FLOP: Tasks for Fitness Landscapes Of Protein wildtypes
Preprint
Abstract
Protein engineering has the potential to create optimized protein variants with improved properties and function. An initial step in the protein optimization process typically consists of a search among natural (wildtype) sequences to find the naturally occurring proteins with the most desirable properties. Promising candidates from this initial discovery phase then form the basis of the second step: a more local optimization procedure, exploring the space of variants separated from this candidate by a number of mutations. While considerable progress has been made on evaluating machine learning methods on single protein datasets, benchmarks of data-driven approaches for global fitness landscape exploration are still lacking. In this paper, we have carefully curated a representative benchmark dataset, which reflects industrially relevant scenarios for the initial wildtype discovery phase of protein engineering. We focus on exploration within a protein family, and investigate the downstream predictive power of various protein representation paradigms, i.e., protein language model-based representations, structure-based representations, and evolution-based representations. Our benchmark highlights the importance of coherent split strategies, and how we can be misled into overly optimistic estimates of the state of the field. The codebase and data can be accessed via https://github.com/petergroth/FLOP .Keywords
This publication has 45 references indexed in Scilit:
- Strategies for the discovery and engineering of enzymes for biocatalysisCurrent Opinion in Chemical Biology, 2013
- COMPUTATIONAL APPROACHES FOR RATIONAL DESIGN OF PROTEINS WITH NOVEL FUNCTIONALITIESComputational and Structural Biotechnology Journal, 2012
- SKEMPI: a Structural Kinetic and Energetic database of Mutant Protein Interactions and its use in empirical modelsBioinformatics, 2012
- A practical guide to modelling enzyme-catalysed reactionsChemical Society Reviews, 2012
- Protein 3D Structure Computed from Evolutionary Sequence VariationPLOS ONE, 2011
- Direct-coupling analysis of residue coevolution captures native contacts across many protein familiesProceedings of the National Academy of Sciences, 2011
- The Pel Polysaccharide Can Serve a Structural and Protective Role in the Biofilm Matrix of Pseudomonas aeruginosaPLOS Pathogens, 2011
- FastTree: Computing Large Minimum Evolution Trees with Profiles instead of a Distance MatrixMolecular Biology and Evolution, 2009
- A decade of CASP: progress, bottlenecks and prognosis in protein structure predictionCurrent Opinion in Structural Biology, 2005
- Predicting functions from protein sequences—where are the bottlenecks?Nature Genetics, 1998