Article
Genetics & Heredity
Benjamin Chidester, Tianming Zhou, Shahul Alam, Jian Ma
Summary: Spatial transcriptomics is a method to reveal spatially resolved gene expression of diverse cells in complex tissues. SpiceMix, an interpretable method based on probabilistic, latent variable modeling, improves on the inference of cell types and their spatial patterns. By analyzing spatial transcriptome data of brain regions in human and mouse, SpiceMix enhances the inference of complex cell identities, reveals interpretable spatial metagenes, and uncovers differentiation trajectories. SpiceMix is a generalizable analysis framework for spatial transcriptome data to investigate cell-type composition and spatial organization of cells in complex tissues.
Article
Computer Science, Artificial Intelligence
Lixin Cheng, Qiuhua Tang, Zikai Zhang, Shiqian Wu
Summary: This paper proposes an adaptive ensemble model for fast and accurate makespan estimation by constructing a high-quality training dataset and utilizing multiple back propagation neural networks. Experimental results show that both the new features and ensemble improvements are effective, with the proposed model significantly outperforming conventional approaches.
JOURNAL OF INTELLIGENT MANUFACTURING
(2021)
Article
Computer Science, Artificial Intelligence
Uzma, Feras Al-Obeidat, Abdallah Tubaishat, Babar Shah, Zahid Halim
Summary: This study proposes a gene encoder feature selection technique for the classification of cancer samples. By aggregating multiple filtering methods and using a genetic algorithm, the optimal feature subset is selected and evaluated using various classifiers. Experimental results suggest better performance of the proposed method.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Diptaraj Sen, Saubhik Paladhi, Jaroslav Frnda, Sankhadeep Chatterjee, Soumen Banerjee, Jan Nedoma
Summary: This study proposes an associative classifier designed using association rule mining methods to efficiently detect dengue fever using gene expression data. The experimental results indicate accurate detection of dengue fever patients at an early stage using the proposed method.
Article
Computer Science, Artificial Intelligence
Kazem Talaei, Amin Rahati, Lhassane Idoumghar
Summary: This paper proposes an improved variant of the harmony search (HS) algorithm called HSGS for solving clustering problems. The HSGS generates two new harmonies at each iteration. The first is produced by the harmony improvisation procedure of the canonical HS and promotes exploration ability.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Biochemical Research Methods
Maryam Pouryahya, Jung Hun Oh, Pedram Javanmard, James C. Mathews, Zehor Belkhatir, Joseph O. Deasy, Allen R. Tannenbaum
Summary: In this study, a novel network-based multiomics clustering method called aWCluster is proposed. By accentuating the genes that have concordant multiomics measurements in their interaction network, aWCluster successfully clusters different cancer types into classes with significantly different survival rates.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2022)
Article
Computer Science, Information Systems
Zhaozhao Xu, Fangyuan Yang, Hong Wang, Junding Sun, Hengde Zhu, Shuihua Wang, Yudong Zhang
Summary: This paper proposes a clustering-guided unsupervised feature selection algorithm for gene expression data, which addresses the problems of existing algorithms such as the need for artificially specifying the number of clusters, failure to consider feature redundancy, and inability to filter redundant features. The proposed algorithm introduces adaptive k-value strategy, feature grouping strategy, and adaptive filtering strategy to select significant features related to diseases. Experimental results demonstrate that the algorithm outperforms existing algorithms in terms of accuracy and correlation indexes.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Automation & Control Systems
Minjie Wang, Genevera Allen
Summary: The study introduces a method for integrating multiple feature sets using a convex formalization which achieves strong empirical performance and effectively addresses the clustering issues in multi-view data sets. An adaptive feature selection method is proposed as well. Experimental results and real data examples show superior empirical performance of the approach in high-dimensional mixed multi-view data sets.
