Showing papers in "Methods in 2020"
••
TL;DR: This paper proposes a new hybrid convolutional and recurrent deep neural network for breast cancer histopathological image classification that outperforms the state-of-the-art method and releases a dataset that covers as many different subclasses spanning different age groups as possible, thus providing enough data diversity to alleviate the problem of relatively low classification accuracy of benign images.
180 citations
••
TL;DR: This review defines ECM, classifies decellularization agents and techniques, and explains different sources ofECM, and the future perspectives of 3d bioprinting technology are discussed.
95 citations
••
TL;DR: An improved step-by-step protocol for sample preparation and the generation of 4C-seq sequencing libraries is presented, including an optimized PCR and 4C template purification strategy, and a data processing pipeline is provided which processes multiplexed 4c-seq reads directly from FASTQ files.
90 citations
••
TL;DR: This work describes how to perform the successive steps of an SMLM workflow, focusing on single-color Stochastic Optical Reconstruction Microscopy (STORM) as well as multicolor DNA Points Accumulation for imaging in Nanoscale Topography (DNA-PAINT) of fixed samples.
67 citations
••
TL;DR: Current techniques for modifying EVs and methodology used for generation and customizing of EVs mimetic-nanovesicles, a type of artificial EVs which can be generated from all cell type with comparable characteristics as EVs for an alternative therapeutic modality are discussed.
54 citations
••
TL;DR: Single-cell combinatorial indexed Hi-C (sci-Hi-C), a high throughput method that enables mapping chromatin interactomes in large number of single cells, is developed and used to identify cellular variability in mammalian chromosomal conformation.
54 citations
••
TL;DR: A hybrid computational framework (SDLDA) for the lncRNA-disease association prediction is proposed that uses singular value decomposition and deep learning to extract linear and non-linear features of lncRNAs and diseases, respectively and has a better performance over existing methods in the leave-one-out cross-validation.
53 citations
••
TL;DR: The hurdles and potential solutions in EV biomarker discovery and verification and validation, and clinical translation are discussed.
49 citations
••
TL;DR: The cell membrane-cloaked nanosystems are reviewed, their novelty is highlighted, the preparation and characterization methods with relevant biomedical applications are introduced, and the prospects for using this novel biomimetic system that was developed from a combination of cell membranes and synthetic nanomaterials are described.
47 citations
••
TL;DR: In this paper, the authors provide an overview of the most commonly used deep learning architectures and feature representations of molecular data and highlight the latest AI-based research that has led to the successful discovery of GPCR bioactive ligands.
44 citations
••
TL;DR: A multi-modal deep auto-encoders based drug representation learning method named DDI-MDAE, to predict DDIs from large-scale, noisy and sparse data and applies a specialized random forest classifier in the positive-unlabeled (PU) learning setting to enhance the prediction accuracy.
••
TL;DR: The advances significantly increase the complexity of the iCLIP2 libraries, resulting in a more comprehensive representation of RBP binding sites, and thereby promote the versatile and flexible application of this important technology.
••
TL;DR: A compilation of state-of-the-art detection techniques for COVID-19 using CRISPR technology which has tremendous potential to transform diagnostics and epidemiology is discussed and presented.
••
TL;DR: A highly heterogeneous ECS is found, where local rheological properties can change drastically within few nanometres, and differences in local ECS diffusion environments in organotypic slices when compared to adult mouse slices are suggested.
••
TL;DR: The production of EVs, their purification and their post-bioengineering, and the biomedical applications of EVs are analyzed, focusing on the developments of methods in producing EVs including biological, physical, and chemical approaches.
••
TL;DR: A novel multi-task based deep learning model for HIstoPatholOgy (named Deep-Hipo) that takes multi-scale patches simultaneously for accurate histopathological image analysis that has outperformed the current state-of-the-art deep learning methods.
••
TL;DR: The bioinformatics tools that have been published over the last few years are discussed and the most popular tools for the design of CRISPR-Cas9 guides are presented.
••
TL;DR: A computational system that uses RNA-seq data to determine operons throughout a genome and combines primary genomic sequence information with expression data from theRNA-seq files in a unified probabilistic model in order to identify operons.
••
TL;DR: This review examines strategies employed to reveal how specific proteins, RNAs and lipids are directed for secretion via EVs, including exosomes and microvesicles, formed via distinct cellular pathways and molecular machineries.
••
TL;DR: Different decellularization techniques are described, including physical, chemical and biological methods, which aim to remove cells from organs or tissues resulting in a cell-free scaffold consisting of the tissues extracellular matrix.
••
TL;DR: Different methods of HAM decellularization were used to achieve an optimal process and the peracetic acid-processed HAM was further functionally evaluated through in vivo assessments that can further lead to tissue reconstruction within the human host.
••
TL;DR: The separated EVs were assessed for morphological, biophysical and proteomic properties of separated EVs by nanoparticle tracking analysis, transmission electron microscopy, and labeled and label-free mass-spectroscopy for protein profiling with step-by-step protocols for each assessment.
••
TL;DR: A Weighted Matrix Factorization model on multi-relational data to predict LncRNA-Disease Associations (WMFLDA), which obtains a much better performance than related data integrative solutions across different experiment settings and evaluation metrics.
••
TL;DR: This review focusses on the latest advancements and future perspectives in the utilisation of natural ECM for the decoration of synthetic porous scaffolds.
••
TL;DR: The working principle of STED is reviewed and general guidelines for successful STED imaging are provided, opening up the prospect of volumetric imaging in living cells and tissues with diffraction-unlimited resolution in all three spatial dimensions.
••
TL;DR: The results support that human waste adipose tissue is an important source for decellularized h ECM as well as stem cells, and adipose hECM scaffold provides a suitable environment for chondrogenic differentiation of hASCs.
••
TL;DR: The decellularization techniques that have been applied to create biomaterials with the potential to promote the repair and regeneration of tissues within the central and peripheral nervous system are reviewed.
••
TL;DR: The workflow covers all steps from the initial quality control of the sequencing reads up to peak calling and quantification of RBP binding, and explains the specific requirements for iCLIP data analysis and suggest optimised parameter settings.
••
TL;DR: This article describes a method to optimize the expression level of dCas9 in order to avoid toxicity while ensuring strong on-target repression activity and demonstrates this method by optimizing a pLZ12 based vector originally developed for S. aureus so that it can work in E. coli.
••
TL;DR: SpineJ offers an intuitive and user-friendly graphical user interface, facilitating fast, accurate, and unbiased analysis of spine morphology, and a semi-automatic ImageJ plugin that is specifically designed for this purpose.