Supported Models

AlignAIR ships with pre-trained models for human B-cell and T-cell receptor analysis. Each model is optimized for specific chain types and comes ready to use in the Docker container.

Quick Reference

IGH Heavy Chain

--chain-type=heavy

/app/pretrained_models/IGH_S5F_576

IGH Heavy Chain Extended

--chain-type=heavy

/app/pretrained_models/IGH_S5F_576_Extended

IGL/IGK Light Chain Extended

--chain-type=light

/app/pretrained_models/IGL_S5F_576

IGL/IGK Light Chain OGRDB

--chain-type=light

legacy

TCRB Beta Chain

--chain-type=trb

/app/pretrained_models/TCRB_UNIFORM_576

IGH Heavy Chain

--chain-type=heavy

stealth

Model Details

IGH Heavy Chain

Immunoglobulin Heavy Chain model trained on S5F mutation patterns

Key Features

V/D/J segmentation

Allele calling

Mutation prediction

Productivity assessment

Usage Example:

python app.py run \
  --model-checkpoint=/app/pretrained_models/IGH_S5F_576 \
  --chain-type=heavy \
  --sequences=/data/input/sequences.csv \
  --save-path=/data/output

Model Metadata

Checkpoint Path

/app/pretrained_models/IGH_S5F_576

Chain Type

heavy

Species

Human

Reference Set

OGRDB V8

Last Updated

February 2025

Input Size

576 nucleotides

IGH Heavy Chain Extended

Immunoglobulin Heavy Chain model trained on S5F mutation patterns

Key Features

V/D/J segmentation

Allele calling

Mutation prediction

Productivity assessment

Usage Example:

python app.py run \
  --model-checkpoint=/app/pretrained_models/IGH_S5F_576_Extended \
  --chain-type=heavy \
  --sequences=/data/input/sequences.csv \
  --save-path=/data/output

Model Metadata

Checkpoint Path

/app/pretrained_models/IGH_S5F_576_Extended

Chain Type

heavy

Species

Human

Reference Set

Human Unified set of Alleles (HUSA)

Last Updated

September 2025

Input Size

576 nucleotides

IGL/IGK Light Chain Extended

Immunoglobulin Lambda and Kappa Light Chain model with enhanced V/J prediction

Key Features

V/J segmentation

Allele calling

Mutation prediction

Productivity assessment

Extended reference set

Usage Example:

python app.py run \
  --model-checkpoint=/app/pretrained_models/IGL_S5F_576 \
  --chain-type=light \
  --sequences=/data/input/sequences.csv \
  --save-path=/data/output

Model Metadata

Checkpoint Path

/app/pretrained_models/IGL_S5F_576

Chain Type

light

Species

Human

Reference Set

Human Unified set of Alleles (HUSA)

Last Updated

September 2025

Input Size

576 nucleotides

IGL/IGK Light Chain OGRDB

Immunoglobulin Lambda Light Chain model with enhanced V/J prediction

Key Features

V/J segmentation

Allele calling

Mutation prediction

Productivity assessment

Usage Example:

python app.py run \
  --model-checkpoint=legacy \
  --chain-type=light \
  --sequences=/data/input/sequences.csv \
  --save-path=/data/output

Model Metadata

Checkpoint Path

legacy

Chain Type

light

Species

Human

Reference Set

OGRDB V2 & V3 extended

Last Updated

March 2025

Input Size

576 nucleotides

TCRB Beta Chain

T Cell Receptor Beta Chain model optimized for TCR repertoire analysis

Key Features

V/D/J segmentation

Allele calling

Productivity assessment

Usage Example:

python app.py run \
  --model-checkpoint=/app/pretrained_models/TCRB_UNIFORM_576 \
  --chain-type=trb \
  --sequences=/data/input/sequences.csv \
  --save-path=/data/output

Model Metadata

Checkpoint Path

/app/pretrained_models/TCRB_UNIFORM_576

Chain Type

trb

Species

Human

Reference Set

IMGT 2022

Last Updated

September 2025

Input Size

576 nucleotides

IGH Heavy Chain

Immunoglobulin Heavy Chain model trained on S5F mutation patterns

Key Features

V/D/J segmentation

Allele calling

Mutation prediction

Productivity assessment

Usage Example:

python app.py run \
  --model-checkpoint=stealth \
  --chain-type=heavy \
  --sequences=/data/input/sequences.csv \
  --save-path=/data/output

Model Metadata

Checkpoint Path

stealth

Chain Type

heavy

Species

Rhesus Macaque

Reference Set

Rhesus Macaque Unified set of Alleles (MUSA)

Last Updated

September 2025

Input Size

576 nucleotides

Model Comparison

Model	Chain Type	Segments	Reference	Use Case
IGH Heavy Chain	`heavy`	V, D, J	OGRDB V8	B-cell heavy chain analysis
IGH Heavy Chain Extended	`heavy`	V, D, J	Human Unified set of Alleles (HUSA)	B-cell heavy chain analysis
IGL/IGK Light Chain Extended	`light`	V, J	Human Unified set of Alleles (HUSA)	B-cell lambda/kappa light chain analysis
IGL/IGK Light Chain OGRDB	`light`	V, J	OGRDB V2 & V3 extended	B-cell lambda/kappa light chain analysis
TCRB Beta Chain	`trb`	V, D, J	IMGT 2022	T-cell receptor beta chain analysis
IGH Heavy Chain	`heavy`	V, D, J	Rhesus Macaque Unified set of Alleles (MUSA)	B-cell heavy chain analysis

All Models Included

All models are pre-installed and ready to use when you pull the AlignAIR Docker container. No additional downloads or setup required.

docker pull thomask90/alignair:latest