From b4f63aea7187f0553248b8fbb17214fd8831c461 Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Fri, 16 Feb 2018 11:40:26 -0500
Subject: [PATCH] update
---
mhcflurry/class1_affinity_predictor.py | 5 ++---
mhcflurry/encodable_sequences.py | 6 +++++-
2 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/mhcflurry/class1_affinity_predictor.py b/mhcflurry/class1_affinity_predictor.py
index c6521046..ea4939b4 100644
--- a/mhcflurry/class1_affinity_predictor.py
+++ b/mhcflurry/class1_affinity_predictor.py
@@ -821,9 +821,7 @@ class Class1AffinityPredictor(object):
raise ValueError("Must specify 'allele' or 'alleles'.")
peptides = EncodableSequences.create(peptides)
- df = pandas.DataFrame({
- 'peptide': peptides.sequences,
- })
+ df = peptides.sequences_df.rename(columns={'sequence': 'peptide'})
if allele is not None:
if alleles is not None:
@@ -948,6 +946,7 @@ class Class1AffinityPredictor(object):
]
columns.remove("normalized_allele")
columns.remove("supported_peptide_length")
+ columns.remove("sequence_length")
if include_percentile_ranks:
if self.allele_to_percent_rank_transform:
diff --git a/mhcflurry/encodable_sequences.py b/mhcflurry/encodable_sequences.py
index 6dcd5e63..da4cf9dc 100644
--- a/mhcflurry/encodable_sequences.py
+++ b/mhcflurry/encodable_sequences.py
@@ -35,7 +35,11 @@ class EncodableSequences(object):
def __init__(self, sequences):
if not all(isinstance(obj, string_types) for obj in sequences):
raise ValueError("Sequence of strings is required")
- self.sequences = numpy.array(sequences)
+ self.sequences_df = pandas.DataFrame({
+ "sequence": numpy.array(sequences),
+ "sequence_length": numpy.array(sequences),
+ })
+ self.sequences = self.sequences_df.sequence.values
self.encoding_cache = {}
self.fixed_sequence_length = None
if len(self.sequences) > 0 and all(
--
GitLab