检索结果-内蒙古大学图书馆

Safeguarding authenticity for mitigating the harms of generative AI: Issues, research agenda, and policies for detection, fact-checking, and ethical AI

引用

ISCIENCE 2024年第2期27卷 108782页

作者： Hamed, Ahmed Abdeen Zachara-Szymanska, Malgorzata Wu, Xindong Sano Ctr Computat Med Network Med & AI Czarnowiejska 36 Bldg C5 PL-30072 Krakow Poland Jagiellonian Univ Fac Int & Polit Studies Wladys Lawa Reymonta 4 PL-30059 Krakow Poland Zhejiang Lab Res Ctr Knowledge Engn Kechuang Ave Hangzhou 311121 Zhejiang Peoples R China

As the influence of transformer-based approaches in general and generative artificial intelligence (AI) in particular continues to expand across various domains, concerns regarding authenticity and explainability are on the rise. Here, we share our perspective on the necessity of implementing effective detection, verification, and explainability mechanisms to counteract the potential harms arising from the proliferation of AI-generated inauthentic content and science. We recognize the transformative potential of generative AI, exemplified by ChatGPT, in the scientific landscape. However, we also emphasize the urgency of addressing associated challenges, particularly in light of the risks posed by disinformation, misinformation, and unreproducible science. This perspective serves as a response to the call for concerted efforts to safeguard the authenticity of information in the age of AI. By prioritizing detection, fact-checking, and explainability policies, we aim to foster a climate of trust, uphold ethical standards, and harness the full potential of AI for the betterment of science and society.

关键词： Biocomputational method bioinformatics Biological sciences computational bioinformatics Natural sciences Neural networks Artificial intelligence Artificial intelligence applications

来源：评论

学校读者我要写书评

暂无评论

Prediction of postpartum prediabetes by machine learning methods in women with gestational diabetes mellitus

引用

ISCIENCE 2023年第10期26卷 107846页

作者： Parkhi, Durga Periyathambi, Nishanthi Ghebremichael-Weldeselassie, Yonas Patel, Vinod Sukumar, Nithya Siddharthan, Rahul Narlikar, Leelavati Saravanan, Ponnusamy Univ Warwick Div Hlth Sci Populat Evidence & Technol Coventry England George Eliot Hosp Dept Diabet Endocrinol & Metab Nuneaton England Open Univ Sch Math & Stat Milton Keynes England Inst Math Sci Dept Computat Biol Chennai India Indian Inst Sci Educ & Res Dept Data Sci Pune India

Early onset of type 2 diabetes and cardiovascular disease are common complications for women diagnosed with gestational diabetes. Prediabetes refers to a condition in which blood glucose levels are higher than normal, but not yet high enough to be diagnosed as type 2 diabetes. Currently, there is no accurate way of knowing which women with gestational diabetes are likely to develop postpartum prediabetes. This study aims to predict the risk of postpartum prediabetes in women diagnosed with gestational diabetes. Our sparse logistic regression approach selects only two variables - antenatal fasting glucose at OGTT and HbA1c soon after the diagnosis of GDM - as relevant, but gives an area under the receiver operating characteristic curve of 0.72, outperforming all other methods. We envision this to be a practical solution, which coupled with a targeted follow-up of high-risk women, could yield better cardiometabolic outcomes in women with a history of GDM.

关键词： Endocrinology Reproductive medicine Female reproductive endocrinology computational bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Polyvalent guide RNAs for CRISPR antivirals

引用

ISCIENCE 2022年第11期25卷 105333页

作者： Bagchi, Rammyani Tinker-Kulberg, Rachel Salehin, Mohammad Supakar, Tinku Chamberlain, Sydney Ligaba-Osena, Ayalew Josephs, Eric A. Univ N Carolina Dept Nanosci Greensboro NC 27401 USA Univ N Carolina Dept Biol Greensboro NC 27401 USA

CRISPR effector Cas13 recognizes and degrades RNA molecules that are complementary to its guide RNA (gRNA) and possesses potential as an antiviral biotechnology because it can degrade viralmRNAandRNAgenomes. Because multiplexed targeting is a critical strategy to improve viral suppression, we developed a strategy to design of gRNAs where individual gRNAs have maximized activity at multiple viral targets, simultaneously, by exploiting the molecular biophysics of promiscuous target recognition by Cas13. These ``polyvalent'' gRNA sequences (``pgRNAs'') provide superior antiviral elimination across tissue/organ scales in a higher organism (Nicotiana benthamiana) compared to conventionally-designed gRNAs-reducing detectable viral RNA by >30-fold, despite lacking perfect complementarity with either of their targets and, when multiplexed, reducing viral RNA by >99.5%. Pairs of pgRNA-targetable sequences are abundant in the genomes of RNA viruses, and this work highlights the need for specific approaches to the challenges of targeting viruses in eukaryotes using CRISPR.

