LIBRA / Git / Diff of /README.md

Models:
AlyssaS/
LIBRA
Downloads: 1
Diff of /README.md [d86a99] .. [63133d]
Switch to unified view


[![Latest version](https://d25lcipzij17d.cloudfront.net/badge.svg?id=py&r=r&type=6e&v=0.0.48&x2=0)](https://pypi.org/project/sc-libra/)
[![Downloads](https://static.pepy.tech/personalized-badge/sc_libra?period=total&units=international_system&left_color=grey&right_color=green&left_text=Downloads)](https://pepy.tech/project/sc_libra)
[![Documentation](https://img.shields.io/readthedocs/sc-libra)](https://sc-libra.readthedocs.io/en/latest/)
[![](https://img.shields.io/badge/doi-10.1101/2021.01.27.428400-red.svg)](https://doi.org/10.1101/2021.01.27.428400)
[![DOI](https://img.shields.io/badge/doi-10.6084/m9.figshare.19466246-blue.svg?style=flat&labelColor=whitesmoke&logo=data%3Aimage%2Fpng%3Bbase64%2CiVBORw0KGgoAAAANSUhEUgAAAB8AAAAfCAYAAAAfrhY5AAAJsklEQVR42qWXd1DTaRrHf%2BiB2Hdt5zhrAUKz4IKEYu9IGiGFFJJQ0gkJCAKiWFDWBRdFhCQUF3UVdeVcRQEBxUI3yY9iEnQHb3bdW1fPubnyz%2F11M7lvEHfOQee2ZOYzPyDv%2B3yf9%2Fk95YX4fx%2BltfUt08GcFEuPR4U9hDDZ%2FVngIlhb%2FSiI6InkTgLzgDcgfvtnovhH4BzoVlrbwr55QnhCtBW4QHXnFrZbPBaQoBh4%2FSYH2EnpBEtqcDMVzB93wA%2F8AFwa23XFGcc8CkT3mxz%2BfXWtq9T9IQlLIXYEuHojudb%2BCM7Hgdq8ydi%2FAHiBXyY%2BLjwFlAEnS6Jnar%2FvnQVhvdzasad0eKvWZKe8hvDB2ofLZ%2FZEcWsh%2BhyIuyO5Bxs2iZIE4nRv7NWAb0EO8AC%2FWPxjYAWuOEX2MSXZVgPxzmRL3xKz3ScGpx6p6QnOx4mDIFqO0w6Q4fEhO5IzwxlSwyD2FYHzwAW%2BAZ4fEsf74gCumykwNHskLM7taQxLYjjIyy8MUtraGhTWdkfhkFJqtvuVl%2F9l2ZquDfEyrH8B0W06nnpH3JtIyRGpH1iJ6SfxDIHjRXHJmdQjLpfHeN54gnfFx4W9QRnovx%2FN20aXZeTD2J84hn3%2BqoF2Tqr14VqTPUCIcP%2B5%2Fly4qC%2BUL3sYxSvNj1NwsVYPsWdMUfomsdkYm3Tj0nbV0N1wRKwFe1MgKACDIBdMAhPE%2FwicwNWxll8Ag40w%2BFfhibJkGHmutjYeQ8gVlaN%2BjO51nDysa9TwNUFMqaGbKdRJZFfOJSp6mkRKsv0rRIpEVWjAvyFkxNOEpwvcAVPfEe%2Bl8ojeNTx3nXLBcWRrYGxSRjDEk0VlpxYrbe1ZmaQ5xuT0u3r%2B2qe5j0J5uytiZPGsRL2Jm32AldpxPUNJ3jmmsN4x62z1cXrbedXBQf2yvIFCeZrtyicZZG2U2nrrBJzYorI2EXLrvTfCSB43s41PKEvbZDEfQby6L4JTj%2FfIwam%2B4%2BwucBu%2BDgNK05Nle1rSt9HvR%2FKPC4U6LTfvUIaip1mjIa8fPzykii23h2eanT57zQ7fsyYH5QjywwlooAUcAdOh5QumgTHx6aAO7%2FL52eaQNEShrxfhL6albEDmfhGflrsT4tps8gTHNOJbeDeBlt0WJWDHSgxs6cW6lQqyg1FpD5ZVDfhn1HYFF1y4Eiaqa18pQf3zzYMBhcanlBjYfgWNayAf%2FASOgklu8bmgD7hADrk4cRlOL7NSOewEcbqSmaivT33QuFdHXj5sdvjlN5yMDrAECmdgDWG2L8P%2BAKLs9ZLZ7dJda%2BB4Xl84t7QvnKfvpXJv9obz2KgK8dXyqISyV0sXGZ0U47hOA%2FAiigbEMECJxC9aoKp86re5O5prxOlHkcksutSQJzxZRlPZmrOKhsQBF5zEZKybUC0vVjG8PqOnhOq46qyDTDnj5gZBriWCk4DvXrudQnXQmnXblebhAC2cCB6zIbM4PYgGl0elPSgIf3iFEA21aLdHYLHUQuVkpgi02SxFdrG862Y8ymYGMvXDzUmiX8DS5vKZyZlGmsSgQqfLub5RyLNS4zfDiZc9Edzh%2FtCE%2BX8j9k%2FqWB071rcZyMImne1SLkL4GRw4UPHMV3jjwEYpPG5uW5fAEot0aTSJnsGAwHJi2nvF1Y5OIqWziVCQd5NT7t6Q8guOSpgS%2Fa1dSRn8JGGaCD3BPXDyQRG4Bqhu8XrgAp0yy8DMSvvyVXDgJcJTcr1wQ2BvFKf65jqhvmxXUuDpGBlRvV36XvGjQzLi8KAKT2lYOnmxQPGorURSV0NhyTIuIyqOmKTMhQ%2BieEsgOgpc4KBbfDM4B3SIgFljvfHF6cef7qpyLBXAiQcXvg5l3Iunp%2FWv4dH6qFziO%2BL9PbrimQ9RY6MQphEfGUpOmma7KkGzuS8sPUFnCtIYcKCaI9EXo4HlQLgGrBjbiK5EqMj2AKWt9QWcIFMtnVvQVDQV9lXJJqdPVtUQpbh6gCI2Ov1nvZts7yYdsnvRgxiWFOtNJcOMVLn1vgptVi6qrNiFOfEjHCDB3J%2BHDLqUB77YgQGwX%2Fb1eYna3hGKdlqJKIyiE4nSbV8VFgxmxR4b5mVkkeUhMgs5YTi4ja2XZ009xJRHdkfwMi%2BfocaancuO7h%2FMlcLOa0V%2FSw6Dq47CumRQAKhgbOP8t%2BMTjuxjJGhXCY6XpmDDFqWlVYbQ1aDJ5Cptdw4oLbf3Ck%2BdWkVP0LpH7s9XLPXI%2FQX8ws%2Bj2In63IcRvOOo%2BTTjiN%2BlssfRsanW%2B3REVKoavBOAPTXABW4AL7e4NygHdpAKBscmlDh9Jysp4wxbnUNna3L3xBvyE1jyrGIkUHaqQMuxhHElV6oj1picvgL1QEuS5PyZTEaivqh5vUCKJqOuIgPFGESns8kyFk7%2FDxyima3cYxi%2FYOQCj%2F%2B9Ms2Ll%2Bhn4FmKnl7JkGXQGDKDAz9rUGL1TIlBpuJr9Be2JjK6qPzyDg495UxXYF7JY1qKimw9jWjF0iV6DRIqE%2B%2FeWG0J2ofmZTk0mLYVd4GLiFCOoKR0Cg727tWq981InYynvCuKW43aXgEjofVbxIqrm0VL76zlH3gQzWP3R3Bv9oXxclrlO7VVtgBRpSP4hMFWJ8BrUSBCJXC07l40X4jWuvtc42ofNCxtlX2JH6bdeojXgTh5TxOBKEyY5wvBE%2BACh8BtOPNPkApjoxi5h%2B%2FFMQQNpWvZaMH7MKFu5Ax8HoCQdmGkJrtnOiLHwD3uS5y8%2F2xTSDrE%2F4PT1yqtt6vGe8ldMBVMEPd6KwqiYECHDlfbvzphcWP%2BJiZuL5swoWQYlS%2Br7Yu5mNUiGD2retxBi9fl6RDGn4Ti9B1oyYy%2BMP5G87D%2FCpRlvdnuy0PY6RC8BzTA40NXqckQ9TaOUDywkYsudxJzPgyDoAWn%2BB6nEFbaVxxC6UXjJiuDkW9TWq7uRBOJocky9iMfUhGpv%2FdQuVVIuGjYqACbXf8aa%2BPeYNIHZsM7l4s5gAQuUAzRUoT51hnH3EWofXf2vkD5HJJ33vwE%2FaEWp36GHr6GpMaH4AAPuqM5eabH%2FhfG9zcCz4nN6cPinuAw6IHwtvyB%2FdO1toZciBaPh25U0ducR2PI3Zl7mokyLWKkSnEDOg1x5fCsJE9EKhH7HwFNhWMGMS7%2BqxyYsbHHRUDUH4I%2FAheQY7wujJNnFUH4KdCju83riuQeHU9WEqNzjsJFuF%2FdTDAZ%2FK7%2F1WaAU%2BAWymT59pVMT4g2AxcwNa0XEBDdBDpAPvgDIH73R25teeuAF5ime2Ul0OUIiG4GpSAEJeYW9wDTf43wfwHgHLKJoPznkwAAAABJRU5ErkJggg%3D%3D)](http://dx.doi.org/10.6084/m9.figshare.19466246)

