Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring

Science

Volumn 286, Issue 5439, 1999, Pages 531-527

  Golub, T R ^a,b   Slonim, D K ^a   Tamayo, P ^a   Huard, C ^a   Gaasenbeek, M ^a   Mesirov, J P ^a   Coller, H ^a   Loh, M L ^b   Downing, J R ^c   Caligiuri, M A ^d   Bloomfield, C D ^d   Lander, E S ^a,e  

^a WHITEHEAD INSTITUTE FOR BIOMEDICAL RESEARCH   (United States)

^b HARVARD MEDICAL SCHOOL   (United States)

^c ST JUDE CHILDREN S RESEARCH HOSPITAL   (United States)

^d OHIO STATE UNIVERSITY   (United States)

^e MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACUTE GRANULOCYTIC LEUKEMIA; ACUTE LEUKEMIA; ACUTE LYMPHOBLASTIC LEUKEMIA; ARTICLE; CANCER CLASSIFICATION; CANCER GENETICS; GENE EXPRESSION; HUMAN; PREDICTION; PRIORITY JOURNAL;

ACUTE DISEASE; ANTINEOPLASTIC COMBINED CHEMOTHERAPY PROTOCOLS; CELL ADHESION; CELL CYCLE; GENE EXPRESSION PROFILING; HOMEODOMAIN PROTEINS; HUMANS; LEUKEMIA, LYMPHOCYTIC, ACUTE; LEUKEMIA, MYELOID; NEOPLASM PROTEINS; NEOPLASMS; OLIGONUCLEOTIDE ARRAY SEQUENCE ANALYSIS; ONCOGENES; PREDICTIVE VALUE OF TESTS; REPRODUCIBILITY OF RESULTS; TREATMENT OUTCOME;

EID: 0033569406     PISSN: 00368075     EISSN: None     Source Type: Journal    
DOI: 10.1126/science.286.5439.531     Document Type: Article

References (80)

1. T. J. Triche et al., Prog. Clin. Biol. Res. 271, 475 (1988).
2. C. F. Stephenson, J. A. Bridge, A. A. Sandberg, Hum. Pathol. 23, 1270 (1992); O. Delattre et al., N. Engl. J. Med. 331, 294 (1994); C. Turc-Carel et al., Cancer Genet. Cytogenet. 19, 361 (1986); E. C. Douglass et al., Cytogenet. Cell Genet. 45, 148 (1987); R. Dalla-Favera et al., Proc. Natl. Acad. Sci. U.S.A. 79, 7824 (1982); R. Taub et al., ibid., p. 7837; G. Balaban-Malenbaum and F. Gilbert, Science 198, 739 (1977).
3. C. F. Stephenson, J. A. Bridge, A. A. Sandberg, Hum. Pathol. 23, 1270 (1992); O. Delattre et al., N. Engl. J. Med. 331, 294 (1994); C. Turc-Carel et al., Cancer Genet. Cytogenet. 19, 361 (1986); E. C. Douglass et al., Cytogenet. Cell Genet. 45, 148 (1987); R. Dalla-Favera et al., Proc. Natl. Acad. Sci. U.S.A. 79, 7824 (1982); R. Taub et al., ibid., p. 7837; G. Balaban-Malenbaum and F. Gilbert, Science 198, 739 (1977).
4. C. F. Stephenson, J. A. Bridge, A. A. Sandberg, Hum. Pathol. 23, 1270 (1992); O. Delattre et al., N. Engl. J. Med. 331, 294 (1994); C. Turc-Carel et al., Cancer Genet. Cytogenet. 19, 361 (1986); E. C. Douglass et al., Cytogenet. Cell Genet. 45, 148 (1987); R. Dalla-Favera et al., Proc. Natl. Acad. Sci. U.S.A. 79, 7824 (1982); R. Taub et al., ibid., p. 7837; G. Balaban-Malenbaum and F. Gilbert, Science 198, 739 (1977).
