Screening Pipeline Research Articles

Using Microfluidic and Conventional Platforms to Evaluate the Effects of Lanthanides on Spheroid Formation

Metastasis contributes to the increased mortality rate of cancer, but the intricate mechanisms remain unclear. Cancer cells from a primary tumor invade nearby tissues and access the lymphatic or circulatory system. If these cells manage to survive and extravasate from the vasculature into distant tissues and ultimately adapt to survive, they will proliferate and facilitate malignant tumor formation. Traditional two-dimensional (2D) cell cultures offer a rapid and convenient method for validating the efficacy of anticancer drugs within a reasonable cost range, but their utility is limited because of tumors’ high heterogeneity in vivo and spatial complexities. Three-dimensional (3D) cell cultures that mimic the physiological conditions of cancer cells in vivo have gained considerable interest. In these cultures, cells assemble into spheroids through gravity, magnetic forces, or their low-adhesion to the plates. Although these approaches address some of the limitations of 2D cultures, they often require a considerable amount of time and cost. Therefore, this study aims to enhance the effectiveness of 3D culture techniques by using microfluidic systems to provide a high-throughput and sensitive pipeline for drug screening. Using these systems, we studied the effects of lanthanide elements, which have garnered interest in cancer treatment, on spheroid formation and cell spreading. Our findings suggest that these elements alter the compactness of cell spheroids and decrease cell mobility.

Discovery of Highly Bioactive Peptides through Hierarchical Structural Information and Molecular Dynamics Simulations.

Peptide drugs play an essential role in modern therapeutics, but the computational design of these molecules is hindered by several challenges. Traditional methods like molecular docking and molecular dynamics (MD) simulation, as well as recent deep learning approaches, often face limitations related to computational resource demands, complex binding affinity assessments, extensive data requirements, and poor model interpretability. Here, we introduce PepHiRe, an innovative methodology that utilizes the hierarchical structural information in peptide sequences and employs a novel strategy called Ladderpath, rooted in algorithmic information theory, to rapidly generate and enhance the efficiency and clarity of novel peptide design. We applied PepHiRe to develop BH3-like peptide inhibitors targeting myeloid cell leukemia-1, a protein associated with various cancers. By analyzing just eight known bioactive BH3 peptide sequences, PepHiRe effectively derived a hierarchy of subsequences used to create new BH3-like peptides. These peptides underwent screening through MD simulations, leading to the selection of five candidates for synthesis and subsequent in vitro testing. Experimental results demonstrated that these five peptides possess high inhibitory activity, with IC50 values ranging from 28.13 ± 7.93 to 167.42 ± 22.15 nM. Our study explores a white-box model driven technique and a structured screening pipeline for identifying and generating novel peptides with potential bioactivity.

Computational screening of umami tastants using deep learning.

Umami, a fundamental human taste modality, refers to the savory flavors in meats and broths, often associated with monosodium glutamate and protein richness. With limited knowledge of umami molecules, the food industry seeks efficient approaches for identifying novel tastants. In this study, we have devised a virtual screening pipeline for identifying highly potent umami tastants from large molecular databases. We curated the most extensive classification dataset containing 439 umami and 428 non-umami molecules and trained a transformer-based architecture to differentiate between the two classes, achieving 93% accuracy. Additionally, we built a neural network model for predicting the potency of umami compounds, the first effort of its kind. The classification and potency prediction models were combined with similarity analysis and toxicity screening to build an end-to-end virtual framework for the rational discovery of novel tastants. We applied this framework to the FooDB database containing around 70,000 molecules as an illustrative use case for screening potent umami compounds. The screened molecules were validated using molecular docking with the umami taste receptor. This study demonstrates the potential of data-driven methods in discovering new tastants from structural and chemical features of molecules and proposes an efficient implementation for industrial applications.

From Small Data Modeling to Large Language Model Screening: A Dual-Strategy Framework for Materials Intelligent Design.

