Design of Cytotoxic T Cell Epitopes by Machine Learning of Human Degrons.

Antigen processing is critical for therapeutic vaccines to generate epitopes for priming cytotoxic T cell responses against cancer and pathogens, but insufficient processing often limits the quantity of epitopes released. We address this challenge using machine learning to ascribe a proteasomal degradation score to epitope sequences. Epitopes with varying scores were translocated into cells using nontoxic anthrax proteins. Epitopes with a low score show pronounced immunogenicity due to antigen processing, but epitopes with a high score show limited immunogenicity. This work sheds light on the sequence-activity relationships between proteasomal degradation and epitope immunogenicity. We anticipate that future efforts to incorporate proteasomal degradation signals into vaccine designs will lead to enhanced cytotoxic T cell priming by these vaccines in clinical settings.

DISPEL: database for ascertaining the best medicinal plants to cure human diseases.

Medicinal plants are anticipated to be one of the most valuable resources for the remedial usage in the treatment of various ailments. The data on key medicinal plants and their therapeutic efficacy against various ailments are quite scattered and not available on a single platform. Moreover, currently there is no means/mechanism of finding the best medicinal plant(s) from numerous plants known to cure any disease. DISPEL (Diseases Plants Eliminate) is a compendium of medicinal plants available across the world that are used to cure infectious as well as non-infectious diseases in humans. The association of a medicinal plant with a disease it cures is hereby referred to as 'medicinal plant-disease cured' linkage. The DISPEL database hosts ∼60 000 'medicinal plant-disease cured' linkages encompassing ∼5500 medicinal plants and ∼1000 diseases. This platform provides interactive and detailed visualization of medicinal plants, diseases and their relations using comprehensible network graph representation. The user has the freedom to search the database by specifying the name of disease(s) as well as the scientific/common name(s) of plant. Each 'medicinal plant-disease cured' relation is scored based on the availability of any medicine/product derived from that medicinal plant, information about active compound(s), knowledge regarding the part of plant that is effective and number of distinct articles/books/websites confirming the effectiveness of the medicinal plant. The user can find the best plant(s) that can be used to cure any desired disease(s). The DISPEL database is the first step towards generating the 'most-effective' combination of plants to cure a disease since it delineates as well as ranks all the therapeutic medicinal plants for that disease. The combination of best medicinal plants can then be used to conduct clinical trials and thus pave the way for their use in clinics for treatment of diseases. Database URL https://compbio.iitr.ac.in/dispel.

A Model Ensemble Approach Enables Data-Driven Property Prediction for Chemically Deconstructable Thermosets in the Low-Data Regime.

Thermosets present sustainability challenges that could potentially be addressed through the design of deconstructable variants with tunable properties; however, the combinatorial space of possible thermoset molecular building blocks (e.g., monomers, cross-linkers, and additives) and manufacturing conditions is vast, and predictive knowledge for how combinations of these molecular components translate to bulk thermoset properties is lacking. Data science could overcome these problems, but computational methods are difficult to apply to multicomponent, amorphous, statistical copolymer materials for which little data exist. Here, leveraging a data set with 101 examples, we introduce a closed-loop experimental, machine learning (ML), and virtual screening strategy to enable predictions of the glass transition temperature (Tg) of polydicyclopentadiene (pDCPD) thermosets containing cleavable bifunctional silyl ether (BSE) comonomers and/or cross-linkers with varied compositions and loadings. Molecular features and formulation variables are used as model inputs, and uncertainty is quantified through model ensembling, which together with heavy regularization helps to avoid overfitting and ultimately achieves predictions within <15 °C for thermosets with compositionally diverse BSEs. This work offers a path to predicting the properties of thermosets based on their molecular building blocks, which may accelerate the discovery of promising plastics, rubbers, and composites with improved functionality and controlled deconstructability.

Design of Cytotoxic T Cell Epitopes by Machine Learning of Human Degrons.

