Three million images and morphological profiles of cells treated with matched chemical and genetic perturbations.

The identification of genetic and chemical perturbations with similar impacts on cell morphology can elucidate compounds' mechanisms of action or novel regulators of genetic pathways. Research on methods for identifying such similarities has lagged due to a lack of carefully designed and well-annotated image sets of cells treated with chemical and genetic perturbations. Here we create such a Resource dataset, CPJUMP1, in which each perturbed gene's product is a known target of at least two chemical compounds in the dataset. We systematically explore the directionality of correlations among perturbations that target the same protein encoded by a given gene, and we find that identifying matches between chemical and genetic perturbations is a challenging task. Our dataset and baseline analyses provide a benchmark for evaluating methods that measure perturbation similarities and impact, and more generally, learn effective representations of cellular state from microscopy images. Such advancements would accelerate the applications of image-based profiling of cellular states, such as uncovering drug mode of action or probing functional genomics.

AIDDISON: Empowering Drug Discovery with AI/ML and CADD Tools in a Secure, Web-Based SaaS Platform.

The widespread proliferation of artificial intelligence (AI) and machine learning (ML) methods has a profound effect on the drug discovery process. However, many scientists are reluctant to utilize these powerful tools due to the steep learning curve typically associated with them. AIDDISON offers a convenient, secure, web-based platform for drug discovery, addressing the reluctance of scientists to adopt AI and ML methods due to the steep learning curve. By seamlessly integrating generative models, ADMET property predictions, searches in vast chemical spaces, and molecular docking, AIDDISON provides a sophisticated platform for modern drug discovery. It enables less computer-savvy scientists to utilize these powerful tools in their daily activities, as demonstrated by an example of identifying a valuable set of molecules for lead optimization. With AIDDISON, the benefits of AI/ML in drug discovery are accessible to all.

3D zero-echo time and 3D T1-weighted gradient-echo MRI sequences as an alternative to CT for the evaluation of the lumbar facet joints and lumbosacral transitional vertebrae.

BACKGROUND: Computed tomography (CT) is the reference standard for assessment of the bone. Magnetic resonance imaging (MRI) developments enable a CT-like visualization of the osseous structures. PURPOSE: To assess the diagnostic performance of 3D zero-echo time (3D-ZTE) and 3D T1-weighted gradient-echo (3D-T1GRE) MRI sequences for the evaluation of lumbar facet joints (LFJs) and the detection of lumbosacral transitional vertebrae (LSTV) using CT as the reference standard. MATERIAL AND METHODS: In total, 87 adult patients were included in this prospective study. Evaluation of degenerative changes of the facet joints at the L3/L4, L4/L5, and L5/S1 levels on both sides was performed by two readers using a 4-point Likert scale. LSTV were classified according to Castelvi et al. Image quality was quantitatively measured using the signal-to-noise (SNR) and contrast-to-noise (CNR) ratios. Intra-reader, inter-reader, and inter-modality reliability were calculated using Cohen's kappa statistic. RESULTS: Intra-reader agreement for 3D-ZTE, 3D-T1GRE, and CT was 0.607, 0.751, and 0.856 and inter-reader agreement was 0.535, 0.563, and 0.599, respectively. The inter-modality agreement between 3D-ZTE and CT was 0.631 and between 3D-T1GRE and CT 0.665. A total of LSTV were identified in both MR sequences with overall comparable accuracy compared to CT. Mean SNR for bone, muscle, and fat was highest for 3D-T1GRE and mean CNR was highest for CT. CONCLUSION: 3D-ZTE and 3D-T1GRE MRI sequences can assess the LFJs and LSTV and may serve as potential alternatives to CT.

Patient-Derived Organoids of Cholangiocarcinoma.

Cholangiocarcinoma (CC) is an aggressive malignancy with an inferior prognosis due to limited systemic treatment options. As preclinical models such as CC cell lines are extremely rare, this manuscript reports a protocol of cholangiocarcinoma patient-derived organoid culture as well as a protocol for the transition of 3D organoid lines to 2D cell lines. Tissue samples of non-cancer bile duct and cholangiocarcinoma were obtained during surgical resection. Organoid lines were generated following a standardized protocol. 2D cell lines were generated from established organoid lines following a novel protocol. Subcutaneous and orthotopic patient-derived xenografts were generated from CC organoid lines, histologically examined, and treated using standard CC protocols. Therapeutic responses of organoids and 2D cell lines were examined using standard CC agents. Next-generation exome and RNA sequencing was performed on primary tumors and CC organoid lines. Patient-derived organoids closely recapitulated the original features of the primary tumors on multiple levels. Treatment experiments demonstrated that patient-derived organoids of cholangiocarcinoma and organoid-derived xenografts can be used for the evaluation of novel treatments and may therefore be used in personalized oncology approaches. In summary, this study establishes cholangiocarcinoma organoids and organoid-derived cell lines, thus expanding translational research resources of cholangiocarcinoma.

