检索结果-内蒙古大学图书馆

Devider: Long-Read Reconstruction of Many Diverse Haplotypes 29th

学校读者我要写书评

暂无评论

Devider: Long-Read Reconstruction of Many Diverse Haplotype...

29th International Conference on Research in computational Molecular Biology, RECOMB 2025

作者： Shaw, Jim Boucher, Christina Yu, Yun William Noyes, Noelle Li, Heng Department of Data Science Dana-Farber Cancer Institute BostonMA02215 United States Department of Biomedical Informatics Harvard Medical School BostonMA02215 United States Department of Computer and Information Science and Engineering University of Florida GainesvilleFL32611 United States Ray and Stephanie Lane Computational Biology Department Carnegie Mellon University PittsburghPA15213 United States Department of Veterinary Population Medicine University of Minnesota St. PaulMN55421 United States

ISBN: (纸本)9783031902512

Reconstructing haplotypes through sequencing of a mixture of similar sequences is a fundamental problem. Long-read sequencing technologies can connect distant alleles to disentangle similar haplotypes, but handling elevated sequencing error rates requires specialized techniques. We present devider, an algorithm for haplotyping small sequences—such as viruses or genes—from long-read sequencing. devider uses a positional de Bruijn graph with sequence-to-graph alignment on an alphabet of informative alleles to provide a fast assembly-inspired approach compatible with various long-read sequencing technologies. Benchmarking on synthetic mixtures of antimicrobial resistance (AMR) genes showed that devider recovered 83% of haplotypes, 23% points higher than the next best method. On real PacBio and Nanopore datasets, devider recapitulates previously known results in seconds, disentangling a bacterial community with >10 strains and an HIV-1 co-infection dataset. We used devider to investigate the within-host diversity of a long-read bovine gut metagenome enriched for AMR genes, discovering a history of recombination for diverse AMR gene haplotypes and showcasing devider ’s ability to unveil ecological signals for heterogeneous mixtures. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Mammals

Transformer-based interpretable multi-modal data fusion for skin lesion classification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cheslerean-Boghiu, Theodor Fleischmann, Melia Willem, Theresa Lasser, Tobias The Group for Computational Imaging and Inverse Problems Department of Informatics School of Computation Information and Technology Munich Institute of Biomedical Engineering The Technical University of Munich Germany The Department of Dermatology and Allergy University Hospital LMU Munich Munich Germany The Institute of History and Ethics in Medicine School of Medicine Munich Germany The Department of Science Technology and Society School of Social Sciences and Technology Technical University of Munich Munich Germany

A lot of deep learning (DL) research these days is mainly focused on improving quantitative metrics regardless of other factors. In human-centered applications, like skin lesion classification in dermatology, DL-driven clinical decision support systems are still in their infancy due to the limited transparency of their decision-making process. Moreover, the lack of procedures that can explain the behavior of trained DL algorithms leads to almost no trust from clinical physicians. To diagnose skin lesions, dermatologists rely on visual assessment of the disease and the data gathered from the patient’s anamnesis. Data-driven algorithms dealing with multi-modal data are limited by the separation of feature-level and decision-level fusion procedures required by convolutional architectures. To address this issue, we enable single-stage multi-modal data fusion via the attention mechanism of transformer-based architectures to aid in diagnosing skin diseases. Our method beats other state-of-the-art single- and multimodal DL architectures in image-rich and patient-data-rich environments. Additionally, the choice of the architecture enables native interpretability support for the classification task both in the image and metadata domain with no additional modifications necessary. Copyright © 2023, The Authors. All rights reserved.

关键词： Dermatology

Representing and extending ensembles of parsimonious evolutionary histories with a directed acyclic graph

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dumm, Will Barker, Mary Howard-Snyder, William DeWitt, William S. Matsen, Frederick A. Computational Biology Program Fred Hutchinson Cancer Research Center SeattleWA United States Howard Hughes Medical Institute Computational Biology Program Fred Hutchinson Cancer Research Center SeattleWA United States Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States Department of Electrical Engineering and Computer Sciences University of California BerkeleyCA United States Department of Genome Sciences University of Washington SeattleWA United States Department of Statistics University of Washington SeattleWA United States

