FRI > Biolab > Supplements

Data set name: DLBCL


Original data set (Shipp et al.)
Data set for Orange
Brief description:
Diffuse large B-cell lymphomas (DLBCL) and follicular lymphomas (FL) are two B-cell lineage malignancies that have very different clinical presentations, natural histories and response to therapy. However, FLs frequently evolve over time and acquire the morphologic and clinical features of DLBCLs and some subsets of DLBCLs have chromosomal translocations characteristic of FLs. The gene-expression based classification model was built to distinguish between these two lymphomas.

Platform: Affymetrix HuGeneFL array

Diagnostic classes:
- Diffuse large B-cell lymphoma (DLBCL): 58 examples (75.3%)
- Follicular lymphoma (FL): 19 examples (24.7%)
Number of genes: 7070
Number of samples: 77
Predictive accuracy with 10-fold cross validation (classifying using the best projection with eight attributes):
Classification accuracy: 90.89%
Area under curve (AUC): 0.944
Following are the three best-ranked visualization with eight, six and four attributes in respect to the visualization score, that is, visualizations where examples from different diagnostic classes are best separated:

Score: 96.15%
Genes:
M57710_at: "lectin, galactoside-binding, soluble, 3 (galectin 3) /// galectin-3 internal gene", LGALS3 /// GALIG
D79997_at: maternal embryonic leucine zipper kinase, MELK
HG1980-HT2023_at: ---, ---
U28386_at: "karyopherin alpha 2 (RAG cohort 1, importin alpha 1)", KPNA2
Z21966_at: "POU domain, class 6, transcription factor 1", POU6F1
D87119_at: tribbles homolog 2 (Drosophila), TRIB2
S73591_at: thioredoxin interacting protein, TXNIP
X03689_s_at: eukaryotic translation elongation factor 1 alpha 1, EEF1A1
Score: 95.78%
Genes:
M57710_at: "lectin, galactoside-binding, soluble, 3 (galectin 3) /// galectin-3 internal gene", LGALS3 /// GALIG
X62078_at: GM2 ganglioside activator, GM2A
X02152_at: lactate dehydrogenase A, LDHA
D87119_at: tribbles homolog 2 (Drosophila), TRIB2
M94880_f_at: "major histocompatibility complex, class I, A", HLA-A
Z21966_at: "POU domain, class 6, transcription factor 1", POU6F1
Score: 94.81%
Genes:
M63138_at: cathepsin D (lysosomal aspartyl peptidase), CTSD
L02426_at: "proteasome (prosome, macropain) 26S subunit, ATPase, 1", PSMC1
M94880_f_at: "major histocompatibility complex, class I, A", HLA-A
L42324_at: G protein-coupled receptor 18, GPR18

Attribute ranking

Following is the histogram of genes showing how often are they present in one of the top 100 radviz visualizations with 8 attributes.

Genes:
X16983_at: "integrin, alpha 4 (antigen CD49D, alpha 4 subunit of VLA-4 receptor)", ITGA4
X02152_at: lactate dehydrogenase A, LDHA
M94880_f_at: "major histocompatibility complex, class I, A", HLA-A
Z21966_at: "POU domain, class 6, transcription factor 1", POU6F1
J03909_at: "interferon, gamma-inducible protein 30", IFI30
D87119_at: tribbles homolog 2 (Drosophila), TRIB2
HG417-HT417_s_at: ---, ---
M22382_at: heat shock 60kDa protein 1 (chaperonin), HSPD1
L17131_rna1_at: high mobility group AT-hook 1, HMGA1
L42324_at: G protein-coupled receptor 18, GPR18
X56494_at: "pyruvate kinase, muscle", PKM2
M63138_at: cathepsin D (lysosomal aspartyl peptidase), CTSD
Z11793_at: "selenoprotein P, plasma, 1", SEPP1
D82348_at: 5-aminoimidazole-4-carboxamide ribonucleotide formyltransferase/IMP cyclohydrolase, ATIC
AB002409_at: chemokine (C-C motif) ligand 21, CCL21
HG1980-HT2023_at: ---, ---
M14328_s_at: "enolase 1, (alpha)", ENO1
J04173_at: phosphoglycerate mutase 1 (brain), PGAM1
X03689_s_at: eukaryotic translation elongation factor 1 alpha 1, EEF1A1
D78134_at: cold inducible RNA binding protein, CIRBP