Lessons learned during the journey of data: from experiment to model for predicting kinase affinity, selectivity, polypharmacology, and resistance.

Recent advances in machine learning (ML) are reshaping drug discovery. Structure-based ML methods use physically-inspired models to predict binding affinities from protein:ligand complexes. These methods promise to enable the integration of data for many related targets, which addresses issues related to data scarcity for single targets and could enable generalizable predictions for a broad range of targets, including mutants.

Therapeutic Peptides Are Preferentially Solubilized in Specific Microenvironments within PEG-PLGA Polymer Nanoparticles.

Polymeric nanoparticles are a highly promising drug delivery formulation. However, a lack of understanding of the molecular mechanisms that underlie their drug solubilization and controlled release capabilities has hindered the efficient clinical translation of such technologies. Polyethylene glycol-poly(lactic--glycolic) acid (PEG-PLGA) nanoparticles have been widely studied as cancer drug delivery vehicles.

Topology-controlled self-assembly of amphiphilic block copolymers.

Contemporary synthetic chemistry approaches can be used to yield a range of distinct polymer topologies with precise control. The topology of a polymer strongly influences its self-assembly into complex nanostructures however a clear mechanistic understanding of the relationship between polymer topology and self-assembly has not yet been developed. In this work, we use atomistic molecular dynamics simulations to provide a nanoscale picture of the self-assembly of three poly(ethylene oxide)-poly(methyl acrylate) block copolymers with different topologies into micelles.

Faster and more diverse de novo molecular optimization with double-loop reinforcement learning using augmented SMILES.

Using generative deep learning models and reinforcement learning together can effectively generate new molecules with desired properties. By employing a multi-objective scoring function, thousands of high-scoring molecules can be generated, making this approach useful for drug discovery and material science. However, the application of these methods can be hindered by computationally expensive or time-consuming scoring procedures, particularly when a large number of function calls are required as feedback in the reinforcement learning optimization.

Modular Software for Generating and Modeling Diverse Polymer Databases.

Machine learning methods offer the opportunity to design new functional materials on an unprecedented scale; however, building the large, diverse databases of molecules on which to train such methods remains a daunting task. Automated computational chemistry modeling workflows are therefore becoming essential tools in this data-driven hunt for new materials with novel properties, since they offer a means by which to create and curate molecular databases without requiring significant levels of user input. This ensures that well-founded concerns regarding data provenance, reproducibility, and replicability are mitigated.

Directly imaging emergence of phase separation in peroxidized lipid membranes.

Lipid peroxidation is a process which is key in cell signaling and disease, it is exploited in cancer therapy in the form of photodynamic therapy. The appearance of hydrophilic moieties within the bilayer's hydrocarbon core will dramatically alter the structure and mechanical behavior of membranes. Here, we combine viscosity sensitive fluorophores, advanced microscopy, and X-ray diffraction and molecular simulations to directly and quantitatively measure the bilayer's structural and viscoelastic properties, and correlate these with atomistic molecular modelling.

Conformational Heterogeneity and Interchain Percolation Revealed in an Amorphous Conjugated Polymer.

Conjugated polymers are employed in a variety of application areas due to their bright fluorescence and strong biocompatibility. However, understanding the structure of amorphous conjugated polymers on the nanoscale is extremely challenging compared to their related crystalline phases. Using a bespoke classical force field, we study amorphous poly(9,9-di--octylfluorene--benzothiadiazole) (F8BT) with molecular dynamics simulations to investigate the role that its nanoscale structure plays in controlling its emergent (and all-important) optical properties.