In many situations, it would be useful to know not just the best phylogenetic tree for a given data set, but the collection of high-quality trees. This goal is typically addressed using Bayesian techniques, however, current Bayesian methods do not scale to large data sets. Furthermore, for large data sets with relatively low signal one cannot even store every good tree individually, especially when the trees are required to be bifurcating. In this paper, we develop a novel object called the "history subpartition directed acyclic graph" (or "history sDAG" for short) that compactly represents an ensemble of trees with labels (e.g. ancestral sequences) mapped onto the internal nodes. The history sDAG can be built efficiently and can also be efficiently trimmed to only represent maximally parsimonious trees. We show that the history sDAG allows us to find many additional equally parsimonious trees, extending combinatorially beyond the ensemble used to construct it. We argue that this object could be useful as the "skeleton" of a more complete uncertainty *** Codes 92-08 (Primary) 92B10, 92-04 (Secondary) Copyright © 2023, The Authors. All rights reserved.

关键词： Phylogenetic

Wait, but Tylenol is Acetaminophen… Investigating and Improving Language Models' Ability to Resist Requests for Misinformation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen Gao, Mingye Sasse, Kuleen Hartvigsen, Tom Anthony, Brian Fan, Lizhou Aerts, Hugo Gallifant, Jack Bitterman, Danielle Program Mass General Brigham Harvard Medical School BostonMA United States Department of Radiation Oncology Brigham and Women’s Hospital Dana-Farber Cancer Institute BostonMA United States Computational Health Informatics Program Boston Children’s Hospital Harvard Medical School BostonMA United States Massachusetts Institute of Technology CambridgeMA United States Johns Hopkins University BaltimoreMD United States Department of Data Science University of Virginia CharlottesvilleVA United States Radiology and Nuclear Medicine GROW & CARIM Maastricht University Netherlands

Background: Large language models (LLMs) are trained to follow directions, but this introduces a vulnerability to blindly comply with user requests even if they generate wrong information. In medicine, this could accelerate the generation of misinformation that impacts human well-being. Objectives/Methods: We analyzed compliance to requests to generate misleading content about medications in settings where models know the request is illogical. We investigated whether in-context directions and instruction-tuning of LLMs to prioritize logical reasoning over compliance reduced misinformation risk. Results: While all frontier LLMs complied with misinformation requests, both prompt-based and parameter-based approaches can improve the detection of logic flaws in requests and prevent the dissemination of medical misinformation. Conclusion: Shifting LLMs to prioritize logic over compliance could reduce risks of exploitation for medical misinformation. © 2024, CC BY-NC-ND.

关键词：

MPCC: Matching Priors and Conditionals for Clustering 16th

学校读者我要写书评

暂无评论

MPCC: Matching Priors and Conditionals for Clustering

16th European Conference on Computer Vision, ECCV 2020

作者： Astorga, Nicolás Huijse, Pablo Protopapas, Pavlos Estévez, Pablo Department of Electrical Engineering Universidad de Chile Santiago Chile Informatics Institute Faculty of Engineering Sciences Universidad Austral de Chile Valdivia Chile Institute for Applied Computational Science Harvard University Cambridge United States Millennium Institute of Astrophysics Santiago Chile

ISBN: (纸本)9783030585914

Clustering is a fundamental task in unsupervised learning that depends heavily on the data representation that is used. Deep generative models have appeared as a promising tool to learn informative low-dimensional data representations. We propose Matching Priors and Conditionals for Clustering (MPCC), a GAN-based model with an encoder to infer latent variables and cluster categories from data, and a flexible decoder to generate samples from a conditional latent space. With MPCC we demonstrate that a deep generative model can be competitive/superior against discriminative methods in clustering tasks surpassing the state of the art over a diverse set of benchmark datasets. Our experiments show that adding a learnable prior and augmenting the number of encoder updates improve the quality of the generated samples, obtaining an inception score of 9.49 ± 0.15 and improving the Fréchet inception distance over the state of the art by a 46.9 % in CIFAR10. © 2020, Springer Nature Switzerland AG.

关键词： Signal encoding

Exploring Regression and Classification in Big Data with Deep Learning

学校读者我要写书评

暂无评论

Exploring Regression and Classification in Big Data with Dee...