5. C. F. Stephenson, J. A. Bridge, A. A. Sandberg, Hum. Pathol. 23, 1270 (1992); O. Delattre et al., N. Engl. J. Med. 331, 294 (1994); C. Turc-Carel et al., Cancer Genet. Cytogenet. 19, 361 (1986); E. C. Douglass et al., Cytogenet. Cell Genet. 45, 148 (1987); R. Dalla-Favera et al., Proc. Natl. Acad. Sci. U.S.A. 79, 7824 (1982); R. Taub et al., ibid., p. 7837; G. Balaban-Malenbaum and F. Gilbert, Science 198, 739 (1977).
6. C. F. Stephenson, J. A. Bridge, A. A. Sandberg, Hum. Pathol. 23, 1270 (1992); O. Delattre et al., N. Engl. J. Med. 331, 294 (1994); C. Turc-Carel et al., Cancer Genet. Cytogenet. 19, 361 (1986); E. C. Douglass et al., Cytogenet. Cell Genet. 45, 148 (1987); R. Dalla-Favera et al., Proc. Natl. Acad. Sci. U.S.A. 79, 7824 (1982); R. Taub et al., ibid., p. 7837; G. Balaban-Malenbaum and F. Gilbert, Science 198, 739 (1977).
7. C. F. Stephenson, J. A. Bridge, A. A. Sandberg, Hum. Pathol. 23, 1270 (1992); O. Delattre et al., N. Engl. J. Med. 331, 294 (1994); C. Turc-Carel et al., Cancer Genet. Cytogenet. 19, 361 (1986); E. C. Douglass et al., Cytogenet. Cell Genet. 45, 148 (1987); R. Dalla-Favera et al., Proc. Natl. Acad. Sci. U.S.A. 79, 7824 (1982); R. Taub et al., ibid., p. 7837; G. Balaban-Malenbaum and F. Gilbert, Science 198, 739 (1977).
8. C. F. Stephenson, J. A. Bridge, A. A. Sandberg, Hum. Pathol. 23, 1270 (1992); O. Delattre et al., N. Engl. J. Med. 331, 294 (1994); C. Turc-Carel et al., Cancer Genet. Cytogenet. 19, 361 (1986); E. C. Douglass et al., Cytogenet. Cell Genet. 45, 148 (1987); R. Dalla-Favera et al., Proc. Natl. Acad. Sci. U.S.A. 79, 7824 (1982); R. Taub et al., ibid., p. 7837; G. Balaban-Malenbaum and F. Gilbert, Science 198, 739 (1977).
9. S. Farber, L. K. Diamond R. D. Mercer, R. F. Sylvester, J. A. Wolff, N. Engl. J. Med. 238, 787 (1948).
10. C. E. Forkner, Leukemia and Allied Disorders (Macmillan, New York, 1938); E. Frei et al., Blood 18, 431 (1961); Medical Research Council, Br. Med. J. 1, 7 (1963).
11. C. E. Forkner, Leukemia and Allied Disorders (Macmillan, New York, 1938); E. Frei et al., Blood 18, 431 (1961); Medical Research Council, Br. Med. J. 1, 7 (1963).
12. C. E. Forkner, Leukemia and Allied Disorders (Macmillan, New York, 1938); E. Frei et al., Blood 18, 431 (1961); Medical Research Council, Br. Med. J. 1, 7 (1963).
13. D. Quaglino and F. G. J. Hayhoe, J. Pathol. 78, 521 (1959); J. M. Bennett and T. F. Dutcher, Blood 33, 341 (1969); R. C. Graham, U. Lundholm, M. J. Karnovsky, J. Histochem. Cytochem. 13, 150 (1965).
14. D. Quaglino and F. G. J. Hayhoe, J. Pathol. 78, 521 (1959); J. M. Bennett and T. F. Dutcher, Blood 33, 341 (1969); R. C. Graham, U. Lundholm, M. J. Karnovsky, J. Histochem. Cytochem. 13, 150 (1965).
