompassing molecules such as TGFs, activins, Bone Morphogenetic Proteins (BMPs), Growth/Differentiation Factor (GDFs) and Nodals, represents the largest family of growth and differentiation factors, playing crucial roles in developmental and physiological processes across animal species (1). These molecules are integral to tissue homeostasis and cell fate determination. Among them, TGF-beta is particularly noted for its regulatory influence on immune responses and tissue fibrosis (2, 3). Recent research has expanded our understanding of the immune functions of other superfamily members, including activin A and BMPs (4). These molecules signal through receptor complexes composed …

Squid Paralarvae Turn With High Agility Using Jets Near The Reynolds Number Threshold For Viscous Domination, Ian K. Bartol, Alissa M. Ganley, Paul S. Krueger, Joseph T. Thompson

Biological Sciences Faculty Publications

Turning is critical for survival in the ocean, as marine animals need to maneuver to capture prey, elude predators, and navigate complex environments. While prior research has focused on turning performance of adult swimmers, less is known about early ontogenetic stages that locomote within lower Reynolds number (Re) regimes, especially young jetters. To evaluate squid paralarval turning proficiency and the role of the pulsed jet in maneuvers, recently hatched longfin squid Doryteuthis pealeii swimming in a viewing chamber were studied using digital particle image velocimetry and kinematic motion analyses. Paralarvae exhibited a wide repertoire of turning behaviors, including those performed …

High Temporal Resolution Gene Expression Analysis Of Acute Heat Stress Response In Acropora Cervicornis And Porites Astreoides, Katherine Parker, Nicolas Evensen, Iliana Baums, Daniel Barshis

Biological Sciences Faculty Publications

Widespread coral bleaching and mortality events are becoming increasingly frequent due to rising ocean temperatures, though certain coral species and populations have displayed higher tolerance to elevated emperatures than others. As such, it is of high research priority to identify thermally tolerant coral populations for research and conservation and assess the biological mechanisms allowing these populations to survive exposure to higher temperatures. This research utilized the Coral Bleaching Automated Stress System (CBASS), a portable experimental aquaria system with precise temperature manipulation, to assess the thermal thresholds and heat stress response of two coral species from Summerland Key, FL, USA. Seven …

Genome-Wide Snp Analyses Reveal High Gene Flow Of Endemic Smallscale Croaker (Boesemania Microlepsis) In The Lower Mekong Basin, Quyen Dang Ha Vu, Christopher E. Bird, Oanh Thi Truong, Sang Quang Tran, Ellen E. Biesack, Amanda S. Ackiss, Kent E. Carpenter, Binh Truy Dang

Biological Sciences Faculty Publications

The Smallscale Croaker, Boesemania microlepis, is a valuable fishery resource in the Mekong River basin that lacks clear biological data to understand its basic ecology and conservation management priorities. This species is common in the southernmost floodplain of the Mekong which extends from Tonlé Sap in Cambodia to the Mekong Delta in Vietnam. This floodplain is of particular biodiversity conservation concern because of the many upstream dams that restrict water flow in an ecology that relies heavily on a flood-pulse cycle. The literature regarding the biology B. microlepis in this region contains conflicting ideas that populations are both highly …

Multifunctional Nanoscale Pigments: Emerging Risks And Circular Strategies For A Sustainable Future, Ajay Vikram Singh, Preeti Bhardwaj, Vimal Kishore, Sunil Choudhary, Akihiko Hirose, Neha Gupta, Madleen Busse, Swarn Lata Singh, Christopher J. Osgood

Biological Sciences Faculty Publications

The substantial penetration of nanoscale pigments into a range of sectors has changed the dynamics of industries such as medical, material science, and many more. Nonetheless, their persistence in the environment and probable adverse impacts on health require that an assessment of such risks be formulated considering the One Health perspective. This viewpoint considers the crossing of boundaries of progress in the nanotechnology of nanoscale pigments with environmental, animal, and human health and emphasizes the significance of collaborative activity. Traditional perspectives explain the distribution of pigment history, while the nanotechnology of today's accessibility poses problems regarding utilization, toxicities, and interactions …

Anthropocene Genetic Diversity Loss In The Marine Tropics, René D. Clark, Brendan N. Reid, Eric Garcia, Marial Malabag, Robin S. Waples, Rene A. Abesamis, Jemelyn Grace P. Baldisimo, Abner A. Bucol, Kyra S. Fitz, Sharon F. Magnuson, Richard N. Muallil, Cleto L. Nanola Jr., Roy Roberts, John C. Whalen, Christopher E. Bird, Kent E. Carpenter, Malin L. Pinsky

