From 7cd518a63658a2cc7814cc9e6fc75f6ba66cd862 Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Wed, 21 Sep 2016 17:42:00 -0400
Subject: [PATCH] First pass on
models_class1_allele_specific_single_kim2014_only
---
.../GENERATE.sh | 53 +++++++++++++++++++
.../README.md | 4 ++
.../imputer.json | 8 +++
.../models.py | 16 ++++++
4 files changed, 81 insertions(+)
create mode 100644 downloads-generation/models_class1_allele_specific_single_kim2014_only/GENERATE.sh
create mode 100644 downloads-generation/models_class1_allele_specific_single_kim2014_only/README.md
create mode 100644 downloads-generation/models_class1_allele_specific_single_kim2014_only/imputer.json
create mode 100644 downloads-generation/models_class1_allele_specific_single_kim2014_only/models.py
diff --git a/downloads-generation/models_class1_allele_specific_single_kim2014_only/GENERATE.sh b/downloads-generation/models_class1_allele_specific_single_kim2014_only/GENERATE.sh
new file mode 100644
index 00000000..3d7eb354
--- /dev/null
+++ b/downloads-generation/models_class1_allele_specific_single_kim2014_only/GENERATE.sh
@@ -0,0 +1,53 @@
+#!/bin/bash
+
+if [[ $# -eq 0 ]] ; then
+ echo 'WARNING: This script is intended to be called with additional arguments to pass to mhcflurry-class1-allele-specific-cv-and-train'
+ echo 'At minimum you probably want to pass --dask-scheduler <IP:PORT> as training many models on one node is extremely '
+ echo 'slow.'
+fi
+
+set -e
+set -x
+
+DOWNLOAD_NAME=models_class1_allele_specific_single_kim2014_only
+SCRATCH_DIR=/tmp/mhcflurry-downloads-generation
+SCRIPT_ABSOLUTE_PATH="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/$(basename "${BASH_SOURCE[0]}")"
+SCRIPT_DIR=$(dirname "$SCRIPT_ABSOLUTE_PATH")
+
+mkdir -p "$SCRATCH_DIR"
+rm -rf "$SCRATCH_DIR/$DOWNLOAD_NAME"
+mkdir "$SCRATCH_DIR/$DOWNLOAD_NAME"
+
+# Send stdout and stderr to a logfile included with the archive.
+exec > >(tee -ia "$SCRATCH_DIR/$DOWNLOAD_NAME/LOG.txt")
+exec 2> >(tee -ia "$SCRATCH_DIR/$DOWNLOAD_NAME/LOG.txt" >&2)
+
+# Log some environment info
+date
+pip freeze
+git rev-parse HEAD
+git status
+
+cd $SCRATCH_DIR/$DOWNLOAD_NAME
+
+mkdir models
+
+cp $SCRIPT_DIR/models.py $SCRIPT_DIR/imputer.json .
+python models.py > models.json
+
+time mhcflurry-class1-allele-specific-cv-and-train \
+ --model-architectures models.json \
+ --imputer-description imputer.json \
+ --train-data "$(mhcflurry-downloads path data_kim2014)/bdata.2009.mhci.public.1.txt" \
+ --test-data "$(mhcflurry-downloads path data_kim2014)/bdata.2013.mhci.public.blind.1.txt" \
+ --min-samples-per-allele 70 \
+ --out-cv-results cv.csv \
+ --out-production-results production.csv \
+ --out-models models \
+ --verbose \
+ "$@"
+
+cp $SCRIPT_ABSOLUTE_PATH .
+tar -cjf "../${DOWNLOAD_NAME}.tar.bz2" *
+
+echo "Created archive: $SCRATCH_DIR/$DOWNLOAD_NAME.tar.bz2"
diff --git a/downloads-generation/models_class1_allele_specific_single_kim2014_only/README.md b/downloads-generation/models_class1_allele_specific_single_kim2014_only/README.md
new file mode 100644
index 00000000..6cecfebb
--- /dev/null
+++ b/downloads-generation/models_class1_allele_specific_single_kim2014_only/README.md
@@ -0,0 +1,4 @@
+# Class I allele specific models (single) trained and tested in Kim 2014 dataset
+
+This is a reimplementation of the analysis in [Predicting Peptide-MHC Binding Affinities With Imputed Training Data](http://biorxiv.org/content/early/2016/05/22/054775).
+
diff --git a/downloads-generation/models_class1_allele_specific_single_kim2014_only/imputer.json b/downloads-generation/models_class1_allele_specific_single_kim2014_only/imputer.json
new file mode 100644
index 00000000..f7614316
--- /dev/null
+++ b/downloads-generation/models_class1_allele_specific_single_kim2014_only/imputer.json
@@ -0,0 +1,8 @@
+{
+ "imputation_method_name": "mice",
+ "n_burn_in": 5,
+ "n_imputations": 50,
+ "n_nearest_columns": 25,
+ "min_observations_per_peptide": 5,
+ "min_observations_per_allele": 100
+}
diff --git a/downloads-generation/models_class1_allele_specific_single_kim2014_only/models.py b/downloads-generation/models_class1_allele_specific_single_kim2014_only/models.py
new file mode 100644
index 00000000..6375cd45
--- /dev/null
+++ b/downloads-generation/models_class1_allele_specific_single_kim2014_only/models.py
@@ -0,0 +1,16 @@
+import sys
+from mhcflurry.class1_allele_specific.train import HYPERPARAMETER_DEFAULTS
+import json
+
+models = HYPERPARAMETER_DEFAULTS.models_grid(
+ #impute=[False, True],
+ impute=[False],
+ activation=["tanh"],
+ layer_sizes=[[12], [64], [128]],
+ embedding_output_dim=[8, 32, 64],
+ dropout_probability=[0, .1, .25],
+ # fraction_negative=[0, .1, .2],
+ n_training_epochs=[250])
+
+sys.stderr.write("Models: %d\n" % len(models))
+print(json.dumps(models, indent=4))
--
GitLab