15. D. Quaglino and F. G. J. Hayhoe, J. Pathol. 78, 521 (1959); J. M. Bennett and T. F. Dutcher, Blood 33, 341 (1969); R. C. Graham, U. Lundholm, M. J. Karnovsky, J. Histochem. Cytochem. 13, 150 (1965).
16. I. Tsukimoto, R. Y. Wong, B. C. Lampkin, N. Engl. J. Med. 294, 245 (1976); S. F. Schlossman et al., Proc. Natl. Acad. Sci. U.S.A. 73, 1288 (1976); M. Roper et al, Blood 61, 830 (1983); B. S. E. Sallan et al., ibid. 55, 395 (1980); J. M. Pesando et al., ibid. 54, 1240 (1979).
17. I. Tsukimoto, R. Y. Wong, B. C. Lampkin, N. Engl. J. Med. 294, 245 (1976); S. F. Schlossman et al., Proc. Natl. Acad. Sci. U.S.A. 73, 1288 (1976); M. Roper et al, Blood 61, 830 (1983); B. S. E. Sallan et al., ibid. 55, 395 (1980); J. M. Pesando et al., ibid. 54, 1240 (1979).
18. I. Tsukimoto, R. Y. Wong, B. C. Lampkin, N. Engl. J. Med. 294, 245 (1976); S. F. Schlossman et al., Proc. Natl. Acad. Sci. U.S.A. 73, 1288 (1976); M. Roper et al, Blood 61, 830 (1983); B. S. E. Sallan et al., ibid. 55, 395 (1980); J. M. Pesando et al., ibid. 54, 1240 (1979).
19. I. Tsukimoto, R. Y. Wong, B. C. Lampkin, N. Engl. J. Med. 294, 245 (1976); S. F. Schlossman et al., Proc. Natl. Acad. Sci. U.S.A. 73, 1288 (1976); M. Roper et al, Blood 61, 830 (1983); B. S. E. Sallan et al., ibid. 55, 395 (1980); J. M. Pesando et al., ibid. 54, 1240 (1979).
20. I. Tsukimoto, R. Y. Wong, B. C. Lampkin, N. Engl. J. Med. 294, 245 (1976); S. F. Schlossman et al., Proc. Natl. Acad. Sci. U.S.A. 73, 1288 (1976); M. Roper et al, Blood 61, 830 (1983); B. S. E. Sallan et al., ibid. 55, 395 (1980); J. M. Pesando et al., ibid. 54, 1240 (1979).
21. T. R. Golub et al., Proc. Natl. Acad. Sci. U.S.A. 92, 4917 (1995); T. W. McLean et al., Blood 88, 4252 (1996); S. A. Shurtleff et al., Leukemia 9, 1985 (1995); S. P. Romana et al., Blood 86, 4263 (1995); J. D. Rowley, Ann. Genet. 16, 109 (1973).
22. T. R. Golub et al., Proc. Natl. Acad. Sci. U.S.A. 92, 4917 (1995); T. W. McLean et al., Blood 88, 4252 (1996); S. A. Shurtleff et al., Leukemia 9, 1985 (1995); S. P. Romana et al., Blood 86, 4263 (1995); J. D. Rowley, Ann. Genet. 16, 109 (1973).
23. T. R. Golub et al., Proc. Natl. Acad. Sci. U.S.A. 92, 4917 (1995); T. W. McLean et al., Blood 88, 4252 (1996); S. A. Shurtleff et al., Leukemia 9, 1985 (1995); S. P. Romana et al., Blood 86, 4263 (1995); J. D. Rowley, Ann. Genet. 16, 109 (1973).
24. T. R. Golub et al., Proc. Natl. Acad. Sci. U.S.A. 92, 4917 (1995); T. W. McLean et al., Blood 88, 4252 (1996); S. A. Shurtleff et al., Leukemia 9, 1985 (1995); S. P. Romana et al., Blood 86, 4263 (1995); J. D. Rowley, Ann. Genet. 16, 109 (1973).
