def test_project_msa_rows(self):
token = '-'
seq1 = tf.convert_to_tensor(self.vocab.encode('XX--X-XX-X'), tf.int32)
seq2 = tf.convert_to_tensor(self.vocab.encode('Y-Y-Y-YYYY'), tf.int32)
mc = tf.convert_to_tensor([False] + 8 * [True] + [False], tf.bool)
proj_msa_fn = align_transforms.ProjectMSARows(token=token, vocab=self.vocab)
out1, out2 = proj_msa_fn.call(seq1, seq2)
self.assertAllEqual(out1, self.vocab.encode('XX-XXX-X'))
self.assertAllEqual(out2, self.vocab.encode('Y-YYYYYY'))
out1, out2 = proj_msa_fn.call(seq1, seq2, mc)
self.assertAllEqual(out1, self.vocab.encode('X-XXX-'))
self.assertAllEqual(out2, self.vocab.encode('-YYYYY'))
def make_pair_builder(max_len=512,
index_keys=('fam_key', 'ci_100'),
process_negatives=True,
gap_token='-',
sequence_key='sequence',
context_sequence_key='full_sequence',
loader_cls=make_pfam_pairs_loader,
pairing_cls=None,
lm_cls=None,
has_context=False,
append_eos=True,
append_eos_context=True,
add_random_tails=False,
**kwargs):
"""Creates a dataset for pairs of sequences."""
# Convenience function to index key pairs.
paired_keys = lambda k: tuple(f'{k}_{i}' for i in (1, 2))
def stack_and_pop(on):
stack = transforms.Stack(on=paired_keys(on), out=on)
pop = transforms.Pop(on=paired_keys(on))
return [stack, pop]
# Defines fields to be read from the TFRecords.
metadata_keys = ['cla_key', 'seq_key'] + list(index_keys)
extra_keys = metadata_keys.copy()
# Pre-paired datasets already been filtered by length, seq_len only needed
# when pairing sequences on-the-fly.
if pairing_cls is not None:
extra_keys.append('seq_len')
# Optionally, adds fields needed by the `AddAlignmentContext` `Transform`.
if has_context:
extra_keys.extend(['start', 'end'])
add_alignment_context_extra_args = (paired_keys(context_sequence_key) +
paired_keys('start') +
paired_keys('end'))
# Accounts for EOS token if necessary.
max_len_eos = max_len - 1 if append_eos else max_len
### Sets up the `DatasetTransform`s.
ds_transformations = []
if pairing_cls is not None:
filter_by_length = transforms.FilterByLength(max_len=max_len_eos)
# NOTE(fllinares): pairing on-the-fly is memory intensive on TPU for some
# reason not yet understood...
pair_sequences = pairing_cls(index_keys=index_keys)
ds_transformations.extend([filter_by_length, pair_sequences])
### Sets up the `Transform`s applied *before* batching.
project_msa_rows = align_transforms.ProjectMSARows(
on=paired_keys(sequence_key), token=gap_token)
append_eos_to_context = transforms.EOS(
on=paired_keys(context_sequence_key))
add_alignment_context = align_transforms.AddAlignmentContext(
on=paired_keys(sequence_key) + add_alignment_context_extra_args,
out=paired_keys(sequence_key),
max_len=max_len_eos,
gap_token=gap_token)
trim_alignment = align_transforms.TrimAlignment(
on=paired_keys(sequence_key), gap_token=gap_token)
pop_add_alignment_context_extra_args = transforms.Pop(
on=add_alignment_context_extra_args)
add_random_prefix_and_suffix = align_transforms.AddRandomTails(
on=paired_keys(sequence_key), max_len=max_len_eos)
create_alignment_targets = align_transforms.CreateAlignmentTargets(
on=paired_keys(sequence_key),
out='alignment/targets',
gap_token=gap_token,
n_prepend_tokens=0)
pid1 = align_transforms.PID(on=paired_keys(sequence_key),
out='alignment/pid1',
definition=1,
token=gap_token)
pid3 = align_transforms.PID(on=paired_keys(sequence_key),
out='alignment/pid3',
definition=3,
token=gap_token)
remove_gaps = transforms.RemoveTokens(on=paired_keys(sequence_key),
tokens=gap_token)
append_eos_to_sequence = transforms.EOS(on=paired_keys(sequence_key))
pad_sequences = transforms.CropOrPad(on=paired_keys(sequence_key),
size=max_len)
pad_alignment_targets = transforms.CropOrPadND(on='alignment/targets',
size=2 * max_len)
transformations = [project_msa_rows]
if has_context:
if append_eos_context:
transformations.append(append_eos_to_context)
transformations.extend([
add_alignment_context, trim_alignment,
pop_add_alignment_context_extra_args
])
if add_random_tails:
transformations.append(add_random_prefix_and_suffix)
transformations.append(create_alignment_targets)
transformations.extend([pid1, pid3, remove_gaps])
if append_eos:
transformations.append(append_eos_to_sequence)
transformations.extend([pad_sequences, pad_alignment_targets])
for key in [sequence_key] + metadata_keys:
transformations.extend(stack_and_pop(key))
### Sets up the `Transform`s applied *after* batching.
flatten_sequence_pairs = transforms.Reshape(on=sequence_key,
shape=[-1, max_len])
flatten_metadata_pairs = transforms.Reshape(on=metadata_keys, shape=[-1])
create_homology_targets = align_transforms.CreateHomologyTargets(
on='fam_key',
out='homology/targets',
process_negatives=process_negatives)
create_alignment_weights = align_transforms.CreateBatchedWeights(
on='alignment/targets', out='alignment/weights')
add_neg_alignment_targets_and_weights = align_transforms.PadNegativePairs(
on=('alignment/targets', 'alignment/weights'))
pad_neg_pid = align_transforms.PadNegativePairs(on=('alignment/pid1',
'alignment/pid3'),
value=-1.0)
batched_transformations = [
flatten_sequence_pairs, flatten_metadata_pairs, create_homology_targets
]
if process_negatives:
batched_transformations.extend([
create_alignment_weights, add_neg_alignment_targets_and_weights,
pad_neg_pid
])
if lm_cls is not None:
create_lm_targets = lm_cls(on=sequence_key,
out=(sequence_key, 'masked_lm/targets',
'masked_lm/weights'))
batched_transformations.append(create_lm_targets)
### Sets up the remainder of the `DatasetBuilder` configuration.
masked_lm_labels = ('masked_lm/targets', 'masked_lm/weights')
alignment_labels = ('alignment/targets' if not process_negatives else
('alignment/targets', 'alignment/weights'))
homology_labels = 'homology/targets'
embeddings = () if lm_cls is None else (masked_lm_labels, )
alignments = (alignment_labels, homology_labels)
return builder.DatasetBuilder(
data_loader=loader_cls(extra_keys),
ds_transformations=ds_transformations,
transformations=transformations,
batched_transformations=batched_transformations,
labels=multi_task.Backbone(embeddings=embeddings,
alignments=alignments),
metadata=('seq_key', 'alignment/pid1', 'alignment/pid3'),
sequence_key=sequence_key,
**kwargs)