Biological Sciences Faculty Publications

Genetic diversity is a crucial component of biodiversity, and as such, its maintenance and preservation is of high conservation concern. Tropical environments are undergoing intense rates of environmental change, and these changes may be driving large declines in genetic diversity. However, data on genetic diversity are highly skewed towards temperate regions. The degree to which diversity loss has occurred in tropical species, particularly marine species, remains an open and important question. Here, we directly compare genomic data from modern and museum collections of two commercially-harvested nearshore marine fishes (Equulites laterofenestra and Gazza minuta) gathered from a single location …

Preservation Of Genetic Diversity And Selection Over A Century In A Coral Reef Fish (Taeniamia Zosterophora) In The Philippines, Kyra S. Fitz, Rene A. Abesamis, Jemelyn Grace P. Baldisimo, Abner A. Bucol, René D. Clark, Eric Garcia, Ivan R. Lopez, Sharon F. Magnuson, Marial J. Malabag, Richard N. Muallil, Lynne R. Parenti, Brendan R. Reid, Mudjekeewis D. Santos, Christopher E. Bird, Kent E. Carpenter, Malin L. Pinsky

Biological Sciences Faculty Publications

Evaluating the evolutionary impacts of anthropogenic activity on populations is key to understanding species resiliency and to designing effective conservation strategies. Sequencing DNA from historical specimens provides the opportunity to establish a historical baseline and empirically assess changes in genetic diversity, changes in effective population size, and selection over time. Here, we sequenced historical and contemporary samples of the cardinalfish Taeniamia zosterophora collected in 1908 and in 2021-2022 across two sites with differing human impact in the Philippines. At both sites, genetic diversity increased over time, with contemporary samples having significantly higher Watterson's Θ than historical samples. This diversity increase …

Efficacy Of Stress Acclimation Techniques In Coastal Wetland Plants (Spartina Alterniflora And S. Patens): Implications For Restoration And Nursery Production, Taylor M. Sloey, Kylie D. Gieser, Kaitlyn Pounders, Sofía E. Báez, Jennifer L. Whytlaw

Biological Sciences Faculty Publications

The implementation of coastal nature-based features, created wetlands, and wetland restoration has increased globally over recent years. Many of these projects have been successful in meeting their goals, however, when projects fail, it is often attributed to mortality of transplanted vegetation. Transplant mortality may be due to inappropriate timing, poor site selection, or abiotic stressors associated with transplant shock. Science-backed guidelines have been well established in many coastal regions regarding site specifications and species selection, but nursery practices for reducing transplant shock remain inconsistent. In this study, we tested a combination of four salinity acclimation treatments and two inundation acclimation …

Symbiodiniaceae Shifts Over The Last Decade On The Hottest Coral Reefs On Earth, Anna Fiesinger, Rachel Alderdice, Luigi Colin, Hannah Manns, Gabriela Perna, Kathryn H. Stankiewicz, Jacob J. Valenzuela, Line K. Bay, Daniel J. Barshis, Nitin S. Baliga, Iliana B. Baums, John A. Burt, Christian R. Voolstra

Biological Sciences Faculty Publications

Corals in the Persian/Arabian Gulf (PAG) are resilient to various stressors, whose levels exceed those of coral reefs globally. These corals thereby offer insight into mechanisms underlying thermal resilience, e.g., regarding the role of endosymbiotic microalgae in the family Symbiodiniaceae. Previous studies have identified the thermotolerant species Cladocopium thermophilum as broadly associated with corals in the southern PAG. However, algal-host specificity at the within-species level and the temporal stability of these associations are not well understood. Here we sampled two dominant stony corals (Porites harrisoni, n = 119 and Platygyra daedalea, n = 79) at three sites …

Description Of All Stages Of A New Tick Species From California Haemaphysalis Vespertina (Acari: Ixodidae), With Redescription Of H. Leporispalustris Packard, 1869 Adults And Phylogenetic Relationships Among Related U.S. Taxa, Andrea Egizi, Santiago Nava, Angie Nakano, Megan E. M. Saunders, Lauren P. Maestas, Autumn D. Angelus, Bruce Noden, Robyn M. Nadolny, Waheed I. Bajwa, Charles Lubelcyzk, Chanakya R. Bhosale, Susan Paskewitz, Holly D. Gaff, Lorenza Beati