Small data in materials present significant challenges to constructing highly accurate machine learning models, severely hindering the widespread implementation of data-driven materials intelligent design. In this study, the Dual-Strategy Materials Intelligent Design Framework (DSMID) is introduced, which integrates two innovative methods. The Adversarial domain Adaptive Embedding Generative network (AAEG) transfers data between related property datasets, even with only 90 data points, enhancing material composition characterization and improving property prediction. Additionally, to address the challenge of screening and evaluating numerous alloy designs, the Automated Material Screening and Evaluation Pipeline (AMSEP) is implemented. This pipeline utilizes large language models with extensive domain knowledge to efficiently identify promising experimental candidates through self-retrieval and self-summarization. Experimental findings demonstrate that this approach effectively identifies and prepares new eutectic High Entropy Alloy (EHEA), notably Al14(CoCrFe)19Ni28, achieving an ultimate tensile strength of 1085 MPa and 24% elongation without heat treatment or extra processing. This demonstrates significantly greater plasticity and equivalent strength compared to the typical as-cast eutectic HEA AlCoCrFeNi2.1. The DSMID framework, combining AAEG and AMSEP, addresses the challenges of small data modeling and extensive candidate screening, contributing to cost reduction and enhanced efficiency of material design. This framework offers a promising avenue for intelligent material design, particularly in scenarios constrained by limited data availability.

The landscape of drug sensitivity and resistance in sarcoma

Sarcomas are rare malignancies with over 100 distinct histological subtypes. Their rarity and heterogeneity pose significant challenges to identifying effective therapies, and approved regimens show varied responses. Novel, personalized approaches to therapy are needed to improve patient outcomes. Patient-derived tumor organoids (PDTOs) model tumor behavior across an array of malignancies. We leverage PDTOs to characterize the landscape of drug resistance and sensitivity in sarcoma, collecting 194 specimens from 126 patients spanning 24 distinct sarcoma subtypes. Our high-throughput organoid screening pipeline tested single agents and combinations, with results available within a week from surgery. Drug sensitivity correlated with clinical features such as tumor subtype, treatment history, and disease trajectory. PDTO screening can facilitate optimal drug selection and mirror patient outcomes in sarcoma. We could identify at least one FDA-approved or NCCN-recommended effective regimen for 59% of the specimens, demonstrating the potential of our pipeline to provide actionable treatment information.

Peer Review of “A Hybrid Pipeline for Covid-19 Screening Incorporating Lungs Segmentation and Wavelet Based Preprocessing of Chest X-Rays (Preprint)”

Peer Review of “A Hybrid Pipeline for Covid-19 Screening Incorporating Lungs Segmentation and Wavelet Based Preprocessing of Chest X-Rays (Preprint)”

Abstract C066: Identifying Transcriptional Drivers of Plasticity in Pancreatic Cancer

