01
Sequence analysis
Work directly with DNA and RNA sequences using predictable, composable primitives.
↗ v1.2.0 is available on PyPI View release notes ↗
Research-grade tools for living data.
GenomeHouse is a modular Python toolkit for sequence analysis, genomic parsing, machine learning, visualization, and the work that connects them.
genomehouse / quickstart.py01
from genomehouse import sequence_tools
# inspect a sequence in one line
sequence = "ATGCGTAC"
gc_content = sequence_tools.gc_content(sequence)
> 50.0
● ready4 tools loaded
6research domains
4file formats
1modular toolkit
Built for the gap between a notebook and a pipeline.
01The platform
One toolkit, many ways into the data.
Start with a single sequence or build a repeatable workflow. Each module stays small enough to understand and useful enough to ship.
02
Genomic parsing
Stream standard research formats without forcing whole files into memory.
↗03
Machine learning
Move from biological sequences to useful features and baseline models quickly.
↗04
Visualization
Create publication-ready views for genomic and biological data.
↗05
Statistics
Turn exploratory measurements into reproducible analysis workflows.
↗06
Extensible API
Compose the toolkit around your own pipelines and research conventions.
↗02Get started
From zero to first result in seconds.
Install the package, open a Python shell, and keep your attention on the biology.
i
GenomeHouse 1.2.0 requires Python 3.8 or newer. Optional dependencies are available for visualization and machine learning.
Terminal
$ pip install genomehouse✓
Ready to importgenomehouse.__version__ → 1.2.0
03In the lab
Small examples. Serious workflows.
A few familiar entry points from the package README, arranged for quick scanning and copying.
Sequence analysissequence_tools
from genomehouse import sequence_tools
seq = "ATGCGTACGGCTA"
gc_content = sequence_tools.gc_content(seq)
print(f"GC Content: {gc_content}%")File parsinggenomic_parsers
from genomehouse import genomic_parsers
for header, sequence in genomic_parsers.parse_fasta("data.fasta"):
print(f">{header}")
print(f"Length: {len(sequence)}")CLI workflowsgenomehouse-cli
genomehouse-cli parse-fasta data/sample.fasta
genomehouse-cli gc-content ATGCGTACA clearer starting point