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.
Sukhithasri V, Nisha N, Vivek V and Raja Biswas
The host innate immune system acts as the first line of defense against invading pathogens. During an infection, the host innate immune cells recognize unique conserved molecules on the pathogen known as Pathogen Associated Molecular Patterns (PAMPs). This recognition of PAMPs helps the host mount an innate immune response leading to the production of cytokines (Akira et al. 2006). Peptidoglycan, one of the most conserved and essential component of the bacterial cell wall is one such PAMP. Peptidoglycan is known to have potent proinflammatory properties (Gust et al. 2007). Host recognize peptidoglycan using Nucleotide oligomerization domain proteins (NODs). This recognition of peptidoglycan activates the NODs and triggers downstream signaling leading to the nuclear translocation of NF-κB and production of cytokines (McDonald et al. 2005). Pathogenic bacteria modify their peptidoglycan as a strategy to evade innate immune recognition, which helps it to establish infection in the host. These peptidoglycan modifications include O-acetylation and N-glycolylation of muramic acid and N-deacetylation of N-acetylglucosamine (Davis et al. 2011). Modification of mycobacterial peptidoglycan by N-glycolylation prevents the catalytic activity of lysozyme (Raymond et al. 2005). Additionally, mycobacterial peptidoglycan is modified by amidation for unknown reasons.
Here, we have investigated the role of amidated peptidoglycan in Mycobacterium sp in modulating the innate immune response. We isolated amidated peptidoglycan from Mycobacterium sp and non-amidated peptidoglycan from Escherichia coli. We made a comparative analysis of the cytokine response produced on stimulation of innate immune cells by peptidoglycan from E. Coli and Mycobacterium sp. Macrophages and whole blood were treated with peptidoglycan and the cytokines secreted into spent medium and plasma respectively were analyzed using ELISA. Our results show that peptidoglycan from Mycobacterium sp is less effective in stimulating innate immune cells to produce cytokines. This intrinsic modulation of the cytokine response suggests that mycobacteria modify their peptidoglycan by amidation to evade innate immune response.