Update README.md

Author: senorred

README.md

@@ -3,7 +3,9 @@
 ###### Virulence Factor Characterization project from 2019 NIH Microbial Virulence in the Cloud Hackathon
 
 # Approach
-We used parallel machine learning methods to approach the problem of characterizing virulence factors (VF) in diseased and healthy metagenomes. Using genes from the core set of the Virulence Factor Database (http://www.mgc.ac.cn/VFs/), we used an HMM to profile known virulence factors and apply profiles to diseased and healthy metagenomes. Using the same gene factors, we found pathogen genomes from the VFDB set and commensal genomes from the NHSN organism list and (other source) and masked the VFDB virulence genes from both datasets. We then trained the VF-subtracted genomes on an SVM model to classify pathogenic and non-pathogenic genomes. Both techniques form a complementary approach to VF characterization by using well-characterized virulence factors to profile similar characteristics in the metagenome space (HMM), and by exploring the potential for uncharacterized or weakly characterized genes within the same metagenomes. 
+While there have been substantial advances in understanding microbial virulence in cultured systems, a metagenomic examination of microbial virulence can capture community relationships and environmental context necessary for understanding disease progression. However, setting an appropriate problem scope for identifying new virulence factors can be challenging as certain contexts, such as an infectious process, can significantly alter the landscape of the microbiome and the pathological potential of individual microbes, including those normally considered commensal. Crucially, few tools exist for probing microbial virulence in metagenomes specifically, constraining the development of culture-free methods in public health and epidemiology.
+
+We used parallel machine learning methods to approach the problem of characterizing virulence factors (VF) in diseased and healthy metagenomes. Using genes from the core set of the Virulence Factor Database (http://www.mgc.ac.cn/VFs/), we used an HMM to profile known virulence factors and apply profiles to diseased and healthy metagenomes. In parallel to this approach, we used a set of labelled pathological and commensal genomes and subtracted the VFDB virulence factor genes from both sets. We then trained the VF-subtracted genomes on an SVM model to classify pathogenic and non-pathogenic genomes. Both techniques form a complementary approach to VF characterization by using well-characterized virulence factors and commensal genomes to profile similar characteristics in the metagenome space (HMM), and by exploring the potential for virulent genes uncharacterized by the VF dataset within the same metagenomes. This combination of techniques can provide spatially-resolved scoring within the metagenome to identify potential virulence factors.
 
 ![workflow](https://github.com/NCBI-Hackathons/Virulence_Factor_Characterization/blob/master/VFCflow.png)