From 1826aae687ab7fd150c7beb70143193bafa04408 Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Wed, 1 Jan 2020 16:24:45 -0500
Subject: [PATCH] Start 1.6.0
---
downloads-generation/data_curated/GENERATE.sh | 10 +-
downloads-generation/data_curated/curate.py | 27 +++--
mhcflurry/downloads.yml | 102 +++++++++++++++++-
3 files changed, 127 insertions(+), 12 deletions(-)
diff --git a/downloads-generation/data_curated/GENERATE.sh b/downloads-generation/data_curated/GENERATE.sh
index 2c404381..6f9a515f 100755
--- a/downloads-generation/data_curated/GENERATE.sh
+++ b/downloads-generation/data_curated/GENERATE.sh
@@ -57,7 +57,6 @@ bzip2 rna_expression.csv
rm -rf ms
-# With mass-spec data
time python curate.py \
--data-iedb \
"$(mhcflurry-downloads path data_iedb)/mhc_ligand_full.csv.bz2" \
@@ -70,6 +69,15 @@ time python curate.py \
--out-affinity-csv curated_training_data.affinity.csv \
--out-mass-spec-csv curated_training_data.mass_spec.csv
+time python curate.py \
+ --data-iedb \
+ "$(mhcflurry-downloads path data_iedb)/mhc_ligand_full.csv.bz2" \
+ --data-kim2014 \
+ "$(mhcflurry-downloads path data_published)/bdata.20130222.mhci.public.1.txt" \
+ --data-systemhc-atlas \
+ "$(mhcflurry-downloads path data_systemhcatlas)/data.csv.bz2" \
+ --out-csv curated_training_data.no_additional_ms.csv
+
for i in $(ls *.csv)
do
bzip2 $i
diff --git a/downloads-generation/data_curated/curate.py b/downloads-generation/data_curated/curate.py
index e14680b6..9c56c2f7 100755
--- a/downloads-generation/data_curated/curate.py
+++ b/downloads-generation/data_curated/curate.py
@@ -252,6 +252,7 @@ def load_data_additional_ms(filename):
df["measurement_type"] = "qualitative"
df["measurement_kind"] = "mass_spec"
df["measurement_source"] = "MS:pmid:" + df["original_pmid"].map(str)
+ df["original_allele"] = ""
return df
@@ -311,18 +312,26 @@ def run():
print("Measurement kind:")
print(df.measurement_kind.value_counts())
- df.to_csv(args.out_csv, index=False)
- print("Wrote: %s" % os.path.abspath(args.out_csv))
+ print("Measurement source / kind:")
+ print(
+ df.groupby(
+ ["measurement_source", "measurement_kind"]
+ ).peptide.count().sort_values())
- if args.out_affinity_csv:
- df.loc[df.measurement_kind == "affinity"].to_csv(
- args.out_affinity_csv, index=False)
- print("Wrote: %s" % os.path.abspath(args.out_affinity_csv))
+ def write(write_df, filename):
+ filename = os.path.abspath(filename)
+ write_df.to_csv(filename, index=False)
+ print("Wrote [%d lines]: %s" % (len(write_df), filename))
+ write(df, args.out_csv)
+ if args.out_affinity_csv:
+ write(
+ df.loc[df.measurement_kind == "affinity"],
+ args.out_affinity_csv)
if args.out_mass_spec_csv:
- df.loc[df.measurement_kind == "mass_spec"].to_csv(
- args.out_mass_spec_csv, index=False)
- print("Wrote: %s" % os.path.abspath(args.out_mass_spec_csv))
+ write(
+ df.loc[df.measurement_kind == "mass_spec"],
+ args.out_mass_spec_csv)
if __name__ == '__main__':
