OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Tf Bind Transformer

Tf Bind Transformer is an MIT-licensed Python research repository for experimenting with transformer-based prediction of DNA–transcription factor binding. It provides an AdapterModel that uses Enformer and examples for training with protein embeddings and experimental context, including binary binding targets and BigWig track data.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Tf Bind Transformer — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want an adaptable research starting point for training binding-prediction experiments and can supply the model inputs, training targets and data files.

Who it is for

  • Computational biology researchers exploring transformer models for transcription-factor binding.
  • Developers building experiments that combine DNA sequence, transcription-factor protein representations and assay context.

Documented uses

  • Train an adapter model on DNA sequences, transcription-factor embeddings, contextual inputs and target values.
  • Configure a binary bind-or-not-bind prediction objective.
  • Prepare BigWig-based track training inputs using sequence, factor, annotation and track files.
  • Compare input representations, including ESM or ProtAlbert protein embeddings and free-text experimental context.
Before you choose

Requirements & limits

The code repository is public and lists an MIT license.

  • The README's examples move the model and tensors to CUDA.
  • The basic example uses Enformer with an AdapterModel and precomputed amino-acid and context embeddings.
  • ESM and ProtAlbert are shown as alternative transcription-factor embedding encoders; the README notes ProtAlbert's longer context length compared with ESM.
  • Free-text context requires enabling use_free_text_context; the README describes encoding it with a text transformer trained on PubMed abstracts.
  • The BigWig example expects multiple local data paths, including FASTA, BED, BigWig and annotation inputs.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the Python package and listed data dependencies

Set up the repository's Python package and install the two additional dependencies named in its README.

Before you start

  • A local copy of the repository and Python environment.
  • Conda, as used by the README for the additional packages.

Steps

  1. From the project root, run the command below.

    Documented command
    python setup.py install --user

  2. Install pybedtools and pyBigWig with conda install --channel conda-forge --channel bioconda pybedtools pyBigWig.

Expected outcome

The repository package and the two separately listed dependencies are installed according to the README's setup instructions.

Guide limitations

  • These steps cover installation only; they do not configure training data, Enformer or a working prediction run.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
lucidrains/tf-bind-transformer · Official homepage title · retained in its source language
How we review sourcesSuggest a correction