Yonatan Belinkov

Phylogenetic tree inference using generative models

This paper introduces BetaInfer, a generative model for phylogenetic tree inference that maps unaligned sequences to trees, achieving competitive performance compared to traditional methods.

Ancestral sequence reconstruction using generative models

This paper introduces BetaReconstruct, a generative model for ancestral sequence reconstruction that outperforms traditional methods without requiring multiple sequence alignments or phylogenetic trees.

BetaAlign: a deep learning approach for multiple sequence alignment

BetaAlign uses deep learning to align biological sequences, achieving accuracy comparable to or better than existing tools.

Protein2Text: Providing Rich Descriptions for Protein Sequences

The paper introduces BetaDescribe, a model that generates rich textual descriptions of proteins, enhancing understanding of their functions and properties.

Effect of Tokenization on Transformers for Biological Sequences

This study evaluates how different tokenization methods affect transformer models' performance on various biological sequence tasks, showing improved accuracy and efficiency with optimized tokenizers.

OM2Seq: Learning retrieval embeddings for optical genome mapping

OM2Seq improves OGM data analysis by using a Transformer-encoder to rapidly and accurately map DNA fragments to a reference genome, outperforming existing methods in speed and accuracy.