search query: @keyword feature extraction / total: 22
reference: 2 / 22
« previous | next »
Author:Uurtio, Viivi
Title:Computational Analysis of Deep Bedrock Bacterial Communities
Syvän peruskallion bakteeriyhteisöjen karakterisointia laskennallisin menetelmin
Publication type:Master's thesis
Publication year:2014
Pages:vii + 70 s. + liitt. 42      Language:   eng
Department/School:Sähkötekniikan korkeakoulu
Main subject:Laskennallinen ja kognitiivinen biotiede   (IL3003)
Supervisor:Rousu, Juho
Instructor:Bomberg, Malin
Electronic version URL: http://urn.fi/URN:NBN:fi:aalto-201404181702
OEVS:
Electronic archive copy is available via Aalto Thesis Database.
Instructions

Reading digital theses in the closed network of the Aalto University Harald Herlin Learning Centre

In the closed network of Learning Centre you can read digital and digitized theses not available in the open network.

The Learning Centre contact details and opening hours: https://learningcentre.aalto.fi/en/harald-herlin-learning-centre/

You can read theses on the Learning Centre customer computers, which are available on all floors.

Logging on to the customer computers

  • Aalto University staff members log on to the customer computer using the Aalto username and password.
  • Other customers log on using a shared username and password.

Opening a thesis

  • On the desktop of the customer computers, you will find an icon titled:

    Aalto Thesis Database

  • Click on the icon to search for and open the thesis you are looking for from Aaltodoc database. You can find the thesis file by clicking the link on the OEV or OEVS field.

Reading the thesis

  • You can either print the thesis or read it on the customer computer screen.
  • You cannot save the thesis file on a flash drive or email it.
  • You cannot copy text or images from the file.
  • You cannot edit the file.

Printing the thesis

  • You can print the thesis for your personal study or research use.
  • Aalto University students and staff members may print black-and-white prints on the PrintingPoint devices when using the computer with personal Aalto username and password. Color printing is possible using the printer u90203-psc3, which is located near the customer service. Color printing is subject to a charge to Aalto University students and staff members.
  • Other customers can use the printer u90203-psc3. All printing is subject to a charge to non-University members.
Location:P1 Ark Aalto  1010   | Archive
Keywords:metagenome
deep bedrock aquifer
multivariate data analysis
kernel methods
optimization
correlation
dimensionality reduction
feature extraction
metagenomi
syvän peruskallion pohjavesikerros
monimuuttuja-analyysi
ydinfunktio-menetelmät
optimointi
korrelaatio
dimension redusointi
hahmontunnistus
Abstract (eng):In the field of metagenomics, the aim is to relate characteristic environmental parameters to the microbial communities inhabiting the study site.
In a computational framework, the objective is to extract subsets of features in metagenomic data that correlate with measurements obtained from the living environment of the microbial communities.
We compared projection-based multivariate methods, principal component analysis (PCA), kernel canonical correlation analysis (KCCA) and asymmetrical sparse canonical correlation analysis (SCCA), by means of correlation and score plots, in order to assess the capability of each method to reveal the underlying correlation structure of two different metagenomic data sets originating from deep bedrock drill holes.
This approach is novel in the sense that correlation and score plots have not yet been applied to the visualization of KCCA and SCCA results.
We also integrated parameter optimization in SCCA in order to further maximize the correlation of the projections.
As a basis of comparison, we computed Pearson's correlation coefficient among the two sets of features.
From a microbiological perspective, we concentrated on the interactions of sulfate reducing bacteria with the geochemical measurements.
In addition to the expected positive correlations with sulfate and total amount of sulfur, we discovered positive correlations among salinity and sulfate reducers.
From a computational perspective, we demonstrated the feasibility and stability of SCCA in the extraction of highly correlating features from two co-dependent data sets in comparison to Pearson's correlation coefficient, PCA and KCCA.
The results of the parameter optimization in SCCA emphasized the importance of selection of projection directions in terms of correlation.
The presented framework of visualizing and selecting the projection directions can also be extended to other multivariate projection-based methods.
Abstract (fin):Metagenomiikan tieteenalalla tutkitaan, miten tietyn ympäristön parametrit liittyvät siinä eläviin mikrobiyhteisöihin.
Laskennallisesti tavoitteena on käsitellä metagenomista dataa siten, että siitä louhitut osajoukot korreloivat mikrobiyhteisöjen elinympäristöstä saatujen mittauksien kanssa.
Tässä työssä louhittiin kahden eri metagenomisen, syvän peruskallion pohjavesikerroksista saadun, datajoukon korrelaatiorakennetta vertailemalla pääkomponenttianalyysiä (PCA) ydinfunktio-menetelmällä laajennetun (KCCA) ja asymmetrisen harvan kanonisen korrelaatioanalyysin (SCCA) kanssa.
Menetelmiä vertailtiin korrelaatio- ja pistearvokuvaajilla, joita ei ole aikaisemmin sovellettu KCCA- tai SCCA-analyyseihin.
Lisäksi SCCA-analyysin projektioiden kanonista korrelaatiota maksimoitiin parametrien optimoinnilla.
Monimuuttujamenetelmien tuloksia vertailtiin Pearsonin lineaaristen korrelaatiokerrointen kanssa.
Tässä työssä keskityttiin siihen, miten sulfaattia pelkistävät bakteeriyhteisöt vuorovaikuttavat elinympäristöstä saatujen geokemiallisten mittauksien kanssa.
Sulfaatin pelkistäjät korreloivat odotetusti sulfaatin ja rikin kokonaismäärän kanssa.
Tämän lisäksi sulfaatin pelkistäjät korreloivat pohjaveden suolaisuuden kanssa.
Laskennallisesta näkökulmasta katsottuna SCCA oli menetelmistä stabiilein ja käyvin.
Eri projektiosuuntien kanonisten korrelaatioiden vaihtelu korostui SCCA-analyysin parametrien optimoinnissa.
Tässä työssä esitettyä tapaa visualisoida monimuuttujamenetelmien tuloksia voidaan hyödyntää myös muihinkin projektioihin perustuviin menetelmiin.
ED:2014-04-20
INSSI record number: 48899
+ add basket
« previous | next »
INSSI