Kentaro Tomii

Prot-LAMBDA: Explicit Distance Learning Enhances Structural Reasoning in Protein Language Models

Prot-LAMBDA improves protein structure prediction by explicitly incorporating spatial relationships, achieving better performance than ESM2-3B in contact prediction and 3D structure prediction.

zsasa: a Zig-based engine for high-throughput solvent accessible surface area at proteome scale

zsasa calculates solvent accessible surface area at proteome scale with high throughput, low memory use, and exact or approximate modes.

The Gompertz curve for estimating growth rates of Protein Data Bank and protein folds

The paper fits the Gompertz curve to PDB growth data to estimate future PDB entries and protein folds, revealing a deceleration in growth.

PIKfyve inhibition induces LRRK2 activation through phosphatidylinositol 3-phosphate and CASM

This study shows that PIKfyve inhibition leads to LRRK2 hyperactivation through PI3P and CASM, revealing a new mechanism involving membrane lipids and Rab proteins.

A transphyletic study of metazoan β-catenin protein complexes

This study compares β-catenin sequences and function across nonbilaterian metazoans and Xenopus embryos, revealing conserved structural and functional properties of β-catenin complexes.

Neuronal and non-neuronal functions of the synaptic cell adhesion molecule, neurexin, in Nematostella vectensis.

This study investigates the functions of neurexins in the cnidarian Nematostella vectensis, revealing both neuronal and non-neuronal roles in synaptic and cell adhesion processes.

Meta-Align: A Novel HMM-based Algorithm for Pairwise Alignment of Error-Prone Sequencing Reads

Meta-Align improves DNA sequence alignment by incorporating quality scores and handling frameshift errors using an HMM-based approach, outperforming TBLASTX in simulated benchmarks.

Deep Neural Network for Protein Contact Prediction by Weighting Sequences in a Multiple Sequence Alignment

The paper introduces a deep neural network for protein contact prediction that directly uses multiple sequence alignments to extract correlation information and improve accuracy over traditional ECA methods.

Simple adjustment of the sequence weight algorithm remarkably enhances PSI-BLAST performance

The paper improves PSI-BLAST performance by adjusting sequence weight calculation to avoid narrow blocks, showing significant gains in benchmark tests.