TRILL: Orchestrating Modular Deep-Learning Workflows for Democratized, Scalable Protein Analysis and Engineering

Abstract

Deep-learning models have been rapidly adopted by many fields, partly due to the deluge of data humanity has amassed. In particular, the petabases of biological sequencing data enable the unsupervised training of protein language models that learn the "language of life." However, due to their prohibitive size and complexity, contemporary deep-learning models are often unwieldy, especially for scientists with limited machine learning backgrounds. TRILL (TRaining and Inference using the Language of Life) is a platform for creative protein design and discovery. Leveraging several state-of-the-art models such as ESM-2, DiffDock, and RFDiffusion, TRILL allows researchers to generate novel proteins, predict 3-D structures, extract high-dimensional representations of proteins, functionally classify proteins and more. What sets TRILL apart is its ability to enable complex pipelines by chaining together models and effectively merging the capabilities of different models to achieve a sum greater than its individual parts. Whether using Google Colab with one GPU or a supercomputer with hundreds, TRILL allows scientists to effectively utilize models with millions to billions of parameters by using optimized training strategies such as ZeRO-Offload and distributed data parallel. Therefore, TRILL not only bridges the gap between complex deep-learning models and their practical application in the field of biology, but also simplifies the orchestration of these models into comprehensive workflows, democratizing access to powerful methods. Documentation: https://trill.readthedocs.io/en/latest/home.html.

Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering

“…LLMs could power these automated systems, with AI flexibly adapting to perform new types of syntheses and screens with robotic scripts written on the fly. − At the same time, multiple desirable properties and activity for multiple reactions could be optimized simultaneously during protein engineering campaigns, powered by generalized ML models that can utilize multimodal representations of proteins. With ever increasing amounts of data on protein structures and sequence-fitness pairs, and new tools to conduct experiments − and make ML methods for proteins more accessible to the broader community, the future of ML-assisted protein engineering is bright.…”

A Perspective on the Prospective Use of AI in Protein Structure Prediction

“…Other ideas correspond to tools that do not exist yet but could be developed in the near future, in particular given the release of the TRILL toolkit for interfacing existing tools, which in turn could facilitate the contribution of experimentalists: A meta-tool that combines all modeling programs in one pass, ranks them globally and suggests an ideal composite model. Although a jury method has been proposed for the prediction of protein–protein complexes, this is still a largely unexplored possibility. A predictor of post-translational modifications.…”