Antigen processing is critical for producing epitope peptides that are presented by HLA molecules for T cell recognition. Therapeutic vaccines aim to harness these epitopes for priming cytotoxic T cell responses against cancer and pathogens, but insufficient processing often reduces vaccine efficacy through limiting the quantity of epitopes released. Here, we set out to improve antigen processing by harnessing protein degradation signals called degrons from the ubiquitin-proteasome system. We used machine learning to generate a computational model that ascribes a proteasomal degradation score between 0 and 100. Epitope peptides with varying degron activities were synthesized and translocated into cells using nontoxic anthrax proteins: protective antigen (PA) and the N-terminus of lethal factor (LFN). Immunogenicity studies revealed epitope sequences with a low score (<25) show pronounced T-cell activation but epitope sequences with a higher score (>75) provide limited activation. This work sheds light on the sequence-activity relationships between proteasomal degradation and epitope immunogenicity, through conserving the epitope region but varying the flanking sequence. We anticipate that future efforts to incorporate proteasomal degradation signals into vaccine designs will lead to enhanced cytotoxic T cell priming by vaccine therapeutics in clinical settings.

Machine Learning Guides Peptide Nucleic Acid Flow Synthesis and Sequence Design.

Peptide nucleic acids (PNAs) are potential antisense therapies for genetic, acquired, and viral diseases. Efficiently selecting candidate PNA sequences for synthesis and evaluation from a genome containing hundreds to thousands of options can be challenging. To facilitate this process, this work leverages machine learning (ML) algorithms and automated synthesis technology to predict PNA synthesis efficiency and guide rational PNA sequence design. The training data is collected from individual fluorenylmethyloxycarbonyl (Fmoc) deprotection reactions performed on a fully automated PNA synthesizer. The optimized ML model allows for 93% prediction accuracy and 0.97 Pearson's r. The predicted synthesis scores are validated to be correlated with the experimental high-performance liquid chromatography (HPLC) crude purities (correlation coefficient R2 = 0.95). Furthermore, a general applicability of ML is demonstrated through designing synthetically accessible antisense PNA sequences from 102 315 predicted candidates targeting exon 44 of the human dystrophin gene, SARS-CoV-2, HIV, as well as selected genes associated with cardiovascular diseases, type II diabetes, and various cancers. Collectively, ML provides an accurate prediction of PNA synthesis quality and serves as a useful computational tool for informing PNA sequence design.

Bottlebrush polymers with flexible enantiomeric side chains display differential biological properties.

Chirality and molecular conformation are central components of life: biological systems rely on stereospecific interactions between discrete (macro)molecular conformers, and the impacts of stereochemistry and rigidity on the properties of small molecules and biomacromolecules have been intensively studied. Nevertheless, how these features affect the properties of synthetic macromolecules has received comparably little attention. Here we leverage iterative exponential growth and ring-opening metathesis polymerization to produce water-soluble, chiral bottlebrush polymers (CBPs) from two enantiomeric pairs of macromonomers of differing rigidity. Remarkably, CBPs with conformationally flexible, mirror image side chains show several-fold differences in cytotoxicity, cell uptake, blood pharmacokinetics and liver clearance; CBPs with comparably rigid, mirror image side chains show no differences. These observations are rationalized with a simple model that correlates greater conformational freedom with enhanced chiral recognition. Altogether, this work provides routes to the synthesis of chiral nanostructured polymers and suggests key roles for stereochemistry and conformational rigidity in the design of future biomaterials.

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.

Synthetic Glycomacromolecules of Defined Valency, Absolute Configuration, and Topology Distinguish between Human Lectins.

