Biology subjects

Drake, Z. C.

Publications and source records attributed to Drake, Z. C..

4 recordsLinked to original sources

bioRxiv2026

Incorporating Surfaced-Induced Dissociation Mass Spectrometry Data into an AlphaFold-derived deep learning network improves protein structure prediction

Surface-Induced Dissociation native Mass Spectrometry (SID-nMS) is a tandem MS activation method that yields information on the connectivity and stoichiometry of protein complexes. While insufficient for direct structure elucidation, the data derived from SID-nMS has considerable potential to inform multimeric protein structure prediction. We hypothesized that incorporating this data into a machine-learning framework could improve multimer prediction accuracy beyond that of existing deep-learning methods. To this end, we developed SIDFold, a novel AlphaFold-based deep-learning network. SIDFold is the first AlphaFold-like network to leverage experimental data during protein complex prediction, and the first deep-learning network to utilize nMS data for structure prediction. We benchmarked SIDFold on the BETA protein set, and observed an improvement in RMSD in 138 of 227 cases including 27 targets in which the predicted structure attained near-native accuracy. We then evaluated the network on 20 proteins with experimental SID-nMS data, yielding an improved RMSD in 18 cases, with five of these cases improving to a high-accuracy complex. Finally, we tested SIDFold against a previously published SID-guided Rosetta docking method, where we saw improvement in 13 of 16 proteins. SIDFold is freely available on GitHub, with example files and commands available in the Supplementary Information.

biochemistry↗

bioRxiv2026

Ion Mobility Mass Spectrometry Guided Modeling with AlphaFold and Rosetta Improves Protein Complex Structure Prediction

Ion mobility mass spectrometry (IM-MS) provides valuable structural information about protein shape and size through collision cross section (CCS). However, it lacks atomic level structural detail. While AlphaFold has been successful in predicting monomeric protein structure, it can struggle with modeling protein complexes. To address these limitations, we developed a method that integrates IM-MS data with AlphaFold and Rosetta to improve complex structure prediction. Our approach uses experimental CCS data to guide the assembly of AlphaFold predicted subunits using a Rosetta docking pipeline and evaluating the resulting complexes with a newly developed score. Using this strategy, we were able to improve root mean square deviation (RMSD) values for 26 of 38 (68%) complexes compared to AlphaFold-Multimer. Furthermore, 16 of these systems improved significantly from greater than 4 [A] RMSD to less than 4 [A]. This method demonstrates a robust approach to overcome limitations in complex assembly modeling. Table of Contents Graphic O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=182 SRC="FIGDIR/small/706193v1_ufig1.gif" ALT="Figure 1"> View larger version (68K): org.highwire.dtl.DTLVardef@cf71c3org.highwire.dtl.DTLVardef@135e09aorg.highwire.dtl.DTLVardef@2cc2fcorg.highwire.dtl.DTLVardef@b53feb_HPS_FORMAT_FIGEXP M_FIG In this integrative modeling work, protein complex structures were modeled by combining AlphaFold predicted subunits with Rosetta docking. Collision cross section data from ion-mobility mass spectrometry were used as evaluation constraints and docked models were scored using the IM-complex score. The best scoring models generally represent accurate protein complex structures. C_FIG

biophysics↗

bioRxiv2024

Deep-Learning Structure Elucidation from Single-Mutant Deep Mutational Scanning

Deep learning has revolutionized the field of protein structure prediction. AlphaFold2, a deep neural network, vastly outperformed previous algorithms to provide near atomic-level accuracy when predicting protein structures. Despite its success, there still are limitations which prevent accurate predictions for numerous protein systems. Here we show that sparse residue burial restraints from deep mutational scanning (DMS) can refine AlphaFold2 to significantly enhance results. Burial information extracted from DMS is used to explicitly guide residue placement during structure generation. DMS-Fold was validated on both simulated and experimental single-mutant DMS, with DMS-Fold outperforming AlphaFold2 for 89% of protein targets and with 253 proteins having an improvement greater than 0.1 in TM-score. DMS-Fold is free and publicly available: https://github.com/LindertLab/DMS-Fold.

biochemistry↗

bioRxiv2022

Protein complex prediction using Rosetta, AlphaFold, and mass spectrometry covalent labeling

Structural mass spectrometry offers several techniques for the characterization of protein structures. Covalent labeling (CL) in combination with mass spectrometry can be used as an analytical tool to study and determine structural properties of protein-protein complexes. Degrees of modification obtained from CL experiments for specific labeled residues can be compared between the unbound and bound states of complexes. This analysis can yield insights into structural features of these protein assemblies, specifically the proximity of specific residues to the protein-protein interface. However, this data is sparse and does not unambiguously elucidate protein structure. Thus, computational algorithms are needed to deduce structure from the CL data. In this work we present a novel hybrid method that combines models of protein complex subunits generated with AlphaFold with differential CL data via a CL-guided protein-protein docking in Rosetta. In a benchmark set, the RMSD (root-mean-square deviation) of the best-scoring models was below 3.6 [A] for 5/5 complexes with inclusion of CL data, whereas the same quality was only achieved for 1/5 complexes without CL data. The average improvement in RMSD observed upon inclusion of CL data was 5.2 [A]. This study suggests that our integrated approach can successfully use data obtained from CL experiments to distinguish between nativelike and non-nativelike models. Significance StatementStructural mass spectrometry can be a powerful and versatile approach to characterize the structure of protein complexes. Data obtained from covalent labeling mass spectrometry can provide insights into higher order protein structure (particularly with respect to residue interactions and solvent accessibility) but needs to be supplemented by computational techniques to elucidate accurate, atomic-detail structural information. Here, we present a method to combine bioanalytical data obtained from covalent labeling with models generated using AlphaFold to accurately predict protein-protein complexes in Rosetta. Differential covalent labeling data can be used to determine the proximity of residues to the binding interface of complexes which we utilized to analyze computational models and improve structure prediction algorithms.

biophysics↗