IF 4.2 3区生物学

Methods Pub Date : 2024-11-27 DOI: 10.1016/j.ymeth.2024.11.014

Jan Devan, Michaela Sandalova, Pamela Bitterli, Nick Herger, Tamara Mengis, Kenta Brender, Irina Heggli, Oliver Distler, Stefan Dudli

{"title":"Massively parallel flow-cytometry-based screening of hematopoietic lineage cell populations from up to 25 donors simultaneously.","authors":"Jan Devan, Michaela Sandalova, Pamela Bitterli, Nick Herger, Tamara Mengis, Kenta Brender, Irina Heggli, Oliver Distler, Stefan Dudli","doi":"10.1016/j.ymeth.2024.11.014","DOIUrl":"10.1016/j.ymeth.2024.11.014","url":null,"abstract":"<p><p>This study aimed to develop a method allowing high-dimensional and technically uniform screening of surface markers on cells of hematopoietic origin. High-dimensional screening of cell phenotypes is primarily the domain of single-cell RNA sequencing (RNAseq), which allows simultaneous analysis of the expression of thousands of genes in several thousands of cells. However, rare cell populations can often substantially impact tissue homeostasis or disease pathogenesis, and dysregulation of rare populations can easily be missed when only a few thousand cells are analyzed. With the presented methodological approach, it is possible to screen hundreds of markers on millions of cells in a technically uniform manner and thus identify and characterize changes in rare populations. We utilize the highly expressed markers CD45 on immune cells and CD71 on erythroid progenitors to create unique fluorescent barcodes on each of the 25 samples. Double-barcoded samples are co-stained with a broad immunophenotyping panel. The panel is designed in such a way that allows the addition of PE-labelled antibody, which was used for screening purposes. Multiplexed samples are divided into hundreds of aliquots and co-stained, each aliquot with a different PE-labelled antibody. Utilizing a broad immunophenotyping panel and machine-learning algorithms, we can predict the co-expression of hundreds of screened markers with a high degree of precision. This technique is suitable for screening immune cells in bone marrow from different locations, blood specimens, or any tissue with a substantial presence of immune cells, such as tumors or inflamed tissue areas in autoimmune conditions. It represents an approach that can significantly improve our ability to recognize dysregulated immune cell populations and, if needed, precisely target subsequent experiments covering lower cell counts such as RNAseq.</p>","PeriodicalId":390,"journal":{"name":"Methods","volume":" ","pages":"45-53"},"PeriodicalIF":4.2,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142749496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

In silico identification of Histone Deacetylase inhibitors using Streamlined Masked Transformer-based Pretrained features 使用基于预训练特征的流式掩码变换器对组蛋白去乙酰化酶抑制剂进行硅学识别。

IF 4.2 3区生物学

Methods Pub Date : 2024-11-23 DOI: 10.1016/j.ymeth.2024.11.009

Tuan Vinh , Thanh-Hoang Nguyen-Vo , Viet-Tuan Le , Xuan-Phuc Phan-Nguyen , Binh P. Nguyen

{"title":"In silico identification of Histone Deacetylase inhibitors using Streamlined Masked Transformer-based Pretrained features","authors":"Tuan Vinh , Thanh-Hoang Nguyen-Vo , Viet-Tuan Le , Xuan-Phuc Phan-Nguyen , Binh P. Nguyen","doi":"10.1016/j.ymeth.2024.11.009","DOIUrl":"10.1016/j.ymeth.2024.11.009","url":null,"abstract":"<div><div>Histone Deacetylases (HDACs) are enzymes that regulate gene expression by removing acetyl groups from histones. They are involved in various diseases, including neurodegenerative, cardiovascular, inflammatory, and metabolic disorders, as well as fibrosis in the liver, lungs, and kidneys. Successfully identifying potent HDAC inhibitors may offer a promising approach to treating these diseases. In addition to experimental techniques, researchers have introduced several <em>in silico</em> methods for identifying HDAC inhibitors. However, these existing computer-aided methods have shortcomings in their modeling stages, which limit their applications. In our study, we present a <u>S</u>treamlined <u>M</u>asked <u>T</u>ransformer-based Pretrained (SMTP) encoder, which can be used to generate features for downstream tasks. The training process of the SMTP encoder was directed by masked attention-based learning, enhancing the model's generalizability in encoding molecules. The SMTP features were used to develop 11 classification models identifying 11 HDAC isoforms. We trained SMTP, a lightweight encoder, with only 1.9 million molecules, a smaller number than other known molecular encoders, yet its discriminant ability remains competitive. The results revealed that machine learning models developed using the SMTP feature set outperformed those developed using other feature sets in 8 out of 11 classification tasks. Additionally, chemical diversity analysis confirmed the encoder's effectiveness in distinguishing between two classes of molecules.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 1-9"},"PeriodicalIF":4.2,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142708536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A roadmap to cysteine specific labeling of membrane proteins for single-molecule photobleaching studies. 用于单分子光漂白研究的膜蛋白半胱氨酸特异性标记路线图。