Degradation of micropollutant cephalexin by ultraviolet (UV) and assessment of residual antimicrobial activity of transformation products.

Cephalexin (CEX) is an antibiotic commonly used to treat bacterial infections in humans and animals. However, it is also a micropollutant. Thus, this study evaluated the degradation of CEX using ultraviolet irradiation (UV-C) and analyzed the by-products as well as their residual antimicrobial activity. A reactor with a mercury vapor lamp was used for the degradation. Irradiated CEX solutions were collected over a period of 4 hours and analyzed using high-performance liquid chromatography coupled with mass spectrometry. For the residual antimicrobial activity the susceptibility test was performed using Staphylococcus aureus and Escherichia coli microorganisms by broth microdilution. It was found that CEX, after treatment, generated a metabolite with a mass of 150 m/z in 15 min. A four- and eightfold increase in the minimum inhibitory concentration of the drug against S. aureus and E. coli could be observed, respectively, after 20 min. Therefore, this treatment proved to be effective in the degradation of CEX, being able to degrade 81% of the initial molecule of the drug in 20 min. Furthermore, the antimicrobial activity of the CEX solution decreased as the irradiation time increased, indicating loss of antimicrobial function of the initial CEX molecule and the resulting by-products.

Large-Scale Assessment of Binding Free Energy Calculations in Active Drug Discovery Projects.

Accurate ranking of compounds with regards to their binding affinity to a protein using computational methods is of great interest to pharmaceutical research. Physics-based free energy calculations are regarded as the most rigorous way to estimate binding affinity. In recent years, many retrospective studies carried out both in academia and industry have demonstrated its potential. Here, we present the results of large-scale prospective application of the FEP+ method in active drug discovery projects in an industry setting at Merck KGaA, Darmstadt, Germany. We compare these prospective data to results obtained on a new diverse, public benchmark of eight pharmaceutically relevant targets. Our results offer insights into the challenges faced when using free energy calculations in real-life drug discovery projects and identify limitations that could be tackled by future method development. The new public data set we provide to the community can support further method development and comparative benchmarking of free energy calculations.

Relative binding affinity prediction of farnesoid X receptor in the D3R Grand Challenge 2 using FEP.

Physics-based free energy simulations have increasingly become an important tool for predicting binding affinity and the recent introduction of automated protocols has also paved the way towards a more widespread use in the pharmaceutical industry. The D3R 2016 Grand Challenge 2 provided an opportunity to blindly test the commercial free energy calculation protocol FEP+ and assess its performance relative to other affinity prediction methods. The present D3R free energy prediction challenge was built around two experimental data sets involving inhibitors of farnesoid X receptor (FXR) which is a promising anticancer drug target. The FXR binding site is predominantly hydrophobic with few conserved interaction motifs and strong induced fit effects making it a challenging target for molecular modeling and drug design. For both data sets, we achieved reasonable prediction accuracy (RMSD ≈ 1.4 kcal/mol, rank 3-4 according to RMSD out of 20 submissions) comparable to that of state-of-the-art methods in the field. Our D3R results boosted our confidence in the method and strengthen our desire to expand its applications in future in-house drug design projects.

Assessment of selenium bioaccumulation in lactic acid bacteria.

Selenium is an essential micronutrient for living beings, as it helps to maintain the normal physiological functions of the organism. The numerous discoveries involving the importance of this element to the health of human beings have fostered interest in research to develop enriched and functional foods. The present study evaluated the potential for bacterial strains of Enterococcus faecalis (CH121 and CH124), Lactobacillus parabuchneri (ML4), Lactobacillus paracasei (ML13, ML33, CH135, and CH139), and Lactobacillus plantarum (CH131) to bioaccumulate Se in their biomass by adding different concentrations of sodium selenite (30 to 200 mg/L) to the culture medium. Quantification of Se with UV and visible molecular absorption spectroscopy showed that the investigated bacteria were able to bioaccumulate this micromineral into their biomass. Two of the L. paracasei strains (ML13 and CH135) bioaccumulated the highest Se concentrations (38.1 ± 1.7 mg/g and 40.7 ± 1.1 mg/g, respectively) after culture in the presence of 150 mg/L of Se. This bioaccumulation potential has applications in the development of dairy products and may be an alternative Se source in the diets of humans and other animals.

