Code for processing FASTA files into batched, tokenized, and padded sequences, and training FlashAttention-based implementations of ESM-2
-
Updated
Apr 4, 2025 - Python
Code for processing FASTA files into batched, tokenized, and padded sequences, and training FlashAttention-based implementations of ESM-2
This paper has been published on Interdisciplinary Sciences: Computational Life Sciences.
🧬 EmbedDiff: A modular machine learning pipeline combining ESM2 embeddings, latent diffusion, and transformer-based decoding for de novo protein design
🧬 EmbedDiff: A modular machine learning pipeline combining ESM2 embeddings, latent diffusion, and transformer-based decoding for de novo protein design
ProteinFlex is a comprehensive platform for protein structure analysis and drug discovery, leveraging advanced AI and machine learning techniques. The platform combines state-of-the-art protein structure prediction with interactive visualization and sophisticated drug discovery tools.
Add a description, image, and links to the esm-2 topic page so that developers can more easily learn about it.
To associate your repository with the esm-2 topic, visit your repo's landing page and select "manage topics."