As sequencing costs continue to decline, a torrent of cancer genomic data is looming. Very soon, our ability to deeply investigate the cancer genome will outpace our ability to correlate these changes with the phenotypes that they produce. We propose the advanced development and extension of a software platform for performing deep phenotype extraction directly from clinical text of cancer patients, with the goal of enabling translational cancer research and precision medicine. The work builds on previous informatics research and software development efforts from Boston Children's Hospital and University of Pittsburgh groups, both individually and together. Multiple software projects developed by our groups that have already passed the initial prototyping and pilot development phase (eMERGE, THYME, TIES, ODIE, Apache cTAKES) will be combined and extended to produce an advanced software platform for accelerating cancer research. Additionally, our research will advance the state of the art in biomedical NLP and information extraction in topics such as temporal relation extraction, gene and variant relation extraction, and discourse reasoning. As part of this project, we will work with three cancer research groups (ovarian cancer, breast cancer and melanoma) to design, adopt and evaluate our software.