25. T. R. Golub et al., Proc. Natl. Acad. Sci. U.S.A. 92, 4917 (1995); T. W. McLean et al., Blood 88, 4252 (1996); S. A. Shurtleff et al., Leukemia 9, 1985 (1995); S. P. Romana et al., Blood 86, 4263 (1995); J. D. Rowley, Ann. Genet. 16, 109 (1973).
26. Recent reviews of ALL and AML therapy can be found in C. H. Pui and W. E. Evans, N. Engl. J. Med. 339, 605 (1998); J. F. Bishop, Med. J. Aust. 170, 39 (1999); R. M. Stone and R. J. Mayer, Hematol. Oncol. Clin. N. Am. 7, 47 (1993).
27. Recent reviews of ALL and AML therapy can be found in C. H. Pui and W. E. Evans, N. Engl. J. Med. 339, 605 (1998); J. F. Bishop, Med. J. Aust. 170, 39 (1999); R. M. Stone and R. J. Mayer, Hematol. Oncol. Clin. N. Am. 7, 47 (1993).
28. Recent reviews of ALL and AML therapy can be found in C. H. Pui and W. E. Evans, N. Engl. J. Med. 339, 605 (1998); J. F. Bishop, Med. J. Aust. 170, 39 (1999); R. M. Stone and R. J. Mayer, Hematol. Oncol. Clin. N. Am. 7, 47 (1993).
29. J. DeRisi et al., Nature Genet. 14, 457 (1996); D. J. Lockhart et al., Nature Biotechnol. 14, 1675 (1996); V. R. lyer et al., Science 283, 83 (1999); L. Wodicka, H. Dong, M. Mittmann, M. H. Ho, D. J. Lockhart, Nature Biotechnol. 15, 1359 (1997); P. T. Spellman et al., Mol. Biol. Cell 9, 3273 (1998); M. Schena et al., Proc. Natl. Acad. Sci. U.S.A. 93, 10614 (1996); G. P. Yang, D. T. Ross, W. W. Kuang, P. O. Brown, R. J. Weigel, Nucleic Acids Res. 27, 1517 (1999).
30. J. DeRisi et al., Nature Genet. 14, 457 (1996); D. J. Lockhart et al., Nature Biotechnol. 14, 1675 (1996); V. R. lyer et al., Science 283, 83 (1999); L. Wodicka, H. Dong, M. Mittmann, M. H. Ho, D. J. Lockhart, Nature Biotechnol. 15, 1359 (1997); P. T. Spellman et al., Mol. Biol. Cell 9, 3273 (1998); M. Schena et al., Proc. Natl. Acad. Sci. U.S.A. 93, 10614 (1996); G. P. Yang, D. T. Ross, W. W. Kuang, P. O. Brown, R. J. Weigel, Nucleic Acids Res. 27, 1517 (1999).
31. J. DeRisi et al., Nature Genet. 14, 457 (1996); D. J. Lockhart et al., Nature Biotechnol. 14, 1675 (1996); V. R. lyer et al., Science 283, 83 (1999); L. Wodicka, H. Dong, M. Mittmann, M. H. Ho, D. J. Lockhart, Nature Biotechnol. 15, 1359 (1997); P. T. Spellman et al., Mol. Biol. Cell 9, 3273 (1998); M. Schena et al., Proc. Natl. Acad. Sci. U.S.A. 93, 10614 (1996); G. P. Yang, D. T. Ross, W. W. Kuang, P. O. Brown, R. J. Weigel, Nucleic Acids Res. 27, 1517 (1999).
32. J. DeRisi et al., Nature Genet. 14, 457 (1996); D. J. Lockhart et al., Nature Biotechnol. 14, 1675 (1996); V. R. lyer et al., Science 283, 83 (1999); L. Wodicka, H. Dong, M. Mittmann, M. H. Ho, D. J. Lockhart, Nature Biotechnol. 15, 1359 (1997); P. T. Spellman et al., Mol. Biol. Cell 9, 3273 (1998); M. Schena et al., Proc. Natl. Acad. Sci. U.S.A. 93, 10614 (1996); G. P. Yang, D. T. Ross, W. W. Kuang, P. O. Brown, R. J. Weigel, Nucleic Acids Res. 27, 1517 (1999).
