Skip to content
develop
Switch branches/tags
Code

Latest commit

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Bio Embeddings

Resources to learn about bio_embeddings:

Project aims:

  • Facilitate the use of language model based biological sequence representations for transfer-learning by providing a single, consistent interface and close-to-zero-friction
  • Reproducible workflows
  • Depth of representation (different models from different labs trained on different dataset for different purposes)
  • Extensive examples, handle complexity for users (e.g. CUDA OOM abstraction) and well documented warnings and error messages.

The project includes:

  • General purpose python embedders based on open models trained on biological sequence representations (SeqVec, ProtTrans, UniRep,...)
  • A pipeline which:
    • embeds sequences into matrix-representations (per-amino-acid) or vector-representations (per-sequence) that can be used to train learning models or for analytical purposes
    • projects per-sequence embedidngs into lower dimensional representations using UMAP or t-SNE (for lightwieght data handling and visualizations)
    • visualizes low dimensional sets of per-sequence embeddings onto 2D and 3D interactive plots (with and without annotations)
    • extracts annotations from per-sequence and per-amino-acid embeddings using supervised (when available) and unsupervised approaches (e.g. by network analysis)
  • A webserver that wraps the pipeline into a distributed API for scalable and consistent workfolws

Installation

You can install bio_embeddings via pip or use it via docker. Mind the additional dependencies for align.

Pip

Install the pipeline like so:

pip install bio-embeddings[all]

To install the unstable version, please install the pipeline like so:

pip install -U "bio-embeddings[all] @ git+https://github.com/sacdallago/bio_embeddings.git"

Docker

We provide a docker image at ghcr.io/bioembeddings/bio_embeddings. Simple usage example:

docker run --rm --gpus all \
    -v "$(pwd)/examples/docker":/mnt \
    -v bio_embeddings_weights_cache:/root/.cache/bio_embeddings \
    -u $(id -u ${USER}):$(id -g ${USER}) \
    ghcr.io/bioembeddings/bio_embeddings:v0.1.6 /mnt/config.yml

See the docker example in the examples folder for instructions. You can also use ghcr.io/bioembeddings/bio_embeddings:latest which is built from the latest commit.

Dependencies

To use the mmseqs_search protocol, or the mmsesq2 functions in align, you additionally need to have mmseqs2 in your path.

Installation notes

bio_embeddings was developed for unix machines with GPU capabilities and CUDA installed. If your setup diverges from this, you may encounter some inconsistencies (e.g. speed is significantly affected by the absence of a GPU and CUDA). For Windows users, we strongly recommend the use of Windows Subsystem for Linux.

What model is right for you?

Each models has its strengths and weaknesses (speed, specificity, memory footprint...). There isn't a "one-fits-all" and we encourage you to at least try two different models when attempting a new exploratory project.

The models prottrans_bert_bfd, prottrans_albert_bfd, seqvec and prottrans_xlnet_uniref100 were all trained with the goal of systematic predictions. From this pool, we believe the optimal model to be prottrans_bert_bfd, followed by seqvec, which has been established for longer and uses a different principle (LSTM vs Transformer).

Usage and examples

We highly recommend you to check out the examples folder for pipeline examples, and the notebooks folder for post-processing pipeline runs and general purpose use of the embedders.

After having installed the package, you can:

  1. Use the pipeline like:

    bio_embeddings config.yml

    A blueprint of the configuration file, and an example setup can be found in the examples directory of this repository.

  2. Use the general purpose embedder objects via python, e.g.:

    from bio_embeddings.embed import SeqVecEmbedder
    
    embedder = SeqVecEmbedder()
    
    embedding = embedder.embed("SEQVENCE")

    More examples can be found in the notebooks folder of this repository.

Cite

If you use bio_embeddings for your research, we would appreciate it if you could cite the following paper:

Dallago, C., Schütze, K., Heinzinger, M., Olenyi, T., Littmann, M., Lu, A. X., Yang, K. K., Min, S., Yoon, S., Morton, J. T., & Rost, B. (2021). Learned embeddings from deep learning to visualize and predict protein sets. Current Protocols, 1, e113. doi: 10.1002/cpz1.113

The corresponding bibtex:

@article{https://doi.org/10.1002/cpz1.113,
author = {Dallago, Christian and Schütze, Konstantin and Heinzinger, Michael and Olenyi, Tobias and Littmann, Maria and Lu, Amy X. and Yang, Kevin K. and Min, Seonwoo and Yoon, Sungroh and Morton, James T. and Rost, Burkhard},
title = {Learned Embeddings from Deep Learning to Visualize and Predict Protein Sets},
journal = {Current Protocols},
volume = {1},
number = {5},
pages = {e113},
keywords = {deep learning embeddings, machine learning, protein annotation pipeline, protein representations, protein visualization},
doi = {https://doi.org/10.1002/cpz1.113},
url = {https://currentprotocols.onlinelibrary.wiley.com/doi/abs/10.1002/cpz1.113},
eprint = {https://currentprotocols.onlinelibrary.wiley.com/doi/pdf/10.1002/cpz1.113},
year = {2021}
}

Additionally, we invite you to cite the work from others that was collected in `bio_embeddings` (see section _"Tools by category"_ below). We are working on an enhanced user guide which will include proper references to all citable work collected in `bio_embeddings`.

Contributors

  • Christian Dallago (lead)
  • Konstantin Schütze
  • Tobias Olenyi
  • Michael Heinzinger

Want to add your own model? See contributing for instructions.

Non-exhaustive list of tools available (see following section for more details):

Datasets

  • prottrans_t5_xl_u50 residue and sequence embeddings of the Human proteome at full precision + secondary structure predictions + sub-cellular localisation predictions: DOI

Tools by category

Pipeline
General purpose embedders