22 papers · ranked by Valyu relevance
Junjun Ren, Zhengqian Zhang, Jiayu Wang, Lingyun Xie + 3 more
Single-cell multi-omics datasets are rapidly expanding, and integrating complementary modalities can provide a more comprehensive view of the molecular mechanisms underlying biological processes. However, cross-modality alignment remains challenging due to modality-specific measurement differences and mismatches in…
Yupeng Xu, Hao Dai, Jinwang Feng, Keren Xu + 3 more
'Chunman Zuo'] The growing availability of spatial transcriptomics data offers key resources for annotating query datasets using reference datasets. However, batch effects, unbalanced reference annotations, and tissue heterogeneity pose significant challenges to alignment analysis. Here, we present stGuide, an…
Moninder S. Bhogal, Thomas Lanyon-Hogg, Katherine A. Johnston, Stuart L. Warriner + 1 more
'Stuart L. Warriner' 'Alison Baker'] Peroxisomes are vital metabolic organelles found in almost all eukaryotic organisms, and they rely exclusively on import of their matrix protein content from the cytosol. In vitro import of proteins into isolated peroxisomal fractions has provided a wealth of knowledge on the import…
Cindy Fang, Kelsey D. Montgomery, Sarah E. Maguire, Anthony D. Ramnauth + 8 more
Recent advances in spatially-resolved transcriptomics have enabled profiling of gene expression in a spatial context, which has led to the generation of large-scale single-cell and spatial atlases with computationally-derived cell type or spatial domain labels. An increasingly important task with these data has become…
Jesus Gonzalez-Ferrer, Julian Lehrer, Ash O’Farrell, Benedict Paten + 4 more
Large single-cell RNA datasets have contributed to unprecedented biological insight. Often, these take the form of cell atlases and serve as a reference for automating cell labeling of newly sequenced samples. Yet, classification algorithms have lacked the capacity to accurately annotate cells, particularly in complex…
Carla Mölbert, Laleh Haghverdi
The transfer of cell type labels from prior annotated (reference) to newly collected data is an important task in single-cell data analysis. As the number of publicly available annotated datasets which can be used as a reference, as well as the number of computational methods for cell type label transfer are constantly…
Yuge Wang, Hongyu Zhao
With continuous progress of single-cell chromatin accessibility profiling techniques, scATAC-seq has become more commonly used in investigating regulatory genomic regions and their involvement in developmental, evolutionary, and disease-related processes. At the same time, accurate cell type annotation plays a crucial…
Zhiqiang Chen, Leelavathi Rajamanickam, Jianfang Cao, Aidi Zhao + 2 more
'Xiaohui Hu' 'Wajid Mumtaz'] This study aims to solve the overfitting problem caused by insufficient labeled images in the automatic image annotation field. We propose a transfer learning model called CNN-2L that incorporates the label localization strategy described in this study. The model consists of an InceptionV3…
Sandhya Aneja, Nagender Aneja, Pg Emeroylariffion Abas, Abdul Ghani Naim
'Abdul Ghani Naim'] Article Info ABSTRACT Article history: Received Jul 19, 2021 Revised Nov 30, 2021 Accepted Dec 12, 2021 Transfer learning allows us to exploit knowledge gained from one task to assist in solving another but relevant task. In modern computer vision research, the question is which architecture…
Michael Gabel, Roland R. Regoes, Frederik Graw, Andrew J. Yates
The adoptive transfer of labelled cell populations has been an essential tool to determine and quantify cellular dynamics. The experimental methods to label and track cells over time range from fluorescent dyes over congenic markers towards single-cell labelling techniques, such as genetic barcodes. While these methods…
Mohamad Zamini, Eun‐jin Kim
—The goal of transfer learning (TL) is providing a framework for exploiting acquired knowledge from source to target data. Transfer learning approaches compared to traditional machine learning approaches are capable of modeling better data patterns from the current domain. However, vanilla TL needs performance…
S. Maryam Hosseini, Abubakr Shafique, Morteza Babaie, H.R. Tizhoosh
In dealing with the lack of sufficient annotated data and in contrast to supervised learning, unsupervised, self-supervised, and semi-supervised domain adaptation methods are promising approaches, enabling us to transfer knowledge from rich labeled source domains to different (but related) unlabeled target domains…
Ramin Moradi, Katrina M. Groth
Advancements in sensing and computing technologies, the development of human and computer interaction frameworks, big data storage capabilities, and the emergence of cloud storage and could computing have resulted in an abundance of data in modern industry. This data availability has encouraged researchers and industry…
David Buterez, Jon Paul Janet, Steven Kiddle, Pietro Liò
We investigate the potential of graph neural networks for transfer learning and improving molecular property prediction on sparse and expensive to acquire high-fidelity data by leveraging low-fidelity measurements as an inexpensive proxy for a targeted property ofinterest. This problem arises in discovery processes…
Robert Guralnick, Raphael LaFrance, Michael Denslow, Samantha Blickhan + 8 more
The initial run of our object detection and classification machine learning pipeline, while credible, had room for significant improvement; success rates for detection and classification of labels were around 75%, which is too low for broad use. In order to improve model results, we developed a new Notes from Nature…
Erik Rodner
As humans we are able to visually recognize and name a large variety of object categories. A rough estimation of Biederman (1987) suggests that we know approximately 30.000 different visual categories, which corresponds to learning five categories per day, on average, in our childhood. Moreover, we are able to learn…
Hailin Chen, Shengping Cui, Sebastián Li
TRANSFER LEARNING RESEARCH PROJECT REPORT Application of Transfer Learning Approaches in Multimodal Wearable Human Activity Recognition Submitter By: CHEN HAILIN, CUI SHENGPING, SEBASTIAN LI SCHOOL OF COMPUTER SCIENCE AND ENGINEERING NANYANG TECHNOLOGICAL UNIVERSITY Machine learning has been the focus of global…
Quanshi Zhang, Yang Yu, Qian Yu, Ying Wu
Instead of learning different networks for different applications, building a universal net with a compact structure for various categories and tasks is one of ultimate objectives of AI. In spite of the gap between current algorithms and the target of learning a huge universal net, it is still meaningful for scientific…
Meng Su, Samuel Roberts, John Sutherland
Ribosomal translation at the origin of life requires controlled aminoacylation to produce mono-aminoacyl esters of tRNAs. Herein, we show that transient annealing of short RNA oligo:amino acid mixed anhydrides to an acceptor strand enables the sequential transfer of aminoacyl residues to the diol of an overhang, first…
Caoimhe Robinson, VUSLAT B. JUSKA, Alan O'Riordan
Electrochemical Impedance Spectroscopy (EIS) is a surface sensitive technique which examines the impedance of an electrochemical cell over a range of frequencies. By immobilising an antigen or antibody to the electrode surface, EIS shows potential for highly specific and sensitive immunosensor performance. Following an…
Authors not listed
The process of label selection holds significant importance in the field of electrochemical biosensors, as it directly impacts the achievement of low detection limits and a wide dynamic range. To attain these objectives, it is necessary to take into account several aspects, including low electroactive potential, high…
Shadman Khan, Amid Shakeri, Jonathan Monteiro, Simrun Tariq + 5 more
With both foodborne illness and food spoilage detrimentally impacting human health and the economy, there is growing interest in the development of in situ sensors that offer real-time monitoring of food quality within enclosed food packages. While oligonucleotide-based fluorescent sensors have illustrated significant…