ratvec 0.1.0

Generating dense embeddings for proteins using kernel PCA

Generating dense embeddings for proteins using kernel PCA.

Installation

Install directly from the source with:

$ pip install git+https://jira.iais.fraunhofer.de/stash/scm/meml/protein_vectors.git

Install in development mode with:

$ git clone https://jira.iais.fraunhofer.de/stash/scm/meml/protein_vectors.git
$ cd ratvec
$ pip install -e .

The -e dynamically links the code in the git repository to the Python site-packages so your changes get reflected immediately.

How to Use

ratvec is automatically installs a command line interface. Check it out with

$ ratvec --help

RatVec has four main commands: generate, train, evaluate and optimize:

1. Generate. Downloads and prepare the SwissProt data set that is showcased in the RatVec paper.

2. Train. Compute KPCA embeddings on a given data set. Please run the following command to see the arguments:

$ ratvec train --help

3. Evaluate. Evaluate and optimize KPCA embeddings. Please run the following command to see the arguments:

$ ratvec evaluate --help

4. Optimize. Evaluate and optimize KPCA embeddings. Please run the following command to see the arguments:

$ ratvec optimize --help

Showcase Dataset

The application presented in the paper (SwissProt dataset [1] used by Boutet et al. [2]) can be downloaded directly from the following website https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/JMFHTN or by running the following command:

$ ratvec generate

References

[1]

Boutet, E. et al. (2016). UniProtKB/Swiss-Prot, the manually annotated section of the UniProt KnowledgeBase: how to use the entry view.. Plant Bioinformatics (pp. 23-54).

[2]

Asgari, E., & Mofrad, M. R. (2015). Continuous distributed representation of biological sequences for deep proteomics and genomics. PloS one, 10(11), e0141287.