biolm.pipeline | BioLM Docs

Multi-stage protein design pipelines with DuckDB caching, resumability, and dependency resolution. See Python SDK overview for SDK onboarding.

Overview

The pipeline framework provides:

Multi-stage orchestration with automatic dependency resolution
DuckDB caching for predictions, embeddings, and structures
Resumability — skip completed stages on re-run
Streaming for large datasets
Visualization — funnel plots, PCA/UMAP, distributions

Quick start

python

from biolm.pipeline import GenerativePipeline, SaturationMutagenesisConfig

config = SaturationMutagenesisConfig(
    parent_sequence="MKTAYIAKQRQ",
    scoring_model="esm2-650m",
    scoring_action="predict",
    score_field="logits",
    top_n=10,
)
pipeline = GenerativePipeline(configs=[config])
results = pipeline.run()

Config hierarchy

All pipeline configs inherit from ScoringProtocolConfig. Use isinstance to dispatch on config type:

python

from biolm.pipeline.generative import (
    ScoringProtocolConfig,
    GenerativeProtocolConfig,
    SaturationMutagenesisConfig,
    IterativeMaskingDMSConfig,
    DirectGenerationConfig,
)

if isinstance(config, SaturationMutagenesisConfig):
    pipeline = GenerativePipeline(configs=[config])
elif isinstance(config, DirectGenerationConfig):
    pipeline = GenerativePipeline(configs=[config])

text

ScoringProtocolConfig
├── SaturationMutagenesisConfig
├── IterativeMaskingDMSConfig
└── DirectGenerationConfig (extends GenerativeProtocolConfig)

Model quick-reference

Config type	Model	Action	Notes
SaturationMutagenesisConfig	esm2-650m	predict	Single-mutant library + scoring
IterativeMaskingDMSConfig	esm2-650m	predict	Greedy MLM argmax DMS
DirectGenerationConfig	proteinmpnn / dsm / antifold	generate	Structure-conditioned generation

Config classes

Field details are documented on each class below.

Pipeline examples

Saturation mutagenesis funnel:

python

from biolm.pipeline import GenerativePipeline, SaturationMutagenesisConfig

config = SaturationMutagenesisConfig(
    parent_sequence="MKTAYIAKQRQ",
    scoring_model="esm2-650m",
    scoring_action="predict",
    score_field="logits",
    top_n=10,
)
pipeline = GenerativePipeline(configs=[config])
results = pipeline.run()

Direct generation (ProteinMPNN):

python

from biolm.pipeline import GenerativePipeline, DirectGenerationConfig

config = DirectGenerationConfig(
    model_name="protein-mpnn",
    structure_path="design.pdb",
    num_sequences=10,
)
pipeline = GenerativePipeline(configs=[config])
results = pipeline.run()

Serialization and resumability

Pipeline definitions can be serialized with PipelineDef for round-trip storage. DuckDB caches predictions and embeddings so re-runs skip completed work.