33. J. DeRisi et al., Nature Genet. 14, 457 (1996); D. J. Lockhart et al., Nature Biotechnol. 14, 1675 (1996); V. R. lyer et al., Science 283, 83 (1999); L. Wodicka, H. Dong, M. Mittmann, M. H. Ho, D. J. Lockhart, Nature Biotechnol. 15, 1359 (1997); P. T. Spellman et al., Mol. Biol. Cell 9, 3273 (1998); M. Schena et al., Proc. Natl. Acad. Sci. U.S.A. 93, 10614 (1996); G. P. Yang, D. T. Ross, W. W. Kuang, P. O. Brown, R. J. Weigel, Nucleic Acids Res. 27, 1517 (1999).
34. J. DeRisi et al., Nature Genet. 14, 457 (1996); D. J. Lockhart et al., Nature Biotechnol. 14, 1675 (1996); V. R. lyer et al., Science 283, 83 (1999); L. Wodicka, H. Dong, M. Mittmann, M. H. Ho, D. J. Lockhart, Nature Biotechnol. 15, 1359 (1997); P. T. Spellman et al., Mol. Biol. Cell 9, 3273 (1998); M. Schena et al., Proc. Natl. Acad. Sci. U.S.A. 93, 10614 (1996); G. P. Yang, D. T. Ross, W. W. Kuang, P. O. Brown, R. J. Weigel, Nucleic Acids Res. 27, 1517 (1999).
35. J. DeRisi et al., Nature Genet. 14, 457 (1996); D. J. Lockhart et al., Nature Biotechnol. 14, 1675 (1996); V. R. lyer et al., Science 283, 83 (1999); L. Wodicka, H. Dong, M. Mittmann, M. H. Ho, D. J. Lockhart, Nature Biotechnol. 15, 1359 (1997); P. T. Spellman et al., Mol. Biol. Cell 9, 3273 (1998); M. Schena et al., Proc. Natl. Acad. Sci. U.S.A. 93, 10614 (1996); G. P. Yang, D. T. Ross, W. W. Kuang, P. O. Brown, R. J. Weigel, Nucleic Acids Res. 27, 1517 (1999).
36. E. S. Lander, Science 274, 536 (1996); J. DeRisi, et al., Nature Genet. 14, 457 (1996); J. Kononen et al., Nature Med. 4, 844 (1998); J. Khan et al., Cancer Res. 58, 5009 (1998); K. A. Cole et al. Nature Genet. 21 (suppl. 1), 38 (1999).
37. E. S. Lander, Science 274, 536 (1996); J. DeRisi, et al., Nature Genet. 14, 457 (1996); J. Kononen et al., Nature Med. 4, 844 (1998); J. Khan et al., Cancer Res. 58, 5009 (1998); K. A. Cole et al. Nature Genet. 21 (suppl. 1), 38 (1999).
38. E. S. Lander, Science 274, 536 (1996); J. DeRisi, et al., Nature Genet. 14, 457 (1996); J. Kononen et al., Nature Med. 4, 844 (1998); J. Khan et al., Cancer Res. 58, 5009 (1998); K. A. Cole et al. Nature Genet. 21 (suppl. 1), 38 (1999).
39. E. S. Lander, Science 274, 536 (1996); J. DeRisi, et al., Nature Genet. 14, 457 (1996); J. Kononen et al., Nature Med. 4, 844 (1998); J. Khan et al., Cancer Res. 58, 5009 (1998); K. A. Cole et al. Nature Genet. 21 (suppl. 1), 38 (1999).
40. E. S. Lander, Science 274, 536 (1996); J. DeRisi, et al., Nature Genet. 14, 457 (1996); J. Kononen et al., Nature Med. 4, 844 (1998); J. Khan et al., Cancer Res. 58, 5009 (1998); K. A. Cole et al. Nature Genet. 21 (suppl. 1), 38 (1999).
