Tal Pupko

A deep-learning-based score to evaluate multiple sequence alignments

The paper develops deep-learning-based scores to assess MSA quality, showing they outperform the SP score in identifying accurate alignments and improving phylogenetic reconstruction.

Identification of protein secretion systems and type III effectors in wood-associated bacteria of the genus Xylophilus

The paper identifies type III secretion systems and effectors in Xylophilus bacteria, revealing differences between plant pathogens and non-host isolates.

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.

The role of plant polyploidy in the structure of plant-pollinator communities

The paper examines how polyploidy affects plant-pollinator community structure by analyzing network metrics and mediating factors.

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.

Evolutionary Insights from the Mitochondrial Genome of Oikopleura dioica: Sequencing Challenges, RNA Editing, Gene Transfers to the Nucleus, and tRNA Loss

This study sequences and annotates the mitochondrial genome of Oikopleura dioica, revealing RNA editing, gene transfers to the nucleus, and tRNA losses, while highlighting sequencing challenges.

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.

Identification of selective sweeps in bacteria

The paper introduces SINCOPA, a phylogeny-based method for detecting locus-specific selective sweeps in bacterial strains, and applies it to over 500 microbial genomes to identify sweeps in genes related to biofilm formation and environmental adaptation.

The evolutionary dynamics that retain long neutral genomic sequences in face of indel deletion bias: a model and its application to human introns

The paper develops a model of indel dynamics incorporating border-induced selection and applies it to human intron length distribution to explain long neutral sequences.

A probabilistic model for indel evolution: differentiating insertions from deletions

This paper introduces a probabilistic model for indel evolution that distinguishes insertions from deletions, showing higher deletion rates and negative correlation with population size in empirical data.