diff --git a/mhcflurry/downloads.yml b/mhcflurry/downloads.yml
index 940e0a40..a9eb33bd 100644
--- a/mhcflurry/downloads.yml
+++ b/mhcflurry/downloads.yml
@@ -8,7 +8,7 @@
# by name, the downloads with "default=true" are downloaded.
# This should usually be the latest release.
-current-release: 1.5.0
+current-release: 1.6.0
# An integer indicating what models the current MHCflurry code base is compatible
# with. Increment this integer when changes are made to MHCflurry that would break
@@ -17,6 +17,104 @@ current-compatibility-version: 2
# Add new releases here as they are made.
releases:
+ 1.6.0:
+ compatibility-version: 2
+ downloads:
+ - name: models_class1_pan
+ url: https://github.com/openvax/mhcflurry/releases/download/1.4.0/models_class1_pan.20200101.tar.bz2
+ default: false
+
+ - name: models_class1_pan_unselected
+ part_urls:
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/models_class1_pan_unselected.20200101.tar.bz2.part.aa
+ default: false
+
+ - name: models_class1_pan_refined
+ url: https://github.com/openvax/mhcflurry/releases/download/1.4.0/models_class1_pan_refined.20191212c.tar.bz2
+ default: false
+
+ - name: models_class1_pan_variants
+ part_urls:
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/models_class1_pan_variants.20200101.tar.bz2.part.aa
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/models_class1_pan_variants.20200101.tar.bz2.part.ab
+ default: false
+
+ - name: data_mass_spec_benchmark
+ part_urls:
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.aa
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.ab
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.ac
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.ad
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.ae
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.af
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.ag
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.ah
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.ai
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.aj
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.ak
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.al
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.am
+ - https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_benchmark.20191225.tar.bz2.part.an
+ default: false
+
+ - name: data_mass_spec_annotated
+ url: https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_mass_spec_annotated.20191226.tar.bz2
+ default: false
+
+ - name: data_references
+ url: https://github.com/openvax/mhcflurry/releases/download/pre-1.4.0/data_references.20190927.tar.bz2
+ default: false
+
+ - name: data_iedb
+ url: https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_iedb.20191220.tar.bz2
+ default: false
+
+ - name: data_systemhcatlas
+ url: http://github.com/openvax/mhcflurry/releases/download/pan-dev1/data_systemhcatlas.20190506.tar.bz2
+ default: false
+
+ - name: allele_sequences
+ url: https://github.com/openvax/mhcflurry/releases/download/1.4.0/allele_sequences.20191231.tar.bz2
+ default: false
+
+ - name: random_peptide_predictions
+ url: http://github.com/openvax/mhcflurry/releases/download/pan-dev1/random_peptide_predictions.20190506.tar.bz2
+ default: false
+
+ - name: data_published
+ url: https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_published.20191220.tar.bz2
+ default: false
+
+ - name: data_curated
+ url: https://github.com/openvax/mhcflurry/releases/download/1.4.0/data_curated.20191226.tar.bz2
+ default: true
+
+ # Older downloads
+ - name: models_class1
+ url: http://github.com/openvax/mhcflurry/releases/download/pre-1.2/models_class1.20180225.tar.bz2
+ default: true
+
+ - name: models_class1_selected_no_mass_spec
+ url: http://github.com/openvax/mhcflurry/releases/download/pre-1.2/models_class1_selected_no_mass_spec.20180225.tar.bz2
+ default: false
+
+ - name: models_class1_unselected
+ url: http://github.com/openvax/mhcflurry/releases/download/pre-1.2/models_class1_unselected.20180221.tar.bz2
+ default: false
+
+ - name: models_class1_trained_with_mass_spec
+ url: http://github.com/openvax/mhcflurry/releases/download/pre-1.2.1/models_class1_trained_with_mass_spec.20180228.tar.bz2
+ default: false
+
+ - name: models_class1_unselected_with_mass_spec
+ url: http://github.com/openvax/mhcflurry/releases/download/pre-1.2.1/models_class1_unselected_with_mass_spec.20180227.tar.bz2
+ default: false
+
+ - name: models_class1_minimal
+ url: http://github.com/openvax/mhcflurry/releases/download/pre-1.2/models_class1_minimal.20180226.tar.bz2
+ default: false
+
+
1.5.0:
compatibility-version: 2
downloads:
@@ -74,7 +172,7 @@ releases:
default: false
- name: allele_sequences
- url: https://github.com/openvax/mhcflurry/releases/download/1.4.0/allele_sequences.20191231.tar.bz2
+ url: http://github.com/openvax/mhcflurry/releases/download/pan-dev1/allele_sequences.20190506.tar.bz2
default: false
- name: random_peptide_predictions
--
GitLab