41. J. DeRisi et al., Nature Genet. 14, 457 (1996); G. P. Yang, D. T. Ross, W. W. Kuang, P. O. Brown, R. J. Weigel, Nucleic Acids Res. 27, 1517 (1999); J. Khan et al., Cancer Res. 58, 5009 (1998); J. Khan et al., Electrophoresis 20, 223 (1999).
42. J. DeRisi et al., Nature Genet. 14, 457 (1996); G. P. Yang, D. T. Ross, W. W. Kuang, P. O. Brown, R. J. Weigel, Nucleic Acids Res. 27, 1517 (1999); J. Khan et al., Cancer Res. 58, 5009 (1998); J. Khan et al., Electrophoresis 20, 223 (1999).
43. J. DeRisi et al., Nature Genet. 14, 457 (1996); G. P. Yang, D. T. Ross, W. W. Kuang, P. O. Brown, R. J. Weigel, Nucleic Acids Res. 27, 1517 (1999); J. Khan et al., Cancer Res. 58, 5009 (1998); J. Khan et al., Electrophoresis 20, 223 (1999).
44. J. DeRisi et al., Nature Genet. 14, 457 (1996); G. P. Yang, D. T. Ross, W. W. Kuang, P. O. Brown, R. J. Weigel, Nucleic Acids Res. 27, 1517 (1999); J. Khan et al., Cancer Res. 58, 5009 (1998); J. Khan et al., Electrophoresis 20, 223 (1999).
45. We compared six normal human kidney biopsies and six kidney tumors (renal cell carcinomas, RCCs) using the methods described for the leukemias. Neighborhood analysis showed a high density of genes correlated with the distinction. Class predictors were constructed using 50 genes, and the predictions proved to be 100% accurate in cross-validation. The informative genes more highly expressed in normal kidney as compared to RCCs included 13 metabolic enzymes, two ion channels, and three isoforms of the heavy-metal chelator metallothionein, all of which function in normal kidney physiology. Those more highly expressed in RCC than normal kidney included interleukin-1, an inflammatory cytokine responsible for the febrile response experienced by patients with RCC, and CCND1, a D-type cyclin amplified in some cases of RCC.
46. The initial 38 samples were all derived from bone marrow aspirates performed at the time of diagnosis, before chemotherapy. After informed consent was obtained, mononuclear cells were collected by Ficoll sedimentation and total RNA extracted with either Trizol (Gibco/BRL) or RNAqueous reagents (Ambion). The 27 ALL samples were derived from childhood ALL patients treated on Dana-Farber Cancer Institute (DFCI) protocols between 1980 and 1999. Samples were randomly selected from the leukemia cell bank based on availability. The 11 adult AML samples were similarly obtained from the Cancer and Leukemia Group B (CALGB) leukemia cell bank. Samples were selected without regard to immunophenotype, cytogenetics, or other molecular features. The independent samples used to confirm the results contained a broader range of samples, including peripheral blood samples and childhood AML cases (23).
47. A total of 3 to 10 μg of total RNA from each sample was used to prepare biotinylated target essentially as previously described, with minor modifications [P. Tamayo et al., Proc. Natl. Acad. Sci. U.S.A. 96, 2907 (1999); L. Wodicka, H. Dong, M. Mittmann, M. Ho, D. Lockhart, Nature Biotechnol. 15, 1359 (1997)]. A complete description of the biochemical and mathematical procedures used in this paper is available through our Web site at www.genome.wi.mit.edu/MPR.
48. A total of 3 to 10 μg of total RNA from each sample was used to prepare biotinylated target essentially as previously described, with minor modifications [P. Tamayo et al., Proc. Natl. Acad. Sci. U.S.A. 96, 2907 (1999); L. Wodicka, H. Dong, M. Mittmann, M. Ho, D. Lockhart, Nature Biotechnol. 15, 1359 (1997)]. A complete description of the biochemical and mathematical procedures used in this paper is available through our Web site at www.genome.wi.mit.edu/MPR.
