Skip to main content

Deep Learning Methods for Parsing T-Cell Receptor Sequencing (TCRSeq) Data

Project description

# DeepTCR

## Deep Learning Methods for Parsing T-Cell Receptor Sequencing (TCRSeq) Data

DeepTCR is a python package that has a collection of unsupervised and supervised
deep learning methods to parse TCRSeq data. To see examples of how the algorithms can
be used on an example datasets, see the subdirectory 'tutorials' for a collection of tutorial
use cases across multiple datasets. For complete documentation for all available methods,
see 'Documentation.txt'.

While DeepTCR will run with Tensorflow-CPU versions, for optimal training times,
we suggest training these algorithms on GPU's (requiring CUDA, cuDNN, and tensorflow-GPU).

DeepTCR now has the added functionality of being able to analyze paired alpha/beta chain inputs as well
as also being able to take in v/d/j gene usage if available. For detailed instructions on
how to upload this type of data, refer to the documentation for loading data into DeepTCR.

For questions or help, email: jsidhom1@jhmi.edu

## Publication

For full description of algorithm and methods behind DeepTCR, refer to the following manuscript:

Sidhom, J. W., Larman, H. B., Pardoll, D. M., & Baras, A. S. (2018). DeepTCR: a deep learning framework for revealing structural concepts within TCR Repertoire. bioRxiv, 464107.

https://www.biorxiv.org/content/early/2018/11/26/464107
## Dependencies

DeepTCR has the following python library dependencies:
1. numpy==1.14.5
2. pandas==0.23.1
3. tensorflow==1.11.0
4. scikit-learn==0.19.1
5. pickleshare==0.7.4
6. matplotlib==2.2.2
7. scipy==1.1.0
8. biopython==1.69
9. seaborn==0.9.0
10. PhenoGraph==1.5.2


## Installation


In order to install DeepTCR:

```python
pip3 install DeepTCR

```

Or to install latest updated versions from Github repo:

Either download package, unzip, and run setup script:

```python
python3 setup.py install
```

Or use:

```python
pip3 install git+https://github.com/sidhomj/DeepTCR.git

```

## Release History

### 1.1
Initial release including two methods for unsupervised learning (VAE & GAN). Also included
ability to handle paired alpha/beta data.

### 1.2
Second release included major refactoring in code to streamline and share methods across
classes. Included ability for algorithm to accept v/d/j gene usage. Added more analytical fetures and
visualization methods. Removed GAN from unsupervised learning techniques.

#### 1.2.7
On-graph clustering method introduced for repertoire classifier to improve classification performance.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

DeepTCR-1.2.8.tar.gz (34.5 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page