Assessment of AI-Based Protein Structure Prediction for the NLRP3 Target.

The recent successes of AlphaFold and RoseTTAFold have demonstrated the value of AI methods in highly accurate protein structure prediction. Despite these advances, the role of these methods in the context of small-molecule drug discovery still needs to be thoroughly explored. In this study, we evaluated whether the AI-based models can reliably reproduce the three-dimensional structures of protein-ligand complexes. The structure we chose was NLRP3, a challenging protein target in terms of obtaining a three-dimensional model both experimentally and computationally. The conformation of the binding pockets generated by the AI models was carefully characterized and compared with experimental structures. Further molecular docking results indicated that AI-predicted protein structures combined with molecular dynamics simulations offers a promising approach in small-molecule drug discovery.

AMPL: A Data-Driven Modeling Pipeline for Drug Discovery.

One of the key requirements for incorporating machine learning (ML) into the drug discovery process is complete traceability and reproducibility of the model building and evaluation process. With this in mind, we have developed an end-to-end modular and extensible software pipeline for building and sharing ML models that predict key pharma-relevant parameters. The ATOM Modeling PipeLine, or AMPL, extends the functionality of the open source library DeepChem and supports an array of ML and molecular featurization tools. We have benchmarked AMPL on a large collection of pharmaceutical data sets covering a wide range of parameters. Our key findings indicate that traditional molecular fingerprints underperform other feature representation methods. We also find that data set size correlates directly with prediction performance, which points to the need to expand public data sets. Uncertainty quantification can help predict model error, but correlation with error varies considerably between data sets and model types. Our findings point to the need for an extensible pipeline that can be shared to make model building more widely accessible and reproducible. This software is open source and available at: https://github.com/ATOMconsortium/AMPL.

A Multi-RNAi Microsponge Platform for Simultaneous Controlled Delivery of Multiple Small Interfering RNAs.

Packaging multiple small interfering RNA (siRNA) molecules into nanostructures at precisely defined ratios is a powerful delivery strategy for effective RNA interference (RNAi) therapy. We present a novel RNA nanotechnology based approach to produce multiple components of polymerized siRNA molecules that are simultaneously self-assembled and densely packaged into composite sponge-like porous microstructures (Multi-RNAi-MSs) by rolling circle transcription. The Multi-RNAi-MSs were designed to contain a combination of multiple polymeric siRNA molecules with precisely controlled stoichiometry within a singular microstructure by manipulating the types and ratios of the circular DNA templates. The Multi-RNAi-MSs were converted into nanosized complexes by polyelectrolyte condensation to manipulate their physicochemical properties (size, shape, and surface charge) for favorable delivery, while maintaining the multifunctional properties of the siRNAs for combined therapeutic effects. These Multi-RNAi-MS systems have great potential in RNAi-mediated biomedical applications, for example, for the treatment of cancer, genetic disorders, and viral infections.

Safety and tolerability of an intratumorally injected DNAzyme, Dz13, in patients with nodular basal-cell carcinoma: a phase 1 first-in-human trial (DISCOVER).

BACKGROUND: The nuclear transcription factor c-Jun is preferentially expressed in basal-cell carcinoma. Dz13 is a deoxyribozyme that targets JUN messenger RNA and has inhibited the growth of a range of tumours in mice. We did a phase 1 study to assess safety and tolerability in human beings. METHODS: Adults with nodular basal-cell carcinoma were recruited from Royal Prince Alfred Hospital, Sydney, Australia, between September, 2010, and October, 2011. Patients were assigned to receive one intratumoral injected dose of 10, 30, or 100 µg Dz13, in a 50 µL volume of lipid carrier, and were assessed for adverse effects in the first 24 h then at 7, 14, and 28 days after injection. Treated tumours were surgically excised 14 days after injection and compared with the baseline biopsy samples for expression of c-Jun and tumorigenesis markers. FINDINGS: Nine patients were recruited, of whom three received each dose of Dz13. All patients completed the study with no drug-related serious adverse events. No systemic Dz13 exposure was detected. c-Jun expression was reduced in the excised tumours of all nine (100%) patients, compared with baseline, and histological tumour depth had decreased in five (56%) of nine. Proportions of cells positive for caspases 3, 8, and 9 and P53 were increased, but those of cells positive for Bcl-2 and MMP-9 were decreased. Infiltration by inflammatory and immune cells was stimulated. INTERPRETATION: Dz13 was safe and well tolerated after single intratumoral injections at all doses. FUNDING: Cancer Institute NSW, Cancer Council Australia, and National Health and Medical Research Council.

Profiling cells with DELs: Small molecule fingerprinting of cell surfaces.

DNA-encoded small molecule library technology has recently emerged as a new paradigm for identifying ligands against drug targets. To date, it has been used to identify ligands against targets that are soluble or overexpressed on cell surfaces. Here, we report applying cell-based selection methods to profile surfaces of mouse C2C12 myoblasts and myotube cells in an unbiased, target agnostic manner. A panel of on-DNA compounds were identified and confirmed for cell binding selectivity. We optimized the cell selection protocol and employed a novel data analysis method to identify cell selective ligands against a panel of human B and T lymphocytes. We discuss the generality of using this workflow for DNA encoded small molecule library selection and data analysis against different cell types, and the feasibility of applying this method to profile cell surfaces for biomarker and target identification.

DELs enable the development of BRET probes for target engagement studies in cells.

DNA-encoded libraries (DELs) provide unmatched chemical diversity and starting points for novel drug modalities. Here, we describe a workflow that exploits the bifunctional attributes of DEL ligands as a platform to generate BRET probes for live cell target engagement studies. To establish proof of concept, we performed a DEL screen using aurora kinase A and successfully converted aurora DEL ligands as cell-active BRET probes. Aurora BRET probes enabled the validation and stratification of the chemical series identified from primary selection data. Furthermore, we have evaluated the effective repurposing of pre-existing DEL screen data to find suitable leads for BRET probe development. Our findings support the use of DEL workflows as an engine to create cell-active BRET probes independent of structure or compound SAR. The combination of DEL and BRET technology accelerates hit-to-lead studies in a live cell setting.

Biodegradable nano-films for capture and non-invasive release of circulating tumor cells.

Selective isolation and purification of circulating tumor cells (CTCs) from whole blood is an important capability for both clinical medicine and biological research. Current techniques to perform this task place the isolated cells under excessive stresses that reduce cell viability, and potentially induce phenotype change, therefore losing valuable information about the isolated cells. We present a biodegradable nano-film coating on the surface of a microfluidic chip, which can be used to effectively capture as well as non-invasively release cancer cell lines such as PC-3, LNCaP, DU 145, H1650 and H1975. We have applied layer-by-layer (LbL) assembly to create a library of ultrathin coatings using a broad range of materials through complementary interactions. By developing an LbL nano-film coating with an affinity-based cell-capture surface that is capable of selectively isolating cancer cells from whole blood, and that can be rapidly degraded on command, we are able to gently isolate cancer cells and recover them without compromising cell viability or proliferative potential. Our approach has the capability to overcome practical hurdles and provide viable cancer cells for downstream analyses, such as live cell imaging, single cell genomics, and in vitro cell culture of recovered cells. Furthermore, CTCs from cancer patients were also captured, identified, and successfully released using the LbL-modified microchips.