2023/05/04 by David H. Brookes, Brookes, David H., Jakub Otwinowski +3 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #Evolution and Genetic Dynamics #Evolutionary Algorithms and Applications #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Metaheuristic Optimization Algorithms Research #Populations and Evolution (q-bio.PE)
paper · pdf · doi:10.48550/arxiv.2305.03136
openalex publication_date 2023/05/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Fitness functions map large combinatorial spaces of biological sequences to properties of interest. Inferring these multimodal functions from experimental data is a central task in modern protein engineering. Global epistasis models are an effective and physically-grounded class of models for estimating fitness functions from observed data. These models assume that a sparse latent function is transformed by a monotonic nonlinearity to emit measurable fitness. Here we demonstrate that minimizing supervised contrastive loss functions, such as the Bradley-Terry loss, is a simple and flexible technique for extracting the sparse latent function implied by global epistasis. We argue by way of a fitness-epistasis uncertainty principle that the nonlinearities in global epistasis models can produce observed fitness functions that do not admit sparse representations, and thus may be inefficient to learn from observations when using a Mean Squared Error (MSE) loss (a common practice). We show that contrastive losses are able to accurately estimate a ranking function from limited data even in regimes where MSE is ineffective and validate the practical utility of this insight by demonstrating that contrastive loss functions result in consistently improved performance on benchmark tasks.