From 0ae107b1a26a81bacea503fad17a1a6110483f43 Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Mon, 4 Dec 2017 13:12:39 -0500
Subject: [PATCH] Train on alleles with >=75 measurements (decreased from 100)

---
 downloads-generation/cross_validation_class1/GENERATE.sh | 2 +-
 downloads-generation/models_class1/GENERATE.sh           | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/downloads-generation/cross_validation_class1/GENERATE.sh b/downloads-generation/cross_validation_class1/GENERATE.sh
index ebbe0b8e..658460f6 100755
--- a/downloads-generation/cross_validation_class1/GENERATE.sh
+++ b/downloads-generation/cross_validation_class1/GENERATE.sh
@@ -31,7 +31,7 @@ cp $SCRIPT_DIR/score.py .
 
 time python split_folds.py \
     "$(mhcflurry-downloads path data_curated)/curated_training_data.csv.bz2" \
-    --min-measurements-per-allele 100 \
+    --min-measurements-per-allele 75 \
     --folds $NFOLDS \
     --random-state 1 \
     --output-pattern-test "./test.fold_{}.csv" \
diff --git a/downloads-generation/models_class1/GENERATE.sh b/downloads-generation/models_class1/GENERATE.sh
index 68a1db10..2e509d23 100755
--- a/downloads-generation/models_class1/GENERATE.sh
+++ b/downloads-generation/models_class1/GENERATE.sh
@@ -32,7 +32,7 @@ time mhcflurry-class1-train-allele-specific-models \
     --hyperparameters hyperparameters.yaml \
     --out-models-dir models \
     --percent-rank-calibration-num-peptides-per-length 1000000 \
-    --min-measurements-per-allele 100
+    --min-measurements-per-allele 75
 
 cp $SCRIPT_ABSOLUTE_PATH .
 bzip2 LOG.txt
-- 
GitLab