Michelle Hermiston, MD, Ph.D.
Assistant Professor, Department of Pediatrics University of California San Francisco, USA
Interrogating Signaling Networks at the Single Cell Level In Primary Human Patient Samples
Multiparameter phosphoflow cytometry is a highly sensitive proteomic approach that enables monitoring of biochemical perturbations at the single cell level. By combining antisera to cell surface markers and key intracellular proteins, perturbations in signaling networks, cell survival and apoptosis mediators, cell cycle regulators, and/or modulators of other cellular processes can be analyzed in a highly reproducible and sensitive manner in the basal state and in response to stimulation or drug treatment. Advantages of this approach include the ability to identify the biochemical consequences of genetic and/or epigenetic changes in small numbers of cells, to map potential interplay between various signaling networks simultaneously in a single cell, and to interrogate potential mechanisms of drug resistance or response in a primary patient sample. Application of this technology to patients with acute lymphoblastic leukemia or the autoimmune disease systemic lupus erythematosus (SLE) will be discussed.
Srisairam Achuthan, Ph.D.
Senior Scientific Programmer, Research Informatics Division, Department of Information Sciences, City of Hope, CA, USA
Applying Machine learning for Automated Identification of Patient Cohorts
Srisairam Achuthan, Mike Chang, Ajay Shah, Joyce Niland
Patient cohorts for a clinical study are typically identified based on specific selection criteria. In most cases considerable time and effort are spent in finding the most relevant criteria that could potentially lead to a successful study. For complex diseases, this process can be more difficult and error prone since relevant features may not be easily identifiable. Additionally, the information captured in clinical notes is in non-coded text format. Our goal is to discover patterns within the coded and non-coded fields and thereby reveal complex relationships between clinical characteristics across different patients that would be difficult to accomplish manually. Towards this, we have applied machine learning techniques such as artificial neural networks and decision trees to determine patients sharing similar characteristics from available medical records. For this proof of concept study, we used coded and non-coded (i.e., clinical notes) patient data from a clinical database. Coded clinical information such as diagnoses, labs, medications and demographics recorded within the database were pooled together with non-coded information from clinical notes including, smoking status, life style (active / inactive) status derived from clinical notes. The non-coded textual information was identified and interpreted using a Natural Language Processing (NLP) tool I2E from Linguamatics.