Skip to main content
eScholarship
Open Access Publications from the University of California

Scholarly Works (3 results)

  • Thesis
  • Peer Reviewed
UC San Diego Electronic Theses and Dissertations (2023)

Cancer, a complex and heterogeneous disease, continues to pose a significant challenge to global mortality. As such, there is a need for increasingly potent and precise therapies, developed rapidly and cost-effectively. Here, we describe a systematic method to uncover tumor-specific genetic co-dependencies and design small-molecule therapies that target those vulnerabilities using deep generative chemistry.

First, CRISPR-Cas9 perturbations are leveraged to profile a network of functional co-dependencies among cyclin-dependent kinases (CDK) genes and associated factors. In tandem, single-cell RNA sequencing is used to interrogate the transcriptomes of perturbed cells and investigate the potential mechanisms by which the observed synthetic lethalities arise. This study revealed a network of 12 synergistic interactions and 43 synthetic lethalities. The synthetic lethalities serve as direct target pairs for polypharmacology drug design.Second, a machine-learning model called CHEMIST is developed to generate de novo polypharmacology compounds that target synthetic lethalities in human cancer. Leveraging recent advances in deep generative chemistry and reinforcement learning, CHEMIST is designed to tune molecular structures to specific and potentially independent goals. CHEMIST is then utilized to design polypharmacology compounds against ten pairs of protein targets observed as synthetic-lethal in at least one human cancer context. Of these compound designs targeting the synthetic-lethal combination of MEK1 (mitogen-activated protein kinase kinase 1) and mTOR (mammalian target of rapamycin), 32 compounds were synthesized and validated in a human adenocarcinoma cell-line model. Together, these works present a framework for quickly designing small-molecule therapies that target tumor-specific vulnerabilities.

    • Article
    • Peer Reviewed
    UC San Diego Previously Published Works (2024)
    Polypharmacology drugs-compounds that inhibit multiple proteins-have many applications but are difficult to design. To address this challenge we have developed POLYGON, an approach to polypharmacology based on generative reinforcement learning. POLYGON embeds chemical space and iteratively samples it to generate new molecular structures; these are rewarded by the predicted ability to inhibit each of two protein targets and by drug-likeness and ease-of-synthesis. In binding data for >100,000 compounds, POLYGON correctly recognizes polypharmacology interactions with 82.5% accuracy. We subsequently generate de-novo compounds targeting ten pairs of proteins with documented co-dependency. Docking analysis indicates that top structures bind their two targets with low free energies and similar 3D orientations to canonical single-protein inhibitors. We synthesize 32 compounds targeting MEK1 and mTOR, with most yielding >50% reduction in each protein activity and in cell viability when dosed at 1-10 μM. These results support the potential of generative modeling for polypharmacology.
      Cover page: De novo generation of multi-target compounds using deep generative chemistry
      • Article
      • Peer Reviewed
      UC San Diego Previously Published Works (2023)
      Cell-cycle control is accomplished by cyclin-dependent kinases (CDKs), motivating extensive research into CDK targeting small-molecule drugs as cancer therapeutics. Here we use combinatorial CRISPR/Cas9 perturbations to uncover an extensive network of functional interdependencies among CDKs and related factors, identifying 43 synthetic-lethal and 12 synergistic interactions. We dissect CDK perturbations using single-cell RNAseq, for which we develop a novel computational framework to precisely quantify cell-cycle effects and diverse cell states orchestrated by specific CDKs. While pairwise disruption of CDK4/6 is synthetic-lethal, only CDK6 is required for normal cell-cycle progression and transcriptional activation. Multiple CDKs (CDK1/7/9/12) are synthetic-lethal in combination with PRMT5, independent of cell-cycle control. In-depth analysis of mRNA expression and splicing patterns provides multiple lines of evidence that the CDK-PRMT5 dependency is due to aberrant transcriptional regulation resulting in premature termination. These inter-dependencies translate to drug-drug synergies, with therapeutic implications in cancer and other diseases.
        Cover page: Multimodal perturbation analyses of cyclin-dependent kinases reveal a network of synthetic lethalities associated with cell-cycle regulation and transcriptional regulation.
        Top