PMID- 16054254
OWN - NLM
STAT- MEDLINE
DCOM- 20060518
LR  - 20060320
IS  - 0167-7012 (Print)
IS  - 0167-7012 (Linking)
VI  - 65
IP  - 1
DP  - 2006 Apr
TI  - An eco-informatics tool for microbial community studies: supervised 
      classification of Amplicon Length Heterogeneity (ALH) profiles of 16S rRNA.
PG  - 49-62
AB  - Support vector machines (SVM) and K-nearest neighbors (KNN) are two computational 
      machine learning tools that perform supervised classification. This paper 
      presents a novel application of such supervised analytical tools for microbial 
      community profiling and to distinguish patterning among ecosystems. Amplicon 
      length heterogeneity (ALH) profiles from several hypervariable regions of 16S 
      rRNA gene of eubacterial communities from Idaho agricultural soil samples and 
      from Chesapeake Bay marsh sediments were separately analyzed. The profiles from 
      all available hypervariable regions were concatenated to obtain a combined 
      profile, which was then provided to the SVM and KNN classifiers. Each profile was 
      labeled with information about the location or time of its sampling. We 
      hypothesized that after a learning phase using feature vectors from labeled ALH 
      profiles, both these classifiers would have the capacity to predict the labels of 
      previously unseen samples. The resulting classifiers were able to predict the 
      labels of the Idaho soil samples with high accuracy. The classifiers were less 
      accurate for the classification of the Chesapeake Bay sediments suggesting 
      greater similarity within the Bay's microbial community patterns in the sampled 
      sites. The profiles obtained from the V1+V2 region were more informative than 
      that obtained from any other single region. However, combining them with profiles 
      from the V1 region (with or without the profiles from the V3 region) resulted in 
      the most accurate classification of the samples. The addition of profiles from 
      the V 9 region appeared to confound the classifiers. Our results show that SVM 
      and KNN classifiers can be effectively applied to distinguish between eubacterial 
      community patterns from different ecosystems based only on their ALH profiles.
FAU - Yang, Chengyong
AU  - Yang C
AD  - Bioinformatics Research Group (BioRG), School of Computer Science, Florida 
      International University, Miami, Florida, 33199, USA.
FAU - Mills, DeEtta
AU  - Mills D
FAU - Mathee, Kalai
AU  - Mathee K
FAU - Wang, Yong
AU  - Wang Y
FAU - Jayachandran, Krish
AU  - Jayachandran K
FAU - Sikaroodi, Masoumeh
AU  - Sikaroodi M
FAU - Gillevet, Patrick
AU  - Gillevet P
FAU - Entry, Jim
AU  - Entry J
FAU - Narasimhan, Giri
AU  - Narasimhan G
LA  - eng
PT  - Journal Article
DEP - 20050727
PL  - Netherlands
TA  - J Microbiol Methods
JT  - Journal of microbiological methods
JID - 8306883
RN  - 0 (DNA, Bacterial)
RN  - 0 (RNA, Ribosomal, 16S)
SB  - IM
MH  - Artificial Intelligence
MH  - DNA, Bacterial/chemistry/*genetics
MH  - *Ecosystem
MH  - Geologic Sediments/*microbiology
MH  - Informatics/*methods
MH  - Pattern Recognition, Automated/methods
MH  - Polymerase Chain Reaction
MH  - RNA, Ribosomal, 16S/chemistry/*genetics
MH  - *Soil Microbiology
EDAT- 2005/08/02 09:00
MHDA- 2006/05/19 09:00
CRDT- 2005/08/02 09:00
PHST- 2005/01/18 00:00 [received]
PHST- 2005/04/22 00:00 [revised]
PHST- 2005/06/24 00:00 [accepted]
PHST- 2005/08/02 09:00 [pubmed]
PHST- 2006/05/19 09:00 [medline]
PHST- 2005/08/02 09:00 [entrez]
AID - S0167-7012(05)00179-X [pii]
AID - 10.1016/j.mimet.2005.06.012 [doi]
PST - ppublish
SO  - J Microbiol Methods. 2006 Apr;65(1):49-62. doi: 10.1016/j.mimet.2005.06.012. Epub 
      2005 Jul 27.