Aalt D. J. van Dijk

This study investigates when combining mechanistic and machine learning models improves predictions of gene regulatory network dynamics using synthetic data.

The paper develops an integrative single-cell and spatial transcriptomics atlas of Gerbera capitulum development, identifying candidate regulatory factors like GAGL12 involved in vasculature development.

The paper models glucosinolate biosynthesis dynamics in Arabidopsis under biotic stress using a mechanistic ODE model constrained by gene expression and metabolite data.

This study shows how a single bacterial enzyme, D4BMY8, influences the composition and metabolism of an infant gut microbial community through its preference for the HMO lacto-N-tetraose.

This study evaluates whether electrostatic representations improve variant effect prediction models using DMS data, but finds no advantage over evolutionary models.

BADDADAN models gene module dynamics under stress using machine learning and ODEs, demonstrating its application on A. thaliana datasets to recover known insights and propose new hypotheses.

The paper shows that structural features of enzymes influence the predictability of variant effects, with consistent dependencies across multiple models.

This study uses pollen sequencing to analyze recombination patterns in tomato hybrids, identifying coldspots and their association with transposable elements and gene complexes, and proposes strategies to overcome recombination barriers.

The paper introduces a fast structure aligner using rotation-invariant shape-mers for protein structures, enabling efficient machine learning analysis of functional and structural similarities.

The paper predicts precursor cation specificity in plant sesquiterpene synthases using machine learning and co-evolution analysis, identifying key residues for enzyme function.

Geometricus embeds protein structures into fixed-length vectors using shape-mers derived from 3D moment invariants, enabling tasks like structure similarity search and clustering.

CAPICE is a machine learning method that prioritizes pathogenic variants in exomes, outperforming existing tools for rare and ultra-rare variants.

The paper introduces PKSpop, a coevolution-based method to predict protein-protein interactions in PKS assembly lines, achieving 80% accuracy in predicting protein order.

The paper analyzes plant sesquiterpene synthases to identify motifs and unexplored sequence regions, and demonstrates a database application for guiding mutagenesis studies on product specificity.

The paper introduces Ouroboros, an algorithm that improves intermolecular contact prediction by reducing noise in protein-protein interaction analysis using coevolutionary analysis with expectation-maximization.