Woodard, J. C. | bioRxiv Science

bioRxiv2024

Rapid prediction of thermodynamically destabilizing tyrosine phosphorylations in cancers

Tyrosine phosphorylations are a prominent characteristic of numerous cancers, necessitating the use of computational tools to comprehensively analyze phosphoproteomes and identify potentially (dys)functional phosphorylations. Here we propose a machine learning-based method to predict the thermodynamic stability change resulting from tyrosine phosphorylation. Our approach, based on prediction of phosphomimetic delta-delta-G from structural features, strongly correlates with experimental mutational scanning cDNA proteolysis data (R = 0.71). We predicted the destabilizing effects of all 384,857 tyrosine residues from the Alphafold2 database. We then applied our approach to a pan-cancer phosphoproteomics dataset, comprising over 600 unique tyrosine phosphorylations across 11 cancer subtypes. We predict destabilizing phosphorylations in both oncogenes and tumor suppressors, where the former likely reflects a generalized relief of auto-inhibition or activating conformational change. We find that the number of circuit topological parallel relations with respect to residues contacting the phosphorylated site is greater for autoinhibited oncogenes than for other proteins (Wilcoxon p = 0.03). Utilizing an extreme gradient-boosting machine learning approach, we obtain an AUC of 0.85 for the prediction of autoinhibited phosphorylation states from circuit topological features. The top destabilized proteins from the pan-cancer data are enriched for chemical and oxidative stress pathways. Among metabolic proteins, highly destabilizing phosphorylations tend to occur in more peripheral proteins with lower network centrality measures (Wilcoxon p = 0.005). We predict 58% of recurrent tyrosine cancer phosphorylations to be destabilizing at the 1 kcal/mol threshold. Our approach can enable rapid screening of destabilizing phosphorylations and phosphomimetic mutations.

systems biology↗

bioRxiv2021

Protein structural features predict responsiveness to pharmacological chaperone treatment for three lysosomal storage disorders

Three-dimensional structures of proteins can provide important clues into the efficacy of personalized treatment. We perform a structural analysis of variants within three inherited lysosomal storage disorders, comparing variants responsive to pharmacological chaperone treatment to those unresponsive to such treatment. We find that predicted {Delta}{Delta}G of mutation is higher on average for variants unresponsive to treatment, in the case of datasets for both Fabry disease and Pompe disease, in line with previous findings. Using both a single decision tree and an advanced machine learning approach based on the larger Fabry dataset, we correctly predict responsiveness of three Gaucher disease variants, and we provide predictions for untested variants. Many variants are predicted to be responsive to treatment, suggesting that drug-based treatments may be effective for a number of variants in Gaucher disease. In our analysis, we observe dependence on a topological feature reporting on contact arrangements which is likely connected to the order of folding of protein residues, and we provide a potential justification for this observation based on steady-state cellular kinetics. Author summaryPharmacological chaperones are small molecule drugs that bind to proteins to help stabilize the folded state. One set of diseases for which this treatment has been effective is the lysosomal storage disorders, which are caused by defective lysosomal enzymes. However, not all genotypes are equally responsive to treatment. For instance, missense mutants that are particularly destabilized relative to WT are less likely to respond. The availability of datasets containing responsiveness data for large numbers of mutants, along with crystal structures of the protein involved in each disease, make machine learning methods incorporating sequence-based and structural data feasible. We hypothesize that data from two diseases, Fabry and Pompe disease, may be useful for predicting responsiveness of variants in the related Gaucher disease. Results suggest that many rare variants in Gaucher disease could be amenable to existing drugs. Results suggest that drug responsiveness depends on protein topology is such a way that mutations in early-to-fold residues are more likely to be non-responsive to pharmacological chaperone treatment, which is consistent with a simple kinetic model of stability rescue. This study provides an example of how machine learning can be used to inform further studies towards personalized treatment in medicine.

biophysics↗