Making variability less variable: matching expression system and host for oxygenase-based biotransformations.

Variability in whole-cell biocatalyst performance represents a critical aspect for stable and productive bioprocessing. In order to investigate whether and how oxygenase-catalyzed reactions are affected by such variability issues in solvent-tolerant Pseudomonas, different inducers, expression systems, and host strains were tested for the reproducibility of xylene and styrene monooxygenase catalyzed hydroxylation and epoxidation reactions, respectively. Significantly higher activity variations were found for biocatalysts based on solvent-tolerant Pseudomonas putida DOT-TIE and S12 compared with solvent-sensitive P. putida KT2440, Escherichia coli JM101, and solvent-tolerant Pseudomonas taiwanensis VLB120. Specific styrene epoxidation rates corresponded to cellular styrene monooxygenase contents. Detected variations in activity strictly depended on the type of regulatory system employed, being high with the alk- and low with the lac-system. These results show that the occurrence of clonal variability in recombinant gene expression in Pseudomonas depends on the combination of regulatory system and host strain, does not correlate with a general phenotype such as solvent tolerance, and must be evaluated case by case.

Machine Learning Assisted Hit Prioritization for High Throughput Screening in Drug Discovery.

Efficient prioritization of bioactive compounds from high throughput screening campaigns is a fundamental challenge for accelerating drug development efforts. In this study, we present the first data-driven approach to simultaneously detect assay interferents and prioritize true bioactive compounds. By analyzing the learning dynamics during training of a gradient boosting model on noisy high throughput screening data using a novel formulation of sample influence, we are able to distinguish between compounds exhibiting the desired biological response and those producing assay artifacts. Therefore, our method enables false positive and true positive detection without relying on prior screens or assay interference mechanisms, making it applicable to any high throughput screening campaign. We demonstrate that our approach consistently excludes assay interferents with different mechanisms and prioritizes biologically relevant compounds more efficiently than all tested baselines, including a retrospective case study simulating its use in a real drug discovery campaign. Finally, our tool is extremely computationally efficient, requiring less than 30 s per assay on low-resource hardware. As such, our findings show that our method is an ideal addition to existing false positive detection tools and can be used to guide further pharmacological optimization after high throughput screening campaigns.

Predicting enzymatic function from global binding site descriptors.

Due to the rising number of solved protein structures, computer-based techniques for automatic protein functional annotation and classification into families are of high scientific interest. DoGSiteScorer automatically calculates global descriptors for self-predicted pockets based on the 3D structure of a protein. Protein function predictors on three levels with increasing granularity are built by use of a support vector machine (SVM), based on descriptors of 26632 pockets from enzymes with known structure and enzyme classification. The SVM models represent a generalization of the available descriptor space for each enzyme class, subclass, and substrate-specific sub-subclass. Cross-validation studies show accuracies of 68.2% for predicting the correct main class and accuracies between 62.8% and 80.9% for the six subclasses. Substrate-specific recall rates for a kinase subset are 53.8%. Furthermore, application studies show the ability of the method for predicting the function of unknown proteins and gaining valuable information for the function prediction field.

DoGSiteScorer: a web server for automatic binding site prediction, analysis and druggability assessment.

MOTIVATION: Many drug discovery projects fail because the underlying target is finally found to be undruggable. Progress in structure elucidation of proteins now opens up a route to automatic structure-based target assessment. DoGSiteScorer is a newly developed automatic tool combining pocket prediction, characterization and druggability estimation and is now available through a web server. AVAILABILITY: The DoGSiteScorer web server is freely available for academic use at http://dogsite.zbh.uni-hamburg.de CONTACT: rarey@zbh.uni-hamburg.de.

Practical guidelines for the use of gradient boosting for molecular property prediction.

