IDEAS home Printed from https://ideas.repec.org/a/plo/pcbi00/1004509.html
   My bibliography  Save this article

Beyond the E-Value: Stratified Statistics for Protein Domain Prediction

Author

Listed:
  • Alejandro Ochoa
  • John D Storey
  • Manuel Llinás
  • Mona Singh

Abstract

E-values have been the dominant statistic for protein sequence analysis for the past two decades: from identifying statistically significant local sequence alignments to evaluating matches to hidden Markov models describing protein domain families. Here we formally show that for “stratified” multiple hypothesis testing problems—that is, those in which statistical tests can be partitioned naturally—controlling the local False Discovery Rate (lFDR) per stratum, or partition, yields the most predictions across the data at any given threshold on the FDR or E-value over all strata combined. For the important problem of protein domain prediction, a key step in characterizing protein structure, function and evolution, we show that stratifying statistical tests by domain family yields excellent results. We develop the first FDR-estimating algorithms for domain prediction, and evaluate how well thresholds based on q-values, E-values and lFDRs perform in domain prediction using five complementary approaches for estimating empirical FDRs in this context. We show that stratified q-value thresholds substantially outperform E-values. Contradicting our theoretical results, q-values also outperform lFDRs; however, our tests reveal a small but coherent subset of domain families, biased towards models for specific repetitive patterns, for which weaknesses in random sequence models yield notably inaccurate statistical significance measures. Usage of lFDR thresholds outperform q-values for the remaining families, which have as-expected noise, suggesting that further improvements in domain predictions can be achieved with improved modeling of random sequences. Overall, our theoretical and empirical findings suggest that the use of stratified q-values and lFDRs could result in improvements in a host of structured multiple hypothesis testing problems arising in bioinformatics, including genome-wide association studies, orthology prediction, and motif scanning.Author Summary: Despite decades of research, it remains a challenge to distinguish homologous relationships between proteins from sequence similarities arising due to chance alone. This is an increasingly important problem as sequence database sizes continue to grow, and even today many computational analyses require that the statistics of billions of sequence comparisons be assessed automatically. Here we explore statistical significance evaluation on data that is stratified—that is, naturally partitioned into subsets that may differ in their amount of signal—and find a theoretically optimal criterion for automatically setting thresholds of significance for each stratum. For the task of domain prediction, an important component of efforts to annotate protein sequences and identify remote sequence homologs, we empirically show that our stratified analysis of statistical significance greatly improves upon a combined analysis. Further, we identify weaknesses in the prevailing random sequence model for assessing statistical significance for a small subset of domain families with repetitive sequence patterns and known biological, structural, and evolutionary properties. Our theoretical findings in statistics are relevant not only for identifying protein domains, but for arbitrary stratified problems in genomics and beyond.

Suggested Citation

  • Alejandro Ochoa & John D Storey & Manuel Llinás & Mona Singh, 2015. "Beyond the E-Value: Stratified Statistics for Protein Domain Prediction," PLOS Computational Biology, Public Library of Science, vol. 11(11), pages 1-21, November.
  • Handle: RePEc:plo:pcbi00:1004509
    DOI: 10.1371/journal.pcbi.1004509
    as

    Download full text from publisher

    File URL: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1004509
    Download Restriction: no

