---
extra_gated_fields:
  Name: text
  Email: text
  Company: text
  Country: country
  Specific date: date_picker
  I want to use this model for:
    type: select
    options: 
      - Research
      - Education
      - label: Other
        value: other
  Would you be willing to share experimental data from model-derived peptides?:
    type: select
    options: 
      - Yes
      - No
extra_gated_prompt: "UbiquiTx License: https://drive.google.com/file/d/1XN6hOK67eis24EGeGc7Hpt6fBUUAtjV0/view?usp=sharing"
extra_gated_heading: Acknowledge license to access the repository
extra_gated_button_content: Acknowledge license

---

# PepPrCLIP
### *De Novo* Generation and Prioritization of Target-Binding Peptide Motifs from Sequence Alone 

To use this repository, you agree to abide by the UbiquiTx license: https://huggingface.co/ubiquitx/pepprclip/blob/main/PepPrCLIP%20Licence%20FINAL.pdf

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b844fa2c1e4bfd2aa9aa4a/X-ABJwktKcKhm8cAPV9zp.png)

Designing binders to target undruggable proteins presents a formidable challenge in drug discovery, requiring innovative approaches to overcome the lack of putative binding sites on pathogenic proteins. Recently, generative models have been trained to design binding proteins from the three-dimensional structure of a target protein alone, but thus exclude design to disordered or conformationally unstable targets. In this work, we provide a generalizable algorithmic framework to design short target-binding peptide motifs, requiring only the amino acid sequence of the target protein. To do this, we propose a process to generate naturalistic peptide candidates through Gaussian perturbation of the peptidic latent space of the state-of-the-art ESM-2 protein language model, and subsequently screen these *de novo* linear sequences for target-selective interaction activity via a CLIP-based contrastive learning architecture. By integrating these generative and discriminative steps, we create a unified **Pep**tide **Pr**ioritization via **CLIP** (**PepPrCLIP**) pipeline.

In this repository, you can find the datasets, model weights, and full code for PepPrCLIP. 

We have developed a user-friendly [Colab notebook](https://colab.research.google.com/drive/1ADeUuxXH2BJGI44VNMzPFBOd9DVQ8Ik8?usp=sharing) for peptide generation with PepPrCLIP! When you download the repository, copy this Colab notebook into the repository's main directory (which should be located at MyDrive/pepprclip) and follow the instructions to generate peptides. 

Authors: Suhaas Bhat, Kalyan Palepu, Sophia Vincoff and Pranam Chatterjee

Contact: info@ubiquitx.com