favapy 0.3.7

Infer Functional Associations using Variational Autoencoders on -Omics data.

FAVA: Functional Associations using Variational Autoencoders

Protein networks are commonly used for understanding the interplay between proteins in the cell as well as for visualizing omics data. Unfortunately, most existing high-quality networks are heavily biased by data availability, in the sense that well-studied proteins have many more interactions than understudied proteins. To create networks that can help elucidate functions for the latter, we must start from data that are not affected by this literature bias, in other words, from omics data such as single cell RNA-seq (scRNA-seq) and proteomics. While networks can be inferred from such data through simple co-expression analysis, this approach does not work well due to high sparseness (many transcripts/proteins are not consistently observed in each cell/sample) and redundancy (many similar cells/samples are analyzed) of such data. We have therefore developed FAVA, Functional Associations using Variational Autoencoders, which deals with both issues by compressing these high-dimensional data into a dense, low-dimensional latent space. We demonstrate that calculating correlations in this latent space results in much improved networks compared to the original representation for large-scale scRNA-seq and proteomics data from the Human Protein Atlas, and from PRIDE, respectively. We show that these networks, which given the nature of the input data should be free of literature bias, indeed have much better coverage of understudied proteins than existing networks.

Data availability

Human Protein Atlas

https://www.proteinatlas.org/humanproteome/single+cell+type

PRIDE - Proteomics Identification Database - EMBL-EBI

https://www.ebi.ac.uk/pride/

Combined network

The Network: https://doi.org/10.5281/zenodo.6803472

Installation:

pip install favapy

Command line interface

Run favapy from the command line as follows:

favapy <path-to-data-file> <path-to-save-output>

Optional parameters:

-t Type of input data ('tsv' or 'csv'). Default value = 'tsv'.

-c The cut-off on the Pearson Correlation scores. Default value = 0.7.

-d The dimensions of the intermediate\hidden layer. Default value = 500.

-l The dimensions of the latent space. Default value = 100.

-e The number of epochs. Default value = 50.

-b The batch size. Default value = 32.