    File URL: https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1004509&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pcbi.1004509?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Stephen F Altschul & John C Wootton & Elena Zaslavsky & Yi-Kuo Yu, 2010. "The Construction and Use of Log-Odds Substitution Scores for Multiple Sequence Alignment," PLOS Computational Biology, Public Library of Science, vol. 6(7), pages 1-17, July.
    2. Sun, Wenguang & Cai, T. Tony, 2007. "Oracle and Adaptive Compound Decision Rules for False Discovery Rate Control," Journal of the American Statistical Association, American Statistical Association, vol. 102, pages 901-912, September.
    3. John D. Storey & Jonathan E. Taylor & David Siegmund, 2004. "Strong control, conservative point estimation and simultaneous conservative consistency of false discovery rates: a unified approach," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 66(1), pages 187-205, February.
    4. Sean R Eddy, 2011. "Accelerated Profile HMM Searches," PLOS Computational Biology, Public Library of Science, vol. 7(10), pages 1-16, October.
    5. Hu, James X. & Zhao, Hongyu & Zhou, Harrison H., 2010. "False Discovery Rate Control With Groups," Journal of the American Statistical Association, American Statistical Association, vol. 105(491), pages 1215-1227.
    6. Cai, T. Tony & Sun, Wenguang, 2009. "Simultaneous Testing of Grouped Hypotheses: Finding Needles in Multiple Haystacks," Journal of the American Statistical Association, American Statistical Association, vol. 104(488), pages 1467-1481.
    7. Sean R Eddy, 2008. "A Probabilistic Model of Local Sequence Alignment That Simplifies Statistical Significance Estimation," PLOS Computational Biology, Public Library of Science, vol. 4(5), pages 1-14, May.
    8. Efron B. & Tibshirani R. & Storey J.D. & Tusher V., 2001. "Empirical Bayes Analysis of a Microarray Experiment," Journal of the American Statistical Association, American Statistical Association, vol. 96, pages 1151-1160, December.
    9. Wing-Cheong Wong & Sebastian Maurer-Stroh & Frank Eisenhaber, 2010. "More Than 1,001 Problems with Protein Domain Databases: Transmembrane Regions, Signal Peptides and the Issue of Sequence Homology," PLOS Computational Biology, Public Library of Science, vol. 6(7), pages 1-19, July.
    10. John D. Storey, 2002. "A direct approach to false discovery rates," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 64(3), pages 479-498, August.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Nikolaos Ignatiadis & Wolfgang Huber, 2021. "Covariate powered cross‐weighted multiple testing," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 83(4), pages 720-751, September.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Nikolaos Ignatiadis & Wolfgang Huber, 2021. "Covariate powered cross‐weighted multiple testing," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 83(4), pages 720-751, September.
    2. Zhao, Haibing & Fung, Wing Kam, 2016. "A powerful FDR control procedure for multiple hypotheses," Computational Statistics & Data Analysis, Elsevier, vol. 98(C), pages 60-70.
    3. T. Tony Cai & Wenguang Sun & Weinan Wang, 2019. "Covariate‐assisted ranking and screening for large‐scale two‐sample inference," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 81(2), pages 187-234, April.
    4. Habiger, Joshua D. & Peña, Edsel A., 2014. "Compound p-value statistics for multiple testing procedures," Journal of Multivariate Analysis, Elsevier, vol. 126(C), pages 153-166.
    5. Xiaoquan Wen, 2017. "Robust Bayesian FDR Control Using Bayes Factors, with Applications to Multi-tissue eQTL Discovery," Statistics in Biosciences, Springer;International Chinese Statistical Association, vol. 9(1), pages 28-49, June.
    6. Chen, Xiongzhi, 2019. "Uniformly consistently estimating the proportion of false null hypotheses via Lebesgue–Stieltjes integral equations," Journal of Multivariate Analysis, Elsevier, vol. 173(C), pages 724-744.
    7. Dennis Leung & Wenguang Sun, 2022. "ZAP: Z$$ Z $$‐value adaptive procedures for false discovery rate control with side information," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 84(5), pages 1886-1946, November.
    8. Haibing Zhao & Xinping Cui, 2020. "Constructing confidence intervals for selected parameters," Biometrics, The International Biometric Society, vol. 76(4), pages 1098-1108, December.
    9. Li Wang, 2019. "Weighted multiple testing procedure for grouped hypotheses with k-FWER control," Computational Statistics, Springer, vol. 34(2), pages 885-909, June.
    10. Wen Shi & Xi Chen & Jennifer Shang, 2019. "An Efficient Morris Method-Based Framework for Simulation Factor Screening," INFORMS Journal on Computing, INFORMS, vol. 31(4), pages 745-770, October.
    11. Ghosh Debashis, 2012. "Incorporating the Empirical Null Hypothesis into the Benjamini-Hochberg Procedure," Statistical Applications in Genetics and Molecular Biology, De Gruyter, vol. 11(4), pages 1-21, July.
    12. Joshua Habiger & David Watts & Michael Anderson, 2017. "Multiple testing with heterogeneous multinomial distributions," Biometrics, The International Biometric Society, vol. 73(2), pages 562-570, June.
    13. Izmirlian, Grant, 2020. "Strong consistency and asymptotic normality for quantities related to the Benjamini–Hochberg false discovery rate procedure," Statistics & Probability Letters, Elsevier, vol. 160(C).
    14. Cipolli III, William & Hanson, Timothy & McLain, Alexander C., 2016. "Bayesian nonparametric multiple testing," Computational Statistics & Data Analysis, Elsevier, vol. 101(C), pages 64-79.
    15. Guo Wenge & Peddada Shyamal, 2008. "Adaptive Choice of the Number of Bootstrap Samples in Large Scale Multiple Testing," Statistical Applications in Genetics and Molecular Biology, De Gruyter, vol. 7(1), pages 1-21, March.
    16. T. Tony Cai & Wenguang Sun, 2017. "Optimal screening and discovery of sparse signals with applications to multistage high throughput studies," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 79(1), pages 197-223, January.
    17. Alessio Farcomeni, 2006. "More Powerful Control of the False Discovery Rate Under Dependence," Statistical Methods & Applications, Springer;Società Italiana di Statistica, vol. 15(1), pages 43-73, May.
    18. Nik Tuzov & Frederi Viens, 2011. "Mutual fund performance: false discoveries, bias, and power," Annals of Finance, Springer, vol. 7(2), pages 137-169, May.
    19. Leek Jeffrey T & Storey John D., 2011. "The Joint Null Criterion for Multiple Hypothesis Tests," Statistical Applications in Genetics and Molecular Biology, De Gruyter, vol. 10(1), pages 1-22, June.
    20. Debashis Ghosh & Wei Chen & Trivellore Raghuanthan, 2004. "The false discovery rate: a variable selection perspective," The University of Michigan Department of Biostatistics Working Paper Series 1040, Berkeley Electronic Press.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pcbi00:1004509. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: ploscompbiol (email available below). General contact details of provider: https://journals.plos.org/ploscompbiol/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.