Evaluation Method for Feature Rankings and their Aggregations for Biomarker Discovery

Ivica Slavkov, Bernard Ženko, Sašo Džeroski
Proceedings of the third International Workshop on Machine Learning in Systems Biology, PMLR 8:122-135, 2009.

Abstract

In this paper we investigate the problem of evaluating ranked lists of biomarkers, which are typically an output of the analysis of high-throughput data. This can be a list of probes from microarray experiments, which are ordered by the strength of their correlation to a disease. Usually, the ordering of the biomarkers in the ranked lists varies a lot if they are a result of different studies or methods. Our work consists of two parts. First, we propose a method for evaluating the “correctness” of the ranked lists. Second, we conduct a preliminary study of different aggregation approaches of the feature rankings, like aggregating rankings produced from different ranking algorithms and different datasets. We perform experiments on multiple public Neuroblastoma microarray studies. Our results show that there is a generally beneficial effect of aggregating feature rankings as compared to the ones produced by a single study or single method.

Cite this Paper

BibTeX
@InProceedings{pmlr-v8-slavkov10a, title = {Evaluation Method for Feature Rankings and their Aggregations for Biomarker Discovery}, author = {Slavkov, Ivica and Ženko, Bernard and Džeroski, Sašo}, booktitle = {Proceedings of the third International Workshop on Machine Learning in Systems Biology}, pages = {122--135}, year = {2009}, editor = {Džeroski, Sašo and Guerts, Pierre and Rousu, Juho}, volume = {8}, series = {Proceedings of Machine Learning Research}, address = {Ljubljana, Slovenia}, month = {05--06 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v8/slavkov10a/slavkov10a.pdf}, url = {https://proceedings.mlr.press/v8/slavkov10a.html}, abstract = {In this paper we investigate the problem of evaluating ranked lists of biomarkers, which are typically an output of the analysis of high-throughput data. This can be a list of probes from microarray experiments, which are ordered by the strength of their correlation to a disease. Usually, the ordering of the biomarkers in the ranked lists varies a lot if they are a result of different studies or methods. Our work consists of two parts. First, we propose a method for evaluating the “correctness” of the ranked lists. Second, we conduct a preliminary study of different aggregation approaches of the feature rankings, like aggregating rankings produced from different ranking algorithms and different datasets. We perform experiments on multiple public Neuroblastoma microarray studies. Our results show that there is a generally beneficial effect of aggregating feature rankings as compared to the ones produced by a single study or single method.} }
Endnote
%0 Conference Paper %T Evaluation Method for Feature Rankings and their Aggregations for Biomarker Discovery %A Ivica Slavkov %A Bernard Ženko %A Sašo Džeroski %B Proceedings of the third International Workshop on Machine Learning in Systems Biology %C Proceedings of Machine Learning Research %D 2009 %E Sašo Džeroski %E Pierre Guerts %E Juho Rousu %F pmlr-v8-slavkov10a %I PMLR %P 122--135 %U https://proceedings.mlr.press/v8/slavkov10a.html %V 8 %X In this paper we investigate the problem of evaluating ranked lists of biomarkers, which are typically an output of the analysis of high-throughput data. This can be a list of probes from microarray experiments, which are ordered by the strength of their correlation to a disease. Usually, the ordering of the biomarkers in the ranked lists varies a lot if they are a result of different studies or methods. Our work consists of two parts. First, we propose a method for evaluating the “correctness” of the ranked lists. Second, we conduct a preliminary study of different aggregation approaches of the feature rankings, like aggregating rankings produced from different ranking algorithms and different datasets. We perform experiments on multiple public Neuroblastoma microarray studies. Our results show that there is a generally beneficial effect of aggregating feature rankings as compared to the ones produced by a single study or single method.
RIS
TY - CPAPER TI - Evaluation Method for Feature Rankings and their Aggregations for Biomarker Discovery AU - Ivica Slavkov AU - Bernard Ženko AU - Sašo Džeroski BT - Proceedings of the third International Workshop on Machine Learning in Systems Biology DA - 2009/03/02 ED - Sašo Džeroski ED - Pierre Guerts ED - Juho Rousu ID - pmlr-v8-slavkov10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 8 SP - 122 EP - 135 L1 - http://proceedings.mlr.press/v8/slavkov10a/slavkov10a.pdf UR - https://proceedings.mlr.press/v8/slavkov10a.html AB - In this paper we investigate the problem of evaluating ranked lists of biomarkers, which are typically an output of the analysis of high-throughput data. This can be a list of probes from microarray experiments, which are ordered by the strength of their correlation to a disease. Usually, the ordering of the biomarkers in the ranked lists varies a lot if they are a result of different studies or methods. Our work consists of two parts. First, we propose a method for evaluating the “correctness” of the ranked lists. Second, we conduct a preliminary study of different aggregation approaches of the feature rankings, like aggregating rankings produced from different ranking algorithms and different datasets. We perform experiments on multiple public Neuroblastoma microarray studies. Our results show that there is a generally beneficial effect of aggregating feature rankings as compared to the ones produced by a single study or single method. ER -
APA
Slavkov, I., Ženko, B. & Džeroski, S.. (2009). Evaluation Method for Feature Rankings and their Aggregations for Biomarker Discovery. Proceedings of the third International Workshop on Machine Learning in Systems Biology, in Proceedings of Machine Learning Research 8:122-135 Available from https://proceedings.mlr.press/v8/slavkov10a.html.

Related Material