Polymer design via SHAP and Bayesian machine learning optimizes pDNA and CRISPR ribonucleoprotein delivery.

We present the facile synthesis of a clickable polymer library with systematic variations in length, binary composition, pKa, and hydrophobicity (clog P) to optimize intracellular pDNA and CRISPR-Cas9 ribonucleoprotein (RNP) performance. We couple physicochemical characterization and machine learning to interpret quantitative structure-property relationships within the combinatorial design space. For the first time, we reveal unexpected disparate design parameters for nucleic acid carriers; via explainable machine learning on 432 formulations, we discover that lower polymer pKa and higher percentages of benzimidazole ethanethiol enhance pDNA delivery, yet polymer length and captamine cation identity improve RNP delivery. Closed-loop Bayesian optimization of 552 formulation ratios further enhances in vitro performance. The top three polymers yield a higher signal and stable transgene expression over 20 days in vivo, and a 1.7-fold enhancement over controls. Our facile coupling of synthesis, characterization, and machine analysis provides powerful tools to quantitate performance parameters accelerating next-generation vehicles for nucleic acid medicines.

Frontiers in nonviral delivery of small molecule and genetic drugs, driven by polymer chemistry and machine learning for materials informatics.

Materials informatics (MI) has immense potential to accelerate the pace of innovation and new product development in biotechnology. Close collaborations between skilled physical and life scientists with data scientists are being established in pursuit of leveraging MI tools in automation and artificial intelligence (AI) to predict material properties in vitro and in vivo. However, the scarcity of large, standardized, and labeled materials data for connecting structure-function relationships represents one of the largest hurdles to overcome. In this Highlight, focus is brought to emerging developments in polymer-based therapeutic delivery platforms, where teams generate large experimental datasets around specific therapeutics and successfully establish a design-to-deployment cycle of specialized nanocarriers. Three select collaborations demonstrate how custom-built polymers protect and deliver small molecules, nucleic acids, and proteins, representing ideal use-cases for machine learning to understand how molecular-level interactions impact drug stabilization and release. We conclude with our perspectives on how MI innovations in automation efficiencies and digitalization of data-coupled with fundamental insight and creativity from the polymer science community-can accelerate translation of more gene therapies into lifesaving medicines.

Predicting locations of cryptic pockets from single protein structures using the PocketMiner graph neural network.

Cryptic pockets expand the scope of drug discovery by enabling targeting of proteins currently considered undruggable because they lack pockets in their ground state structures. However, identifying cryptic pockets is labor-intensive and slow. The ability to accurately and rapidly predict if and where cryptic pockets are likely to form from a structure would greatly accelerate the search for druggable pockets. Here, we present PocketMiner, a graph neural network trained to predict where pockets are likely to open in molecular dynamics simulations. Applying PocketMiner to single structures from a newly curated dataset of 39 experimentally confirmed cryptic pockets demonstrates that it accurately identifies cryptic pockets (ROC-AUC: 0.87) >1,000-fold faster than existing methods. We apply PocketMiner across the human proteome and show that predicted pockets open in simulations, suggesting that over half of proteins thought to lack pockets based on available structures likely contain cryptic pockets, vastly expanding the potentially druggable proteome.

An Artificial Intelligence Dataset for Solar Energy Locations in India.

Rapid development of renewable energy sources, particularly solar photovoltaics (PV), is critical to mitigate climate change. As a result, India has set ambitious goals to install 500 gigawatts of solar energy capacity by 2030. Given the large footprint projected to meet renewables energy targets, the potential for land use conflicts over environmental values is high. To expedite development of solar energy, land use planners will need access to up-to-date and accurate geo-spatial information of PV infrastructure. In this work, we developed a spatially explicit machine learning model to map utility-scale solar projects across India using freely available satellite imagery with a mean accuracy of 92%. Our model predictions were validated by human experts to obtain a dataset of 1363 solar PV farms. Using this dataset, we measure the solar footprint across India and quantified the degree of landcover modification associated with the development of PV infrastructure. Our analysis indicates that over 74% of solar development In India was built on landcover types that have natural ecosystem preservation, or agricultural value.

Combinatorial Polycation Synthesis and Causal Machine Learning Reveal Divergent Polymer Design Rules for Effective pDNA and Ribonucleoprotein Delivery.

The development of polymers that can replace engineered viral vectors in clinical gene therapy has proven elusive despite the vast portfolios of multifunctional polymers generated by advances in polymer synthesis. Functional delivery of payloads such as plasmids (pDNA) and ribonucleoproteins (RNP) to various cellular populations and tissue types requires design precision. Herein, we systematically screen a combinatorially designed library of 43 well-defined polymers, ultimately identifying a lead polycationic vehicle (P38) for efficient pDNA delivery. Further, we demonstrate the versatility of P38 in codelivering spCas9 RNP and pDNA payloads to mediate homology-directed repair as well as in facilitating efficient pDNA delivery in ARPE-19 cells. P38 achieves nuclear import of pDNA and eludes lysosomal processing far more effectively than a structural analogue that does not deliver pDNA as efficiently. To reveal the physicochemical drivers of P38's gene delivery performance, SHapley Additive exPlanations (SHAP) are computed for nine polyplex features, and a causal model is applied to evaluate the average treatment effect of the most important features selected by SHAP. Our machine learning interpretability and causal inference approach derives structure-function relationships underlying delivery efficiency, polyplex uptake, and cellular viability and probes the overlap in polymer design criteria between RNP and pDNA payloads. Together, combinatorial polymer synthesis, parallelized biological screening, and machine learning establish that pDNA delivery demands careful tuning of polycation protonation equilibria while RNP payloads are delivered most efficaciously by polymers that deprotonate cooperatively via hydrophobic interactions. These payload-specific design guidelines will inform further design of bespoke polymers for specific therapeutic contexts.

Author Correction: How machine learning can help select capping layers to suppress perovskite degradation.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

How machine learning can help select capping layers to suppress perovskite degradation.

Environmental stability of perovskite solar cells (PSCs) has been improved by trial-and-error exploration of thin low-dimensional (LD) perovskite deposited on top of the perovskite absorber, called the capping layer. In this study, a machine-learning framework is presented to optimize this layer. We featurize 21 organic halide salts, apply them as capping layers onto methylammonium lead iodide (MAPbI3) films, age them under accelerated conditions, and determine features governing stability using supervised machine learning and Shapley values. We find that organic molecules' low number of hydrogen-bonding donors and small topological polar surface area correlate with increased MAPbI3 film stability. The top performing organic halide, phenyltriethylammonium iodide (PTEAI), successfully extends the MAPbI3 stability lifetime by 4 ± 2 times over bare MAPbI3 and 1.3 ± 0.3 times over state-of-the-art octylammonium bromide (OABr). Through characterization, we find that this capping layer stabilizes the photoactive layer by changing the surface chemistry and suppressing methylammonium loss.