Abstract Pancreatic ductal adenocarcinoma (PDAC) remains a deadly disease with few effective treatments. Even with the advent of mutationally-directed therapies targeting the KRAS oncogene, PDAC transcriptional plasticity remains a major mechanism of therapeutic resistance. As a result, there is a desperate need to develop additional strategies to treat this deadly disease. In addition to the canonical genomic alterations in KRAS, TP53, CDKN2A, and SMAD4, PDAC tumors exhibit diverse transcriptional programs, or "cell states," with prognostic implications: PDAC tumors in the “classical state” are more responsive to upfront chemotherapy and have better outcomes, while those in the “basal state” are more aggressive with poorer prognoses. Currently, PDAC cell states are not used to direct therapy. Cell state is an integrative property shaped by both cell-intrinsic (e.g., mutations, epigenetics) and cell-extrinsic (e.g., tumor microenvironment) factors. In our prior work, single-cell analyses of clinical PDAC samples demonstrated notable cell state heterogeneity and plasticity. In addition, longitudinal monitoring of patient-derived organoids showed that cells can shift from classical to basal or coexpressor states as the environment changes, and that these cell states can drastically influence drug response. However, it remains unknown which signaling and transcriptional pathways induce basal or classical states, and whether these gene regulatory networks can be targeted therapeutically. Thus, there is a pressing need to devise scalable methods to determine essential drivers for prognostically relevant cancer cell states.Here, we aim to systematically and unbiasedly identify transcription factors (TFs) that drive basal and classical cell states in PDAC. We have successfully established a high-throughput screening pipeline to 1) over-express all human TF isoforms in a pooled format within a cohort of PDAC models; 2) sort cells using antibodies against state-specific cell surface markers; and 3) perform single-cell RNA sequencing on sorted cells to nominate individual TFs or combinations that induce specific cell state transitions. Preliminary results identify both previously reported (e.g., GATA4) and new TFs that can induce the classical state. By overexpressing TFs individually or in combination, we are able to engineer PDAC cell line models that more faithfully reflect the transcriptional phenotypes observed in patient tumors. Ultimately, we aim to use this approach to construct high-fidelity isogenic but state-variant PDAC models for use both in therapeutic screening and as a substrate for investigating mechanisms governing cancer cell state plasticity. Citation Format: Yuzhou Evelyn Tong, Aswanth Mahalingam, Walaa E Katan, Julia Joung, Alex K Shalek, Peter S Winter, Srivatsan Raghavan. Identifying Transcriptional Drivers of Plasticity in Pancreatic Cancer [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Advances in Pancreatic Cancer Research; 2024 Sep 15-18; Boston, MA. Philadelphia (PA): AACR; Cancer Res 2024;84(17 Suppl_2):Abstract nr C066.

Discovery of novel BfmR inhibitors restoring carbapenem susceptibility against carbapenem-resistant Acinetobacter baumannii by structure-based virtual screening and biological evaluation

ABSTRACT The emergence and spread of Acinetobacter baumannii pose a severe threat to public health, highlighting the urgent need for the next generation of therapeutics due to its increasing resistance to existing antibiotics. BfmR, a response regulator modulating virulence and antimicrobial resistance, shows a promising potential as a novel antimicrobial target. Developing BfmR inhibitors may propel a new therapeutic direction for intractable infection of resistant strains. In this study, we conducted a structure-based hierarchical virtual screening pipeline combining molecular docking, molecular dynamic simulation, and MM/GBSA calculation to sift the Specs chemical library and finally discover three novel potential BfmR inhibitors. The three hits can reduce the MIC of meropenem for the carbapenem-resistant Acinetobacter baumannii (CRAB) strain ZJ06. Similar to the BfmR knockout strain, Cmp-98 was demonstrated to downregulate the expression of K locus genes, indicating it as a BfmR inhibitor. Bacteria underwent harmful morphological changes after treatment with these inhibitors. Molecular dynamic simulations found that all the hits tend to dynamically bind to different positions of the phosphorylation site of BfmR. Wherein we identified a potential inhibitory-binding cleft, beside a possible activated binding cleft at the edge of the phosphorylation site. Restraining the ligand binding poses may help exert inhibitory effects. This study reports a group of new scaffold BfmR inhibitors, offering new insights for novel antibiotic therapeutics against CRAB.

A Drug Discovery Pipeline for MAPK/ERK Pathway Inhibitors in Caenorhabditis elegans.

Many tumors depend on MAPK/ERK signaling to sustain growth, avoid cell death, and metastasize. We show that specific and clinically relevant MAPK/ERK signaling inhibitors can be discovered in vivo with a high-throughput screening pipeline in small animals.

Multitask Learning on Graph Convolutional Residual Neural Networks for Screening of Multitarget Anticancer Compounds.