JOURNAL OF MACHINE LEARNING RESEARCH
(2021)
Article
Biochemical Research Methods
Isabelle Bichindaritz, Guanghui Liu, Christopher Bartlett
Summary: The study proposes an adaptive multi-task learning method for survival prediction of breast cancer patients using multi-modal learning, achieving more effective results compared to existing approaches. By combining different gene features, reducing dimensions, and introducing auxiliary loss, an ordinal Cox hazards model is built to predict patients' survival risk.
Article
Computer Science, Artificial Intelligence
Shudong Huang, Zhao Kang, Zenglin Xu, Quanhui Liu
Summary: Clustering aims to divide input data into different groups based on distance or similarity, with k-means being a widely used method. A deep k-means model is proposed in this study to improve clustering performance by extracting deep representations using deep learning techniques.
PATTERN RECOGNITION
(2021)
Article
Biochemical Research Methods
Fei Qin, Xizhi Luo, Feifei Xiao, Guoshuai Cai
Summary: This study developed a novel simulator for single-cell RNA sequencing (scRNA-seq) data that accurately captures important data features and performs well in recovering cell-cell distances. The simulator also helped evaluate differential expression analysis methods and identify the best-performing ones.
Article
Green & Sustainable Science & Technology
Hao Chen
Summary: This paper proposes a wind power modeling approach based on clustering and ensemble learning algorithms. The results show that the ensemble models with clustering outperform those without clustering by approximately 15% on average in simulating wind power. The best performing clustering algorithm improves computational speed by around 30%. The performance of the model is further boosted by about 5% by introducing stacking.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2022)
Article
Biochemical Research Methods
Adam Gayoso, Zoe Steier, Romain Lopez, Jeffrey Regier, Kristopher L. Nazor, Aaron Streets, Nir Yosef
Summary: totalVI is a framework for end-to-end joint analysis of CITE-seq data which probabilistically represents data as a composite of biological and technical factors, providing a cohesive solution for common analysis tasks. It demonstrates strong performance in tasks such as dimensionality reduction, dataset integration, correlation estimation, and differential expression testing.
Article
Genetics & Heredity
Yujia Li, Yusi Fang, Hung-Ching Chang, Michael Gorczyca, Peng Liu, George C. Tseng
Summary: In this study, two adaptive Fisher methods, AFp and AFz, were extended and evaluated for phenotype-mRNA association analysis. The proposed method effectively aggregates heterogeneous phenotype-gene effects and allows association with different types of phenotypes. Extensive simulations demonstrate the superior performance of AFp compared to existing methods in terms of type I error control, statistical power, and biological interpretation. The method is applied to transcriptomic and clinical datasets from lung disease, breast cancer, and brain aging and generates intriguing biological findings.
Article
Computer Science, Hardware & Architecture
Nahid Gholizadeh, Hamid Saadatfar, Nooshin Hanafi
Summary: This study aims to accelerate the execution speed of the DBSCAN algorithm in order to handle big datasets. By applying initial grouping and cluster merging, the efficiency of DBSCAN execution was successfully improved.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Cell Biology
Jenia Gutin, Ronen Sadeh, Nitzan Bodenheimer, Daphna Joseph-Strauss, Avital Klein-Brill, Adi Alajem, Oren Ram, Nir Friedman