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Ravindra Pandey Aruna Sri Rongali S. Gopinath Nilesh Anute Forda Nama Sachin Pund Department - Management Hult International Business School Doctoral Information Technology/Information Technology Emphasis/Information Technology University of The Cumberlands US Department of Electronics And Communication Engineering Karpagam Institute of Technology Coimbatore Management ASM's Institute of Business Management and Research Pune Department of Informatics Doctoral Program of Environtmental Science University of Lampung Bandar Lampung Department of Industrial Engineering Shri Ramdeobaba College of Engineering and Management Nagpur Maharashtra India

Deep gaining knowledge is a synthetic intelligence approach used to recognize complex facts. It uses many facts to recognize the complicated relationships between various factors. With deep learning, models can be built which might be capable of understanding the complicated patterns within big datasets. In this paper, we can explore using deep mastering in regression and type tasks on large datasets. In particular, we can use deep learning strategies to build a regression model that predicts a target value primarily based on the functions in a massive dataset and a classification version that can classify an object into one of the many classes of an extensive dataset. We can then discuss the overall performance of the fashions in comparison to standard models and talk about capability areas for development. Moreover, we will analyze the scalability of deep mastering strategies used on large datasets and discuss exceptional practices for building deep mastering fashions on massive datasets. Finally, we will summarize our findings and offer our conclusions approximately the use of deep studying in regression and type obligations on large datasets.

关键词：

Towards Fabrication of Next-Generation Physical Sensors Through Integrating Suspended Sub-Micron Silicon Nanowires with Microelectromechanical Systems

学校读者我要写书评

暂无评论

Towards Fabrication of Next-Generation Physical Sensors Thro...

IEEE SENSORS

作者： Basit Ali Mehdi Bostan Shirin Muhammad Muzammil Ege Nacarkucuk Sina Zare Pakzad Umut Kerimzade B. Erdem Alaca Department of Mechanical Engineering Koç University Istanbul Turkey Computational Sciences and Engineering Program Koç University Istanbul Turkey Institute of Sensor and Actuator Systems TU Wien Austria Christian Doppler Laboratory for Piezoelectric Silicon MEMS with Enhanced Sensitivity and Responsivity Institute of Sensor and Actuator Systems TU Wien Austria nSTAR-Koç University Nanofabrication and Nanocharacterization Center for Scientific and Technological Advanced Research Koç University Istanbul Turkey Surface Science and Technology Center (KUYTAM) Koç University Istanbul Turkey

ISBN: (数字)9798350363517

ISBN: (纸本)9798350363524

Silicon nanowires possess superior mechanical, electrical, and optical properties, making them ideal for next-generation sensors. This study presents a scalable technology for monolithic fabrication of sub-micron silicon nanowires with micro electromechanical systems, achieving integration of suspended sub-micron silicon nanowires within microelectromechanical systems up to 80 μm thick on Si substrates, with high yield and repeatability. The technological approach is validated on silicon-on-insulator substrates, followed by electromechanical characterization via electrical probe measurements and vibrational testing for performance validation. The presented technology is promising for the potential development of next-generation high-performance physical sensors such as accelerometers and gyroscopes.

关键词： Microelectromechanical systems Sensor phenomena and characterization Vibration measurement Silicon Sensor systems Nanowires Optical sensors Next generation networking Substrates Electromechanical sensors

Estimation of the main air pollutants from different biomasses under combustion atmospheres by artificial neural networks

学校读者我要写书评

暂无评论

Chemosphere 2024年 352卷 141484页

作者： Monteiro, Thalyssa Oliveira Alves, Pedro Augusto Araújo da Silva de Almeida Nava Barradas Filho, Alex Oliveira Villa-Vélez, Harvey Alexander Cruz, Glauber Postgraduate Program in Mechanical Engineering (PPGMEC) Department of Mechanics and Materials Federal Institute of Education Science and Technology of Maranhão (IFMA) Maranhão São Luís Brazil Postgraduate Program in Computer Science and Computational Mathematics (PPG-CCMC) Department of Computer Science University of São Paulo (USP) São Carlos São Paulo Brazil Data Analysis and Artificial Intelligence Laboratory (DARTi) Department of Computational Engineering Federal University of Maranhão (UFMA) Maranhão São Luís Brazil Department of Chemical Engineering Federal University of Maranhão (UFMA) Maranhão São Luís Brazil Processes and Thermal Systems Laboratory (LPSisTer) Department of Mechanical Engineering Federal University of Maranhão (UFMA) Maranhão São Luís Brazil