Recently, various modern experimental screening pipelines and assays have been developed to find promising anticancer drug candidates. However, it is time-consuming and almost infeasible to screen an immense number of compounds for anticancer activity via experimental approaches. To partially address this issue, several computational advances have been proposed. In this study, we present iACP-GCR, a model based on multitask learning on graph convolutional residual neural networks with two types of shortcut connections, to identify multitarget anticancer compounds. In our architecture, the graph convolutional residual neural networks are shared by all the prediction tasks before being separately customized. The NCI-60 data set, one of the most reliable and well-known sources of experimentally verified compounds, was used to develop our model. From that data set, we collected and refined data about compounds screened across nine cancer types (panels), including breast, central nervous system, colon, leukemia, nonsmall cell lung, melanoma, ovarian, prostate, and renal, for model training and evaluation. The model performance evaluated on an independent test set shows that iACP-GCR surpasses the three advanced computational methods for multitask learning. The integration of two shortcut connection types in the shared networks also improves the prediction efficiency. We also deployed the model as a public web server to assist the research community in screening potential anticancer compounds.

In vitro small molecule screening to inform novel candidates for use in fluconazole combination therapy in vivo against Coccidioides.

Developing new drugs, especially for regional orphan diseases, such as Valley Fever, is a slow and costly endeavor. However, there is a wealth of FDA-approved drugs available for repurposing, offering a more economical and expedited approach to improve treatment. Those existing compounds with antifungal properties can become novel therapies with relative ease: a considerable advantage for patients in need of alternative treatment. Despite the scope of remaining tasks, our comprehensive screening of potential candidates has revealed promising combinations for further exploration. This effort outlines a practical pipeline for Valley fever drug screening and identifies viable drug combinations that could impact patients more rapidly than single drug development pathways.

The potential of Chlorella spp. as antiviral source against African swine fever virus through a virtual screening pipeline

African swine fever (ASF) causes high mortality in pigs and threatens global swine production. There is still a lack of therapeutics available, with two vaccines under scrutiny and no approved small-molecule drugs. Eleven (11) viral proteins were used to identify potential antivirals in in silico screening of secondary metabolites (127) from Chlorella spp. The metabolites were screened for affinity and binding selectivity. High-scoring compounds were assessed through in silico ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) predictions, compared to structurally similar drugs, and checked for off-target docking with prepared swine receptors. Molecular dynamics (MD) simulations determined binding stability while binding energy was measured in Molecular Mechanics - Generalized Born Surface Area (MMGBSA) or Poisson-Boltzmann Surface Area (MMPBSA). Only six (6) compounds passed until MD analyses, of which five (5) were stable after 100 ns of MD runs. Of these five compounds, only three had binding affinities that were comparable to or stronger than controls. Specifically, phytosterols 24,25-dihydrolanosterol and CID 4206521 that interact with the RNA capping enzyme (pNP868R), and ergosterol which bound to the Erv-like thioreductase (pB119L). The compounds identified in this study can be used as a theoretical basis for in vitro screening to develop potent antiviral drugs against ASFV.

Identification and Validation of New DNA-PKcs Inhibitors through High-Throughput Virtual Screening and Experimental Verification.

DNA-PKcs is a crucial protein target involved in DNA repair and response pathways, with its abnormal activity closely associated with the occurrence and progression of various cancers. In this study, we employed a deep learning-based screening and molecular dynamics (MD) simulation-based pipeline, identifying eight candidates for DNA-PKcs targets. Subsequent experiments revealed the effective inhibition of DNA-PKcs-mediated cell proliferation by three small molecules (5025-0002, M769-1095, and V008-1080). These molecules exhibited anticancer activity with IC50 (inhibitory concentration at 50%) values of 152.6 μM, 30.71 μM, and 74.84 μM, respectively. Notably, V008-1080 enhanced homology-directed repair (HDR) mediated by CRISPR/Cas9 while inhibiting non-homologous end joining (NHEJ) efficiency. Further investigations into the structure-activity relationships unveiled the binding sites and critical interactions between these small molecules and DNA-PKcs. This is the first application of DeepBindGCN_RG in a real drug screening task, and the successful discovery of a novel DNA-PKcs inhibitor demonstrates its efficiency as a core component in the screening pipeline. Moreover, this study provides important insights for exploring novel anticancer therapeutics and advancing the development of gene editing techniques by targeting DNA-PKcs.

