Szczegóły publikacji
Opis bibliograficzny
Mining a massive RNA-seq dataset with biclustering: are evolutionary approaches ready for big data? / Patryk ORZECHOWSKI, Jason H. Moore // W: GECCO 2019 [Dokument elektroniczny] : the Genetic and Evolutionary Computation Conference : a recombination of the 28th International Conference on Genetic Algorithms (ICGA) and the 24rd Annual Genetic Programming Conference (GP) : July 13th–17th 2019, Prague, Czech Republic. — Wersja do Windows. — Dane tekstowe. — USA : ACM, cop. 2019. — e-ISBN: 978-1-4503-6748-6. — S. 304–305. — Wymagania systemowe: Adobe Reader. — Tryb dostępu: https://dl.acm.org/ft_gateway.cfm?id=3321916=2071065 [2019-09-18]. — Bibliogr. s. 305, Abstr. — P. Orzechowski – dod. afilicja: University of Pennsylvania
Autorzy (2)
- AGHOrzechowski Patryk
- Moore Jason H.
Słowa kluczowe
Dane bibliometryczne
ID BaDAP | 124341 |
---|---|
Data dodania do BaDAP | 2019-10-09 |
DOI | 10.1145/3319619.3321916 |
Rok publikacji | 2019 |
Typ publikacji | materiały konferencyjne (aut.) |
Otwarty dostęp | |
Wydawca | Association for Computing Machinery (ACM) |
Konferencja | Genetic and Evolutionary Computation Conference |
Abstract
Finding meaningful structures in big data is challenging, especially within big and noisy data. In this short paper, we present the results of the application of 6 different biclustering methods to a massive human RNA-seq dataset with over 35k genes from over 125k samples. We assess which biclustering methods can handle that large data and compare the results to the mini-batch k-means, a popular clustering approach. Finally, we assess the importance of evolutionary-based approaches in biclustering 'big data'. © 2019 Copyright held by the owner/author(s). Publication rights licensed to the Association for Computing Machinery.