Protein Length

Evaluate whether protein length falls within acceptable range

This constraint is open source. Any third-party models, product names, or trademarks referenced are the property of their respective owners, and Proto is not affiliated with them.

---

Source

proto-bio/proto-language/proto_language/constraint/protein_quality/protein_length_constraint.py

View source

Evaluate whether protein sequence lengths fall within an acceptable range.

This constraint function checks if protein sequences have lengths within a specified range, penalizing sequences that are too short or too long. This is useful for filtering out spurious ORF predictions. Penalties scale linearly with the distance outside the acceptable range.

API Reference

ConfigProteinLengthConfig Source

Configuration object for protein length constraint.

This class defines configuration parameters for evaluating whether protein sequences fall within an acceptable length range. Length constraints are useful for filtering proteins that are too short or too long. The penalty scales linearly with the distance outside the acceptable range. For example, a protein 10 amino acids below min_length receives a proportionally smaller penalty than one 50 amino acids below.

min_length · integer · required

Minimum acceptable protein length below which sequences are penalized

max_length · integer · required

Maximum acceptable protein length above which sequences are penalized

ReturnsConstraintOutput

One result per sequence. A score of 0.0 indicates length is within the acceptable range [min_length, max_length] and higher values indicate greater deviation from the acceptable range. Penalties scale linearly: a sequence 10 amino acids outside the range receives half the penalty of one 20 amino acids outside. metadata carries:

• protein_length: Integer length of the protein sequence in amino acids

Usage

Evaluating protein length within range:

python

>>> from proto_language.core import Sequence, SequenceType
>>> config = ProteinLengthConfig(min_length=10, max_length=500)
>>> seq = Sequence("MVLSPADKTNVKAAWGKVGAHAGEYGAEALERMFLSF", "protein")
>>> results = protein_length_constraint([(seq,)], config)
>>> print(results[0].score)  # 0.0
>>> print(results[0].metadata["protein_length"])  # 37

Metadata

Property	Value
Key	protein-length
Function	protein_length_constraint
Category	protein_quality
Mode	discrete
Uses GPU	False
Supported Types	protein