Daniel Griffith

Metapredict enables accurate disorder prediction across the Tree of Life

Metapredict V3 predicts intrinsically disordered regions across 20,000 proteomes to assess disorder prevalence across life kingdoms.

High-throughput affinity measurements of direct interactions between activation domains and co-activators

This study quantifies direct interactions between 204 human activation domains and eight co-activators using a microfluidic platform, revealing 334 novel binding pairs and demonstrating the utility of analytical models for predicting activation.

The formation of a fuzzy complex in the negative arm regulates the robustness of the circadian clock.

The paper identifies a fuzzy complex formed by negative-arm proteins that regulates the robustness of the circadian clock through electrostatic interactions and conserved motifs.

Metapredict V2: An update to metapredict, a fast, accurate, and easy-to-use predictor of consensus disorder and structure

metapredict V2 claims better disorder-prediction accuracy than the legacy model, shipping as a web server, Python package and command-line tool, illustrated on human transcription factors.

PARROT: a flexible recurrent neural network framework for analysis of large protein datasets

PARROT is a deep learning framework for analyzing large protein datasets, capable of classification and regression tasks using only raw protein sequences.

metapredict: a fast, accurate, and easy-to-use predictor of consensus disorder and structure

The paper introduces metapredict, a deep-learning-based tool for fast and accurate prediction of consensus disorder and structure in proteins, outperforming existing methods and offering user-friendly access.