关键词： Biocomputational method computational bioinformatics Biological sciences tools

来源：评论

学校读者我要写书评

暂无评论

A multi-center performance assessment for automated histopathological classification and grading of glioma using whole slide images

引用

ISCIENCE 2023年第11期26卷 108041页

作者： Jin, Lei Sun, Tianyang Liu, Xi Cao, Zehong Liu, Yan Chen, Hong Ma, Yixin Zhang, Jun Zou, Yaping Liu, Yingchao Shi, Feng Shen, Dinggang Wu, Jinsong Fudan Univ Huashan Hosp Neurol Surg Dept Glioma Surg Div Shanghai 200040 Peoples R China Fudan Univ Huashan Hosp Natl Ctr Neurol Disorders Shanghai 200040 Peoples R China Shanghai United Imaging Intelligence Co Ltd Dept Res & Dev Shanghai 200030 Peoples R China Fudan Univ Huashan Hosp Dept Pathol Shanghai 200040 Peoples R China Wuhan Zhongji Biotechnol Co Ltd Wuhan 430206 Peoples R China Shandong First Med Univ Prov Hosp Dept Neurosurg Jinan 250021 Shandong Peoples R China ShanghaiTech Univ Sch Biomed Engn Shanghai 201210 Peoples R China Shanghai Clin Res & Trial Ctr Shanghai 201210 Peoples R China

Accurate pathological classification and grading of gliomas is crucial in clinical diagnosis and treatment. The application of deep learning techniques holds promise for automated histological pathology diagnosis. In this study, we collected 733 whole slide images from four medical centers, of which 456 were used for model training, 150 for internal validation, and 127 for multi-center testing. The study includes 5 types of common gliomas. A subtask-guided multi-instance learning image-to-label training pipeline was employed. The pipeline leveraged "patch prompting"for the model to converge with reasonable computational cost. Experiments showed that an overall accuracy of 0.79 in the internal validation dataset. The performance on the multi-center testing dataset showed an overall accuracy to 0.73. The findings suggest a minor yet acceptable performance decrease in multi-center data, demonstrating the model's strong generalizability and establishing a robust foundation for future clinical applications.

关键词： Cancer computational bioinformatics Health informatics Pathology

来源：评论

学校读者我要写书评

暂无评论

FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments

引用

ISCIENCE 2024年第1期27卷 108756页

作者： Yin, Zeyu Chen, Yu Hao, Yajie Pandiyan, Sanjeevi Shao, Jinsong Wang, Li Nantong Univ Sch Informat Sci & Technol Nantong 226001 Peoples R China Nantong Univ Res Ctr Intelligent Informat Technol Nantong 226001 Peoples R China

Compound-protein interaction (CPI) affinity prediction plays an important role in reducing the cost and time of drug discovery. However, the interpretability of how fragments function in CPI is impacted by the fact that current methods ignore the affinity relationships between fragments of compounds and frag-ments of proteins in CPI modeling. This article introduces an improved Transformer called FOTF-CPI (a Fusion of Optimal Transport Fragments compound-protein interaction prediction model). We use an optimal transport-based fragmentation approach to improve the model's understanding of compound and protein sequences. Additionally, a fused attention mechanism is employed, which combines the fea-tures of fragments to capture full affinity information. This fused attention redistributes higher attention scores to fragments with higher affinity. Experimental results show FOTF-CPI achieves an average 2% higher performance than other models on all three datasets. Furthermore, the visualization confirms the potential of FOTF-CPI for drug discovery applications.

关键词： Biocomputational method computational bioinformatics In silico biology

来源：评论

学校读者我要写书评

暂无评论

Selection for immune evasion in SARS-CoV-2 revealed by high-resolution epitope mapping and sequence analysis

引用

ISCIENCE 2023年第8期26卷 107394页

作者： N'Guessan, Arnaud Kailasam, Senthilkumar Mostefai, Fatima Poujol, Raphael Grenier, Jean-Christophe Ismailova, Nailya Contini, Paola De Palma, Raffaele Haber, Carsten Stadler, Volker Bourque, Guillaume Hussin, Julie G. Shapiro, B. Jesse Fritz, Jorg H. Piccirillo, Ciriaco A. McGill Univ Dept Microbiol & Immunol Montreal PQ Canada McGill Univ McGill Genome Ctr Montreal PQ Canada Canadian Ctr Computat Genom Montreal PQ Canada McGill Univ Dept Human Genet Montreal PQ Canada Montreal Heart Inst Res Ctr Montreal PQ Canada Univ Montreal Dept Biochim & Med Mol Montreal PQ Canada Univ Genoa Dept Internal Med Genoa Italy PEPperPRINT GmbH Heidelberg Germany Univ Montreal Dept Med Montreal PQ Canada McGill Univ McGill Univ Res Ctr Complex Traits MRCCT Montreal PQ Canada McGill Infect Dis & Immun Global Hlth Program Res Inst Hlth Ctr Montreal PQ Canada McGill Univ Dahdaleh Inst Med DIgM Montreal PQ Canada

