2020/12/25 by Amy X. Lu, Lu, Amy X., Alex X. Lu +3 · 2 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Biomolecules (q-bio.BM) #Blind Source Separation Techniques #Domain Adaptation and Few-Shot Learning #FOS: Biological sciences #FOS: Computer and information sciences #Genomics and Phylogenetic Studies #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.2012.13475
openalex publication_date 2020/12/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Self-supervised representation learning of biological sequence embeddings alleviates computational resource constraints on downstream tasks while circumventing expensive experimental label acquisition. However, existing methods mostly borrow directly from large language models designed for NLP, rather than with bioinformatics philosophies in mind. Recently, contrastive mutual information maximization methods have achieved state-of-the-art representations for ImageNet. In this perspective piece, we discuss how viewing evolution as natural sequence augmentation and maximizing information across phylogenetic "noisy channels" is a biologically and theoretically desirable objective for pretraining encoders. We first provide a review of current contrastive learning literature, then provide an illustrative example where we show that contrastive learning using evolutionary augmentation can be used as a representation learning objective which maximizes the mutual information between biological sequences and their conserved function, and finally outline rationale for this approach.