De novo generation of multi-target compounds using deep generative chemistry.

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.

Interpretation of cancer mutations using a multiscale map of protein systems.

A major goal of cancer research is to understand how mutations distributed across diverse genes affect common cellular systems, including multiprotein complexes and assemblies. Two challenges­how to comprehensively map such systems and how to identify which are under mutational selection­have hindered this understanding. Accordingly, we created a comprehensive map of cancer protein systems integrating both new and published multi-omic interaction data at multiple scales of analysis. We then developed a unified statistical model that pinpoints 395 specific systems under mutational selection across 13 cancer types. This map, called NeST (Nested Systems in Tumors), incorporates canonical processes and notable discoveries, including a PIK3CA-actomyosin complex that inhibits phosphatidylinositol 3-kinase signaling and recurrent mutations in collagen complexes that promote tumor proliferation. These systems can be used as clinical biomarkers and implicate a total of 548 genes in cancer evolution and progression. This work shows how disparate tumor mutations converge on protein assemblies at different scales.

A global transcriptional network connecting noncoding mutations to changes in tumor gene expression.

Although cancer genomes are replete with noncoding mutations, the effects of these mutations remain poorly characterized. Here we perform an integrative analysis of 930 tumor whole genomes and matched transcriptomes, identifying a network of 193 noncoding loci in which mutations disrupt target gene expression. These 'somatic eQTLs' (expression quantitative trait loci) are frequently mutated in specific cancer tissues, and the majority can be validated in an independent cohort of 3,382 tumors. Among these, we find that the effects of noncoding mutations on DAAM1, MTG2 and HYI transcription are recapitulated in multiple cancer cell lines and that increasing DAAM1 expression leads to invasive cell migration. Collectively, the noncoding loci converge on a set of core pathways, permitting a classification of tumors into pathway-based subtypes. The somatic eQTL network is disrupted in 88% of tumors, suggesting widespread impact of noncoding mutations in cancer.

Disruption of NSD1 in Head and Neck Cancer Promotes Favorable Chemotherapeutic Responses Linked to Hypomethylation.

Human papillomavirus (HPV)-negative head and neck squamous cell carcinoma (HNSCC) represents a distinct classification of cancer with worse expected outcomes. Of the 11 genes recurrently mutated in HNSCC, we identify a singular and substantial survival advantage for mutations in the gene encoding Nuclear Set Domain Containing Protein 1 (NSD1), a histone methyltransferase altered in approximately 10% of patients. This effect, a 55% decrease in risk of death in NSD1-mutated versus non-mutated patients, can be validated in an independent cohort. NSD1 alterations are strongly associated with widespread genome hypomethylation in the same tumors, to a degree not observed for any other mutated gene. To address whether NSD1 plays a causal role in these associations, we use CRISPR-Cas9 to disrupt NSD1 in HNSCC cell lines and find that this leads to substantial CpG hypomethylation and sensitivity to cisplatin, a standard chemotherapy in head and neck cancer, with a 40% to 50% decrease in the IC50 value. Such results are reinforced by a survey of 1,001 cancer cell lines, in which loss-of-function NSD1 mutations have an average 23% decrease in cisplatin IC50 value compared with cell lines with wild-type NSD1Significance: This study identifies a favorable subtype of HPV-negative HNSCC linked to NSD1 mutation, hypomethylation, and cisplatin sensitivity. Mol Cancer Ther; 17(7); 1585-94. ©2018 AACR.

Combinatorial CRISPR-Cas9 screens for de novo mapping of genetic interactions.

We developed a systematic approach to map human genetic networks by combinatorial CRISPR-Cas9 perturbations coupled to robust analysis of growth kinetics. We targeted all pairs of 73 cancer genes with dual guide RNAs in three cell lines, comprising 141,912 tests of interaction. Numerous therapeutically relevant interactions were identified, and these patterns replicated with combinatorial drugs at 75% precision. From these results, we anticipate that cellular context will be critical to synthetic-lethal therapies.

A Network of Conserved Synthetic Lethal Interactions for Exploration of Precision Cancer Therapy.

An emerging therapeutic strategy for cancer is to induce selective lethality in a tumor by exploiting interactions between its driving mutations and specific drug targets. Here we use a multi-species approach to develop a resource of synthetic lethal interactions relevant to cancer therapy. First, we screen in yeast ∼169,000 potential interactions among orthologs of human tumor suppressor genes (TSG) and genes encoding drug targets across multiple genotoxic environments. Guided by the strongest signal, we evaluate thousands of TSG-drug combinations in HeLa cells, resulting in networks of conserved synthetic lethal interactions. Analysis of these networks reveals that interaction stability across environments and shared gene function increase the likelihood of observing an interaction in human cancer cells. Using these rules, we prioritize ∼10(5) human TSG-drug combinations for future follow-up. We validate interactions based on cell and/or patient survival, including topoisomerases with RAD17 and checkpoint kinases with BLM.

Chemogenetic profiling identifies RAD17 as synthetically lethal with checkpoint kinase inhibition.

Chemical inhibitors of the checkpoint kinases have shown promise in the treatment of cancer, yet their clinical utility may be limited by a lack of molecular biomarkers to identify specific patients most likely to respond to therapy. To this end, we screened 112 known tumor suppressor genes for synthetic lethal interactions with inhibitors of the CHEK1 and CHEK2 checkpoint kinases. We identified eight interactions, including the Replication Factor C (RFC)-related protein RAD17. Clonogenic assays in RAD17 knockdown cell lines identified a substantial shift in sensitivity to checkpoint kinase inhibition (3.5-fold) as compared to RAD17 wild-type. Additional evidence for this interaction was found in a large-scale functional shRNA screen of over 100 genotyped cancer cell lines, in which CHEK1/2 mutant cell lines were unexpectedly sensitive to RAD17 knockdown. This interaction was widely conserved, as we found that RAD17 interacts strongly with checkpoint kinases in the budding yeast Saccharomyces cerevisiae. In the setting of RAD17 knockdown, CHEK1/2 inhibition was found to be synergistic with inhibition of WEE1, another pharmacologically relevant checkpoint kinase. Accumulation of the DNA damage marker γH2AX following chemical inhibition or transient knockdown of CHEK1, CHEK2 or WEE1 was magnified by knockdown of RAD17. Taken together, our data suggest that CHEK1 or WEE1 inhibitors are likely to have greater clinical efficacy in tumors with RAD17 loss-of-function.