Here, we exploit a deep serological profiling strategy coupled with an integrated, computational framework for the analysis of SARS-CoV-2 humoral immune responses. Applying a high-density peptide array (HDPA) spanning the entire proteomes of SARS-CoV-2 and endemic human coronaviruses allowed identification of B cell epitopes and relate them to their evolutionary and structural properties. We identify hotspots of pre-existing immunity and identify cross-reactive epitopes that contribute to increasing the overall humoral immune response to SARS-CoV-2. Using a public dataset of over 38,000 viral genomes from the early phase of the pandemic, capturing both inter- and within-host genetic viral diversity, we determined the evolutionary profile of epitopes and the differences across proteins, waves, and SARS-CoV-2 variants. Lastly, we show that mutations in spike and nucleocapsid epitopes are under stronger selection between than within patients, suggesting that most of the selective pressure for immune evasion occurs upon transmission between hosts.

关键词： Immunology Virology Structural biology computational bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Predicting miRNA-disease association through combining miRNA function and network topological similarities based on MINE

引用

ISCIENCE 2022年第11期25卷 105299页

作者： Cao, Buwen Li, Renfa Xiao, Sainan Deng, Shuguang Zhou, Xiangjun Zhou, Lang Hunan City Univ Coll Informat & Elect Engn Yiyang 413000 Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Key Lab Embedded & Cyber Phys Syst Changsha 410082 Peoples R China

Predicting associations between microRNAs (miRNAs) and diseases from the viewpoint of function modules has become increasingly popular However, existing methods obtained the relations between diseases and miRNAs only through the construction of similarity networks and neglected the complex network characteristic. In this paper, a new method named combining mirNA function similarities and network topology similarities based on module identification in networks (ComSim-MINE) was developed. Combined similarity is calculated from the harmonic mean between miRNA function similarities aid network topology similarities. Experimental results showed that ComSim-MINE can compete with several state-of-the-art weighted function module algorithms, such as ClusterONE, MCODE, NEMO, and SPICi, and achieved the satisfactory results in terms of the composite score of F-measure, sensitivity, and accuracy based on the generated miRNA function interaction network. From the analysis of case studies, some new findings obtained from our proposed method provide clinicians new clues for epidemic diseases, such as COVID-19.

关键词： Biological sciences bioinformatics computational bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Genetic overlap for ten cardiovascular diseases: A comprehensive gene-centric pleiotropic association analysis and Mendelian randomization study

引用

ISCIENCE 2023年第11期26卷 108150页

作者： Liu, Zeye Xu, Jing Tan, Jiangshan Li, Xiaofei Zhang, Fengwen Ouyang, Wenbin Wang, Shouzheng Huang, Yuan Li, Shoujun Pan, Xiangbin Natl Ctr Cardiovasc Dis Dept Struct Heart Dis Beijing 100037 Peoples R China Chinese Acad Med Sci & Peking Union Med Coll Fuwai Hosp Beijing 100037 Peoples R China Natl Hlth Commiss Key Lab Cardiovasc Regenerat Med Beijing 100037 Peoples R China Chinese Acad Med Sci Key Lab Innovat Cardiovasc Devices Beijing 100037 Peoples R China Chinese Acad Med Sci Fuwai Hosp Natl Clin Res Ctr Cardiovasc Dis Beijing 100037 Peoples R China Chinese Acad Med Sci & Peking Union Med Coll Natl Ctr Cardiovasc Dis Fuwai Hosp State Key Lab Cardiovasc Dis Beijing Peoples R China Chinese Acad Med Sci & Peking Union Med Coll Key Lab Pulm Vasc Med Natl Clin Res Ctr Cardiovasc Dis State Key Lab Cardiovasc DisFuwai HospNatl Ctr C Beijing 100037 Peoples R China Chinese Acad Med Sci & Peking Union Med Coll Fuwai Hosp Dept Cardiol Beijing Peoples R China Chinese Acad Med Sci & Peking Union Med Coll Fuwai Hosp Pediat Cardiac Surg Ctr State Key Lab Cardiovasc DisNatl Ctr Cardiovasc D Beijing Peoples R China