49. Samples were excluded if they yielded less than 15 ug of biotinylated RNA, if the hybridization was weak (see our Web site for quantitative criteria), or if there were visible defects in the array (such as scratches). A total of 80 leukemia samples were analyzed during the course of the experiments reported here. Of these, eight were excluded on the basis of these a priori quality control criteria.
50. 2(c,r) of radius r around class 1 and class 2 were defined to be the sets of genes such that P(g,c) = r and P(g,c) = -r, respectively. An unusually large number of genes within the neighborhoods indicates that many genes have expression patterns closely correlated with the class vector.
51. A permutation test was used to calculate whether the density of genes in a neighborhood was statistically significantly higher than expected. We compared the number of genes in the neighborhood to the number of genes in similar neighborhoods around idealized expression patterns corresponding to random class distinctions, obtained by permuting the coordinates of c. We performed 400 permutations and determined the 5 and 1% significance levels for the number of genes contained within neighborhoods of various levels of correlation with c. See also the legend to Fig. 2.
52. The set of informative genes consists of the n/2 genes closest to a class vector high in class 1 [that is, P(g,c) as large as possible] and the n/2 genes closest to class 2 [that is, -P(g,c) as large as possible]. The number n of informative genes is the only free parameter in defining the class predictor.
53. 2 for class 2 is obtained by summing the absolute values of the negative votes.
54. lose are the vote totals for the winning and losing classes. The measure PS reflects the relative margin of victory of the vote.
55. The appropriate PS threshold depends on the number n of genes in the predictor, because the PS is a sum of n variables corresponding to the individual genes, and thus its fluctuation for random input data scales inversely with √n. See our Web site concerning the specific choice of PS threshold.
56. In cross-validation, the entire prediction process is repeated from scratch with 37 of the 38 samples. This includes identifying the 50 informative genes to be used in the predictor and defining parameters for weighted voting.
57. The independent set of leukemia samples comprised 24 bone marrow and 10 peripheral blood specimens, all obtained at the time of leukemia diagnosis. The ALL samples were obtained from the DFCI childhood ALL bank (n = 17) or St. Jude Children's Research Hospital (SJCRH) (n = 3). Whereas the AML samples in the initial data set were all derived from adult patients, the AML samples in the independent data set were derived from both adults and children. The samples were obtained from either the CALGB (adult AML, n = 4), SJCRH (childhood AML, n = 5), or the Children's Cancer Group (childhood AML, n = 5) leukemia banks. The samples were processed as described (73), with the exception of the samples from SJCRH. which used a very different protocol. The SJCRH samples were subjected to hypotonic lysis [rather than Ficoll sedimentation), and RNA was prepared by an aqueous extraction (Qiagen).
58. Although the number of genes used had no significant effect on the outcome in this case (median PS for cross-validation ranged from 0.81 to 0.68 over a range of predictors using 10 to 200 genes, all with 0% error), it may matter in other instances. One approach is to vary the number of genes used, select the number that maximizes the accuracy rate in cross-validation, and then use the resulting model on the independent data set. In any case, we recommend using at least 10 genes for two reasons. Class predictors using a small number of genes may depend too heavily on any one gene and can produce spuriously high prediction strengths (because a large "margin of victory" can occur by chance due to statistical fluctuation resulting from a small number of genes). In general, we also considered the 99% confidence line in neighborhood analysis to be the upper bound for gene selection.
59. P. A. Dinndorf et al., Med. Pediatr. Oncot. 20, 192 (1992); P. S. Master, S. J. Richards, J. Kendall, B. E. Roberts, C. S. Scott, Blut 59, 221 (1989); V. Buccheri et al., Blood 82, 853 (1993).
60. P. A. Dinndorf et al., Med. Pediatr. Oncot. 20, 192 (1992); P. S. Master, S. J. Richards, J. Kendall, B. E. Roberts, C. S. Scott, Blut 59, 221 (1989); V. Buccheri et al., Blood 82, 853 (1993).
61. P. A. Dinndorf et al., Med. Pediatr. Oncot. 20, 192 (1992); P. S. Master, S. J. Richards, J. Kendall, B. E. Roberts, C. S. Scott, Blut 59, 221 (1989); V. Buccheri et al., Blood 82, 853 (1993).
