EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ScribbleDom: using scribble-annotated histology images to identify domains in spatial transcriptomics data

Mohammad Nuwaisir Rahman iD, Abdullah Al Noman iD, Abir Mohammad Turza iD, Mohammed Abid Abrar iD, Md Abul Hassan Samee iD, M Saifur Rahman iD

Bioinformatics · 2023

DOI: 10.1093/bioinformatics/btad594 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2023. Verfasst von Mohammad Nuwaisir Rahman und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, Bangladesh. Hauptthemen laut MEDLINE: Neural Networks, Computer, Transcriptome, Gene Expression Profiling, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: RISE Student Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Spatial domain identification is a very important problem in the field of spatial transcriptomics. The state-of-the-art solutions to this problem focus on unsupervised methods, as there is lack of data for a supervised learning formulation. The results obtained from these methods highlight significant opportunities for improvement. Results In this article, we propose a potential avenue for enhancement through the development of a semi-supervised convolutional neural network based approach. Named “ScribbleDom”, our method leverages human expert’s input as a form of semi-supervision, thereby seamlessly combines the cognitive abilities of human experts with the computational power of machines. ScribbleDom incorporates a loss function that integrates two crucial components: similarity in gene expression profiles and adherence to the valuable input of a human annotator through scribbles on histology images, providing prior knowledge about spot labels. The spatial continuity of the tissue domains is taken into account by extracting information on the spot microenvironment through convolution filters of varying sizes, in the form of “Inception” blocks. By leveraging this semi-supervised approach, ScribbleDom significantly improves the quality of spatial domains, yielding superior results both quantitatively and qualitatively. Our experiments on several benchmark datasets demonstrate the clear edge of ScribbleDom over state-of-the-art methods—between 1.82% to 169.38% improvements in adjusted Rand index for 9 of the 12 human dorsolateral prefrontal cortex samples, and 15.54% improvement in the melanoma cancer dataset. Notably, when the expert input is absent, ScribbleDom can still operate, in a fully unsupervised manner like the state-of-the-art methods, and produces results that remain competitive. Availability and implementation Source code is available at Github (https://github.com/1alnoman/ScribbleDom) and Zenodo (https://zenodo.org/badge/latestdoi/681572669).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerTranscriptomeGene Expression ProfilingImage Processing, Computer-AssistedHumansComputational BiologyAlgorithms

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka 1000, Bangladesh.
  • Department of Computer Science and Engineering, Brac University, Dhaka 1212, Bangladesh.
  • Department of Integrative Physiology, Baylor College of Medicine, Houston, TX 77030, United States.

ORCID-Profile: Mohammad Nuwaisir Rahman, Abdullah Al Noman, Abir Mohammad Turza, Mohammed Abid Abrar, Md Abul Hassan Samee, M Saifur Rahman

Förderung

  • RISE Student Research

Zitieren

APA

Rahman, M. N., Noman, A. A., Turza, A. M., Abrar, M. A., Samee, M. A. H., & Rahman, M. S. (2023). ScribbleDom: using scribble-annotated histology images to identify domains in spatial transcriptomics data. Bioinformatics. https://doi.org/10.1093/bioinformatics/btad594

Vancouver

Rahman MN, Noman AA, Turza AM, Abrar MA, Samee MAH, Rahman MS. ScribbleDom: using scribble-annotated histology images to identify domains in spatial transcriptomics data. Bioinformatics. 2023. doi:10.1093/bioinformatics/btad594

BibTeX
@article{Rahman2023,
  author = {Rahman, Mohammad Nuwaisir and Noman, Abdullah Al and Turza, Abir Mohammad and Abrar, Mohammed Abid and Samee, Md Abul Hassan and Rahman, M Saifur},
  title = {ScribbleDom: using scribble-annotated histology images to identify domains in spatial transcriptomics data},
  journal = {Bioinformatics},
  year = {2023},
  doi = {10.1093/bioinformatics/btad594}
}
Kostenlos starten →