Can I modify and re-export existing FCS files?

Yes, the skill allows you to read an existing file, modify the event data or metadata, and then export it as a new FCS 3.1 compliant file.

Does this skill support multi-dataset FCS files?

Yes, it provides dedicated functionality to detect multiple datasets within a single file and process them individually or collectively.

Can I extract metadata without loading the entire dataset?

Yes, FlowIO includes a memory-efficient mode that allows you to parse only the TEXT segment keywords while skipping the larger DATA and ANALYSIS sections.

Is FlowIO suitable for machine learning workflows?

Absolutely. By converting event data into NumPy arrays and handling channel scaling automatically, it is ideal for preparing cytometry data for ML model training.

Which FCS versions are supported by this skill?

FlowIO supports reading Flow Cytometry Standard versions 2.0, 3.0, and 3.1, and supports writing data to the 3.1 standard.

FlowIO Flow Cytometry Handler

Name: FlowIO Flow Cytometry Handler
Author: jimmc414

byjimmc414

•

324

Data Science & ML

Parses and manipulates Flow Cytometry Standard (FCS) files for scientific data preprocessing and analysis.

About

FlowIO is a specialized skill designed to handle Flow Cytometry Standard (FCS) files across versions 2.0, 3.0, and 3.1. It enables Claude to programmatically extract event data into NumPy arrays, read rich metadata from TEXT segments, and generate new FCS files from scratch. This skill is essential for bioinformatics workflows, allowing for the conversion of complex cytometry data into interoperable formats like CSV or DataFrames, and includes advanced features for handling multi-dataset files and correcting offset discrepancies in problematic instrument outputs.

Key Features

Comprehensive parsing of FCS versions 2.0 through 3.1
Automated preprocessing including gain scaling and logarithmic transformations
324 GitHub stars
High-fidelity metadata extraction including instrument and channel information
Support for creating and exporting new FCS 3.1 files from raw data
Seamless conversion of event data to NumPy arrays and Pandas DataFrames

Use Cases

Preprocessing raw flow cytometry data for machine learning and AI discovery pipelines
Converting proprietary instrument data into standardized formats for cross-lab collaboration
Automating the batch extraction of experiment metadata and channel labels

About

Key Features

Comprehensive parsing of FCS versions 2.0 through 3.1
Automated preprocessing including gain scaling and logarithmic transformations
324 GitHub stars
High-fidelity metadata extraction including instrument and channel information
Support for creating and exporting new FCS 3.1 files from raw data
Seamless conversion of event data to NumPy arrays and Pandas DataFrames

Use Cases

Preprocessing raw flow cytometry data for machine learning and AI discovery pipelines
Converting proprietary instrument data into standardized formats for cross-lab collaboration
Automating the batch extraction of experiment metadata and channel labels