ApisTox: a new benchmark dataset for the classification of small molecules toxicity on honey bees
2024

ApisTox: A New Dataset for Honey Bee Toxicity

Sample size: 1035 publication 10 minutes Evidence: high

Author Information

Author(s): Jakub Adamczyk, Jakub Poziemski, Pawel Siedlecki

Primary Institution: AGH University of Krakow, Department of Computer Science, Cracow, Poland

Hypothesis

The study aims to create a comprehensive dataset to assess the toxicity of pesticides on honey bees.

Conclusion

The ApisTox dataset provides a high-quality, curated resource for studying pesticide toxicity on honey bees, addressing significant gaps in existing data.

Supporting Evidence

  • The dataset combines data from ECOTOX, PPDB, and BPDB, providing a more comprehensive resource than previous datasets.
  • ApisTox includes toxicity levels for various pesticides and their publication dates, enhancing the dataset's utility for research.
  • The dataset allows for benchmarking molecular property prediction methods, facilitating advancements in environmental science.

Takeaway

ApisTox is a big collection of information about how different chemicals affect honey bees, helping scientists understand and protect them better.

Methodology

The dataset was created by combining and curating data from multiple sources, focusing on the median lethal dose (LD50) as a measure of toxicity.

Potential Biases

Potential biases may arise from the selection of data sources and the methods used for data curation.

Limitations

The dataset may still have inconsistencies due to the variability in data sources and the inherent uncertainty in toxicity measurements.

Participant Demographics

The dataset focuses on honey bees (Apis mellifera) and includes various pesticides affecting them.

Digital Object Identifier (DOI)

10.1038/s41597-024-04232-w

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication