Bioactivity Prediction Research Articles

Exploring Tenebrio molitor as a source of low-molecular-weight antimicrobial peptides using a n in silico approach: correlation of molecular features and molecular docking.

Yellow mealworm (Tenebrio molitor) larvae are increasingly recognized as a potential source of bioactive peptides due to their high protein content. Antimicrobial peptides from sustainable sources are a research topic of interest. This study aims to characterize the peptidome of T. molitor flour and an Alcalase-derived hydrolysate, and to explore the potential presence of antimicrobial peptides using in silico analyses, including prediction tools, molecular docking and parameter correlations. T. molitor protein was hydrolysed using Alcalase, resulting in a hydrolysate (TMH10A) with a 10% degree of hydrolysis. The peptidome was analysed using LC-TIMS-MS/MS, yielding over 6000 sequences. These sequences were filtered using the PeptideRanker tool, selecting the top 100 sequences with scores >0.8. Bioactivity predictions indicated that specific peptides, particularly WLNSKGGF and GFIPYEPFLKKMMA, showed significant antimicrobial potential, particularly against bacteria, fungi and viruses. Correlations were found between antifungal activity and physicochemical properties such as net charge, hydrophobicity and isoelectric point. The study identified specific T. molitor-derived peptides with strong predicted antimicrobial activity through in silico analysis. These peptides, particularly WLNSKGGF and GFIPYEPFLKKMMA, might offer potential applications in food safety and healthcare. Further experimental validation is required to confirm their efficacy. © 2024 The Author(s). Journal of the Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Polyene Macrolactams from Marine Micromonospora sp.

Introduction: Three novel macrolactams, FW8-1 (1), FW8-4 (2), and FW60-20 (3), were isolated from a culture of Micromonospora sp. The structures of these compounds were elucidated using Mass Spectrometry (MS) and comprehensive Nuclear Magnetic Resonance (NMR) analyses. Methods: The relative configurations of compounds 1-3 were assigned through theoretical calculations of their NMR spectra. objective: The objective is to obtain PMLs with novel structures and to characterize and evaluate them. Results: The isolation and determination of the relative configurations of these macrolactams have provided fresh perspectives on the biosynthetic pathways, leading to the formation of polyene macrolactams. Conclusion: Further, virtual screening and bioactivity predictions have suggested compounds 1-3 to possess potential anti-tumor, anti-inflammatory, and neuroprotective properties.

Identification of novel salt-enhancing peptides in soy protein and molecular docking studies with transmembrane channel-like 4 (TMC4)

The aim of this study was to rapidly screen novel salt-enhancing peptides from soy protein by virtual screening and molecular docking. Potential salt-enhancing peptides were screened by computerized virtual hydrolysis, bioactivity prediction, toxicity prediction, and water solubility prediction. Sensory evaluation and e-tongue analysis further indicated that the peptides DIF (Asp-Ile-Phe), QPR (Gln-Pro-Arg), MMR (Met-Met-Arg), and DPIY (Asp-Pro-Ile-Tyr) had significant salting enhancing effects. Among them, MMR had the most significant salting effect, replacing at least about 40.35% of NaCl. In addition, a transmembrane channel-like 4 (TMC4) salty receptor model was built, and molecular docking was performed using computational techniques. Glu286, His293, Glu319, and Ser585 were hypothesized to be key binding sites. Molecular dynamics simulations further confirmed the stability of the complex system. This study discovered new salt-enhancing peptides in soy protein and provided a rapid and effective approach for further research in this area.

Application of Ensemble Machine Learning Methods for QSAR Classification of Leukotriene A4 Hydrolase Inhibitors in Drug Discovery

Inflammatory diseases such as asthma, rheumatoid arthritis, and cardiovascular conditions are driven by overproduction of leukotriene B4 (LTB4), a potent inflammatory mediator. Leukotriene A4 hydrolase (LTA4H) plays a critical role in converting leukotriene A4 into LTB4, making it a prime target for drug discovery. Despite ongoing efforts, developing effective LTA4H inhibitors has been challenging due to the complex binding properties of the enzyme and the structural diversity of potential inhibitors. Traditional drug discovery methods, like high-throughput screening (HTS), are often time-consuming and inefficient, prompting the need for more advanced approaches. Quantitative Structure-Activity Relationship (QSAR) modeling, enhanced by ensemble machine learning techniques, provides a promising solution by enabling accurate prediction of compound bioactivity based on molecular descriptors. In this study, six ensemble machine learning methods—AdaBoost, Extra Trees, Gradient Boosting, LightGBM, Random Forest, and XGBoost—were employed to classify LTA4H inhibitors. The dataset, comprising 636 compounds labeled as active or inactive based on pIC50 values, was processed to extract 450 molecular descriptors after feature engineering. The results show that the LightGBM model achieved the highest classification accuracy (83.59%) and Area Under the Curve (AUC) value (0.901), outperforming other models. XGBoost and Random Forest also demonstrated strong performance, with AUC values of 0.890 and 0.895, respectively. The high sensitivity (95.24%) of the XGBoost model highlights its ability to accurately identify active compounds, though it exhibited slightly lower specificity (61.36%), indicating a higher false-positive rate. These findings suggest that ensemble machine learning models, particularly LightGBM, are highly effective in predicting bioactivity, offering valuable tools for early-stage drug discovery. The results indicate that ensemble methods significantly enhance QSAR model accuracy, making them viable for identifying promising LTA4H inhibitors, potentially accelerating the development of anti-inflammatory therapies.

Leveraging multiple data types for improved compound-kinase bioactivity prediction

Machine learning provides efficient ways to map compound-kinase interactions. However, diverse bioactivity data types, including single-dose and multi-dose-response assay results, present challenges. Traditional models utilize only multi-dose data, overlooking information contained in single-dose measurements. Here, we propose a machine learning methodology for compound-kinase activity prediction that leverages both single-dose and dose-response data. We demonstrate that our two-stage approach yields accurate activity predictions and significantly improves model performance compared to training solely on dose-response labels. This superior performance is consistent across five diverse machine learning methods. Using the best performing model, we carried out extensive experimental profiling on a total of 347 selected compound-kinase pairs, achieving a high hit rate of 40% and a negative predictive value of 78%. We show that these rates can be improved further by incorporating model uncertainty estimates into the compound selection process. By integrating multiple activity data types, we demonstrate that our approach holds promise for facilitating the development of training activity datasets in a more efficient and cost-effective way.

Peptidomic profiling of endogenous peptides in the spleens of mouse models of Graves' disease

BackgroundGraves' disease (GD) is a common autoimmune thyroid disorder. The pathogenesis of GD involves an autoimmune response to the A subunit of the human thyrotropin receptor (hTSHR), although the specific mechanisms are not fully elucidated. MethodsThis study established a GD model by immunizing BALB/c mice with a recombinant adenovirus expressing the hTSHR A subunit. Spleen tissues were collected and analyzed using liquid chromatography-tandem mass spectrometry (LC-MS/MS) to identify differentially expressed peptides (DEPs). Gene Ontology (GO) analysis and KEGG pathway analysis were further utilized to annotate the functions of these DEPs. Additionally, peptide bioactivity prediction and molecular docking studies were conducted using Alphafold and Pymol software, respectively, to assess the binding affinity of specific peptides to the hTSHR A subunit. ResultsThe GD mouse model was successfully established, and 1,428 DEPs were identified in the spleen, with 368 upregulated and 1,060 downregulated. Functional analysis indicated that these DEPs are mainly involved in cellular endocytosis, regulation of gene expression, and nucleocytoplasmic transport. Notably, molecular docking studies revealed that the abnormally highly expressed peptide HG2A-24aa demonstrated potential bioactivity and strong binding affinity with hTSHR-289aa. ConclusionThe specific bioactive peptides may play key roles in the pathogenesis of GD, particularly HG2A-24aa, which may have a significant role in the MHC II antigen presentation pathway mediated by the hTSHR A subunit.

