exML: An Explainable Maximum Likelihood Tool for Proportion Estimation in DNA Data

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Estimating proportions of elements in a given set is a key problem in multiple scenarios. A particular use case of interest is the analysis of ancient DNA, where the goal is to estimate the proportion of species in a set of DNA reads extracted from sediments in archaeological sites. While there is a plethora of existing solutions for this type of problem, they lack explainability, which leads to challenges in their debugging and deployment as well as in downstream analysis tasks. To this end, we have developed exML, a Maximum Likelihood Estimator equipped with novel explanation methods. We propose to demonstrate exML in the context of analyzing ancient DNA samples. We will show use cases where the explanations generated by exML provide insights on otherwise ambiguous classification results.

Original languageEnglish
Title of host publicationCIKM 2022 - Proceedings of the 31st ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages4818-4822
Number of pages5
ISBN (Electronic)9781450392365
DOIs
StatePublished - 17 Oct 2022
Event31st ACM International Conference on Information and Knowledge Management, CIKM 2022 - Atlanta, United States
Duration: 17 Oct 202221 Oct 2022

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings

Conference

Conference31st ACM International Conference on Information and Knowledge Management, CIKM 2022
Country/TerritoryUnited States
CityAtlanta
Period17/10/2221/10/22

Keywords

  • ancient DNA
  • computational genomics
  • explainability
  • maximum likelihood
  • Shapley value

Fingerprint

Dive into the research topics of 'exML: An Explainable Maximum Likelihood Tool for Proportion Estimation in DNA Data'. Together they form a unique fingerprint.

Cite this