Skip to main content

Interpretable Modeling of RNA–Protein Interactions from eCLIP-Seq Profiles for Motif-Free RBPs

Project description

NoMoCLIP

Interpretable Modeling of RNA–Protein Interactions from eCLIP‑Seq Profiles for Motif‑Free RBPs

1. Data availability

NoMoCLIP_dataset

2. Environment Setup

2.1 Create and activate a new virtual environment

conda create -n NoMoCLIP python=3.7.16 
conda activate NoMoCLIP

2.2 Install the package and other requirements

pip install NoMoCLIP
nomoclip install

3. Process data

3.1 Sequential encoding

nomoclip run position_inf  --set_path <PATH_TO_YOUR_DATA>  --out_path <PATH_TO_YOUR_OUTPUT_DIRECTORY>

3.2 Structural encoding

This feature requires the RNAplfold tool, which is executed in a Python 2.7 environment. Please set the --env parameter to the local RNAplfold environment.

nomoclip run structure_inf  --env <NAME_OF_YOUR_ENV>  --set_path <PATH_TO_YOUR_DATA>  --out_path <PATH_TO_YOUR_OUTPUT_DIRECTORY>

3.3 Semantic encoding

nomoclip run attention_graph \
  --kmer 1 \
  --set_path <PATH_TO_YOUR_DATA> \
  --out_path <PATH_TO_YOUR_OUTPUT_DIRECTORY> \
  --model_type <PATH_TO_YOUR_NLP_MODEL> \ 
  --maxlen 101 \
  --device cuda:1 \
  --device1 cuda:1 \
  --device2 cuda:1 

3.4 Functional properties

For this feature, you need to use the corain. Please set the --env parameter to the local corain environment.

nomoclip run instinct_inf \
  --env <NAME_OF_YOUR_ENV> \
  --base_path <PATH_TO_YOUR_DATA> \
  --set_path <PATH_TO_YOUR_INTERMEDIATE_OUTPUT_DIRECTORY> \
  --out_path <PATH_TO_YOUR_OUTPUT_DIRECTORY> \
  --method_path <PATH_TO_YOUR_CORAIN_DIRECTORY> \ 
  --num 2

Note: The argument --num should be tested with all values in [2, 3, 5, 7, 10].

4. Training Process

nomoclip run model_train \
  --base_path <PATH_TO_YOUR_DATA_DIRECTORY> \
  --set_path <PATH_TO_YOUR_FEATURE_DIRECTORY> \
  --out_path <PATH_TO_YOUR_OUTPUT_DIRECTORY> \
  --fold 5  \
  --gpu_id 1

5. Prediction

nomoclip run model_predict \
  --set_path <PATH_TO_YOUR_FEATURE_DIRECTORY> \
  --out_path <PATH_TO_YOUR_OUTPUT_DIRECTORY> \
  --model_path <PATH_TO_YOUR_MODEL> \
  --gpu_id 1

🧬 Motif analysis

Motif extraction requires the installation of the MEME Suite package.

6.1 Sequential motifs

nomoclip run seq_motifs \
  --layer <THE_LAYER_OF_MODEL_YOU_SELECTED> \
  --set_path <PATH_TO_YOUR_FEATURE_DIRECTORY> \
  --out_path <PATH_TO_YOUR_OUTPUT_DIRECTORY> \
  --model_path <PATH_TO_YOUR_MODEL> \
  --pwm_path <PATH_TO_YOUR_PWM_FILE> \
  --motif_size 7 \
  --gpu_id 1

6.2 Structural motifs

nomoclip run structure_motifs \
  --layer <THE_LAYER_OF_MODEL_YOU_SELECTED> \
  --set_path <PATH_TO_YOUR_FEATURE_DIRECTORY> \
  --out_path <PATH_TO_YOUR_OUTPUT_DIRECTORY> \
  --model_path <PATH_TO_YOUR_MODEL> \
  --motif_size 7 \
  --gpu_id 1

📊 High attention regions

nomoclip run high_attention_region \
  --set_path <PATH_TO_YOUR_FEATURE_DIRECTORY> \
  --out_path <PATH_TO_YOUR_OUTPUT_DIRECTORY> \
  --model_path <PATH_TO_YOUR_MODEL> \
  --gpu_id 1

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

NoMoCLIP-1.0.0.tar.gz (29.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

NoMoCLIP-1.0.0-py3-none-any.whl (43.5 kB view details)

Uploaded Python 3

File details

Details for the file NoMoCLIP-1.0.0.tar.gz.

File metadata

  • Download URL: NoMoCLIP-1.0.0.tar.gz
  • Upload date:
  • Size: 29.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.7.16

File hashes

Hashes for NoMoCLIP-1.0.0.tar.gz
Algorithm Hash digest
SHA256 2bcba400077be5e5090d3a1059231c4874f200ec1d58c3ebe6f36dbd9cacae17
MD5 cf11d156dbf993fc79280f9bc9ad22cb
BLAKE2b-256 0405ee1a6c35b38b0f14e001968ac18f7d106ce4cd51a21ba916c54fd1d034bd

See more details on using hashes here.

File details

Details for the file NoMoCLIP-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: NoMoCLIP-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 43.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.7.16

File hashes

Hashes for NoMoCLIP-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ee7ad407f0d61740b970c92b21a8e05a0ee257e57376317526982bd77b043547
MD5 e98019538596ee60d518b9f0fa637a17
BLAKE2b-256 a69ada9d63ec3d2ea0736d711ac172d4522926f32528b2431bb6be22c9d2d15f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page