From 4241da44fd68279b2483a3d1fb86c38b54da39dd Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Tue, 27 Aug 2019 14:34:02 -0400
Subject: [PATCH] fix
---
.../GENERATE.WITH_HPC_CLUSTER.sh | 1 +
.../cluster_submit_script_header.mssm_hpc.lsf | 1 +
.../calibrate_percentile_ranks_command.py | 21 ++++++++++++++++---
mhcflurry/class1_affinity_predictor.py | 6 ++++--
4 files changed, 24 insertions(+), 5 deletions(-)
diff --git a/downloads-generation/models_class1_pan/GENERATE.WITH_HPC_CLUSTER.sh b/downloads-generation/models_class1_pan/GENERATE.WITH_HPC_CLUSTER.sh
index 7a31a652..84e040cd 100755
--- a/downloads-generation/models_class1_pan/GENERATE.WITH_HPC_CLUSTER.sh
+++ b/downloads-generation/models_class1_pan/GENERATE.WITH_HPC_CLUSTER.sh
@@ -74,6 +74,7 @@ do
--allele $(bzcat "$MODELS_DIR/train_data.csv.bz2" | cut -f 1 -d , | grep -v allele | uniq | sort | uniq) \
--verbosity 1 \
--worker-log-dir "$SCRATCH_DIR/$DOWNLOAD_NAME" \
+ --prediction-batch-size 524288 \
--cluster-parallelism \
--cluster-submit-command bsub \
--cluster-results-workdir ~/mhcflurry-scratch \
diff --git a/downloads-generation/models_class1_pan_unselected/cluster_submit_script_header.mssm_hpc.lsf b/downloads-generation/models_class1_pan_unselected/cluster_submit_script_header.mssm_hpc.lsf
index 4d334e0d..6fb96c1f 100644
--- a/downloads-generation/models_class1_pan_unselected/cluster_submit_script_header.mssm_hpc.lsf
+++ b/downloads-generation/models_class1_pan_unselected/cluster_submit_script_header.mssm_hpc.lsf
@@ -18,6 +18,7 @@ export PYTHONUNBUFFERED=1
export KMP_SETTINGS=1
set -e
+set -x
free -m
module add cuda/10.0.130 cudnn/7.1.1
diff --git a/mhcflurry/calibrate_percentile_ranks_command.py b/mhcflurry/calibrate_percentile_ranks_command.py
index e06d0bfd..31aeccc1 100644
--- a/mhcflurry/calibrate_percentile_ranks_command.py
+++ b/mhcflurry/calibrate_percentile_ranks_command.py
@@ -80,6 +80,11 @@ parser.add_argument(
nargs=2,
help="Min and max peptide length to calibrate, inclusive. "
"Default: %(default)s")
+parser.add_argument(
+ "--prediction-batch-size",
+ type=int,
+ default=4096,
+ help="Keras batch size for predictions")
parser.add_argument(
"--verbosity",
type=int,
@@ -149,7 +154,10 @@ def run(argv=sys.argv[1:]):
GLOBAL_DATA["args"] = {
'motif_summary': args.motif_summary,
'summary_top_peptide_fractions': args.summary_top_peptide_fraction,
- 'verbose': args.verbosity > 0
+ 'verbose': args.verbosity > 0,
+ 'model_kwargs': {
+ 'batch_size': args.prediction_batch_size,
+ }
}
del encoded_peptides
@@ -222,13 +230,20 @@ def calibrate_percentile_ranks(
peptides=None,
motif_summary=False,
summary_top_peptide_fractions=[0.001],
- verbose=False):
+ verbose=False,
+ model_kwargs={}):
+ if verbose:
+ print("Calibrating", allele)
+ start = time.time()
summary_results = predictor.calibrate_percentile_ranks(
peptides=peptides,
alleles=[allele],
motif_summary=motif_summary,
summary_top_peptide_fractions=summary_top_peptide_fractions,
- verbose=verbose)
+ verbose=verbose,
+ model_kwargs=model_kwargs)
+ if verbose:
+ print("Done calibrating", allele, "in", time.time() - start, "sec")
transforms = {
allele: predictor.allele_to_percent_rank_transform[allele],
}
diff --git a/mhcflurry/class1_affinity_predictor.py b/mhcflurry/class1_affinity_predictor.py
index 241560d9..b3a54bfe 100644
--- a/mhcflurry/class1_affinity_predictor.py
+++ b/mhcflurry/class1_affinity_predictor.py
@@ -1157,7 +1157,8 @@ class Class1AffinityPredictor(object):
bins=None,
motif_summary=False,
summary_top_peptide_fractions=[0.001],
- verbose=False):
+ verbose=False,
+ model_kwargs={}):
"""
Compute the cumulative distribution of ic50 values for a set of alleles
over a large universe of random peptides, to enable computing quantiles in
@@ -1208,7 +1209,8 @@ class Class1AffinityPredictor(object):
length_distributions = None
for (i, allele) in enumerate(alleles):
start = time.time()
- predictions = self.predict(encoded_peptides, allele=allele)
+ predictions = self.predict(
+ encoded_peptides, allele=allele, model_kwargs=model_kwargs)
if verbose:
elapsed = time.time() - start
print(
--
GitLab