G–PLIP: Knowledge graph neural network for structure-free protein–ligand bioactivity prediction

Protein–ligand interactions (PLIs) determine the efficacy and safety profiles of small molecule drugs. Existing methods rely on either structural information or resource-intensive computations to predict PLI, casting doubt on whether it is possible to perform structure-free PLI predictions at low computational cost. Here we show that a light-weight graph neural network (GNN), trained with quantitative PLIs of a small number of proteins and ligands, is able to predict the strength of unseen PLIs. The model has no direct access to structural information about the protein–ligand complexes. Instead, the predictive power is provided by encoding the entire chemical and proteomic space in a single heterogeneous graph, encapsulating primary protein sequence, gene expression, the protein–protein interaction network, and structural similarities between ligands. This novel approach performs competitively with, or better than, structure-aware models. Our results suggest that existing PLI prediction methods may be improved by incorporating representation learning techniques that embed biological and chemical knowledge.

Step Forward Cross Validation for Bioactivity Prediction: Out of Distribution Validation in Drug Discovery.

Recent advances in machine learning methods for materials science have significantly enhanced accurate predictions of the properties of novel materials. Here, we explore whether these advances can be adapted to drug discovery by addressing the problem of prospective validation - the assessment of the performance of a method on out-of-distribution data. First, we tested whether k-fold n-step forward cross-validation could improve the accuracy of out-of-distribution small molecule bioactivity predictions. We found that it is more helpful than conventional random split cross-validation in describing the accuracy of a model in real-world drug discovery settings. We also analyzed discovery yield and novelty error, finding that these two metrics provide an understanding of the applicability domain of models and an assessment of their ability to predict molecules with desirable bioactivity compared to other small molecules. Based on these results, we recommend incorporating a k-fold n-step forward cross-validation and these metrics when building state-of-the-art models for bioactivity prediction in drug discovery.

PepExplainer: An explainable deep learning model for selection-based macrocyclic peptide bioactivity prediction and optimization

Macrocyclic peptides possess unique features, making them highly promising as a drug modality. However, evaluating their bioactivity through wet lab experiments is generally resource-intensive and time-consuming. Despite advancements in artificial intelligence (AI) for bioactivity prediction, challenges remain due to limited data availability and the interpretability issues in deep learning models, often leading to less-than-ideal predictions. To address these challenges, we developed PepExplainer, an explainable graph neural network based on substructure mask explanation (SME). This model excels at deciphering amino acid substructures, translating macrocyclic peptides into detailed molecular graphs at the atomic level, and efficiently handling non-canonical amino acids and complex macrocyclic peptide structures. PepExplainer's effectiveness is enhanced by utilizing the correlation between peptide enrichment data from selection-based focused library and bioactivity data, and employing transfer learning to improve bioactivity predictions of macrocyclic peptides against IL-17C/IL-17 RE interaction. Additionally, PepExplainer underwent further validation for bioactivity prediction using an additional set of thirteen newly synthesized macrocyclic peptides. Moreover, it enabled the optimization of the IC50 of a macrocyclic peptide, reducing it from 15 nM to 5.6 nM based on the contribution score provided by PepExplainer. This achievement underscores PepExplainer's skill in deciphering complex molecular patterns, highlighting its potential to accelerate the discovery and optimization of macrocyclic peptides.

From Deep Learning to the Discovery of Promising VEGFR-2 Inhibitors.

Vascular endothelial growth factor receptor 2 (VEGFR-2) stands as a prominent therapeutic target in oncology, playing a critical role in angiogenesis, tumor growth, and metastasis. FDA-approved VEGFR-2 inhibitors are associated with diverse side effects. Thus, finding novel and more effective inhibitors is of utmost importance. In this study, a deep learning (DL) classification model was first developed and then employed to select putative active VEGFR-2 inhibitors from an in-house chemical library including 187 druglike compounds. A pool of 18 promising candidates was shortlisted and screened against VEGFR-2 by using molecular docking. Finally, two compounds, RHE-334 and EA-11, were prioritized as promising VEGFR-2 inhibitors by employing PLATO, our target fishing and bioactivity prediction platform. Based on this rationale, we prepared RHE-334 and EA-11 and successfully tested their anti-proliferative potential against MCF-7 human breast cancer cells with IC50 values of 26.78±4.02 and 38.73±3.84 μM, respectively. Their toxicities were instead challenged against the WI-38. Interestingly, expression studies indicated that, in the presence of RHE-334, VEGFR-2 was equal to 0.52±0.03, thus comparable to imatinib equal to 0.63±0.03. In conclusion, this workflow based on theoretical and experimental approaches demonstrates effective in identifying VEGFR-2 inhibitors and can be easily adapted to other medicinal chemistry goals.

In silico bioactivity prediction of proteins interacting with graphene-based nanomaterials guides rational design of biosensor

Graphene-based nanomaterials have attracted significant attention for their potentials in biomedical and biotechnology applications in recent years, owing to the outstanding physical and chemical properties. However, the interaction mechanism and impact on biological activity of macro/micro biomolecules still require more concerns and further research in order to enhance their applicability in biosensors, etc. Herein, an integrated method has been developed to predict the protein bioactivity performance when interacting with nanomaterials for protein-based biosensor. Molecular dynamics simulation and molecular docking technique were consolidated to investigate several nanomaterials: C60 fullerene, single-walled carbon nanotube, pristine graphene and graphene oxide, and their effect when interacting with protein. The adsorption behavior, secondary structure changes and protein bioactivity changes were simulated, and the results of protein activity simulation were verified in combination with atomic force spectrum, circular dichroism spectrum fluorescence and electrochemical experiments. The best quantification alignment between bioactivity obtained by simulation and experiment measurements was further explored. The two proteins, RNase A and Exonuclease III, were regarded as analysis model for the proof of concept, and the prediction accuracy of protein bioactivity could reach up to 0.98. The study shows an easy-to-operate and systematic approach to predict the effects of graphene-based nanomaterials on protein bioactivity, which holds guiding significance for the design of protein-related biosensors. In addition, the proposed prediction model is not limited to carbon-based nanomaterials and can be extended to other types of nanomaterials. This facilitates the rapid, simple, and low-cost selection of efficient and biosafe nanomaterials candidates for protein-related applications in biosensing and biomedical systems.

OLB-AC: toward optimizing ligand bioactivities through deep graph learning and activity cliffs.

Deep graph learning (DGL) has been widely employed in the realm of ligand-based virtual screening. Within this field, a key hurdle is the existence of activity cliffs (ACs), where minor chemical alterations can lead to significant changes in bioactivity. In response, several DGL models have been developed to enhance ligand bioactivity prediction in the presence of ACs. Yet, there remains a largely unexplored opportunity within ACs for optimizing ligand bioactivity, making it an area ripe for further investigation. We present a novel approach to simultaneously predict and optimize ligand bioactivities through DGL and ACs (OLB-AC). OLB-AC possesses the capability to optimize ligand molecules located near ACs, providing a direct reference for optimizing ligand bioactivities with the matching of original ligands. To accomplish this, a novel attentive graph reconstruction neural network and ligand optimization scheme are proposed. Attentive graph reconstruction neural network reconstructs original ligands and optimizes them through adversarial representations derived from their bioactivity prediction process. Experimental results on nine drug targets reveal that out of the 667 molecules generated through OLB-AC optimization on datasets comprising 974 low-activity, noninhibitor, or highly toxic ligands, 49 are recognized as known highly active, inhibitor, or nontoxic ligands beyond the datasets' scope. The 27 out of 49 matched molecular pairs generated by OLB-AC reveal novel transformations not present in their training sets. The adversarial representations employed for ligand optimization originate from the gradients of bioactivity predictions. Therefore, we also assess OLB-AC's prediction accuracy across 33 different bioactivity datasets. Results show that OLB-AC achieves the best Pearson correlation coefficient (r2) on 27/33 datasets, with an average improvement of 7.2%-22.9% against the state-of-the-art bioactivity prediction methods. The code and dataset developed in this work are available at github.com/Yueming-Yin/OLB-AC.