The production of biofuels to be used as bioenergy under combustion processes generates some gaseous emissions (CO, CO2, NOx, SOx, and other pollutants), affecting living organisms and requiring careful assessments. H... 详细信息

The production of biofuels to be used as bioenergy under combustion processes generates some gaseous emissions (CO, CO₂, NO_x, SO_x, and other pollutants), affecting living organisms and requiring careful assessments. However, obtaining such information experimentally for data evaluation is costly and time-consuming and its in situ obtaining for regional biomasses (e.g., those from Northeast Brazil (NEB) is still a major challenge. This paper reports on the application of artificial neural networks (ANNs) for the prediction of the main air pollutants (CO, CO₂, NO, and SO₂) produced during the direct biomass combustion (N₂/O₂:80/20%) with the use of ultimate analysis (carbon, hydrogen, nitrogen, sulfur, and oxygen). 116 worldwide biomasses were used as input data, which is a relevant alternative to overcome the lack of experimental resources in NEB and obtain such information. Cross-validation was conducted with k-fold to optimize the ANNs and performance was analyzed with the use of statistical errors for accuracy assessments. The results showed an acceptable statistical performance for all architectures of ANNs, with 0.001–12.41% MAPE, 0.001–5.82 mg Nm⁻³ MAE, and 0.03–52.30 mg Nm⁻³ RMSE, highlighting the high precision of the emissions studied. On average, the differences between predicted and real values for CO, CO₂, NO, and SO₂ emissions from NEB biomasses were approximately 0.01%, 10⁻⁶%, 0.14%, and 0.05%, respectively. Pearson coefficient provided consistent results of concentration of the ultimate analysis in relation to the emissions studied and effectiveness of the test set in the developed models. © 2024 Elsevier Ltd

关键词： Brazilian northeastern Environmental statistics Evaluation metrics Gaseous emissions Predictive models Thermoconversion

Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Peng Wang, Jianmin Li, Chunyan Wang, Zixu Liu, Yiping Sun, Siqi Lin, Jianxin Wei, Leyi Cai, Xibao Lai, Houtim Liu, Wei Wang, Longyue Liu, Yuansheng Zeng, Xiangxiang College of Information Science and Engineering Hunan University Changsha China The Interdisciplinary Graduate Program in Integrative Biotechnology Yonsei University Incheon21983 Korea Republic of School of Informatics Yunnan Normal University Kunming650500 China Department of Computer Science University of Tsukuba Tsukuba3058577 Japan Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China Shanghai AI Laboratory Shanghai200232 China Centre for Artificial Intelligence driven Drug Discovery Faculty of Applied Science Macao Polytechnic University China School of Informatics Xiamen University Xiamen China Tencent AI Lab China

While various models and computational tools have been proposed for structure and property analysis of molecules, generating molecules that conform to all desired structures and properties remains a challenge. Here, we introduce a multi-constraint molecular generation large language model, TSMMG, which, akin to a student, incorporates knowledge from various small models and tools, namely, the 'teachers'. To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers', enabling it to generate novel molecules that conform to the descriptions through various text prompts. We experimentally show that TSMMG remarkably performs in generating molecules meeting complex, natural language-described property requirements across two-, three-, and four-constraint tasks, with an average molecular validity of over 99% and success ratio of 82.58%, 68.03%, and 67.48%, respectively. The model also exhibits adaptability through zero-shot testing, creating molecules that satisfy combinations of properties that have not been encountered. It can comprehend text inputs with various language styles, extending beyond the confines of outlined prompts, as confirmed through empirical validation. Additionally, the knowledge distillation feature of TSMMG contributes to the continuous enhancement of small models, while the innovative approach to dataset construction effectively addresses the issues of data scarcity and quality, which positions TSMMG as a promising tool in the domains of drug discovery and materials science. Copyright © 2024, The Authors. All rights reserved.

关键词： Students