Discovery and Preclinical Characterization of XMT-1660, an Optimized B7-H4-Targeted Antibody-Drug Conjugate for the Treatment of Cancer.

Antibody-drug conjugates (ADC) achieve targeted drug delivery to a tumor and have demonstrated clinical success in many tumor types. The activity and safety profile of an ADC depends on its construction: antibody, payload, linker, and conjugation method, as well as the number of payload drugs per antibody [drug-to-antibody ratio (DAR)]. To allow for ADC optimization for a given target antigen, we developed Dolasynthen (DS), a novel ADC platform based on the payload auristatin hydroxypropylamide, that enables precise DAR-ranging and site-specific conjugation. We used the new platform to optimize an ADC that targets B7-H4 (VTCN1), an immune-suppressive protein that is overexpressed in breast, ovarian, and endometrial cancers. XMT-1660 is a site-specific DS DAR 6 ADC that induced complete tumor regressions in xenograft models of breast and ovarian cancer as well as in a syngeneic breast cancer model that is refractory to PD-1 immune checkpoint inhibition. In a panel of 28 breast cancer PDXs, XMT-1660 demonstrated activity that correlated with B7-H4 expression. XMT-1660 has recently entered clinical development in a phase I study (NCT05377996) in patients with cancer.

Deep Learning Enables Discovery of a Short Nuclear Targeting Peptide for Efficient Delivery of Antisense Oligomers.

Therapeutic macromolecules such as proteins and oligonucleotides can be highly efficacious but are often limited to extracellular targets due to the cell's impermeable membrane. Cell-penetrating peptides (CPPs) are able to deliver such macromolecules into cells, but limited structure-activity relationships and inconsistent literature reports make it difficult to design effective CPPs for a given cargo. For example, polyarginine motifs are common in CPPs, promoting cell uptake at the expense of systemic toxicity. Machine learning may be able to address this challenge by bridging gaps between experimental data in order to discern sequence-activity relationships that evade our intuition. Our earlier data set and deep learning model led to the design of miniproteins (>40 amino acids) for antisense delivery. Here, we leveraged and expanded our model with data augmentation in the short CPP sequence space of the data set to extrapolate and discover short, low-arginine-content CPPs that would be easier to synthesize and amenable to rapid conjugation to desired cargo, and with minimal in vivo toxicity. The lead predicted peptide, termed P6, is as active as a polyarginine CPP for the delivery of an antisense oligomer, while having only one arginine side chain and 18 total residues. We determined the pentalysine motif and the C-terminal cysteine of P6 to be the main drivers of activity. The antisense conjugate was able to enhance corrective splicing in an animal model to produce functional eGFP in heart tissue in vivo while remaining nontoxic up to a dose of 60 mg/kg. In addition, P6 was able to deliver an enzyme to the cytosol of cells. Our findings suggest that, given a data set of long CPPs, we can discover by extrapolation short, active sequences that deliver antisense oligomers.

Deep learning to design nuclear-targeting abiotic miniproteins.

There are more amino acid permutations within a 40-residue sequence than atoms on Earth. This vast chemical search space hinders the use of human learning to design functional polymers. Here we show how machine learning enables the de novo design of abiotic nuclear-targeting miniproteins to traffic antisense oligomers to the nucleus of cells. We combined high-throughput experimentation with a directed evolution-inspired deep-learning approach in which the molecular structures of natural and unnatural residues are represented as topological fingerprints. The model is able to predict activities beyond the training dataset, and simultaneously deciphers and visualizes sequence-activity predictions. The predicted miniproteins, termed 'Mach', reach an average mass of 10 kDa, are more effective than any previously known variant in cells and can also deliver proteins into the cytosol. The Mach miniproteins are non-toxic and efficiently deliver antisense cargo in mice. These results demonstrate that deep learning can decipher design principles to generate highly active biomolecules that are unlikely to be discovered by empirical approaches.

Impact of Zika virus on the human type I interferon osteoimmune response.

BACKGROUND: The developing field of osteoimmunology supports importance of an interferon (IFN) response pathway in osteoblasts. Clarifying osteoblast-IFN interactions is important because IFN is used as salvage anti-tumor therapy but systemic toxicity is high with variable clinical results. In addition, osteoblast response to systemic bursts and disruptions of IFN pathways induced by viral infection may influence bone remodeling. ZIKA virus (ZIKV) infection impacts bone development in humans and IFN response in vitro. Consistently, initial evidence of permissivity to ZIKV has been reported in human osteoblasts. HYPOTHESIS: Osteoblast-like Saos-2 cells are permissive to ZIKV and responsive to IFN. METHODS: Multiple approaches were used to assess whether Saos-2 cells are permissive to ZIKV infection and exhibit IFN-mediated ZIKV suppression. Proteomic methods were used to evaluate impact of ZIKV and IFN on Saos-2 cells. RESULTS: Evidence is presented confirming Saos-2 cells are permissive to ZIKV and support IFN-mediated suppression of ZIKV. ZIKV and IFN differentially impact the Saos-2 proteome, exemplified by HELZ2 protein which is upregulated by IFN but non responsive to ZIKV. Both ZIKV and IFN suppress proteins associated with microcephaly/pseudo-TORCH syndrome (BI1, KI20A and UBP18), and ZIKV induces potential entry factor PLVAP. CONCLUSIONS: Transient ZIKV infection influences osteoimmune state, and IFN and ZIKV activate distinct proteomes in Saos-2 cells, which could inform therapeutic, engineered, disruptions.