Article
Cell Biology
Avital Klein-Brill, Daphna Joseph-Strauss, Alon Appleboim, Nir Friedman
Article
Biochemistry & Molecular Biology
Enia Gutin, Daphna Joseph-Strauss, Amit Sadeh, Eli Shalom Nir Friedman
MOLECULAR SYSTEMS BIOLOGY
(2019)
Article
Multidisciplinary Sciences
Mor Nitzan, Nikos Karaiskos, Nir Friedman, Nikolaus Rajewsky
Article
Biotechnology & Applied Microbiology
Carl G. de Boer, Eeshit Dhaval Vaishnav, Ronen Sadeh, Esteban Luis Abeyta, Nir Friedman, Aviv Regev
NATURE BIOTECHNOLOGY
(2020)
Correction
Biotechnology & Applied Microbiology
Carl G. de Boer, Eeshit Dhaval Vaishnav, Ronen Sadeh, Esteban Luis Abeyta, Nir Friedman, Aviv Regev
NATURE BIOTECHNOLOGY
(2020)
Article
Multidisciplinary Sciences
Ivan Haralampiev, Simon Prisner, Mor Nitzan, Matthias Schade, Fabian Jolmes, Max Schreiber, Maria Loidolt-Kruger, Kalle Jongen, Jasmine Chamiolo, Niklaas Nilson, Franziska Winter, Nir Friedman, Oliver Seitz, Thorsten Wolff, Andreas Herrmann
NATURE COMMUNICATIONS
(2020)
Article
Biotechnology & Applied Microbiology
Ronen Sadeh, Israa Sharkia, Gavriel Fialkoff, Ayelet Rahat, Jenia Gutin, Alon Chappleboim, Mor Nitzan, Ilana Fox-Fisher, Daniel Neiman, Guy Meler, Zahala Kamari, Dayana Yaish, Tamar Peretz, Ayala Hubert, Jonathan E. Cohen, Azzam Salah, Mark Temper, Albert Grinshpun, Myriam Maoz, Samir Abu-Gazala, Ami Ben Ya'acov, Eyal Shteyer, Rifaat Safadi, Tommy Kaplan, Ruth Shemer, David Planer, Eithan Galun, Benjamin Glaser, Aviad Zick, Yuval Dor, Nir Friedman
Summary: Cell-free DNA in human plasma can provide important molecular information about pathological processes, with cfChIP-seq being a valuable tool to analyze active chromatin modifications in different samples. The study revealed the potential of cfChIP-seq in diagnosing diseases and understanding physiological and pathological processes using blood samples.
NATURE BIOTECHNOLOGY
(2021)
Article
Biochemical Research Methods
Noa Moriel, Enes Senel, Nir Friedman, Nikolaus Rajewsky, Nikos Karaiskos, Mor Nitzan
Summary: The single-cell RNA-sequencing (scRNA-seq) technologies have revolutionized modern biomedical sciences by incorporating spatial information to study tissue organization and spatial gene expression patterns. NovoSpaRc is a computational framework that probabilistically assigns cells to tissue locations based on a structural correspondence hypothesis, which spatially reconstructs tissues.
Article
Cell Biology
Alon Chappleboim, Daphna Joseph-Strauss, Ayelet Rahat, Israa Sharkia, Miriam Adam, Daniel Kitsberg, Gavriel Fialkoff, Matan Lotem, Omer Gershon, Anna-Kristina Schmidtner, Esther Oiknine-Djian, Agnes Klochendler, Ronen Sadeh, Yuval Dor, Dana Wolf, Naomi Habib, Nir Friedman
Summary: This study introduces a novel NGS diagnostic method called ApharSeq, which significantly improves virus detection efficiency and accuracy, while reducing labor costs and reagent requirements.
SCIENCE TRANSLATIONAL MEDICINE
(2021)
Article
Biochemistry & Molecular Biology
Alon Chappleboim, Daphna Joseph-Strauss, Omer Gershon, Nir Friedman
Summary: Multiple studies in the last decade have shown that cells maintain a balance of mRNA production and degradation, but the mechanisms behind this balance are still unknown. This study monitored the mRNA profiles in cells after the depletion of Xrn1, the main mRNA exonuclease, and observed an accumulation of mRNA followed by a reduction in transcription and subsequent return to normal levels. The study also found that this transcriptional response is not specific to Xrn1 depletion and occurs earlier when upstream factors in the degradation pathway are disturbed.