62. M. Konopleva et al. Blood 93, 1668 (1999).
63. A. W. Crawford and M. C. Beckerle, J. Biol. Chem. 266, 5847 (1991).
64. W. Ross, T. Rowe, B. Glisson, J. Yalowich, L. Liu, Cancer Res. 44, 5857 (1984).
65. Treatment failure was defined as failure to achieve a complete remission after a standard induction regimen including 3 days of anthracycline and 7 days of cytarabine. Treatment successes were defined as patients in continuous complete remission for a minimum of 3 years. FAB subclass M3 patients were excluded but samples were otherwise not selected with regard to FAB criteria.
66. J. Borrow et al., Nature Genet. 12, 159 (1996); T. Nakamura, et al., ibid., p. 154; S. Y. Huang et al., Br. J. Haematol. 96, 682 (1997).
67. J. Borrow et al., Nature Genet. 12, 159 (1996); T. Nakamura, et al., ibid., p. 154; S. Y. Huang et al., Br. J. Haematol. 96, 682 (1997).
68. J. Borrow et al., Nature Genet. 12, 159 (1996); T. Nakamura, et al., ibid., p. 154; S. Y. Huang et al., Br. J. Haematol. 96, 682 (1997).
69. E. Kroon et al., EMBO J. 17, 3714 (1998).
70. P. Tamayo et al., Proc. Natl. Acad. Sci. U.S.A. 96, 2907 (1999).
71. The SOM was constructed using our GENECLUSTER software (32), with a variation filter excluding genes with less than fivefold variation across the collection of samples.
72. For testing putative clusters derived from the SOM or chosen at random, we constructed class predictors with various number of genes (ranging from 10 to 100) and selected the one with the highest crossvalidation accuracy rate (in this case, 20 genes).
73. A related approach would be to represent each cluster only as the subset of points lying near the centroid of the cluster.
74. Various statistical methods can be used to compare the predictors derived from the SOM-derived clusters with predictors derived from random classes. We compared the median prediction strength. Specifically, 100 predictors corresponding to random classes of comparable size were constructed, and the median PS for each predictor was determined. The performance for the actual predictor was then compared to the distribution of these 100 median PSs, to obtain empirical significance levels. The observed median PS in the initial data set was 0.86, which exceeded the median PS for all 100 random predictors; the empirical significance level was thus <1%. The observed median PS for the independent data set was 0.61, which exceed the median PS for all but 4 of the 100 random permutations; the empirical significance level was thus 4%.
75. j). It may be possible to improve the statistical power of this test by using techniques for multiclass prediction.
76. Thirty-three ALL. samples were tested by cross-validation using a 50-gene predictor. Thirty-two of 33 samples were correctly assigned as T-ALL or B-ALL; the remaining sample received a PS < 0.3, and no prediction was therefore made. Details are provided on our Web site.
77. T. R. Golub, unpublished results.
78. S. Turc-Carel et al., Cancer Genet. Cytogenet. 19, 361 (1986); E. C. Douglass et al., ibid. 45, 148 (1987).
79. S. Turc-Carel et al., Cancer Genet. Cytogenet. 19, 361 (1986); E. C. Douglass et al., ibid. 45, 148 (1987).
80. We are grateful to S. Sallan, J. Ritz, K. Loughlin, S. Shurtleff, P. Kourlas, F. Smith, the Cancer and Leukemia Group B, and Children's Cancer Group for providing valuable patient samples. We thank R. Klausner, D. G. Gilliland, D. Nathan, G. Daley, J. Staunton, M. Angelo, A. Leblanc, P. Lee, Z. Kikinis, G. Acton, and members of the Lander and Golub laboratories for helpful discussions. This work was supported in part by the Leukemia Society of America (T.R.G); the National Institutes of Health and the Leukemia Clinical Research Foundation (C.D.B); and Affymetrix, Millennium Pharmaceutical, and Bristol-Myers Squibb (E.S.L).