IF 4.2 3区生物学

Methods Pub Date : 2024-11-23 DOI: 10.1016/j.ymeth.2024.10.013

Melanie Ernst, Robyn Mahoney-Kruszka, Nathan B Zelt, Janice L Robertson

{"title":"A roadmap to cysteine specific labeling of membrane proteins for single-molecule photobleaching studies.","authors":"Melanie Ernst, Robyn Mahoney-Kruszka, Nathan B Zelt, Janice L Robertson","doi":"10.1016/j.ymeth.2024.10.013","DOIUrl":"10.1016/j.ymeth.2024.10.013","url":null,"abstract":"<p><p>Single-molecule photobleaching analysis is a useful approach for quantifying reactive membrane protein oligomerization in membranes. It provides a binary readout of a fluorophore attached to a protein subunit at dilute conditions. However, quantification of protein stoichiometry from this data requires information about the subunit labeling yields and whether there is non-specific background labeling. Any increases in subunit-specific labeling improves the ability to determine oligomeric states with confidence. A common strategy for site-specific labeling is by conjugation of a fluorophore bearing a thiol-reactive maleimide group to a substituted cysteine. Yet, cysteine reactivity can be difficult to predict as it depends on many factors such as solvent accessibility and electrostatics from the surrounding protein structure. Here we report a general methodology for screening potential cysteine labeling sites on purified membrane proteins. We present the results of two example systems for which the dimerization reactions in membranes have been characterized: (1) the CLC-ec1 Cl<sup>-</sup>/H<sup>+</sup> antiporter, an Escherichia coli homologue of voltage-gated chloride ion channels in humans and (2) a mutant form of a member of the family of fluoride channels Fluc from Bordetella pertussis (Fluc-Bpe-N43S). To demonstrate how we identify such sites, we first discuss considerations of residue positions hypothesized to be suitable and then describe the specific steps to rigorously assess site-specific labeling while maintaining functional activity and robust single-molecule fluorescence signals. We find that our initial, well rationalized choices are not strong predictors of success, as rigorous testing of the labeling sites shows that only ≈ 30 % of sites end up being useful for single-molecule photobleaching studies.</p>","PeriodicalId":390,"journal":{"name":"Methods","volume":" ","pages":"21-35"},"PeriodicalIF":4.2,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142714807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust feature learning using contractive autoencoders for multi-omics clustering in cancer subtyping 利用收缩自编码器进行稳健特征学习，用于癌症亚型中的多组学聚类。

IF 4.2 3区生物学

Methods Pub Date : 2024-11-20 DOI: 10.1016/j.ymeth.2024.11.013

Mengke Guo, Xiucai Ye, Dong Huang, Tetsuya Sakurai

{"title":"Robust feature learning using contractive autoencoders for multi-omics clustering in cancer subtyping","authors":"Mengke Guo, Xiucai Ye, Dong Huang, Tetsuya Sakurai","doi":"10.1016/j.ymeth.2024.11.013","DOIUrl":"10.1016/j.ymeth.2024.11.013","url":null,"abstract":"<div><div>Cancer can manifest in virtually any tissue or organ, necessitating precise subtyping of cancer patients to enhance diagnosis, treatment, and prognosis. With the accumulation of vast amounts of omics data, numerous studies have focused on integrating multi-omics data for cancer subtyping using clustering techniques. However, due to the heterogeneity of different omics data, extracting important features to effectively integrate these data for accurate clustering analysis remains a significant challenge. This study proposes a new multi-omics clustering framework for cancer subtyping, which utilizes contractive autoencoder to extract robust features. By encouraging the learned representation to be less sensitive to small changes, the contractive autoencoder learns robust feature representations from different omics. To incorporate survival information into the clustering analysis, Cox proportional hazards regression is used to further select the key features significantly associated with survival for integration. Finally, we utilize K-means clustering on the integrated feature to obtain the clustering result. The proposed framework is evaluated on ten different cancer datasets across four levels of omics data and compared to other existing methods. The experimental results indicate that the proposed framework effectively integrates the four omics datasets and outperforms other methods, achieving higher C-index scores and showing more significant differences between survival curves. Additionally, differential gene analysis and pathway enrichment analysis are performed to further demonstrate the effectiveness of the proposed method framework.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"233 ","pages":"Pages 52-60"},"PeriodicalIF":4.2,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142692388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing Retinal Imaging: Evaluation of ultrasmall TiO2 nanoparticle- fluorescein conjugates for improved Fundus Fluorescein Angiography 优化视网膜成像：评估超小 TiO2 纳米粒子-荧光素共轭物对改进眼底荧光素血管造影的作用。

