aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorelavington <27739361+elavington@users.noreply.github.com>2017-08-31 13:22:32 -0400
committerGitHub <noreply@github.com>2017-08-31 13:22:32 -0400
commite387bd409e271a149692d45a952e6475f3b706be (patch)
treed5bce0ee6161ae8f877b1c7e7c2ba7e840d34bd0
parentc5a53342b9be73b7ff11a44e22cfc39eb7af551c (diff)
downloadcressdna-e387bd409e271a149692d45a952e6475f3b706be.tar.gz
cressdna-e387bd409e271a149692d45a952e6475f3b706be.zip
Create README.md
Description of files
-rw-r--r--README.md11
1 files changed, 11 insertions, 0 deletions
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..11336e4
--- /dev/null
+++ b/README.md
@@ -0,0 +1,11 @@
+# cressdna
+Circular Eukaryotic Single Stranded DNA site source
+
+index.html is the main web page
+classifier.py is a python script that takes the submitted textarea form from index.html (needs to be FASTA format input) and makes a prediction
+ of the CRESS virus genus for each sample, given the caveats listed on the submission form page
+
+ This script is meant to output a new index.html type page with the results of the prediction as an HTML table in the Results tab
+
+SVM_linear_aa_clf.pkl is a compressed trained SVM classifier for prediction
+UniqRepsGemys_6089_StSCALER.pkl is a compressed trained scaler to fit input data to the same scale as the trained data