Barbara R. Terlouw

Systematic engineering and machine learning analysis of intrinsic terminators reveal crucial nucleotides directly upstream of the terminator hairpin.

The paper systematically engineers and analyzes intrinsic terminators in bacteria, finding that an adenosine upstream of the terminator hairpin improves protein production and reduces read-through.

RetroMol: Parsing a shared encoding from natural products and their biosynthetic gene clusters

RetroMol converts natural product structures and biosynthetic gene clusters into shared primary sequences to enable biosynthetic similarity comparisons.

PARAS: high-accuracy machine-learning of substrate specificities in nonribosomal peptide synthetases

Random forest predictors PARAS and PARASECT, trained on 3,653 curated adenylation domains, outperform earlier NRPS substrate predictors and correctly assigned L-Trp to an unusual tryptopeptin synthetase domain.

Revealing determinants of translation efficiency via whole-gene codon randomisation and machine learning

This study uses codon randomisation and machine learning to show that the first 8 codons of a gene strongly predict protein production levels in E. coli.