Decision tree ensembles are among the most robust, high-performing and computationally efficient machine learning approaches for quantitative structure-activity relationship (QSAR) modeling. Among them, gradient boosting has recently garnered particular attention, for its performance in data science competitions, virtual screening campaigns, and bioactivity prediction. However, different variants of gradient boosting exist, the most popular being XGBoost, LightGBM and CatBoost. Our study provides the first comprehensive comparison of these approaches for QSAR. To this end, we trained 157,590 gradient boosting models, which were evaluated on 16 datasets and 94 endpoints, comprising 1.4 million compounds in total. Our results show that XGBoost generally achieves the best predictive performance, while LightGBM requires the least training time, especially for larger datasets. In terms of feature importance, the models surprisingly rank molecular features differently, reflecting differences in regularization techniques and decision tree structures. Thus, expert knowledge must always be employed when evaluating data-driven explanations of bioactivity. Furthermore, our results show that the relevance of each hyperparameter varies greatly across datasets and that it is crucial to optimize as many hyperparameters as possible to maximize the predictive performance. In conclusion, our study provides the first set of guidelines for cheminformatics practitioners to effectively train, optimize and evaluate gradient boosting models for virtual screening and QSAR applications.

SUMO: In Silico Sequence Assessment Using Multiple Optimization Parameters.

To select the most promising screening hits from antibody and VHH display campaigns for subsequent in-depth profiling and optimization, it is highly desirable to assess and select sequences on properties beyond only their binding signals from the sorting process. In addition, developability risk criteria, sequence diversity, and the anticipated complexity for sequence optimization are relevant attributes for hit selection and optimization. Here, we describe an approach for the in silico developability assessment of antibody and VHH sequences. This method not only allows for ranking and filtering multiple sequences with regard to their predicted developability properties and diversity, but also visualizes relevant sequence and structural features of potentially problematic regions and thereby provides rationales and starting points for multi-parameter sequence optimization.

Longitudinal data on humoral response and neutralizing antibodies against SARS-CoV-2 Omicron BA.1 and subvariants BA.4/5 and BQ.1.1 after COVID-19 vaccination in cancer patients.

PURPOSE: The SARS-CoV-2 Omicron variant of concern (VOC) and subvariants like BQ.1.1 demonstrate immune evasive potential. Little is known about the efficacy of booster vaccinations regarding this VOC and subvariants in cancer patients. This study is among the first to provide data on neutralizing antibodies (nAb) against BQ.1.1. METHODS: Cancer patients at our center were prospectively enrolled between 01/2021 and 02/2022. Medical data and blood samples were collected at enrollment and before and after every SARS-CoV-2 vaccination, at 3 and 6 months. RESULTS: We analyzed 408 samples from 148 patients (41% female), mainly with solid tumors (85%) on active therapy (92%; 80% chemotherapy). SARS-CoV-2 IgG and nAb titers decreased over time, however, significantly increased following third vaccination (p < 0.0001). NAb (ND50) against Omicron BA.1 was minimal prior and increased significantly after the third vaccination (p < 0.0001). ND50 titers against BQ.1.1 after the third vaccination were significantly lower than against BA.1 and BA.4/5 (p < 0.0001) and undetectable in half of the patients (48%). Factors associated with impaired immune response were hematologic malignancies, B cell depleting therapy and higher age. Choice of vaccine, sex and treatment with chemo-/immunotherapy did not influence antibody response. Patients with breakthrough infections had significantly lower nAb titers after both 6 months (p < 0.001) and the third vaccination (p = 0.018). CONCLUSION: We present the first data on nAb against BQ.1.1 following the third vaccination in cancer patients. Our results highlight the threat that new emerging SARS-CoV-2 variants pose to cancer patients and support efforts to apply repeated vaccines. Since a considerable number of patients did not display an adequate immune response, continuing to exhibit caution remains reasonable.

Resting cells of recombinant E. coli show high epoxidation yields on energy source and high sensitivity to product inhibition.

Metabolically active resting (i.e., nongrowing) bacterial cells have a high potential in cofactor-dependent redox biotransformations. Where growing cells require carbon and energy for biomass production, resting cells can potentially exploit their metabolism more efficiently for redox biocatalysis allowing higher specific activities and product yields on energy source. Here, the potential of resting recombinant E. coli containing the styrene monooxygenase StyAB was investigated for enantioselective styrene epoxidation in a two-liquid phase setup. Resting cells indeed showed twofold higher specific activities as compared to growing cells in a similar setup. However, product formation rates decreased steadily resulting in lower final product concentrations. The low intrinsic stability of the reductase component StyB was found to limit overall biocatalyst stability. Such limitation by enzyme stability was overcome by increasing intracellular StyB levels. Beyond that, product inhibition was identified as a limiting factor, whereas complete toxification of the bacterial cells, as it was observed with growing cells, and deactivation of the multicomponent enzyme system did not occur. The resting cell setup allowed high product yields on glucose of more than 5 mol mol(glucose)(-1), which makes the use of resting cells a promising approach for ecologically as well as economically sustainable oxygenase-based whole-cell biocatalysis.

