D. Gary Gilliland

Department of Medicine
Brigham and Women's Hospital
1 Blackfan Circle, Room 5.0210
Boston, MA 02115
Tel: (617) 355-9092
Fax: (617) 355-9093
Email: ggilliland@rics.bwh.harvard.edu

Assistant: Alexis Bywater, abywater@rics.bwh.harvard.edu
12 postdoctoral fellows, 6 graduate students

We are interested in understanding the genetic basis of human cancer, with an ultimate goal of translating these insights into more effective and less toxic therapies.  We have focused most of our attention on hematopoietic malignancies.  Our basic approach is to use cutting-edge, genome wide screening technologies to identify disease alleles, to characterize the function of the mutated oncogenes and their wildtype counterparts, and to use insights gained from these studies to develop novel therapeutic strategies for human cancer. 

As one recent example of this approach, we used high-throughput DNA sequence analysis of all tyrosine kinases in the human genome to identify a mutation in the JAK2 tyrosine kinase in patients with a spectrum of myeloproliferative diseases (MPD).  These MPD include polycythemia vera (PV) characterized by overproduction of red cells, essential thrombocythemia (ET) characterized by overproduction of platelets, and myeloid metaplasia with myelofibrosis (MF) characterized by bone marrow fibrosis.  We discovered that a V617F mutation in the context of JAK2 results in its constitutive phosphorylation, and activation of downstream effectors that phenotypically confer proliferative and survival advantage to hematopoietic progenitors (Levine et al).  The JAK2V617F mutation is present in essentially all patients with PV, and in a majority of patients with ET and MF.  When expressed in murine bone marrow in vivo, JAK2V617F recapitulates the human disease phenotype, validating it as a potential target for therapeutic intervention.  We have characterized several clinical grade small molecule inhibitors of JAK2 that are planned for Phase I/II trials in humans within the coming year.

We have also focused increasing attention on cancer stem cells, and their relationship to their normal tissue counterparts.  The cancer stem cell hypothesis, which is best validated in the hematopoietic system, holds that only a small subpopulation of cells within a tumor  – cancer stem cells – have properties of long term self-renewal.  It is thought that these cells are ultimately responsible for continued growth and propagation of tumors, and are likely to be the culprits that explain relapse of cancer after initial response to therapy.  Our goal is to understand the biological characteristics of these cells, and how they differ from normal stem cells, in order that we might exploit this difference therapeutically.  To this end, we have developed model systems for genesis of leukemia stem cells from committed progenitors that normally lack self-renewal potential, in order that we might study the transcriptional programs engaged by leukemia oncogenes that confer self-renewal (Huntly et al).

To fully understand the biology of leukemia stem cells, we are also investigating the role of transcription factors that are known targets of leukemia oncogenes, and are assessing their roles in normal hematopoietic stem cell homeostasis.  For example, the FoxO family of transcription factors are targets for inactivation by a spectrum of leukemogenic tyrosine kinases.  We have observed that these transcription factors are critical mediators of hematopoietic stem cell longevity, and modulate this effect at least in part through management of reactive oxygen.  These observations provide novel insights into the function of normal stem cells, and how we might selectively target leukemic cells for inhibition and death (Tothova et al). 

Our efforts are facilitated by close interfaces between our laboratory and the Harvard Stem Cell Institute, as well as the Broad Institute of Harvard and MIT. 

References:

• Levine RL et al.  Activating mutation in the tyrosine kinase JAK2 in polycythemia vera, essential thrombocythemia, and myeloid metaplasia with myelofibrosis.  Cancer Cell. 2005 Apr;7(4):387-97.
• Huntly BJ et al.  MOZ-TIF2, but not BCR-ABL, confers properties of leukemic stem cells to committed murine hematopoietic progenitors.  Cancer Cell. 2004 Dec;6(6):587-96.
• Tothova Z et al.  FoxOs are critical mediators of hematopoietic stem cell resistance to physiologic oxidative stress. Cell. 2007 Jan 26;128(2):325-39.