IF 4.2 3区生物学

Methods Pub Date : 2024-11-19 DOI: 10.1016/j.ymeth.2024.11.012

Marina França Dias , Rodrigo Ken Kawassaki , Lutiana Amaral de Melo , Koiti Araki , Robson Raphael Guimarães , Sílvia Ligorio Fialho

{"title":"Optimizing Retinal Imaging: Evaluation of ultrasmall TiO2 nanoparticle- fluorescein conjugates for improved Fundus Fluorescein Angiography","authors":"Marina França Dias , Rodrigo Ken Kawassaki , Lutiana Amaral de Melo , Koiti Araki , Robson Raphael Guimarães , Sílvia Ligorio Fialho","doi":"10.1016/j.ymeth.2024.11.012","DOIUrl":"10.1016/j.ymeth.2024.11.012","url":null,"abstract":"<div><div>Fundus Fluorescein Angiography (FFA) has been extensively used for the identification, management, and diagnosis of various retinal and choroidal diseases, such as age-related macular degeneration, diabetic retinopathy, retinopathy of prematurity, among others. This exam enables clinicians to evaluate retinal morphology and the pathophysiology of retinal vasculature. However, adverse events, including from mild to severe reactions to sodium fluorescein, have been reported. Titanium dioxide nanoparticles (NPTiO<sub>2</sub>) have shown significant potential in numerous biological applications. Coating or conjugating these nanoparticles with small molecules can enhance their stability, photochemical properties, and biocompatibility, as well as increase the hydrophilicity of the nanoparticles, making them more suitable for biomedical applications. This work demonstrates the potential use of ultrasmall titanium dioxide nanoparticles conjugated with sodium fluorescein to improve the quality of angiography exams. The strategy of conjugating fluorescein with NPTiO<sub>2</sub> successfully enhanced the fluorescence photostability of the contrast agent and increased its retention time in the retina. Preliminary <em>in vivo</em> and <em>in vitro</em> safety tests suggest that these nanoparticles are safe for the intended application demonstrating low tendency to hemolysis, and no significant changes in the retina thickness or in the electroretinography a-wave and b-wave amplitudes. Overall, the conjugation of fluorescein to NPTiO<sub>2</sub> has produced a nanomaterial with favorable properties for use as an innovative contrast agent in FFA examinations. By providing a clear description of our methodology of analysis, we also aim to offer better perspectives and reproducible conditions for future research.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"233 ","pages":"Pages 30-41"},"PeriodicalIF":4.2,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142680419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring drug-target interaction prediction on cold-start scenarios via meta-learning-based graph transformer. 通过基于元学习的图转换器探索冷启动情景下的药物-目标相互作用预测。

IF 4.2 3区生物学

Methods Pub Date : 2024-11-15 DOI: 10.1016/j.ymeth.2024.11.010

Chengxin He, Zhenjiang Zhao, Xinye Wang, Huiru Zheng, Lei Duan, Jie Zuo

{"title":"Exploring drug-target interaction prediction on cold-start scenarios via meta-learning-based graph transformer.","authors":"Chengxin He, Zhenjiang Zhao, Xinye Wang, Huiru Zheng, Lei Duan, Jie Zuo","doi":"10.1016/j.ymeth.2024.11.010","DOIUrl":"10.1016/j.ymeth.2024.11.010","url":null,"abstract":"<p><p>Predicting drug-target interaction (DTI) is of great importance for drug discovery and development. With the rapid development of biological and chemical technologies, computational methods for DTI prediction are becoming a promising approach. However, there are few solutions to the cold-start problem in DTI prediction scenarios, as these methods rely on existing interaction information to support their modeling. Consequently, they are unable to effectively predict DTIs for new drugs or targets with limited interaction data in the existing work. To this end, we propose a graph transformer method based on meta-learning named MGDTI (short for Meta-learning-based Graph Transformer for Drug-Target Interaction prediction) to fill this gap. Technically, we employ drug-drug similarity and target-target similarity as additional information to mitigate the scarcity of interactions. Besides, we trained MGDTI via meta-learning to be adaptive to cold-start tasks. Moreover, we employed graph transformer to prevent over-smoothing by capturing long-range dependencies. Extensive results on the benchmark dataset demonstrate that MGDTI is effective on DTI prediction under cold-start scenarios.</p>","PeriodicalId":390,"journal":{"name":"Methods","volume":" ","pages":"10-20"},"PeriodicalIF":4.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142643674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SITP: A single cell bioinformatics analysis flow captures proteasome markers in the development of breast cancer SITP：单细胞生物信息学分析流捕捉乳腺癌发展过程中的蛋白酶体标记。