Modified five times simulated body fluid for efficient biomimetic mineralization

Simulated body fluid (SBF) is widely utilized in preclinical research for estimating the mineralization efficacy of biomaterials. Therefore, it is of great significance to construct an efficient and stable SBF mineralization system. The conventional SBF solutions cannot maintain a stable pH value and are prone to precipitate homogeneous calcium salts at the early stages of the biomimetic process because of the release of gaseous CO2. In this study, a simple but efficient five times SBF buffered by 5 % CO2 was developed and demonstrated to achieve excellent mineralized microstructure on a type of polymer-aligned nanofibrous scaffolds, which is strikingly similar to the natural human bone tissue. Scanning electron microscopy and energy-dispersive X-ray examinations indicated the growth of heterogeneous apatite with a high-calcium-to-phosphate ratio on the aligned nanofibers under 5 times SBF buffered by 5 % CO2. Moreover, X-ray diffraction spectroscopy and Fourier transform infrared analyses yielded peaks associated with carbonated hydroxyapatite with less prominent crystallization. In addition, the biomineralized aligned polycaprolactone nanofibers demonstrated excellent cell attachment, alignment, and proliferation characteristics in vitro. Overall, the results of this study showed that 5 × SBFs buffered by 5 % CO2 partial pressure are attractive alternatives for the efficient biomineralization of scaffolds in bone tissue engineering, and could be used as a model for the prediction of the bone-bonding bioactivity of biomaterials.

How does a Saccharomyces cerevisiae extract influence the components of isolated rotavirus particles from stool samples collected in a clinical setting from children?

Human Rotavirus (HRV) is the causative pathogen of severe acute enteric infections that cause mortality among children worldwide. This study focuses on developing a new and effective treatment for rotavirus infection using an extract from Saccharomyces cerevisiae, aiming to make this treatment easily accessible to everyone. 15 antigens and 26 antibodies were detected in serum and stool using ELISA. The titers of HRVq1, HRVq2, HRVC1, and HRVC2 on Vero cells were determined to be 1.2x106, 3.0x106, 4.2x106, and 7.5x105 (Plaque forming unit, PFU/ml) four days after infection, respectively. The HRVq1 isolate induced cytopathic effects, i.e., forming multinucleated, rounded, enlarged, and expanding gigantic cells. RT-PCR identified this isolate, and the accession number 2691714 was assigned to GeneBank. The molecular docking analysis revealed that nonstructural proteins (NSPs) NSP1, NSP2, NSP3, NSP4, NSP5, and NSP6 exhibited significant binding with RNA. NSP2 demonstrated the highest binding affinity and the lowest binding energy (−8.9 kcal/mol). This affinity was maintained via hydrophobic interactions and hydrogen bonds spanning in length from 1.12 Å to 3.11 Å. The ADMET and bioactivity predictions indicated that the yeast extract possessed ideal solubility, was nontoxic, and did not cause cancer. The inhibitory constant values predicted for the S. cerevisiae extract in the presence of HRV vital proteins varied from 5.32 to 7.45 mM, indicating its potential as a viable drug candidate. Saccharomyces cerevisiae extract could be utilized as a dietary supplement to combat HRV as an alternative dietary supplement.

Quantifying the Hardness of Bioactivity Prediction Tasks for Transfer Learning.

