Timezone: »

Neural Distance Embeddings for Biological Sequences
Gabriele Corso · Rex Ying · Michal Pándy · Petar Veličković · Jure Leskovec · Pietro Liò

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @ None #None

The development of data-dependent heuristics and representations for biological sequences that reflect their evolutionary distance is critical for large-scale biological research. However, popular machine learning approaches, based on continuous Euclidean spaces, have struggled with the discrete combinatorial formulation of the edit distance that models evolution and the hierarchical relationship that characterises real-world datasets. We present Neural Distance Embeddings (NeuroSEED), a general framework to embed sequences in geometric vector spaces, and illustrate the effectiveness of the hyperbolic space that captures the hierarchical structure and provides an average 38% reduction in embedding RMSE against the best competing geometry. The capacity of the framework and the significance of these improvements are then demonstrated devising supervised and unsupervised NeuroSEED approaches to multiple core tasks in bioinformatics. Benchmarked with common baselines, the proposed approaches display significant accuracy and/or runtime improvements on real-world datasets. As an example for hierarchical clustering, the proposed pretrained and from-scratch methods match the quality of competing baselines with 30x and 15x runtime reduction, respectively.

Author Information

Gabriele Corso (University of Cambridge)
Rex Ying (Stanford University)
Michal Pándy (University of Cambridge)
Petar Veličković (DeepMind)
Jure Leskovec (Stanford University/Pinterest)
Pietro Liò (University of Cambridge)

More from the Same Authors