IF 4.2 3区生物学

Methods Pub Date : 2024-11-15 DOI: 10.1016/j.ymeth.2024.11.011

Xue-Jie Zhou , Xiao-Feng Liu , Xin Wang , Xu-Chen Cao

{"title":"SITP: A single cell bioinformatics analysis flow captures proteasome markers in the development of breast cancer","authors":"Xue-Jie Zhou , Xiao-Feng Liu , Xin Wang , Xu-Chen Cao","doi":"10.1016/j.ymeth.2024.11.011","DOIUrl":"10.1016/j.ymeth.2024.11.011","url":null,"abstract":"<div><div>Single cell sequencing and related databases have been widely used in the exploration of cancer occurrence and development, but there is still no in-depth explanation of specific and complicated cellular protein modification processes. Ubiquitin-Proteasome System (UPS), as a specific and precise protein modification and degradation process, plays an important role in the biological functions of cancer cell proliferation and apoptosis. Proteasomes, vital multi-catalytic proteinases in eukaryotic cells, play a crucial role in protein degradation and contribute to tumor regulation. The 26S proteasome, part of the ubiquitin–proteasome system. In this study, we have enrolled a common SITP process including analysis of single cell sequencing to elucidate a flow that can capture typical proteasome markers in the oncogenesis and progression of breast cancer. PSMD11, a key component of the 26S proteasome regulatory particle, has been identified as a critical survival factor in cancer cells. Results suggest that PSMD11’s rapid degradation is linked to acute apoptosis in cancer cells, making it a potential target for cancer treatment. Our study explored the potential mechanisms of PSMD11 in breast cancer development. The findings revealed the feasibility of disclosing ubiquitinating biomarkers from public database, as well as presented new evidence supporting PSMD11 as a potential therapeutic biomarker for breast cancer.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"233 ","pages":"Pages 1-10"},"PeriodicalIF":4.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142643675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ab-Amy 2.0: Predicting light chain amyloidogenic risk of therapeutic antibodies based on antibody language model Ab-amy 2.0：基于抗体语言模型预测治疗性抗体的轻链淀粉样蛋白致病风险。

IF 4.2 3区生物学

Methods Pub Date : 2024-11-15 DOI: 10.1016/j.ymeth.2024.11.005

Yuwei Zhou , Wenwen Liu , Chunmei Luo , Ziru Huang , Gunarathne Samarappuli Mudiyanselage Savini , Lening Zhao , Rong Wang , Jian Huang

{"title":"Ab-Amy 2.0: Predicting light chain amyloidogenic risk of therapeutic antibodies based on antibody language model","authors":"Yuwei Zhou , Wenwen Liu , Chunmei Luo , Ziru Huang , Gunarathne Samarappuli Mudiyanselage Savini , Lening Zhao , Rong Wang , Jian Huang","doi":"10.1016/j.ymeth.2024.11.005","DOIUrl":"10.1016/j.ymeth.2024.11.005","url":null,"abstract":"<div><div>Therapeutic antibodies have emerged as a promising treatment option for a wide range of diseases. However, the light chain of antibodies can potentially induce amyloidosis, a condition characterized by protein misfolding and aggregation, posing a significant safety concern. Therefore, it is crucial to assess the amyloidogenic risk of therapeutic antibodies during the early stages of drug development. In this study, we introduce AB-Amy 2.0, a new computational model with enhanced performance for assessing the light chain amyloidogenic risk of therapeutic antibodies. By employing pretrained protein language models (PLMs) embeddings, AB-Amy 2.0 achieves higher accuracy in amyloidogenic risk prediction compared with traditional features offering a crucial tool for early-stage identification of antibodies with low aggregation propensity. The AB-Amy 2.0 was trained on antiBERTy embeddings and utilizes the SVM algorithm, resulting in superior performance metrics. On an independent test dataset, the model achieved high sensitivity, specificity, ACC, MCC and AUC of 93.47%, 89.23%, 91.92%, 0.8261 and 0.9739, respectively. These results highlight the effectiveness and robustness of AB-Amy 2.0 in predicting light chain amyloidogenic risk accurately. To facilitate user-friendly access, we have developed an online web server (<span><span><u>http://i.uestc.edu.cn/AB-Amy2</u></span><svg><path></path></svg></span>) and a command line tool (<span><span><u>https://github.com/zzyywww/ABAmy2</u></span><svg><path></path></svg></span>). These resources enable the broader application of this advanced model and promise to enhance the development of safer therapeutic antibodies.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"233 ","pages":"Pages 11-18"},"PeriodicalIF":4.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142643649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Data preprocessing methods for selective sweep detection using convolutional neural networks 使用卷积神经网络进行选择性扫频检测的数据预处理方法。

