Identification of Subpopulations in Breast Cancer Data through Different Clustering Algorithms

1
Identification of Sub-populations inBreast
Cancer Data throughDifferent Clustering
Algorithms

• Daniele Soria
• http//www.cs.nott.ac.uk/dqs
• Supervisors Jon Garibaldi, Elia Biganzoli, Ian
  Ellis
• BIOPTRAIN Meeting 09-01-2007

2
Background

• Identification of biologically distinct groups
  with clinical and prognostic relevance.
• TMA technology allows concomitant analyses of
  many proteins on tumour samples.
• Started from Abd El-Rehim et al. (2005) 1
• IHC applied to TMA preparations of cases of
  invasive breast cancer
• To study the combined protein expression profiles
  of a large panel of biomarkers.

3
Abd El-Rehim et al. (2005)

• IHC results analyzed with hierarchical clustering
• ANN to categorize cases into groups
• Six groups obtained
• Each group driven by different markers
• Arbitrary choice of clusters number

4
Aims of our work

• Apply different clustering techniques
• Integrate previous results and compare them with
  ours
• Verify stability of results across different
  methods

5
Patients

• Patients entered into the Nottingham Tenovus
  Primary Breast Carcinoma Series between 1986 and
  1998
• A total of 1076 cases informative for all 25
  biological markers
• Clinical information (grade, size, age, survival,
  follow-up, etc.)

6
Methods

• Algorithms we used (2?20)
• Fuzzy c-means (FCM)
• K-means (KM)
• Partitioning Around Medoids (PAM)
• Validity indices computed
• Software R used (www.r-project.org)
• Methods provided by other authors
• Hierarchical (Hier)
• Adaptive Resonance Theory (ART)

7
Results

• FCM quite unstable
• KM not clear classification (3 or 6 groups)
• PAM best computational method (4 groups)
• Hier same results as in 1
• ART six (fixed) groups
• Classes definition and characterisation

8
KM and PAM
9
Principal Components
km1, km2, km3,
pam1, pam2, pam3, pam4 km4, km5,
km6
10
Results

• FCM quite unstable
• KM not clear classification (6 groups)
• PAM best computational method (4 groups)
• Hier same results as in 1
• ART six (fixed) groups
• Classes definition and characterisation

11
Classes
class1 class2 class3 class4 class5 cla
ss6 62 of data
12
Box plots
13
Actual and future work

• Clinical interpretation of the results
• Survival analysis (second events)
• Recover all the missing information
• Different initialization techniques

14
Main references

• D.M. Abd El-Rehim, G. Ball, S.E. Pinder, E.
  Rakha, C. Paish, J.F. Robertson, D. Macmillan,
  R.W. Blamey, I.O. Ellis, High-throughput protein
  expression analysis using tissue microarray
  technology of a large well-characterised series
  identifies biologically distinct classes of
  breast cancer confirming recent cDNA expression
  analyses, Int. Journal of Cancer, 116, 340-350,
  2005.
• L. Kaufman, P.J. Rousseeuw, Finding groups in
  data, Wiley series in probability and
  mathematical statistics, 1990.
• A. Weingessel, E. Dimitriadou and S. Dolnicar, An
  Examination Of Indexes For Determining The Number
  Of Clusters In Binary Data Sets, Working Paper
  No.29, 1999.

15
Identification of Sub-populations inBreast
Cancer Data throughDifferent Clustering
Algorithms

• Thank you!

16
BIOPTRAIN web page

• Talk given (ASAP group seminar)
• Courses attended (biology and bioinformatics
  ones)
• Research skills modules (Grad School)
• Communication skills modules (CELE)
• All entries divided by year