Biological Sciences Faculty Publications

All active stages of Haemaphysalis vespertina sp. nov. (Acari: Ixodidae), a tick previously identified as H. leporispalustris Packard, 1869, are described from specimens collected on the vegetation and from leporids in California and Oregon. The adults of H. leporispalustris Packard, 1969 are redescribed based on type material. Adults of the two species can be distinguished by their overall size, the dorsal shape of palpal segment II, the number and shape of dorsal and ventral setae on palpal segment II, the number of spurs on coxae II, the length of setae on scutum, legs and coxae, and the pattern of scutal …

Dengue Virus Modulates Critical Cell Cycle Regulatory Proteins In Human Megakaryocyte Cells, Swarnendu Basak, Shovan Dutta, Supreet Khanal, Girish Neelakanta, Hameeda Sultana

Biological Sciences Faculty Publications

Suppression of human megakaryocytes by dengue virus (DENV) infection significantly reduces the platelet count that eventually leads to thrombocytopenia, severe dengue and death. To understand DENV interactions with megakaryocytes, we investigated the cell cycle in leukemic human megakaryocytic in vitro cell line (MEG-01 cells). Megakaryocytes are known for complex endomitotic cell cycle leading to their polyploidy state. Our study shows that DENV uses these polyploid cells for its replication. Understanding the modulation of DENV-mediated cell cycle regulation in megakaryocytes is therefore highly important. We show that DENV2 (serotype 2) infection significantly modulates cell cycle signaling. Our protein profile microarray data …

Heterotrophy Of Particulate Organic Matter Subsidies Contributes To Divergent Bleaching Responses In Tropical Sclaractinian Corals, Connor R. Love, Kelly E. Speare, Michael D. Fox, Veronica Z. Radice, Kelton W. Mcmahon, Gretchen E. Hofmann,, David L. Valentine, Marie E. Strader

Biological Sciences Faculty Publications

Heterotrophic feeding on plankton and particulate organic matter (POM) by tropical Scleractinian corals is known to aid in the resistance and recovery from thermally induced bleaching. However, the relative importance of heterotrophy in promoting bleaching resistance and recovery is likely to vary based on ecological context and the severity of heat stress. In 2019, the Pacific Island of Mo'orea experienced mass coral mortality during a widespread marine heatwave. Many Acropora hyacinthus colonies on the shallow reef slope (5 m) were resistant to bleaching, while colonies on the deeper fore reef (14 m) often bleached and subsequently recovered, despite similar thermal …

Seasonal Variability Of Surface Ocean Carbon Uptake And Chlorophyll-A Concentration In The West Antarctic Peninsula Over Two Decades, Jessica S. Turner, David R. Munro, Amanda Fay, Sharon Stammerjohn, Heather Kim, Oscar Schofield, Heidi Dierssen

OES Faculty Publications

The Southern Ocean plays a vital role in global CO₂ uptake, but the magnitude and even the sign of the flux remain uncertain, and the influence of phytoplankton phenology is underexplored. This study focuses on the West Antarctic Peninsula, a region experiencing rapid climate change, to examine shifts in seasonal carbon uptake. Using 20 years of in situ air-sea CO₂ flux and satellite-derived Chlorophyll-a, we observe that the seasonal cycles of both air-sea CO₂ flux and Chlorophyll-a intensify poleward. The amplitude of the seasonal cycle of the non-thermal component of surface ocean pCO₂ increases with increasing latitude, while the amplitude …

Effect Of Family-Centered Care Interventions On Motor And Neurobehavior Development Of Very Preterm Infants: A Systematic Review And Meta-Analysis, Manasa Kolibylu Raghupathy, Shradha S. Parsekar, Shubha R. Nayak, Kalesh M. Karun, Sonia Khurana, Alicia J. Spittle, Leslie Edward S. Lewis, Bhamini Krishna Rao

Rehabilitation Sciences Faculty Publications

Aim

To assess the effectiveness of family-centered care (FCC) interventions on motor and neurobehavior development of very preterm infants.

