Search for: All records

The link between p53 tumor suppressive functions and organismal lifespan is multifaceted. Its DNA-repair mechanism is longevity-enhancing while its role in cellular senescence pathways induces pro-aging phenotypes. To understand how p53 may regulate organismal lifespan, cross-species genotype-phenotype (GP) studies of the p53 DNA-binding domain (DBD) have been used to assess the correlation of amino acid changes to lifespan. Amino acid changes in non-DNA-binding regions such as the transactivation (TAD), proline-rich (PRD), regulatory (REG), and tetramerization (TET) are largely unexplored. In addition, existing GP correlation tools such as SigniSite do not account for phylogenetic relationships between aligned sequences in correlating genotypic differences to phenotypes such as lifespan. To identify phylogenetically significant, longevity-correlated residues in full-length p53 alignments, we developed a Python- and R-based workflow, Relative Evolutionary Scoring (RES). While RES-predicted longevity-associated residues (RPLARs) are concentrated primarily in the DBD, the PRD, TET, and REG domains also house RPLARs. While yeast functional assay enrichment reveals that RPLARs may be dispensable for p53-mediated transactivation, PEPPI and Rosetta-based protein-protein interaction prediction suggests a role for RPLARs in p53 stability and interaction interfaces of tumor suppressive protein-protein complexes. With experimental validation of the RPLARs’ roles in p53 stability, transactivation, and involvement in senescence-regulatory pathways, we can gain crucial insights into mechanisms underlying dysregulated tumor suppression and accelerated aging. 

Systematically discovering protein-ligand interactions across the entire human and pathogen genomes is critical in chemical genomics, protein function prediction, drug discovery, and many other areas. However, more than 90% of gene families remain “dark”—i.e., their small-molecule ligands are undiscovered due to experimental limitations or human/historical biases. Existing computational approaches typically fail when the dark protein differs from those with known ligands. To address this challenge, we have developed a deep learning framework, called PortalCG, which consists of four novel components: (i) a 3-dimensional ligand binding site enhanced sequence pre-training strategy to encode the evolutionary links between ligand-binding sites across gene families; (ii) an end-to-end pretraining-fine-tuning strategy to reduce the impact of inaccuracy of predicted structures on function predictions by recognizing the sequence-structure-function paradigm; (iii) a new out-of-cluster meta-learning algorithm that extracts and accumulates information learned from predicting ligands of distinct gene families (meta-data) and applies the meta-data to a dark gene family; and (iv) a stress model selection step, using different gene families in the test data from those in the training and development data sets to facilitate model deployment in a real-world scenario. In extensive and rigorous benchmark experiments, PortalCG considerably outperformed state-of-the-art techniques of machine learning and protein-ligand docking when applied to dark gene families, and demonstrated its generalization power for target identifications and compound screenings under out-of-distribution (OOD) scenarios. Furthermore, in an external validation for the multi-target compound screening, the performance of PortalCG surpassed the rational design from medicinal chemists. Our results also suggest that a differentiable sequence-structure-function deep learning framework, where protein structural information serves as an intermediate layer, could be superior to conventional methodology where predicted protein structures were used for the compound screening. We applied PortalCG to two case studies to exemplify its potential in drug discovery: designing selective dual-antagonists of dopamine receptors for the treatment of opioid use disorder (OUD), and illuminating the understudied human genome for target diseases that do not yet have effective and safe therapeutics. Our results suggested that PortalCG is a viable solution to the OOD problem in exploring understudied regions of protein functional space.