LIBRA - Machine Translation between paired <img src="https://github.com/TranslationalBioinformaticsUnit/LIBRA/blob/main/gaf/figures/LIBRA_icon_2.png?raw=true" width="181px" align="right" />  
Single-Cell Multi-Omics Data 
===========
This repository contains the [LIBRA code](https://github.com/TranslationalBioinformaticsUnit/LIBRA/blob/main/code_snapshots/) and [online data](#datasets) used for Single-cell multi-omics integration and prediction analysis employed on [LIBRA manuscript](https://www.biorxiv.org/content/10.1101/2021.01.27.428400v2). [Libra metrics](https://github.com/TranslationalBioinformaticsUnit/LIBRA/blob/main/code_snapshots/R/LIBRA_code/) are also available for quantifying outputs quality as well as novel PPJI preservation measurement. [Seurat code](https://github.com/TranslationalBioinformaticsUnit/LIBRA/blob/main/code_snapshots/R/Seurat_code/) employed to analyze LIBRA input omics as well as for clustering and visualization pipelines are providen. 

The Python package [sc-Libra](https://pypi.org/project/sc-libra/), has been developed with the aim of extending and summarizing the developer code used on the paper to a user-friendly version and is freely available in the PyPI repository. Read online package [documentation](https://sc-libra.readthedocs.io/en/latest/) for detailled description and guidelines.

- [Summary](#summary)
- [Installation](#installation)
- [Datasets](#datasets)
- [Usage](#usage)
- [Material of interest](#material-of-interest)

# Summary
LIBRA is a deep learning model that is designed for Single-cell multi-omics integration and prediction. LIBRA performs this by using an unbalance Autoencoder which learns a shared low-dimensional embedding from both experiment omics, combining each sample's uniqueness for generating a enriched representation of integrated data respect to the original experiment independent data. This tool has been first developed in [R code](https://github.com/TranslationalBioinformaticsUnit/LIBRA/blob/main/code_snapshots/R/LIBRA_code/), a code snapshot is providen for R users. Next, adaptative LIBRA (aLIBRA) tool has been develop for paralellize training of LIBRA models using a grid structure for selecting optimal hyperparameters in a automatic way excluding the requirement of doing this by users saving considerable time. Snapshot code is providen in [Python code](https://github.com/TranslationalBioinformaticsUnit/LIBRA/blob/main/code_snapshots/Python/LIBRA_fine_tune_code/) for conceptual understanding.

As a result from these raw developer-codes provided, [sc-Libra](https://pypi.org/project/sc-libra/) package is provided as a built-in resource to perform the pipeline propossed.

For further details, please refer to the [online manuscript](https://www.biorxiv.org/content/10.1101/2021.01.27.428400v2) currently at biorxiv repository (will be updated asap).

# Installation
 
To run sc-Libra pipeline the following settings are required:
- Install Python **>=3.7.0**.
- Install R **>=3.5.2**.
- Install sc-libra python package:
      ```
      $ pip install sc_libra
      ```

For stepwise guide follow the online [documentation](https://sc-libra.readthedocs.io/en/latest/).

# Datasets  
Find [Neurips](https://openproblems.bio/neurips_2021/) provided dataset for LIBRA testing at figsahre repository to be downloaded [here](https://figshare.com/s/d7ad0c6b8285e75de40f). 