IF 4.2 3区生物学

Methods Pub Date : 2024-11-15 DOI: 10.1016/j.ymeth.2024.11.003

Hanqing Zhao, Nikolaos Alachiotis

{"title":"Data preprocessing methods for selective sweep detection using convolutional neural networks","authors":"Hanqing Zhao, Nikolaos Alachiotis","doi":"10.1016/j.ymeth.2024.11.003","DOIUrl":"10.1016/j.ymeth.2024.11.003","url":null,"abstract":"<div><div>The identification of positive selection has been framed as a classification task, with Convolutional Neural Networks (CNNs) already outperforming summary statistics and likelihood-based approaches in accuracy. Despite the prevalence of CNN-based methods that manipulate the pixels of images representing raw genomic data as a preprocessing step to improve classification accuracy, the efficacy of these pixel-rearrangement techniques remains inadequately examined, particularly in the presence of confounding factors like population bottlenecks, migration and recombination hotspots. We introduce a set of pixel rearrangement algorithms aimed at enhancing CNN classification accuracy in detecting selective sweeps. These algorithms are employed to assess the performance of four CNN models for selective sweep detection. Our findings illustrate that the judicious application of rearrangement algorithms notably enhances the overall classification accuracy of a CNN across various datasets simulating confounding factors. We observed that sorting the columns of the genomic matrices has higher on CNN performance than rearranging the sequences. To some extent, these rearrangement algorithms are more robust to misspecified demographic models compared with the utilization of the default preprocessing algorithm as suggested by the respective authors of each CNN architecture. We provide the data rearrangement algorithms as a distinct package available for download at: <span><span>https://github.com/Zhaohq96/Genetic-data-rearrangement</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"233 ","pages":"Pages 19-29"},"PeriodicalIF":4.2,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142643673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SpaInGNN: Enhanced clustering and integration of spatial transcriptomics based on refined graph neural networks SpaInGNN：基于精炼图神经网络的空间转录组学增强聚类和整合。

IF 4.2 3区生物学

Methods Pub Date : 2024-11-13 DOI: 10.1016/j.ymeth.2024.11.006

Fangqin Zhang, Zhan Shen, Siyi Huang, Yuan Zhu, Ming Yi

{"title":"SpaInGNN: Enhanced clustering and integration of spatial transcriptomics based on refined graph neural networks","authors":"Fangqin Zhang, Zhan Shen, Siyi Huang, Yuan Zhu, Ming Yi","doi":"10.1016/j.ymeth.2024.11.006","DOIUrl":"10.1016/j.ymeth.2024.11.006","url":null,"abstract":"<div><div>Recent developments in spatial transcriptomics (ST) technology have markedly enhanced the proposed capacity to comprehensively characterize gene expression patterns within tissue microenvironments while crucially preserving spatial context. However, the identification of spatial domains at the single-cell level remains a significant challenge in elucidating biological processes. To address this, SpaInGNN was developed, a sophisticated graph neural network (GNN) framework that accurately delineates spatial domains by integrating spatial location data, histological information, and gene expression profiles into low-dimensional latent embeddings. Additionally, to fully leverage spatial coordinate data, spatial integration using graph neural network (SpaInGNN) refines the graph constructed for spatial locations by incorporating both tissue image distance and Euclidean distance, following a pre-clustering of gene expression profiles. This refined graph is then embedded using a self-supervised GNN, which minimizes self-reconfiguration loss. By applying SpaInGNN to refined graphs across multiple consecutive tissue slices, this study mitigates the impact of batch effects in data analysis. The proposed method demonstrates substantial improvements in the accuracy of spatial domain recognition, providing a more faithful representation of the tissue organization in both mouse olfactory bulb and human lateral prefrontal cortex samples.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"233 ","pages":"Pages 42-51"},"PeriodicalIF":4.2,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142611449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Methods最新文献