Today, machine learning methods are widely employed in drug discovery. However, the chronic lack of data continues to hamper their further development, validation, and application. Several modern strategies aim to mitigate the challenges associated with data scarcity by learning from data on related tasks. These knowledge-sharing approaches encompass transfer learning, multitask learning, and meta-learning. A key question remaining to be answered for these approaches is about the extent to which their performance can benefit from the relatedness of available source (training) tasks; in other words, how difficult ("hard") a test task is to a model, given the available source tasks. This study introduces a new method for quantifying and predicting the hardness of a bioactivity prediction task based on its relation to the available training tasks. The approach involves the generation of protein and chemical representations and the calculation of distances between the bioactivity prediction task and the available training tasks. In the example of meta-learning on the FS-Mol data set, we demonstrate that the proposed task hardness metric is inversely correlated with performance (Pearson's correlation coefficient r = -0.72). The metric will be useful in estimating the task-specific gain in performance that can be achieved through meta-learning.

GraphEGFR: Multi-task and transfer learning based on molecular graph attention mechanism and fingerprints improving inhibitor bioactivity prediction for EGFR family proteins on data scarcity.

The proteins within the human epidermal growth factor receptor (EGFR) family, members of the tyrosine kinase receptor family, play a pivotal role in the molecular mechanisms driving the development of various tumors. Tyrosine kinase inhibitors, key compounds in targeted therapy, encounter challenges in cancer treatment due to emerging drug resistance mutations. Consequently, machine learning has undergone significant evolution to address the challenges of cancer drug discovery related to EGFR family proteins. However, the application of deep learning in this area is hindered by inherent difficulties associated with small-scale data, particularly the risk of overfitting. Moreover, the design of a model architecture that facilitates learning through multi-task and transfer learning, coupled with appropriate molecular representation, poses substantial challenges. In this study, we introduce GraphEGFR, a deep learning regression model designed to enhance molecular representation and model architecture for predicting the bioactivity of inhibitors against both wild-type and mutant EGFR family proteins. GraphEGFR integrates a graph attention mechanism for molecular graphs with deep and convolutional neural networks for molecular fingerprints. We observed that GraphEGFR models employing multi-task and transfer learning strategies generally achieve predictive performance comparable to existing competitive methods. The integration of molecular graphs and fingerprints adeptly captures relationships between atoms and enables both global and local pattern recognition. We further validated potential multi-targeted inhibitors for wild-type and mutant HER1 kinases, exploring key amino acid residues through molecular dynamics simulations to understand molecular interactions. This predictive model offers a robust strategy that could significantly contribute to overcoming the challenges of developing deep learning models for drug discovery with limited data and exploring new frontiers in multi-targeted kinase drug discovery for EGFR family proteins.

Unveiling the antibreast cancer mechanism of Euphorbia hirta ethanol extract: computational and experimental study

Breast cancer, the most prevalent cancer in women globally, is characterized by a low survival rate. Euphorbia hirta is predicted to exhibit promising antibreast cancer properties. This study aimed to explore the active compounds present in the ethanol extract of E. hirta and elucidate their mechanism for countering breast cancer using computational and experimental methodologies. The active components of the E. hirta ethanol extract were determined using Liquid chromatography high-resolution mass spectrometry. Furthermore, the identified active compounds were subjected to computational analysis involving drug-likeness screening, membrane permeability, bioactivity, toxicity assessment and protein target prediction using QSAR principles followed by molecular docking and molecular dynamics simulations. In vitro experimental investigations included toxicity, rhodamine, apoptosis, cell migration and colony formation assays. These findings indicated that six compounds with drug-like properties and physicochemical features exhibited bioactivity relevant to breast cancer. These compounds, namely, quercetin, luteolin, gallic acid, gentisic acid, quinic acid and caffeic acid, target proteins associated with breast cancer progression, including EGFR, KDR, SRC, FASN, CDK4 and ERBB2. According to molecular docking and dynamics studies, these active compounds bind securely, potentially inhibiting their target protein activity. The ethanol extract of E. hirta was toxic and selective for T47D cells. The extract induced apoptosis and loss of mitochondrial membrane potential in T47D cells, restraining their migration and colony formation. The research findings demonstrate that the extract of E. hirta effectively antagonizes breast cancer by inducing apoptosis, suppressing cellular migration, and inhibiting cell colony formation through the targeted modulation of associated proteins.