Following datasets consist only on the sparse versions without cell/feature identity, go to corresponding autor references for original datasets.
| LIBRA name | GSE link | Modalities | Technology | Genomic ref used | Download sparse matrix |
|    :---:    |    :---:    |    :---:    |    :---:    |    :---:    |    :---:    |
| DataSet1 | [GSE126074](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE126074) | scRNAseq + scATACseq | SNARE-seq | [Mus_musculus.GRCm38 Ver: 3.0.0](https://support.10xgenomics.com/single-cell-gene-expression/software/release-notes/build#) | [RNA](https://figshare.com/s/c9b87f4ac1d1c030e128) and [ATAC](https://figshare.com/s/9ff9ea93a2108478bb36) |
| DataSet2 | [GSE128639](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi) | scRNAseq + scADT | CITE-seq | [Homo_sapiens.GRCh38 Ver: 3.0.0](https://support.10xgenomics.com/single-cell-gene-expression/software/release-notes/build#) | [RNA](https://figshare.com/s/5f5cfa6fda4ae3512c0d) and [ADT](https://figshare.com/s/5e34cd80455398855ad8) |
| DataSet3 | [GSE130399](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi) | scRNAseq + scATACseq | Paired-seq | [Mus_musculus.GRCm38 Ver: 3.0.0](https://support.10xgenomics.com/single-cell-gene-expression/software/release-notes/build#) | [RNA](https://figshare.com/s/a1f4a5ef0735d1b4167d) and [ATAC](https://figshare.com/s/80d9b9d84ada526668a6) |
| DataSet4 | [GSE140203](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi) | scRNAseq + scATACseq | SHARE-seq | [Mus_musculus.GRCm38 Ver: 3.0.0](https://support.10xgenomics.com/single-cell-gene-expression/software/release-notes/build#) | [RNA](https://figshare.com/s/71312a335649b04972b8) and [ATAC](https://figshare.com/s/0b581450cd6e1f8fb64c) |
| DataSet5 | [10X Genomics](https://support.10xgenomics.com/single-cell-multiome-atac-gex/datasets/1.0.0/pbmc_granulocyte_sorted_10k) | scRNAseq + scATACseq | 10X multiome | [Homo_sapiens.GRCh38 Ver: 3.0.0](https://support.10xgenomics.com/single-cell-gene-expression/software/release-notes/build#) | [RNA](https://figshare.com/s/90b237227f0cc07d075d) and [ATAC](https://figshare.com/s/4086bce6032f6a206a13) |
| DataSet6 | [GSE194122](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi) | scRNAseq + scATACseq | 10X multiome | [Homo_sapiens.GRCh38 Ver: 3.0.0](https://support.10xgenomics.com/single-cell-gene-expression/software/release-notes/build#) | [RNA](https://figshare.com/s/134562c3ec74a3a50c84) and [ATAC](https://figshare.com/s/378a630ec9c6ddadf4f5) |
| DataSet7 | [GSE194122](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi) | scRNAseq + scADT | CITE-seq | [Homo_sapiens.GRCh38 Ver: 3.0.0](https://support.10xgenomics.com/single-cell-gene-expression/software/release-notes/build#) | [RNA](https://figshare.com/s/41bdbfe7479e9729c800) and [ADT](https://figshare.com/s/975cd8a5bbc57c8d2c8c) |
| DataSet8 | [GSE109262](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi) | scRNAseq + scATACseq | scNMT-seq | [Mus_musculus.GRCm38 Ver: 3.0.0](https://support.10xgenomics.com/single-cell-gene-expression/software/release-notes/build#) | [RNA](https://figshare.com/s/4a158e6d243bcd45a171) and [ATAC](https://figshare.com/s/f13136b52f3b387d1a66) |

# Usage

- Easiest way of running LIBRA analysis is though [sc-Libra](https://pypi.org/project/sc-libra/) python package. 
- Package [documentation](https://sc-libra.readthedocs.io/en/latest/) is online available using "Read the Docs" platform.

# Material of interest

### LIBRA benchmarking comparison:
For validating LIBRA performance we compared it against other:

- Integration performance compared to - published/available: [BABEL](https://github.com/wukevin/babel).

- Prediction performance compared to - published/available: [Seurat3](https://satijalab.org/seurat/articles/integration_mapping.html), [Seurat4](https://github.com/satijalab/seurat), [MOFA+](https://biofam.github.io/MOFA2/index.html), [totalVI](https://github.com/YosefLab/scvi-tools), [BABEL](https://github.com/wukevin/babel), [multiVI](https://github.com/scverse/scvi-tutorials/blob/master/MultiVI_tutorial.ipynb) and [multigrate](https://github.com/theislab/multigrate).

**Further details are provided at supplementary material added at [LIBRA manuscript](https://www.biorxiv.org/content/10.1101/2021.01.27.428400v1).**

### LIBRA visual workflow:
![workflow.png](https://github.com/TranslationalBioinformaticsUnit/LIBRA/blob/main/gaf/figures/how_to.png?raw=true)