HydraScreen: A Generalizable Structure-Based Deep Learning Approach to Drug Discovery.

We propose HydraScreen, a deep-learning framework for safe and robust accelerated drug discovery. HydraScreen utilizes a state-of-the-art 3D convolutional neural network designed for the effective representation of molecular structures and interactions in protein-ligand binding. We designed an end-to-end pipeline for high-throughput screening and lead optimization, targeting applications in structure-based drug design. We assessed our approach using established public benchmarks based on the CASF-2016 core set, achieving top-tier results in affinity and pose prediction (Pearson's r = 0.86, RMSE = 1.15, Top-1 = 0.95). We introduced a novel approach for interaction profiling, aimed at detecting potential biases within both the model and data sets. This approach not only enhanced interpretability but also reinforced the impartiality of our methodology. Finally, we demonstrated HydraScreen's ability to generalize effectively across novel proteins and ligands through a temporal split. We also provide insights into potential avenues for future development aimed at enhancing the robustness of machine learning scoring functions. HydraScreen (accessible at http://hydrascreen.ro5.ai/paper) provides a user-friendly GUI and a public API, facilitating the easy-access assessment of protein-ligand complexes.

Development of a Crystallographic Screening to Identify Sudan Virus VP40 Ligands.

The matrix protein VP40 of the highly pathogenic Sudan virus (genus Orthoebolavirus) is a multifunctional protein responsible for the recruitment of viral nucleocapsids to the plasma membrane and the budding of infectious virions. In addition to its role in assembly, VP40 also downregulates viral genome replication and transcription. VP40's existence in various homo-oligomeric states is presumed to underpin its diverse functional capabilities during the viral life cycle. Given the absence of licensed therapeutics targeting the Sudan virus, our study focused on inhibiting VP40 dimers, the structural precursors to critical higher-order oligomers, as a novel antiviral strategy. We have established a crystallographic screening pipeline for the identification of small-molecule fragments capable of binding to VP40. Dimeric VP40 of the Sudan virus was recombinantly expressed in bacteria, purified, crystallized, and soaked in a solution of 96 different preselected fragments. Salicylic acid was identified as a crystallographic hit with clear electron density in the pocket between the N- and the C-termini of the VP40 dimer. The binding interaction is predominantly coordinated by amino acid residues leucine 158 (L158) and arginine 214 (R214), which are key in stabilizing salicylic acid within the binding pocket. While salicylic acid displayed minimal impact on the functional aspects of VP40, we delved deeper into characterizing the druggability of the identified binding pocket. We analyzed the influence of residues L158 and R214 on the formation of virus-like particles and viral RNA synthesis. Site-directed mutagenesis of these residues to alanine markedly affected both VP40's budding activity and its effect on viral RNA synthesis, underscoring the potential of the salicylic acid binding pocket as a drug target. In summary, our findings lay the foundation for structure-guided drug design to provide lead compounds against Sudan virus VP40.

Assessment and process optimization of high throughput biofabrication of immunocompetent breast cancer model for drug screening applications

Recent advancements in 3D cancer modeling have significantly enhanced our ability to delve into the intricacies of carcinogenesis. Despite the pharmaceutical industry’s substantial investment of both capital and time in the drug screening and development pipeline, a concerning trend persists: drug candidates screened on conventional cancer models exhibit a dismal success rate in clinical trials. One pivotal factor contributing to this discrepancy is the absence of drug testing on pathophysiologically biomimetic 3D cancer models during pre-clinical stages. Unfortunately, current manual methods of 3D cancer modeling, such as spheroids and organoids, suffer from limitations in reproducibility and scalability. In our study, we have meticulously developed 3D bioprinted breast cancer model utilizing decellularized adipose tissue-based hydrogel obtained via a detergent-free decellularization method. Our innovative printing techniques allows for rapid, high-throughput fabrication of 3D cancer models in a 96-well plate format, demonstrating unmatched scalability and reproducibility. Moreover, we have conducted extensive validation, showcasing the efficacy of our platform through drug screening assays involving two potent anti-cancer drugs, 5-Fluorouracil and PRIMA-1Met. Notably, our platform facilitates effortless imaging and gene expression analysis, streamlining the evaluation process. In a bid to enhance the relevance of our cancer model, we have introduced a heterogeneous cell population into the DAT-based bioink. Through meticulous optimization and characterization, we have successfully developed a biomimetic immunocompetent breast cancer model, complete with microenvironmental cues and diverse cell populations. This breakthrough paves the way for rapid multiplex drug screening and the development of personalized cancer models, marking a paradigm shift in cancer research and pharmaceutical development.

