Biology subjects

Folkers, G. E.

Publications and source records attributed to Folkers, G. E..

2 recordsLinked to original sources

bioRxiv2026

Large-scale exploration of protein space by automated NMR

Protein structures can now be predicted and designed at scale, yet experimental access to dynamics and conformational heterogeneity remains limited in throughput. This gap prevents a systematic understanding of how protein sequences encode motion and functional flexibility. Here, we establish a scalable experimental pipeline combining protein design, automated production, and nuclear magnetic resonance (NMR) spectroscopy to enable high-throughput characterization of protein structure and dynamics at atomic resolution. A single operator can produce and analyze hundreds of isotopically labeled proteins per week, with per-sample cost largely defined by DNA synthesis. To benchmark this approach, we experimentally characterized 384 de novo designed proteins spanning diverse regions of structure space. High-quality two-dimensional NMR spectra were obtained for 239 samples (62% of designs overall). NMR characterization confirmed that the designed proteins adopt their intended folds, and revealed unexpected local dynamics that are not captured by current computational models. Our approach establishes a foundation for data-driven modelling of sequence-structure-dynamics relationships and unlocks a new regime of statistical structural biology, where insight into protein biophysics is gained from experimental ensemble studies of suitably designed protein clusters.

biophysics↗

bioRxiv2018

iSEE: Interface Structure, Evolution and Energy-based machine learning predictor of binding affinity changes upon mutations

Quantitative evaluation of binding affinity changes upon mutations is crucial for protein engineering and drug design. Machine learning-based methods are gaining increasing momentum in this field. Due to the limited number of experimental data, using a small number of sensitive predictive features is vital to the generalization and robustness of such machine learning methods. Here we introduce a fast and reliable predictor of binding affinity changes upon single point mutation, based on a random forest approach. Our method, iSEE, uses a limited number of interface Structure, Evolution and Energy-based features for the prediction. iSEE achieves, using only 31 features, a high prediction performance with a Pearson correlation coefficient (PCC) of 0.80 and a root mean square error of 1.41 kcal mol-1 on a diverse training dataset consisting of 1102 mutations in 57 protein-protein complexes. It competes with existing state-of-the-art methods on two blind test datasets. Predictions for a new dataset of 540 mutations in 58 protein complexes from the recently published SKEMPI 2.0 database reveals that none of the current methods perform well (PCC<0.4), although their combination does improve the predictions. Feature analysis for iSEE underlines the significance of evolutionary conservations for quantitative prediction of mutation effects.

bioinformatics↗