Species-level distribution of microbiota with secondary metabolic potential in Chinese Baijiu fermentation

Chinese Baijiu fermentation is a typical spontaneous fermentation with complex microbial community. However, the species-level distribution of microbiota with secondary metabolic potential in Baijiu fermentation has not been well studied so far. In this study, taking soy sauce aroma type Baijiu and light aroma type Baijiu fermentations as examples, we identified 1575 biosynthetic gene clusters (BGCs) belonging to 874 gene cluster families (GCFs) through metagenomic analysis. Bioactivity prediction analysis revealed 210 BGCs producing potential bioactive secondary metabolites (probabilities of bioactivities ≥70%). We recovered 66 bacterial metagenome-assembled genomes (MAGs) to explore distribution of bioactive secondary metabolites at a higher resolution taxonomic level. A total of 16 MAGs were identified as BGC-rich MAGs (>3 BGCs), and they belonged to 11 genera. Four MAGs, annotated to be Bacillus velezensis, Bacillus licheniformis, Kroppenstedtia eburnea and Kroppenstedtia spp., contained more than 3 BGC-producing potential bioactive secondary metabolites and had more than 1 counts per million (CPM) abundance in fermentations. They were identified as the potential producers of bioactive secondary metabolites. This study contributed to characterising the diversity and distribution of microbiota with secondary metabolic potential in Baijiu fermentation, and mining novel secondary metabolites and their producers.

Cell Painting-based bioactivity prediction boosts high-throughput screening hit-rates and compound diversity

Identifying active compounds for a target is a time- and resource-intensive task in early drug discovery. Accurate bioactivity prediction using morphological profiles could streamline the process, enabling smaller, more focused compound screens. We investigate the potential of deep learning on unrefined single-concentration activity readouts and Cell Painting data, to predict compound activity across 140 diverse assays. We observe an average ROC-AUC of 0.744 ± 0.108 with 62% of assays achieving ≥0.7, 30% ≥0.8, and 7% ≥0.9. In many cases, the high prediction performance can be achieved using only brightfield images instead of multichannel fluorescence images. A comprehensive analysis shows that Cell Painting-based bioactivity prediction is robust across assay types, technologies, and target classes, with cell-based assays and kinase targets being particularly well-suited for prediction. Experimental validation confirms the enrichment of active compounds. Our findings indicate that models trained on Cell Painting data, combined with a small set of single-concentration data points, can reliably predict the activity of a compound library across diverse targets and assays while maintaining high hit rates and scaffold diversity. This approach has the potential to reduce the size of screening campaigns, saving time and resources, and enabling primary screening with more complex assays.

Benchmarking docking, density functional theory and molecular dynamics studies to assess the aldose reductase inhibitory potential of Trigonella foenum-graecum compounds for managing diabetes-associated complications

Inhibition of aldose reductase (AR) could be a beneficial strategy for managing diabetes-associated complications. Trigonella foenum-graecum (TFG) is used around the globe as a traditional medicine for the management of diabetes. Our study aimed to assess the potential of TFG phytocompounds as inhibitors of AR in the context of diabetes-related complications. Our research work employed molecular docking, density functional theory (DFT) and molecular dynamics (MD) to evaluate the efficacy of TFG compounds. The study compared the predictive power of AutoDock and AutoDock Vina docking software and found that AutoDock Vina performs better in ranking and discriminating actives and decoys. The research identified five compounds as potential AR inhibitors from fifty-eight reported TFG phytoconstituents. Tigogenin and Gitogenin stood out as the most promising AR inhibitors. The electronic properties of the compounds were analysed through DFT studies and provided insights into their binding potential. Finally, the results of MD simulations indicated that Tigogenin and Gitogenin bound robustly with AR throughout the simulation period. This study predicted the AR inhibitory potential of TFG compounds for managing diabetes-associated complications and supports further drug development from TFG. The benchmarking approach used in this study improves the accuracy and dependability of bioactivity prediction.