Exploring Biomedical Engineering (BME): Advances within Accelerated Computing and Regenerative Medicine for a Computational and Medical Science Perspective Exploration Analysis

The field of molecular engineering in medicine has made significant strides in recent years, transforming healthcare, diagnostics, and therapy development. However, the COVID-19 pandemic highlighted the ongoing need for further innovative progress and detailed investigation. This research delves into the interdisciplinary domain of biomedical engineering with molecular engineering, examining its impact on the domains of regenerative medicine, biomaterials, tissue engineering, and the acceleration of health science through advanced biotechnologies. The primary objective of this research is to conduct an in-depth exploration of biomaterial applications and their roles in regenerative medicine, along with advancements in tissue engineering, organon-a-chip device mechanics, and the transformative potential of bioprinting in creating functional tissues and organs. This research also includes a case study analysis of drug discovery, immune engineering, precision medicine, and gene editing, with insights into the processing, design, and screening pipelines for biologics, as well as the future role of therapeutics and drugs in healthcare. Throughout this exploration, meaningful discussions with conclusions are drawn regarding the advanced technologies investigated, employing systematic technical computing methods at each step of the research process. The rapid advancements in terms of technological computing have brought about significant growth and transformation in various types of domains of biomedical engineering, particularly in the field of medical science and human health. With the progress in artificial intelligence (AI), computer vision, deep learning, image processing, machine learning there has been a revolutionary change in healthcare, addressing a wide range of medical conditions and human anatomy perspectives. The integration of these immersive technologies has not only improved in the realm of medication and disease control but has also provided solutions for complex tasks and issues related to human anatomy threats within the health sector. This research also focuses on the impact of accelerated computing in biomedical engineering, providing insights into the modern utility of toolsets in Bioinformatics and mechanics with artificial intelligence within medical science and also diving into understanding the human anatomy. Additionally, it explores the concept of functional genomics and its potential to provide insights into future disease and health issues, paving the way for advancements in healthcare for the foreseeable future and beyond.

In Silico Drug Repurposing Uncovered the Antiviral Potential of the Antiparasitic Drug Oxibendazole Against the Chikungunya Virus.

Chikungunya virus (CHIKV) has been reported in over 120 countries and is the causative agent of Chikungunya fever. The debilitating nature of this disease, which can persist months to years after acute infection, drastically impacts the quality of life of patients. Yet, specific antivirals are lacking for the treatment of this disease, which makes the search for new drugs necessary. In this context, the nsP2 protease emerges as an attractive therapeutic target, and drug repurposing strategies have proven to be valuable. Therefore, we combined in silico and in vitro methods to identify known drugs as potential CHIKV nsP2 protease inhibitors with antiviral properties within DrugBank. Herein, we developed a hybrid virtual screening pipeline comprising pharmacophore- and target-based screening, drug-like, and pharmaceutical filtering steps. Six virtual hits were obtained, and two of them, capecitabine (CPB) and oxibendazole (OBZ), were evaluated against CHIKV replication in Vero cells. CPB did not present antiviral activity, whereas OBZ inhibited the replication of two different strains of CHIKV, namely, 181-25 (Asian genotype) and BRA/RJ/18 (clinical isolate from ECSA genotype). OBZ showed potent antiviral activity against the CHIKV BRA/RJ/18 (EC50 = 11.4 μM) with a high selectivity index (>44). Analogs of OBZ (albendazole, fenbendazole, and mebendazole) were also evaluated, but none exhibited anti-CHIKV activity, and further, their stereoelectronic features were analyzed. Additionally, we observed that OBZ acts mainly at post-entry steps. Hence, our results support further in vivo studies to investigate the antiviral potential of OBZ, which offers a new alternative to fight CHIKV infections.