Method

Randomized and quasi-randomized trials assessing the effect of FCC on motor and neurobehavioral outcomes in very preterm infants (28–32 wk gestation) were included. Five electronic databases and grey literature were searched from January 2010 to August 2022. Two reviewers independently screened the titles/abstracts and full texts, assessed the risk of bias, and extracted data. The Cochrane Risk of Bias 2.0 Tool and GRADE were used for risk and evidence certainty assessments. Meta-analysis or narrative synthesis was performed based on data …

Protein Marker-Dependent Drug Discovery Targeting Breast Cancer Stem Cells, Ashley V. Huang, Yali Kong, Kan Wang, Milton L. Brown, David Mu

Department of Biomedical and Translational Sciences Faculty Publications

Breast cancer is one of the most common cancers globally. Unfortunately, many patients with breast cancer develop resistance to chemotherapy and tumor recurrence, which is primarily driven by breast cancer stem cells (BCSCs). BCSCs behave like stem cells and can self-renew and differentiate into mature tumor cells, enabling the cancer to regrow and metastasize. Key markers like CD44 and aldehyde dehydrogenase-1 (ALDH1), along with pathways like Wingless-related integration site (Wnt), Notch, and Hedgehog, are critical to regulating this stem-like behavior of BCSCs and, thus, are being investigated as targets for various new therapies. This review summarizes marker-dependent strategies for targeting …

Lrtm Left-Right Transition Matrices For Molecular Interaction Prediction, Kaitlin Zheng, Guihua Duan, Mengyun Yang, Wei Wu, Yao-Hang Li, Jianxin Wang

Computer Science Faculty Publications

Molecular interactions are central to most biological processes. The discovery and identification of potential associations between molecules can provide insights into biological exploration, diagnostic and therapeutic interventions, and drug development. So far many relevant computational methods have been proposed, but most of them are usually limited to specific domains and rely on complex preprocessing procedures, which restricts the models’ ability to be applied to other tasks. Therefore, it remains a challenge to explore a generalized approach to accurately predicting potential associations. In this study, We propose Left-Right Transition Matrices (LRTM) for molecular interaction prediction. From the perspective on the diffusion …

Heterogeneous Clustering Of Multiomics Data For Breast Cancer Subgroup Classification And Detection, Joseph Pateras, Musaddiq Lodi, Pratip Rana, Preetam Ghosh

Computer Science Faculty Publications

The rapid growth of diverse -omics datasets has made multiomics data integration crucial in cancer research. This study adapts the expectation–maximization routine for the joint latent variable modeling of multiomics patient profiles. By combining this approach with traditional biological feature selection methods, this study optimizes latent distribution, enabling efficient patient clustering from well-studied cancer types with reduced computational expense. The proposed optimization subroutines enhance survival analysis and improve runtime performance. This article presents a framework for distinguishing cancer subtypes and identifying potential biomarkers for breast cancer. Key insights into individual subtype expression and function were obtained through differentially expressed gene …

Foundation Models In Bioinformatics, Fei Guo, Renchu Guan, Yaohang Li, Qi Liu, Xiaowo Wang, Can Yang, Jianxin Wang

Computer Science Faculty Publications

With the adoption of foundation models (FMs), artificial intelligence (AI) has become increasingly significant in bioinformatics and has successfully addressed many historical challenges, such as pre-training frameworks, model evaluation and interpretability. FMs demonstrate notable proficiency in managing large-scale, unlabeled datasets, because experimental procedures are costly and labor intensive. In various downstream tasks, FMs have consistently achieved noteworthy results, demonstrating high levels of accuracy in representing biological entities. A new era in computational biology has been ushered in by the application of FMs, focusing on both general and specific biological issues. In this review, we introduce recent advancements in bioinformatics FMs …

Gramseq-Dta: A Grammar-Based Drug-Target Affinity Prediction Approach Fusing Gene Expression Information, Kasul Debnath, Pratip Rana, Preetam Ghosh

Computer Science Faculty Publications

Drug–target affinity (DTA) prediction is a critical aspect of drug discovery. The meaningful representation of drugs and targets is crucial for accurate prediction. Using 1D string-based representations for drugs and targets is a common approach that has demonstrated good results in drug–target affinity prediction. However, these approach lacks information on the relative position of the atoms and bonds. To address this limitation, graph-based representations have been used to some extent. However, solely considering the structural aspect of drugs and targets may be insufficient for accurate DTA prediction. Integrating the functional aspect of these drugs at the genetic level can enhance …