Recent studies suggest that pleiotropic effects may explain the genetic architecture of cardiovascular diseases (CVDs). We conducted a comprehensive gene-centric pleiotropic association analysis for ten CVDs using genome-wide association study (GWAS) summary statistics to identify pleiotropic genes and pathways that may underlie multiple CVDs. We found shared genetic mechanisms underlying the pathophysiology of CVDs, with over two-thirds of the diseases exhibiting common genes and single-nucleotide polymorphisms (SNPs). Significant positive genetic correlations were observed in more than half of paired CVDs. Additionally, we investigated the pleiotropic genes shared between different CVDs, as well as their functional pathways and distribution in different tissues. Moreover, six hub genes, including ALDH2, XPO1, HSPA1L, ESR2, WDR12, and RAB1A, as well as 26 targeted potential drugs, were identified. Our study provides further evidence for the pleiotropic effects of genetic variants on CVDs and highlights the importance of considering pleiotropy in genetic association studies.

关键词： Cardiovascular medicine Human Genetics Quantitative genetics computational bioinformatics Association analysis

来源：评论

学校读者我要写书评

暂无评论

Deep learning model of somatic hypermutation reveals importance of sequence context beyond hotspot targeting

引用

ISCIENCE 2022年第1期25卷 103668页

作者： Tang, Catherine Krantsevich, Artem MacCarthy, Thomas SUNY Stony Brook Dept Appl Math & Stat Stony Brook NY 11794 USA SUNY Stony Brook Laufer Ctr Phys & Quantitat Biol Stony Brook NY 11794 USA Merck & Co Inc Exploratory Sci Ctr Cambridge MA USA

B cells undergo somatic hypermutation (SHM) of the Immunoglobulin (Ig) variable region to generate high-affinity antibodies. SHM relies on the activity of activation-induced deaminase (AID), which mutates C>U preferentially targeting WRC (W=A/T, R=A/G) hotspots. Downstream mutations at WA Polymerase eta hotspots contribute further mutations. computational models of SHM can describe the probability of mutations essential for vaccine responses. Previous studies using short subsequences (k-mers) failed to explain divergent mutability for the same k-mer. We developed the DeepSHM (Deep learning on SHM) model using k-mers of size 5-21, improving accuracy over previous models. Interpretation of DeepSHM identified an extended WWRCT motif with particularly high mutability. Increased mutability was further associated with lower surrounding G content. Our model also discovered a conserved AGYCTGGGGG (Y=C/T) motif within FW1 of IGHV3 family genes with unusually high T>G substitution rates. Thus, a wider sequence context increases predictive power and identifies features that drive mutational targeting.

关键词： Biological sciences computational bioinformatics Immunology

来源：评论

学校读者我要写书评

暂无评论

Single-cell transcriptome and crosstalk analysis reveals immune alterations and key pathways in the bone marrow of knee OA patients

引用

ISCIENCE 2024年第9期27卷 110827页

作者： Chatterjee, Paramita Stevens, Hazel Y. Kippner, Linda E. Bowles-Welch, Annie C. Drissi, Hicham Mautner, Kenneth Yeago, Carolyn Gibson, Greg Roy, Krishnendu Georgia Inst Technol Parker H Petit Inst Bioengn & Biosci Marcus Ctr Therapeut Cell Characterizat & Mfg Atlanta GA 30332 USA Georgia Inst Technol Parker H Petit Inst Bioengn & Biosci Atlanta GA USA Emory Univ Sch Med Dept Orthopaed Atlanta GA 30322 USA Georgia Inst Technol Sch Biol Sci Atlanta GA 30332 USA Vanderbilt Univ Sch Engn Dept Biomed Engn Nashville TN 37235 USA Vanderbilt Univ Sch Med Dept Pathol Microbiol & Immunol Nashville TN 37235 USA Vanderbilt Univ Sch Engn Dept Chem & Biomol Engn Nashville TN 37235 USA

Knee osteoarthritis (OA) is a significant medical and economic burden. To understand systemic immune effects, we performed deep exploration of bone marrow aspirate concentrates (BMACs) from knee-OA patients via single-cell RNA sequencing and proteomic analyses from a randomized clinical trial (MILES: NCT03818737). We found significant cellular and immune alterations in the bone marrow, specifically in MSCs, T cells and NK cells, along with changes in intra-tissue cellular crosstalk during OA progression. Unlike previous studies focusing on injury sites or peripheral blood, our probe into the bone marrow-an inflammation and immune regulation hub-highlights remote organ impact of OA, identifying cell types and pathways for potential therapeutic targeting. Our findings highlight increased cellular senescence and inflammatory pathways, revealing key upstream genes, transcription factors, and ligands. Additionally, we identified significant enrichment in key biological pathways like PI3-AKT-mTOR signaling and IFN responses, showing their potentially crucial role in OA onset and progression.

关键词： Biopsy sample computational bioinformatics Transcriptomics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：