Combining global and local measures for structure-based druggability predictions.

Predicting druggability and prioritizing certain disease modifying targets for the drug development process is of high practical relevance in pharmaceutical research. DoGSiteScorer is a fully automatic algorithm for pocket and druggability prediction. Besides consideration of global properties of the pocket, also local similarities shared between pockets are reflected. Druggability scores are predicted by means of a support vector machine (SVM), trained, and tested on the druggability data set (DD) and its nonredundant version (NRDD). The DD consists of 1069 targets with assigned druggable, difficult, and undruggable classes. In 90% of the NRDD, the SVM model based on global descriptors correctly classifies a target as either druggable or undruggable. Nevertheless, global properties suffer from binding site changes due to ligand binding and from the pocket boundary definition. Therefore, local pocket properties are additionally investigated in terms of a nearest neighbor search. Local similarities are described by distance dependent histograms between atom pairs. In 88% of the DD pocket set, the nearest neighbor and the structure itself conform with their druggability type. A discriminant feature between druggable and undruggable pockets is having less short-range hydrophilic-hydrophilic pairs and more short-range lipophilic-lipophilic pairs. Our findings for global pocket descriptors coincide with previously published methods affirming that size, shape, and hydrophobicity are important global pocket descriptors for automatic druggability prediction. Nevertheless, the variety of pocket shapes and their flexibility upon ligand binding limit the automatic projection of druggable features onto descriptors. Incorporating local pocket properties is another step toward a reliable descriptor-based druggability prediction.

Production host selection for asymmetric styrene epoxidation: Escherichia coli vs. solvent-tolerant Pseudomonas.

Selection of the ideal microbe is crucial for whole-cell biotransformations, especially if the target reaction intensively interacts with host cell functions. Asymmetric styrene epoxidation is an example of a reaction which is strongly dependent on the host cell owing to its requirement for efficient cofactor regeneration and stable expression of the styrene monooxygenase genes styAB. On the other hand, styrene epoxidation affects the whole-cell biocatalyst, because it involves toxic substrate and products besides the burden of additional (recombinant) enzyme synthesis. With the aim to compare two fundamentally different strain engineering strategies, asymmetric styrene epoxidation by StyAB was investigated using the engineered wild-type strain Pseudomonas sp. strain VLB120ΔC, a styrene oxide isomerase (StyC) knockout strain able to accumulate (S)-styrene oxide, and recombinant E. coli JM101 carrying styAB on the plasmid pSPZ10. Their performance was analyzed during fed-batch cultivation in two-liquid phase biotransformations with respect to specific activity, volumetric productivity, product titer, tolerance of toxic substrate and products, by-product formation, and product yield on glucose. Thereby, Pseudomonas sp. strain VLB120ΔC proved its great potential by tolerating high styrene oxide concentrations and by the absence of by-product formation. The E. coli-based catalyst, however, showed higher specific activities and better yields on glucose. The results not only show the importance but also the complexity of host cell selection and engineering. Finding the optimal strain engineering strategy requires profound understanding of bioprocess and biocatalyst operation. In this respect, a possible negative influence of solvent tolerance on yield and activity is discussed.

Tuning gradient boosting for imbalanced bioassay modelling with custom loss functions.

While in the last years there has been a dramatic increase in the number of available bioassay datasets, many of them suffer from extremely imbalanced distribution between active and inactive compounds. Thus, there is an urgent need for novel approaches to tackle class imbalance in drug discovery. Inspired by recent advances in computer vision, we investigated a panel of alternative loss functions for imbalanced classification in the context of Gradient Boosting and benchmarked them on six datasets from public and proprietary sources, for a total of 42 tasks and 2 million compounds. Our findings show that with these modifications, we achieve statistically significant improvements over the conventional cross-entropy loss function on five out of six datasets. Furthermore, by employing these bespoke loss functions we are able to push Gradient Boosting to match or outperform a wide variety of previously reported classifiers and neural networks. We also investigate the impact of changing the loss function on training time and find that it increases convergence speed up to 8 times faster. As such, these results show that tuning the loss function for Gradient Boosting is a straightforward and computationally efficient method to achieve state-of-the-art performance on imbalanced bioassay datasets without compromising on interpretability and scalability.