bio-rs

bio-rs turns biological sequences into validated, model-ready inputs for bio-AI workflows.

FASTA -> validated protein/DNA/RNA sequence -> protein token ids -> model-ready JSON

Status: pre-1.0 CLI and JSON contract stabilization.

Why bio-rs?

Most bio-AI models are born in Python, but the tooling around them often needs to run somewhere else:

• local CLIs
• CI pipelines
• servers
• browsers
• agents

bio-rs focuses on the boring but important layer before inference:

• parse biological sequence input
• validate it with structured diagnostics
• tokenize it into stable IDs
• emit machine-readable JSON contracts
• keep preprocessing reproducible outside notebooks

The goal is not to replace Python research workflows.

The goal is to make the input layer around bio-AI models faster, more portable, and easier to trust.

Quickstart

cargo install biors --version 0.34.0
biors tokenize examples/protein.fasta
biors workflow --max-length 8 examples/protein.fasta
biors batch validate --kind auto examples/
biors tokenizer inspect --profile protein-20-special

Full commands, demos, and install options: docs/quickstart.md

Proof

bio-rs keeps performance claims tied to reproducible in-repo benchmarks.

Latest recorded FASTA benchmark baseline:

Benchmark details:

• Datasets:
  • UniProt human reference proteome (UP000005640, 9606)
  • 100MB+ large FASTA generated by repeating the same real proteome to isolate large-input throughput
  • 20,000 short 48-residue records generated from the same proteome residue stream
  • one 960,000-residue sequence generated from the same proteome residue stream
• Matched workloads:
  • pure parse
  • parse plus validation
  • parse plus tokenization
• Current best recorded raw throughput:
  • human proteome parse + validation: 315.4M residues/s, 360.6 MB/s
  • 100MB+ FASTA parse + validation: 350.8M residues/s, 401.1 MB/s
  • human proteome parse + tokenization: 189.0M residues/s, 216.1 MB/s
  • 100MB+ FASTA parse + tokenization: 209.7M residues/s, 239.8 MB/s
• Benchmark doc: benchmarks/fasta_vs_biopython.md
• Benchmark script: scripts/benchmark_fasta_vs_biopython.py

This benchmark measures biors-core directly and excludes CLI startup and JSON serialization overhead. It is still workload-specific, not a broad claim that bio-rs is faster than Biopython across every FASTA workload or researcher input shape.

What works today

biors-core provides the Rust engine and data contracts.

biors provides the CLI surface.

Current capabilities:

• FASTA parsing and normalization
• shared FASTA parser/tokenizer scanner with an ASCII fast path and Unicode fallback
• buffered reader APIs for FASTA parse/validate/tokenize paths
• FASTA validation with line and record-index diagnostics
• FASTA record identifier validation
• protein-20 tokenization
• protein-20-special tokenization with explicit UNK/PAD/CLS/SEP/MASK policy
• tokenizer JSON config loading
• tokenizer inspection JSON output
• JSON vocab loading for tokenizer contracts
• positional token alignment preserved with explicit unknown-token IDs for unresolved residues
• residue warning/error reporting
• model-ready input records
• attention masks
• padding/truncation policy
• model-input CLI output
• workflow CLI output that combines validation, tokenization, model input, readiness issues, and reproducibility provenance
• workflow provenance hashes for tokenizer vocabulary and output-content reproducibility
• diff CLI output for canonical JSON/raw output comparison with SHA-256 hashes and first-difference metadata
• pipeline CLI output for no-config validate -> tokenize -> export workflow composition
• pipeline lockfile generation for config-driven workflows with package/model and runtime provenance pins
• debug CLI output for sequence -> token -> model-input step inspection and compact residue error visualization
• batch validate for multiple files, recursive directory inputs, quoted glob inputs, empty-glob errors, and memory-bounded validation summaries
• doctor CLI diagnostics for platform, toolchain, WASM target, and committed fixture readiness
• model-input safety checks for unresolved residues
• explicit checked and unchecked model-input builders
• writer-based CLI success JSON serialization to reduce peak allocations for large outputs
• package manifest inspect/validate
• typed package validation issue codes
• typed package manifest enums for schema version, model format, runtime target, and tensor dtypes
• runtime bridge planning reports
• manifest-relative asset validation
• package preprocessing steps can reference checked pipeline config artifacts
• package path escape rejection for manifest and observation assets
• SHA-256 package and fixture checksum verification
• package fixture verification from observed artifact paths
• structured package fixture mismatch issue codes and first-difference reports
• committed FASTA, tokenizer, manifest, and verification fixtures
• draft model-input contract and reference Python preprocessing parity fixtures
• JSON success/error envelopes