A Data-Driven Sliding-Window Pairwise Comparative Approach For The Estimation Of Transmission Fitness Of Sars-Cov-2 Variants And The Construction Of The Evolution Fitness Landscape, Md Jubair Pantho, Richard Annan, Landen Alexander Bauder, Sophia Huang, Letu Qingge, Hong Qin

Computer Science Faculty Publications

Estimating the transmission fitness of SARS-CoV-2 variants and understanding their evolutionary fitness trends are important for epidemiological forecasting. Existing methods are often constrained by their parametric natures and do not satisfactorily align with the observations during COVID-19. Here, we introduce a sliding-window data-driven pairwise comparison method, the differential population growth rate (DPGR) that uses viral strains as internal controls to mitigate sampling biases. DPGR is applicable in time windows in which the logarithmic ratio of two variant subpopulations is approximately linear. We apply DPGR to genomic surveillance data and focus on variants of concern (VOCs) in multiple countries and regions. …

Cath-Ddg: Towards Robust Mutation Effect Prediction On Protein-Protein Interactions Out Of Cath Homologous Superfamily, Guanglei Yu, Xuehua Bi, Teng Ma, Yaohang Li, Jianxin Wang

Computer Science Faculty Publications

Motivation: Protein-protein interactions (PPIs) are fundamental aspects in understanding biological processes. Accurately predicting the effects of mutations on PPIs remains a critical requirement for drug design and disease mechanistic studies. Recently, deep learning models using protein 3D structures have become predominant for predicting mutation effects. However, significant challenges remain in practical applications, in part due to the considerable disparity in generalization capabilities between easy and hard mutations. Specifically, a hard mutation is defined as one with its maximum TM-score < 0.6 when compared to the training set. Additionally, compared to physics-based approaches, deep learning models may overestimate performance due to potential data leakage.

Results: We propose new training/test splits that mitigate data leakage according to the CATH homologous superfamily. Under the constraints of physical …

Benchmarking Batch-Effect Correction Methods Towards The Construction Of A Triple-Negative Breast Cancer Cell Atlas, Peter Scheible, Amy H. Tang, Jing He, Jiangwen Sun

Computer Science Faculty Publications

Triple-negative breast cancer (TNBC) requires detailed cellular mapping given its aggressive nature, immense tumor heterogeneity and genetic diversity. We integrated 156,794 cells from six scRNA-seq datasets—including tumors, metastases, and cell lines—to build a TNBC scRNA cell atlas, focusing on batch effect mitigation while maintaining biological and molecular details. Preprocessing f ilters noise, normalizes data, and leverages PCA for integration readiness. We utilized scANVI, a semi-supervised tool, to align datasets, preserving TNBC’s complex tumor heterogeneity via marker annotations [1]. UMAPs demonstrate biological clustering in integrated data, contrasted with datasetdriven unintegrated patterns. Assessments verifying effective batch correction. This method aligns with NASA’s …

Coldstartcpi: Induced-Fit Theory-Guided Dti Predictive Model With Improved Generalization Performance, Qichang Zhao, Haochen Zhao, Linyuan Gao, Kai Zheng, Yajie Li, Qiao Ling, Jing Tang, Yaohang Li, Jianxin Wang

Computer Science Faculty Publications

Predicting compound-protein interactions (CPIs) plays a crucial role in drug discovery. Traditional methods, based on the key-lock theory and rigid docking, often fail with novel compounds and proteins due to their inability to account for molecular flexibility and the high sparsity of CPI data. Here, we introduce ColdstartCPI, a framework inspired by induced-fit theory, which leverages unsupervised pre-training features and a Transformer module to learn both compound and protein characteristics. ColdstartCPI treats proteins and compounds as flexible molecules during inference, aligning with biological insights. It outperforms state-of-the-art sequence-based models, particularly for unseen compounds and proteins, and shows strong generalization capability …

A Survey On Deep Learning For Drug-Target Binding Prediction: Models, Benchmarks, Evaluation, And Case Studies, Kusal Debnath, Pratip Rana, Preetam Ghosh

Computer Science Faculty Publications

Conventional drug discovery is expensive, time-consuming, and prone to failure. Artificial intelligence has become a potent substitute over the last decade, providing strong answers to challenging biological issues in this field. Among these difficulties, drug-target binding (DTB) is a key component of drug discovery techniques. In this context, drug-target affinity and drug–target interaction are complementary and essential frameworks that work together to improve our comprehension of DTB dynamics. In this work, we thoroughly analyze the most recent deep learning models, popular benchmark datasets, and assessment metrics for DTB prediction. We look at the paradigm shift in the development of drug …

