Molecular Mechanisms of NRAS-Mediated Leukemia Stem Cell Self-Renewal
Acute myeloid leukemia (AML) is frequently fatal because patients who initially respond to chemotherapy eventually relapse. Leukemia stem cells (LSCs) recapitulate the disease by self-renewal. LSC self-renewal is therefore critical to relapse. NRASG12V is required for self-renewal in a murine AML model. Most anticancer therapies are designed to inhibit proliferation. Yet, in hematopoietic stem cells, the mechanisms of NRAS-mediated proliferation are distinct from self-renewal. Consequently, targeting proliferation may explain the failure of traditional chemotherapy to eradicate this disease. To study NRAS-mediated leukemia self-renewal, these researchers use a transgenic mouse model of AML with an Mll-AF9 fusion and a tetracycline repressible, NRASG12V. Doxycycline abolishes NRASG12V expression leading to leukemia remission. These researchers hypothesize that NRAS-activated pathways required for self-renewal are limited to a subpopulation of cells with the LSC immunophenotype.
During 2015, the researchers examined the NRAS-activated stem-cell containing subpopulation of their mouse model by capturing single cells (~200 cells) and performing single cell RNA sequencing (along with bulk RNA population controls). They also started to capture cells from human AML samples (~100 cells) to investigate if subpopulations exist in these cells and if a self-renewing signature could be detected. They were able to implement this analysis using MSI HPC and storage resources. During 2016, they plan to capture and sequence more mouse model cells (~300) and human AML patient cells (~500). Both of these projects will include the proper population controls. They also plan to process a small set (20 samples) of bulk RNA sequencing on sorted subpopulations that they have identified in the mouse model.
The group is actively investigating if these important biomarkers of self-renewal using this NRAS AML mouse model are present in the human AML cells. Ultimately, the goal of this research is to target this self-renewing population therapeutically so that relapse of AML can be dramatically reduced.
Return to this PI's main page.
Large Scale Machine Learning and Its Applications
This group works on large scale machine learning and data analysis, applied to the problems of climate prediction, anomaly detection and recommendation systems. Each of these problems involves large number of computations as they search through piles of explicit and implicit information, either observed or unobserved. The researchers are working on three projects during 2016, all of which require HPC resources.
- Anomaly detection: This project is concerned with the analysis of a large flight dataset to discover anomalous aviation situations. The dataset contains about 180,000 flights, each consisting of 186 time-series of various lengths.
- Recommendation system: The objective of this project is to build a model for news article recommendation. The accuracy of the ranked list of recommended items is expected to be computed in large scale datasets, where at least millions of observations (users who rated/clicked on an article) is given. Although online models will be tested, the researchers also need to compare them with offline models, for which all training data will be needed.
- Deep learning methods for climate science: This project will train deep networks for prediction tasks on Global Climate Model (GCM) climate datasets. The output of all GCM models combined consist of around 50,000 observations, each of which has 10,000-60,000 dimensions of observations of various climatic parameters like temperature, precipitation etc. The dataset is to be used for two prediction tasks: prediction of Indian summer monsoon rainfall, and prediction of air temperature on nine land locations in different parts of the world. Each of these areas will explore the use of deep learning models like convolutional nets, recurrent nets, restricted Boltzmann machines, auto-encoders, etc. with each model having many parameters to be trained. The researchers believe that this is one of the first applications proposing using deep networks on GCM datasets and as such will require running multiple iterations of these models for tuning and testing.
Return to this PI's main page.