Documentation

• Quickstart — install, first commands, demos
• Launch demo — researcher-facing demo workflow
• Installation and distribution — cargo, binaries, completions
• CLI contract — commands, JSON envelopes, exit codes
• Package format — manifest layout and research metadata
• Pipeline config — config-driven static preprocessing workflows
• Error code registry
• Reliability and input safety
• Python interop
• WASM readiness
• 1.0 contract candidates
• Versioning policy
• Schema versioning
• Final release checklist
• Changelog
• JSON schemas
• Citation metadata

Not yet

These are roadmap directions, not current capabilities:

• hosted web workflows
• Python bindings
• model inference backends
• package registry or plugin ecosystem
• general-purpose chemistry tooling
• structure tooling
• no-code or low-code workflows

Development

Run checks:

scripts/check.sh

Run the faster local commit gate:

scripts/check-fast.sh

The check suite runs:

• cargo fmt
• shell and Python syntax checks for repo scripts
• benchmark Markdown regeneration check
• release workflow publish-order invariant check
• Rust checks
• biors-core wasm32-unknown-unknown build check
• tests
• cargo clippy with warnings denied

Reproduce the FASTA benchmark:

cargo build --release -p biors-core --example benchmark_fasta
python3 -m venv .venv-bench
. .venv-bench/bin/activate
pip install biopython
python scripts/benchmark_fasta_vs_biopython.py
cat benchmarks/fasta_vs_biopython.json

The benchmark script updates both benchmarks/fasta_vs_biopython.json and benchmarks/fasta_vs_biopython.md. scripts/check-benchmark-docs.sh verifies that the Markdown report still matches the JSON artifact.

Compare two benchmark artifacts:

python scripts/compare-benchmark-artifacts.py before.json after.json

Run the Rust library example:

cargo run -p biors-core --example tokenize

Workspace

packages/
  rust/
    biors/       CLI
    biors-core/  Core engine + contracts

schemas/
  batch-validation-output.v0.json
  cli-error.v0.json
  cli-success.v0.json
  fasta-validation-output.v0.json
  inspect-output.v0.json
  model-input-output.v0.json
  output-diff.v0.json
  pipeline-output.v0.json
  pipeline-config.v0.json
  pipeline-lock.v0.json
  sequence-workflow-output.v0.json
  sequence-debug-output.v0.json
  package-bridge-output.v0.json
  package-inspect-output.v0.json
  package-manifest.v0.json
  package-manifest.v1.json
  package-validation-report.v0.json
  package-verify-output.v0.json
  tokenizer-inspect-output.v0.json
  tokenize-output.v0.json

examples/
  protein.fasta
  multi.fasta
  model-input-contract/
    protein-20-special.config.json
    protein-20-special.expected.json
    reference-python-parity.json
  python/
    esm_from_biors_json.py
    pandas_numpy_friendly.py
    protbert_from_biors_json.py
    reference_preprocess.py
  protein-package/
    models/
    docs/
    manifest.json
    observations.json
    fixtures/
    observed/
    tokenizers/
    vocabs/
    pipelines/
  pipeline/
    protein.toml
    protein.yaml
    protein.json
    pipeline.lock

Protein-20 alphabet

A C D E F G H I K L M N P Q R S T V W Y

Token IDs follow that order, starting at 0.

Contributing

See CONTRIBUTING.md for local setup, checks, and PR expectations.

License

Dual licensed under MIT OR Apache-2.0. If you use bio-rs in research software or publications, cite the repository and version via CITATION.cff.