NUCLEIC ACIDS RESEARCH
(2022)
Article
Multidisciplinary Sciences
Bayan Mashahreh, Shir Armony, Kristoffer Ene Johansson, Alon Chappleboim, Nir Friedman, Richard G. Gardner, Rasmus Hartmann-Petersen, Kresten Lindorff-Larsen, Tommer Ravid
Summary: This study identifies a large cohort of proteome-derived degrons through an unbiased peptidome stability screen in yeast and establishes constraints governing degron potency. The results suggest that degrons with transmembrane domain-like characteristics are the most probable sequences to act as key quality control determinants.
NATURE COMMUNICATIONS
(2022)
Article
Oncology
Lorinc Sandor Pongor, Christopher W. Schultz, Lorenzo Rinaldi, Darawalee Wangsa, Christophe E. Redon, Nobuyuki Takahashi, Gavriel Fialkoff, Parth Desai, Yang Zhang, Sandra Burkett, Nadav Hermoni, Noa Vilk, Jenia Gutin, Rona Gergely, Yongmei Zhao, Samantha Nichols, Rasa Vilimas, Linda Sciuto, Chante Graham, Juan Manuel Caravaca, Sevilay Turan, Tsai-wei Shen, Vinodh N. Rajapakse, Rajesh Kumar, Deep Upadhyay, Suresh Kumar, Yoo Sun Kim, Nitin Roper, Bao Tran, Stephen M. Hewitt, David E. Kleiner, Mirit I. Aladjem, Nir Friedman, Gordon L. Hager, Yves Pommier, Thomas Ried, Anish Thomas
Summary: In this study, it was found that ecDNA is the primary source of gene amplifications and fusions in small-cell lung cancer (SCLC), leading to transcriptional amplification and high heterogeneity of the tumor. Furthermore, cell-free nucleosome profiling can noninvasively detect ecDNA amplifications, facilitating genome-wide investigation in SCLC and other cancers.
Article
Cell Biology
Ori Fridlich, Ayelet Peretz, Ilana Fox-Fisher, Sheina Pyanzin, Ziv Dadon, Eilon Shcolnik, Ronen Sadeh, Gavriel Fialkoff, Israa Sharkia, Joshua Moss, Ludovica Arpinati, Shachar Nice, Christopher D. Nogiec, Samuel Terkper Ahuno, Rui Li, Eddie Taborda, Sonia Dunkelbarger, Zvi G. Fridlender, Paz Polak, Tommy Kaplan, Nir Friedman, Benjamin Glaser, Ruth Shemer, Naama Constantini, Yuval Dor
Summary: Strenuous physical exercise leads to a significant increase in circulating cell-free DNA (cfDNA), with its concentration correlating with the intensity and duration of exercise. The main source of cfDNA during exercise is extramedullary polymorphonuclear neutrophils. After a marathon, there is an elevated concentration of cardiomyocyte cfDNA, indicating low-level, delayed cardiac cell death. Factors such as physical impact, low oxygen levels, and elevated core body temperature contribute to the release of cfDNA from neutrophils, while muscle contraction, increased heart rate, b-adrenergic signaling, or steroid treatment do not cause an elevation in cfDNA levels. Physical training reduces the release of neutrophil cfDNA after exercise, suggesting a relationship between cfDNA release and the activation of neutrophils in exercise-induced muscle damage.
CELL REPORTS MEDICINE
(2023)
Article
Biochemistry & Molecular Biology
Haiyue Liu, Roberto Arsie, Daniel Schwabe, Marcel Schilling, Igor Minia, Jonathan Alles, Anastasiya Boltengagen, Christine Kocks, Martin Falcke, Nir Friedman, Markus Landthaler, Nikolaus Rajewsky
Summary: SLAM-Drop-seq is a method that allows detection of newly synthesized and preexisting mRNAs in single cells. Using this method, researchers found that the transcription and degradation rates of the majority of genes in the cell cycle are dynamically regulated, indicating the importance of temporally regulated mRNA degradation for the correct expression of most cycling genes.
MOLECULAR SYSTEMS BIOLOGY
(2023)