VenusFactory: A Unified Platform for Protein Engineering Data Retrieval and Language Model Fine-Tuning
This work addresses data and application barriers for researchers in protein engineering and computer science, though it is incremental as it builds on existing PLM methods.
The authors tackled the challenge of limited interdisciplinary adoption of protein language models (PLMs) in protein engineering by developing VenusFactory, a unified platform that integrates data retrieval, task benchmarking, and fine-tuning, resulting in support for over 40 datasets and 40 PLMs with open-source availability.
Natural language processing (NLP) has significantly influenced scientific domains beyond human language, including protein engineering, where pre-trained protein language models (PLMs) have demonstrated remarkable success. However, interdisciplinary adoption remains limited due to challenges in data collection, task benchmarking, and application. This work presents VenusFactory, a versatile engine that integrates biological data retrieval, standardized task benchmarking, and modular fine-tuning of PLMs. VenusFactory supports both computer science and biology communities with choices of both a command-line execution and a Gradio-based no-code interface, integrating $40+$ protein-related datasets and $40+$ popular PLMs. All implementations are open-sourced on https://github.com/tyang816/VenusFactory.