A Bibliographic And Topic Modeling Analysis Of The P-Adic Theory Literature Using Latent Dirichlet Allocation, Humberto Llinás, Ismael Gutiérrez, Anselmo Torresblanca, Javier De La Hoz, Brian Llinás

Computer Science Faculty Publications

P-adic analysis, introduced by Kurt Hensel in the early 20th century, has developed into a fundamental area of mathematical research with broad applications in number theory, algebraic geometry, and mathematical physics. This study aims to examine the thematic evolution and scholarly impact of p-adic research through a comprehensive topic modeling and bibliometric analysis. Using classical bibliometric techniques (e.g., performance analysis, co-authorship, and co-citation networks) combined with Latent Dirichlet Allocation (LDA), we analyzed 7388 peer-reviewed documents published between 1965 and 2024. The computational workflow was conducted using R (version 4.4.1) and VOSviewer (version 1.6.20), which enabled the identification of 20 distinct …

Benchmarking And Improving Foundation Model Dietary Estimates From Meal Images, Yongcheng Mu, Jiangwen Sun, Jing He

Computer Science Faculty Publications

Accurate quantifying dietary contents, such as calories, proteins, carbohydrates, and fats, from an image of a meal plate is vital for managing diabetes. Recently, Large Multimodal Models (LMMs) have excelled in complex vision-language tasks due to their use of very large, highly diverse data. This study benchmarked the use of seven LMMs that include full and lightweight models of GPT, Gemini, and Llama for nutrition estimation based on Google's Nutrition5k dataset and our own phone-collected DonateAndLearn dataset. We analyzed the performance of LMMs and the RGB-D fusion model, in which the RGB-D model was specifically trained using Nutrition5k data. On …

Deepssetracer 2.0: Improved Deep Learning Model Performance For Protein Secondary Structure Segmentation From Cryo-Em Maps, Bryan Hawickhorst, Thu Nguyen, Willy Wriggers, Jiangwen Sun, Jing He

Computer Science Faculty Publications

DeepSSETracer is a method for segmenting protein secondary structure from medium-resolution (5-10Å) cryogenic electron microscopy (cryo-EM) density maps. We conducted experiments and ablation studies to examine the effects of normalization methods, max-pooling, activation functions, and loss calculation region on DeepSSETracer. By combining multiple technical improvements, the performance of the new version, DeepSSETracer 2.0, was significantly enhanced compared to DeepSSETracer 1.1. On a set of 77 test cases, the weighted average per-voxel F1 score increased from 62.1% to 70.3% for helix detection, and from 47.8% to 62.5% for β-sheet detection. While each of the five modifications in the network enhanced the …

Icu-Length Of Stay Prediction On Electronic Health Records Using Graph Neural Networks And Homogeneous Similarity Graphs, Ahmad F. Al Musawi, Pratip Rana, Sibtanu Raha, Joshua Braunstein, William C. Sleeman Iv, Rishabh Kapoor, Preetam Ghosh

Computer Science Faculty Publications

Predicting the length of stay (LoS) is important for hospital administration, as it helps allocate proper resources, such as bed management and hospital staffing. Patients' Electronic Health Records (EHRs) contain highly relevant data for LoS prediction; however, their integration and effective use in predictive modeling for accurately estimating LoS remain challenging. To address this, we propose a homogeneous Graph Neural Network (GNN)-based framework for predicting LoS. This method employs a comprehensive data fusion strategy based on the hospital Visit-based Similarity Graph (VSG), which integrates diverse multi-modal clinical features into a coherent, homogeneous graph representation. Next, this VSG is fed into …

Humans Vs. Llms On Open Domain Scientific Claim Verification: A Baseline Study, Benjamin Curtis, Stefania Dzhaman, Matthew Maisonave, Jian Wu

Computer Science Faculty Publications

Verifying scientific claims is challenging for the general public because most people lack domain knowledge. Manual verification by subject domain experts is accurate, but it is obviously not scalable to meet the rising number of scientific claims on the Web. Whether the emerging large language models and large reasoning models can be used for scientific claim verification, and how their performances compare to humans, are still research questions. To this end, we developed a new benchmark MSVEC2 that consists of 138 claims from credible fact verification websites and science news outlets. Two tasks were given to both human and LLM …