LINKER-Pred-Lite

A high-speed Disordered Flexible Linker (DFL) predictor trained on DLD domain Linker dataset and Disprot Database.

📝 Description

LINKER-Pred-Lite project belongs to a series of LINKER-Pred-Suite projects which focus on the Structure and Function prediction of Disordered Flexible Linkers (DFLs). Currently we have LINKER-Pred2 for fast DFL prediction and LINKER-Pred2 for more accurate DFL prediction. LINKER-Pred-Lite is trained on more than 2000 DFL linker datasets from our DLD dataset and Disprot, its performance is better than TOP predictors on the CAID2 Linker dataset. There is no MSA searching needed for the prediction. Therefore, compared to LINKER-Pred2, the prediction may be slightly worse, but it only cost ~0.1 second for one prediction.

🐣 Getting Started

Pre-requirements

This predictor requires sequences embedded with ProtTrans. Note,

• File format should be [SEQUENCE_NAME/ID].npy, replace SEQUENCE_NAME/ID with the actual sequence ID, it should be the same as the name from the .fasta file.
• Matrix shape:
  ProtTrans: (1, SEQUENCE_LENGTH, 1024)

📣‼️If you don't have them available, please visit the embedding section of our project first to embed the sequences.‼️

(We maintain this separation due to the requirements from CAID3, but we may edit or merge them in the future.)

Docker (Recommended)

Dependencies

• Go to embedding if you don't have ProtTrans embedded sequences;
• Docker Desktop 4.27.2 or higher;

Installing

• Pull the Docker image from DockerHub

  docker pull dimeng851/punch_linker_light:v2

Executing program

• RUN the following command:

  Replace
  CONTAINER_NAME - any name you like;
  PATH_TO_INPUT_FASTA - path to input file, which is ONE FASTA file including all query sequences;
  PATH_TO_PROTTRANS - a folder which includes all protTrans embedded sequences;
  PATH_OUTPUT - a folder which will be used to save all outputs, including: a. timings.csv; b. disorder folder, where we will keep all the prediction results.

  docker run -d \
  -it \
  --name [CONTAINER_NAME] \
  --mount type=bind,source=[PATH_TO_INPUT_FASTA],target=/punch_linker_light/data/input.fasta \
  --mount type=bind,source=[PATH_TO_PROTTRANS],target=/punch_linker_light/data/protTrans \
  --mount type=bind,source=[PATH_OUTPUT],target=/punch_linker_light/output \
  dimeng851/punch_linker_light:v2

  An example:

  docker run -d \
  -it \
  --name punch_linker_light_con \
  --mount type=bind,source=data/input.fasta,target=/punch_linker_light/data/input.fasta \
  --mount type=bind,source=data/protTrans,target=/punch_linker_light/data/protTrans \
  --mount type=bind,source=data/results,target=/punch_linker_light/output \
  dimeng851/punch_linker_light:v2

• Find the results in OUTPUT folder.

Contact & Help 📩

Email Di.

di.meng@ucdconnect.ie

Authors

📬 Di Meng - di.meng@ucdconnect.ie
📬 Juliana Glavina - jglavina@iib.unsam.edu.ar
📬 Gianluca Pollastri - gianluca.pollastri@ucd.ie
📬 Lucía Beatriz Chemes - lchemes@iib.unsam.edu.ar

Project

https://github.com/deemeng/punch_linker_light