Transformers enable accurate prediction of acute and chronic chemical toxicity in aquatic organisms

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Search: WFRF:(Backhaus Erik) > Transformers enable...

Details
MARC

Gustavsson, MikaelGothenburg University,Göteborgs universitet,Institutionen för matematiska vetenskaper,Institutionen för nationalekonomi med statistik, Enheten för miljöekonomi,Department of Mathematical Sciences,Department of Economics, Environmental Economics Unit (author)

Transformers enable accurate prediction of acute and chronic chemical toxicity in aquatic organisms

Article/chapterEnglish2024

Publisher, publication year, extent ...

2024

Numbers

LIBRIS-ID:oai:gup.ub.gu.se/335579
https://gup.ub.gu.se/publication/335579URI
https://doi.org/10.1126/sciadv.adk6669DOI

Supplementary language notes

Language:English

Part of subdatabase

SwePubSwePub

Classification

Subject category:ref swepub-contenttype
Subject category:art swepub-publicationtype

Notes

Environmental hazard assessments are reliant on toxicity data that cover multiple organism groups. Generating experimental toxicity data is, however, resource-intensive and time-consuming. Computational methods are fast and cost-efficient alternatives, but the low accuracy and narrow applicability domains have made their adaptation slow. Here, we present a AI-based model for predicting chemical toxicity. The model uses transformers to capture toxicity-specific features directly from the chemical structures and deep neural networks to predict effect concentrations. The model showed high predictive performance for all tested organism groups—algae, aquatic invertebrates and fish—and has, in comparison to commonly used QSAR methods, a larger applicability domain and a considerably lower error. When the model was trained on data with multiple effect concentrations (EC50/EC10), the performance was further improved. We conclude that deep learning and transformers have the potential to markedly advance computational prediction of chemical toxicity.

Subject headings and genre

NATURVETENSKAP Data- och informationsvetenskap hsv//swe
NATURAL SCIENCES Computer and Information Sciences hsv//eng
SAMHÄLLSVETENSKAP Ekonomi och näringsliv Nationalekonomi hsv//swe
SOCIAL SCIENCES Economics and Business Economics hsv//eng
AI-based transformers model Prediction of chemical toxicity Chemical regulation

Added entries (persons, corporate bodies, meetings, titles ...)

Käll, Styrbjörn,1998Gothenburg University,Göteborgs universitet,Institutionen för matematiska vetenskaper,Department of Mathematical Sciences(Swepub:gu)xkasty (author)
Svedberg, PatrikGothenburg University,Göteborgs universitet,Institutionen för biologi och miljövetenskap,Department of Biological and Environmental Sciences(Swepub:gu)xsvedx (author)
Inda Díaz, Juan Salvador,1984Gothenburg University,Göteborgs universitet,Institutionen för matematiska vetenskaper,Department of Mathematical Sciences(Swepub:gu)xindju (author)
Molander, Sverker,1957Gothenburg University,Göteborgs universitet,FRAM Centrum för framtidens kemiska riskanalyser och styrning,FRAM Centre for Future Chemical Risk Assessment and Management Strategies (author)
Coria, Jessica,1979Gothenburg University,Göteborgs universitet,Institutionen för nationalekonomi med statistik, Enheten för miljöekonomi,FRAM Centrum för framtidens kemiska riskanalyser och styrning,Department of Economics, Environmental Economics Unit,FRAM Centre for Future Chemical Risk Assessment and Management Strategies(Swepub:gu)xcorij (author)
Backhaus, Thomas,1967Gothenburg University,Göteborgs universitet,FRAM Centrum för framtidens kemiska riskanalyser och styrning,Institutionen för biologi och miljövetenskap,FRAM Centre for Future Chemical Risk Assessment and Management Strategies,Department of Biological and Environmental Sciences(Swepub:gu)xbacth (author)
Kristiansson, Erik,1978Gothenburg University,Göteborgs universitet,Institutionen för matematiska vetenskaper,Department of Mathematical Sciences(Swepub:gu)xkrier (author)
Göteborgs universitetInstitutionen för matematiska vetenskaper (creator_code:org_t)

Related titles

In:Sciences Advances10:10

Internet link

Find in a library

Sciences Advances (Search for host publication in LIBRIS)

To the university's database

Find more in SwePub

By the author/editor: Gustavsson, Mika ...; Käll, Styrbjörn, ...; Svedberg, Patrik; Inda Díaz, Juan ...; Molander, Sverke ...; Coria, Jessica, ...; show more...; Backhaus, Thomas ...; Kristiansson, Er ...; show less...

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...

SOCIAL SCIENCES: SOCIAL SCIENCES; and Economics and Bu ...; and Economics

Articles in the publication: Sciences Advance ...

By the university: University of Gothenburg

Search outside SwePub

Extend your search to:: Google; 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.

LIBRIS.kb.se