GASP: A Pan-Specific Predictor of Family 1 Glycosyltransferase Acceptor Specificity Enabled by a Pipeline for Substrate Feature Generation and Large-Scale Experimental Screening.

Glycosylation represents a major chemical challenge; while it is one of the most common reactions in Nature, conventional chemistry struggles with stereochemistry, regioselectivity, and solubility issues. In contrast, family 1 glycosyltransferase (GT1) enzymes can glycosylate virtually any given nucleophilic group with perfect control over stereochemistry and regioselectivity. However, the appropriate catalyst for a given reaction needs to be identified among the tens of thousands of available sequences. Here, we present the glycosyltransferase acceptor specificity predictor (GASP) model, a data-driven approach to the identification of reactive GT1:acceptor pairs. We trained a random forest-based acceptor predictor on literature data and validated it on independent in-house generated data on 1001 GT1:acceptor pairs, obtaining an AUROC of 0.79 and a balanced accuracy of 72%. The performance was stable even in the case of completely new GT1s and acceptors not present in the training data set, highlighting the pan-specificity of GASP. Moreover, the model is capable of parsing all known GT1 sequences, as well as all chemicals, the latter through a pipeline for the generation of 153 chemical features for a given molecule taking the CID or SMILES as input (freely available at https://github.com/degnbol/GASP). To investigate the power of GASP, the model prediction probability scores were compared to GT1 substrate conversion yields from a newly published data set, with the top 50% of GASP predictions corresponding to reactions with >50% synthetic yields. The model was also tested in two comparative case studies: glycosylation of the antihelminth drug niclosamide and the plant defensive compound DIBOA. In the first study, the model achieved an 83% hit rate, outperforming a hit rate of 53% from a random selection assay. In the second case study, the hit rate of GASP was 50%, and while being lower than the hit rate of 83% using expert-selected enzymes, it provides a reasonable performance for the cases when an expert opinion is unavailable. The hierarchal importance of the generated chemical features was investigated by negative feature selection, revealing properties related to cyclization and atom hybridization status to be the most important characteristics for accurate prediction. Our study provides a GT1:acceptor predictor which can be trained on other data sets enabled by the automated feature generation pipelines. We also release the new in-house generated data set used for testing of GASP to facilitate the future development of GT1 activity predictors and their robust benchmarking.

Multiplexed CRISPR-Cas9 mutagenesis of rice PSBS1 noncoding sequences for transgene-free overexpression.

Understanding CRISPR-Cas9's capacity to produce native overexpression (OX) alleles would accelerate agronomic gains achievable by gene editing. To generate OX alleles with increased RNA and protein abundance, we leveraged multiplexed CRISPR-Cas9 mutagenesis of noncoding sequences upstream of the rice PSBS1 gene. We isolated 120 gene-edited alleles with varying non-photochemical quenching (NPQ) capacity in vivo-from knockout to overexpression-using a high-throughput screening pipeline. Overexpression increased OsPsbS1 protein abundance two- to threefold, matching fold changes obtained by transgenesis. Increased PsbS protein abundance enhanced NPQ capacity and water-use efficiency. Across our resolved genetic variation, we identify the role of 5'UTR indels and inversions in driving knockout/knockdown and overexpression phenotypes, respectively. Complex structural variants, such as the 252-kb duplication/inversion generated here, evidence the potential of CRISPR-Cas9 to facilitate significant genomic changes with negligible off-target transcriptomic perturbations. Our results may inform future gene-editing strategies for hypermorphic alleles and have advanced the pursuit of gene-edited, non-transgenic rice plants with accelerated relaxation of photoprotection.