Choosing negative examples for the prediction of protein-protein interactions

Abstract

The protein-protein interaction networks of even well-studied model organisms are sketchy at best, highlighting the continued need for computational methods to help direct experimentalists in the search for novel interactions. This need has prompted the development of a number of methods for predicting protein-protein interactions based on various sources of data and methodologies. The common method for choosing negative examples for training a predictor of protein-protein interactions is based on annotations of cellular localization, and the observation that pairs of proteins that have different localization patterns are unlikely to interact. While this method leads to high quality sets of non-interacting proteins, we find that this choice can lead to biased estimates of prediction accuracy, because the constraints placed on the distribution of the negative examples makes the task easier. The effects of this bias are demonstrated in the context of both sequence-based and non-sequence based features used for predicting protein-protein interactions.

References 32

1. 1.

   This reference’s wording can’t be shown under the paper’s licence.

   Not in our library10.1038/nature750

2. 2.

   This reference’s wording can’t be shown under the paper’s licence.

   Not in our library10.1006/jmbi.2001.4920

3. 3.

   This reference’s wording can’t be shown under the paper’s licence.

   Not in our library10.1101/gr.153002

4. 4.

   This reference’s wording can’t be shown under the paper’s licence.

   Not in our library10.1093/bioinformatics/btg352

5. 5.

   This reference’s wording can’t be shown under the paper’s licence.

   Not in our library

6. 6.

   This reference’s wording can’t be shown under the paper’s licence.

   Not in our library10.1093/bioinformatics/bth483

7. 7.

   This reference’s wording can’t be shown under the paper’s licence.

   Not in our library10.1093/bioinformatics/bti1016

8. 8.

   This reference’s wording can’t be shown under the paper’s licence.

   Not in our library10.1016/s0022-2836(03)00114-1

9. 9.

   This reference’s wording can’t be shown under the paper’s licence.

   Not in our library10.1002/prot.10074

10. 10.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1126/science.285.5428.751

11. 11.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1126/science.1087361

12. 12.
    Predicting co-complexed protein pairs using genomic and proteomic data integration · 2004

    Not checked
13. 13.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1186/1471-2105-5-154

14. 14.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1016/s0022-2836(03)00239-0

15. 15.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1074/mcp.m100037-mcp200

16. 16.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1016/j.mib.2004.08.012

17. 17.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library

18. 18.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1093/nar/gkg466

19. 19.
    Genomic Expression Programs in the Response of Yeast Cells to Environmental ChangesD⃞ · 2000

    Not checked
20. 20.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1038/75556

21. 21.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library

22. 22.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1093/bioinformatics/btg153

23. 23.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1073/pnas.102102699

24. 24.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1093/nar/29.1.242

25. 25.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1093/nar/28.1.37

26. 26.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1093/nar/30.1.303

27. 27.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library

28. 28.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library

29. 29.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library

30. 30.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library

31. 31.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1093/bioinformatics/btg1002

32. 32.

    This reference’s wording can’t be shown under the paper’s licence.

    Not in our library10.1093/nar/gki060

Cited by papers we hold 9

• AnOxPePred: using deep learning for the prediction of antioxidative properties of peptides · 2020
  No notice
• Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases · 2018
  No notice
• Negatome 2.0: a database of non-interacting proteins derived by literature mining, manual annotation and protein structure analysis · 2013
  No notice
• The Impact of Multifunctional Genes on "Guilt by Association" Analysis · 2011
  No notice
• Proteome scanning to predict PDZ domain interactions using support vector machines · 2010
  Not checked
• A human functional protein interaction network and its application to cancer data analysis · 2010
  No notice
• Semantic Similarity in Biomedical Ontologies · 2009
  No notice
• Finding function: evaluation methods for functional genomic data · 2006
  No notice
• LIGSITEcsc: predicting ligand binding sites using the Connolly surface and degree of conservation. · 2006
  No notice

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.