Carbohydrate-binding proteins (lectins) play vital roles in cell recognition and signaling, including pathogen binding and innate immunity. Thus, targeting lectins, especially those on the surface of immune cells, could advance immunology and drug discovery. Lectins are typically oligomeric; therefore, many of the most potent ligands are multivalent. An effective strategy for lectin targeting is to display multiple copies of a single glycan epitope on a polymer backbone; however, a drawback to such multivalent ligands is they cannot distinguish between lectins that share monosaccharide binding selectivity (e.g., mannose-binding lectins) as they often lack molecular precision. Here, we describe the development of an iterative exponential growth (IEG) synthetic strategy that enables facile access to synthetic glycomacromolecules with precisely defined and tunable sizes up to 22.5 kDa, compositions, topologies, and absolute configurations. Twelve discrete mannosylated "glyco-IEGmers" are synthesized and screened for binding to a panel of mannoside-binding immune lectins (DC-SIGN, DC-SIGNR, MBL, SP-D, langerin, dectin-2, mincle, and DEC-205). In many cases, the glyco-IEGmers had distinct length, stereochemistry, and topology-dependent lectin-binding preferences. To understand these differences, we used molecular dynamics and density functional theory simulations of octameric glyco-IEGmers, which revealed dramatic effects of glyco-IEGmer stereochemistry and topology on solution structure and reveal an interplay between conformational diversity and chiral recognition in selective lectin binding. Ligand function also could be controlled by chemical substitution: by tuning the side chains of glyco-IEGmers that bind DC-SIGN, we could alter their cellular trafficking through alteration of their aggregation state. These results highlight the power of precision synthetic oligomer/polymer synthesis for selective biological targeting, motivating the development of next-generation glycomacromolecules tailored for specific immunological or other therapeutic applications.

Deep Learning for Prediction and Optimization of Fast-Flow Peptide Synthesis.

The chemical synthesis of polypeptides involves stepwise formation of amide bonds on an immobilized solid support. The high yields required for efficient incorporation of each individual amino acid in the growing chain are often impacted by sequence-dependent events such as aggregation. Here, we apply deep learning over ultraviolet-visible (UV-vis) analytical data collected from 35 427 individual fluorenylmethyloxycarbonyl (Fmoc) deprotection reactions performed with an automated fast-flow peptide synthesizer. The integral, height, and width of these time-resolved UV-vis deprotection traces indirectly allow for analysis of the iterative amide coupling cycles on resin. The computational model maps structural representations of amino acids and peptide sequences to experimental synthesis parameters and predicts the outcome of deprotection reactions with less than 6% error. Our deep-learning approach enables experimentally aware computational design for prediction of Fmoc deprotection efficiency and minimization of aggregation events, building the foundation for real-time optimization of peptide synthesis in flow.

Quantitative Mapping of Molecular Substituents to Macroscopic Properties Enables Predictive Design of Oligoethylene Glycol-Based Lithium Electrolytes.

Molecular details often dictate the macroscopic properties of materials, yet due to their vastly different length scales, relationships between molecular structure and bulk properties can be difficult to predict a priori, requiring Edisonian optimizations and preventing rational design. Here, we introduce an easy-to-execute strategy based on linear free energy relationships (LFERs) that enables quantitative correlation and prediction of how molecular modifications, i.e., substituents, impact the ensemble properties of materials. First, we developed substituent parameters based on inexpensive, DFT-computed energetics of elementary pairwise interactions between a given substituent and other constant components of the material. These substituent parameters were then used as inputs to regression analyses of experimentally measured bulk properties, generating a predictive statistical model. We applied this approach to a widely studied class of electrolyte materials: oligo-ethylene glycol (OEG)-LiTFSI mixtures; the resulting model enables elucidation of fundamental physical principles that govern the properties of these electrolytes and also enables prediction of the properties of novel, improved OEG-LiTFSI-based electrolytes. The framework presented here for using context-specific substituent parameters will potentially enhance the throughput of screening new molecular designs for next-generation energy storage devices and other materials-oriented contexts where classical substituent parameters (e.g., Hammett parameters) may not be available or effective.