# bio-rs
[](https://github.com/bio-rs/bio-rs/actions)
[](https://github.com/bio-rs/bio-rs/actions/workflows/release.yml)
[](benchmarks/fasta_vs_biopython.md)
[](docs/public-contract-1.0-candidates.md)
[](LICENSE-MIT)
bio-rs turns biological sequences into validated, model-ready inputs for bio-AI workflows.
```txt
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
```bash
cargo install biors --version 0.20.1
biors tokenize examples/protein.fasta
```
Full commands, demos, and install options: [docs/quickstart.md](docs/quickstart.md)
## Proof
bio-rs keeps performance claims tied to reproducible in-repo benchmarks.
Latest recorded FASTA benchmark baseline:
| Human proteome | Parse + validation | **0.036s** | 0.584s | **16.09x** |
| Human proteome | Parse + tokenization | **0.061s** | 0.587s | **9.68x** |
| 100MB+ FASTA | Parse + validation | **0.294s** | 3.994s | **13.59x** |
| 100MB+ FASTA | Parse + tokenization | **0.492s** | 4.040s | **8.22x** |
| Many short records | Parse + validation | **0.007s** | 0.204s | **28.35x** |
| Many short records | Parse + tokenization | **0.010s** | 0.205s | **20.54x** |
| Single long sequence | Parse + validation | **0.005s** | 0.176s | **34.48x** |
| Single long sequence | Parse + tokenization | **0.007s** | 0.177s | **26.67x** |
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](benchmarks/fasta_vs_biopython.md)
- Benchmark script: [scripts/benchmark_fasta_vs_biopython.py](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
- 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
- `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 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
- JSON success/error envelopes
## Documentation
- [Quickstart](docs/quickstart.md) — install, first commands, demos
- [Launch demo](docs/demo.md) — researcher-facing demo workflow
- [Installation and distribution](docs/install.md) — cargo, binaries, completions
- [CLI contract](docs/cli-contract.md) — commands, JSON envelopes, exit codes
- [Error code registry](docs/error-codes.md)
- [Reliability and input safety](docs/reliability.md)
- [1.0 contract candidates](docs/public-contract-1.0-candidates.md)
- [Versioning policy](docs/versioning.md)
- [Final release checklist](docs/final-release-checklist.md)
- [JSON schemas](schemas)
- [Citation metadata](CITATION.cff)
## 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:
```bash
scripts/check.sh
```
Run the faster local commit gate:
```bash
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:
```bash
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:
```bash
python scripts/compare-benchmark-artifacts.py before.json after.json
```
Run the Rust library example:
```bash
cargo run -p biors-core --example tokenize
```
## Workspace
```txt
packages/
rust/
biors/ CLI
biors-core/ Core engine + contracts
schemas/
cli-error.v0.json
cli-success.v0.json
fasta-validation-output.v0.json
inspect-output.v0.json
model-input-output.v0.json
package-bridge-output.v0.json
package-inspect-output.v0.json
package-manifest.v0.json
package-validation-report.v0.json
package-verify-output.v0.json
tokenize-output.v0.json
examples/
protein.fasta
multi.fasta
protein-package/
models/
manifest.json
observations.json
fixtures/
observed/
tokenizers/
vocabs/
```
## Protein-20 alphabet
```txt
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](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](CITATION.cff).