id:"swepub:oai:DiVA.org:his-20941"
Search: id:"swepub:oai:DiVA.org:his-20941" > Deep neural network...
- 1 of 1
- Previous record
- Next record
- To hitlist
- Magnusson, Rasmus,1992-Linköpings universitet,Högskolan i Skövde,Institutionen för biovetenskap,Forskningsmiljön Systembiologi,Bioinformatics, Department of Physics, Chemistry and Biology, Linköping University, Sweden,Translational Bioinformatics,Avdelningen för medicinsk teknik,Tekniska fakulteten,Univ Skovde, Sweden (author)
Deep neural network prediction of genome-wide transcriptome signatures – beyond the Black-box
- Article/chapterEnglish2022
Publisher, publication year, extent ...
- 2022-02-23
- Springer Nature,2022
- electronicrdacarrier
Numbers
- LIBRIS-ID:oai:DiVA.org:his-20941
- https://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-20941URI
- https://doi.org/10.1038/s41540-022-00218-9DOI
- https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-183400URI
- http://kipublications.ki.se/Default.aspx?queryparsed=id:148910137URI
Supplementary language notes
- Language:English
- Summary in:English
Part of subdatabase
- SwePubSwePub
Classification
Notes
- CC BY 4.0Correspondence and requests for materials should be addressed to Rasmus Magnusson email: rasmus.magnusson@his.seOpen access funding provided by University of Skövde.
- Funding Agencies|Swedish Research CouncilSwedish Research CouncilEuropean Commission [2019-04193]; Swedish foundation for strategic researchSwedish Foundation for Strategic Research [SB16-0095]; Center for Industrial IT (CENIIT); Systems Biology Research Centre at University of Skovde under Knowledge Foundation [20200014]; King Abdullah University of Science and Technology (KAUST)King Abdullah University of Science & Technology; Swedish National Infrastructure for Computing (SNIC) [SNIC 2020/5-177, LiU-2019-25]
- Prediction algorithms for protein or gene structures, including transcription factor binding from sequence information, have been transformative in understanding gene regulation. Here we ask whether human transcriptomic profiles can be predicted solely from the expression of transcription factors (TFs). We find that the expression of 1600 TFs can explain >95% of the variance in 25,000 genes. Using the light-up technique to inspect the trained NN, we find an over-representation of known TF-gene regulations. Furthermore, the learned prediction network has a hierarchical organization. A smaller set of around 125 core TFs could explain close to 80% of the variance. Interestingly, reducing the number of TFs below 500 induces a rapid decline in prediction performance. Next, we evaluated the prediction model using transcriptional data from 22 human diseases. The TFs were sufficient to predict the dysregulation of the target genes (rho = 0.61, P < 10−216). By inspecting the model, key causative TFs could be extracted for subsequent validation using disease-associated genetic variants. We demonstrate a methodology for constructing an interpretable neural network predictor, where analyses of the predictors identified key TFs that were inducing transcriptional changes during disease.
Subject headings and genre
- NATURVETENSKAP Biologi Bioinformatik och systembiologi hsv//swe
- NATURAL SCIENCES Biological Sciences Bioinformatics and Systems Biology hsv//eng
- NATURVETENSKAP Biologi Genetik hsv//swe
- NATURAL SCIENCES Biological Sciences Genetics hsv//eng
- NATURVETENSKAP Biologi Biokemi och molekylärbiologi hsv//swe
- NATURAL SCIENCES Biological Sciences Biochemistry and Molecular Biology hsv//eng
- Bioinformatik
- Bioinformatics
Added entries (persons, corporate bodies, meetings, titles ...)
- Tegnér, Jesper N.Biological and Environmental Sciences and Engineering Division, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia ; Unit of Computational Medicine, Department of Medicine, Solna, Center for Molecular Medicine, Karolinska Institutet, Stockholm, Sweden ; Science for Life Laboratory, Solna, Sweden,King Abdullah Univ Sci & Technol KAUST, Saudi Arabia; Dept Med, Sweden; Karolinska Inst, Sweden; Sci Life Lab, Sweden (author)
- Gustafsson, MikaLinköpings universitet,Bioinformatik,Tekniska fakulteten(Swepub:liu)mikgu75 (author)
- Högskolan i SkövdeInstitutionen för biovetenskap (creator_code:org_t)
Related titles
- In:npj Systems Biology and Applications: Springer Nature8:12056-7189
Internet link
- https://doi.org/10.1038/s41540-022-00218-9Fulltext
- https://his.diva-portal.org/smash/get/diva2:1640666/FULLTEXT01.pdffulltext:print
- https://www.nature.com/articles/s41540-022-00218-9.pdf
- https://liu.diva-portal.org/smash/get/diva2:1643530/FULLTEXT01.pdffulltext:print
- https://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-20941
- https://doi.org/10.1038/s41540-022-00218-9
- https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-183400
- http://kipublications.ki.se/Default.aspx?queryparsed=id:148910137
Find in a library
- npj Systems Biology and Applications (Search for host publication in LIBRIS)
To the university's database
- 1 of 1
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- Magnusson, Rasmu ...
- Tegnér, Jesper N ...
- Gustafsson, Mika
- About the subject
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Biological Scien ...
- and Bioinformatics a ...
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Biological Scien ...
- and Genetics
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Biological Scien ...
- and Biochemistry and ...
- Articles in the publication
- npj Systems Biol ...
- By the university
- University of Skövde
- Linköping University
- Karolinska Institutet
Search outside SwePub
- Extend your search to:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - National Library Systems
- LIBRIS.kb.se
