Evaluation of AlphaFold2 Structures for Hit Identification across Multiple Scenarios.

The introduction of AlphaFold2 (AF2) has sparked significant enthusiasm and generated extensive discussion within the scientific community, particularly among drug discovery researchers. Although previous studies have addressed the performance of AF2 structures in virtual screening (VS), a more comprehensive investigation is still necessary considering the paramount importance of structural accuracy in drug design. In this study, we evaluate the performance of AF2 structures in VS across three common drug discovery scenarios: targets with holo, apo, and AF2 structures; targets with only apo and AF2 structures; and targets exclusively with AF2 structures. We utilized both the traditional physics-based Glide and the deep-learning-based scoring function RTMscore to rank the compounds in the DUD-E, DEKOIS 2.0, and DECOY data sets. The results demonstrate that, overall, the performance of VS on AF2 structures is comparable to that on apo structures but notably inferior to that on holo structures across diverse scenarios. Moreover, when a target has solely AF2 structure, selecting the holo structure of the target from different subtypes within the same protein family produces comparable results with the AF2 structure for VS on the data set of the AF2 structures, and significantly better results than the AF2 structures on its own data set. This indicates that utilizing AF2 structures for docking-based VS may not yield most satisfactory outcomes, even when solely AF2 structures are available. Moreover, we rule out the possibility that the variations in VS performance between the binding pockets of AF2 and holo structures arise from the differences in their biological assembly composition.

Artificial intelligence methods in kinase target profiling: Advances and challenges.

Kinases have a crucial role in regulating almost the full range of cellular processes, making them essential targets for therapeutic interventions against various diseases. Accurate kinase-profiling prediction is vital for addressing the selectivity/specificity challenges in kinase drug discovery, which is closely related to lead optimization, drug repurposing, and the understanding of potential drug side effects. In this review, we provide an overview of the latest advancements in machine learning (ML)-based and deep learning (DL)-based quantitative structure-activity relationship (QSAR) models for kinase profiling. We highlight current trends in this rapidly evolving field and discuss the existing challenges and future directions regarding experimental data set construction and model architecture design. Our aim is to offer practical insights and guidance for the development and utilization of these approaches.

Sigmoid Accelerated Molecular Dynamics: An Efficient Enhanced Sampling Method for Biosystems.

Gaussian accelerated molecular dynamics (GaMD) is recognized as a popular enhanced sampling method for tackling long-standing challenges in biomolecular simulations. Inspired by GaMD, Sigmoid accelerated molecular dynamics (SaMD) is proposed in this work by adding a Sigmoid boost potential to improve the balance between the highest acceleration and accurate reweighting. Compared with GaMD, SaMD extends the accessible time scale and improves the computational efficiency as tested in three tasks. In the alanine dipeptide task, SaMD can produce the free energy landscape with better accuracy and efficiency. In the chignolin folding task, the estimated Gibbs free energy difference can converge to the experimental value ∼30% faster. In the protein-ligand binding task, the bound conformations are closer to the crystal structure with a minimal ligand root-mean-square deviation of 1.7 Å. The binding of the ligand XK263 to the HIV protease is reproduced by SaMD in ∼60% less simulation time.

Can molecular dynamics simulations improve predictions of protein-ligand binding affinity with machine learning?

Binding affinity prediction largely determines the discovery efficiency of lead compounds in drug discovery. Recently, machine learning (ML)-based approaches have attracted much attention in hopes of enhancing the predictive performance of traditional physics-based approaches. In this study, we evaluated the impact of structural dynamic information on the binding affinity prediction by comparing the models trained on different dimensional descriptors, using three targets (i.e. JAK1, TAF1-BD2 and DDR1) and their corresponding ligands as the examples. Here, 2D descriptors are traditional ECFP4 fingerprints, 3D descriptors are the energy terms of the Smina and NNscore scoring functions and 4D descriptors contain the structural dynamic information derived from the trajectories based on molecular dynamics (MD) simulations. We systematically investigate the MD-refined binding affinity prediction performance of three classical ML algorithms (i.e. RF, SVR and XGB) as well as two common virtual screening methods, namely Glide docking and MM/PBSA. The outcomes of the ML models built using various dimensional descriptors and their combinations reveal that the MD refinement with the optimized protocol can improve the predictive performance on the TAF1-BD2 target with considerable structural flexibility, but not for the less flexible JAK1 and DDR1 targets, when taking docking poses as the initial structure instead of the crystal structures. The results highlight the importance of the initial structures to the final performance of the model through conformational analysis on the three targets with different flexibility.

Conservation of Imprinting and Methylation of MKRN3, MAGEL2 and NDN Genes in Cattle.

Genomic imprinting is the epigenetic mechanism of transcriptional regulation that involves differential DNA methylation modification. Comparative analysis of imprinted genes between species can help us to investigate the biological significance and regulatory mechanisms of genomic imprinting. MKRN3, MAGEL2 and NDN are three maternally imprinted genes identified in the human PWS/AS imprinted locus. This study aimed to assess the allelic expression of MKRN3, MAGEL2 and NDN and to examine the differentially methylated regions (DMRs) of bovine PWS/AS imprinted domains. An expressed single-nucleotide polymorphism (SNP)-based approach was used to investigate the allelic expression of MKRN3, MAGEL2 and NDN genes in bovine adult tissues and placenta. Consistent with the expression in humans and mice, we found that the MKRN3, MAGEL2 and NDN genes exhibit monoallelic expression in bovine somatic tissues and the paternal allele expressed in the bovine placenta. Three DMRs, PWS-IC, MKRN3 and NDN DMR, were identified in the bovine PWS/AS imprinted region by analysis of the DNA methylation status in bovine tissues using the bisulfite sequencing method and were located in the promoter and exon 1 of the SNRPN gene, NDN promoter and 5' untranslated region (5'UTR) of MKRN3 gene, respectively. The PWS-IC DMR is a primary DMR inherited from the male or female gamete, but NDN and MKRN3 DMR are secondary DMRs that occurred after fertilization by examining the methylation status in gametes.

ZNF597 is a maternally expressed imprinted gene in the Holstein breed.

Genomic imprinting is an epigenetic phenomenon that leads to the preferential expression of genes from either the paternal or maternal allele. Imprinted genes play important roles in mammalian growth and development and a central role in placental function. ZNF597 and NAA60 are two paternally imprinted genes in the human ZNF597-NAA60 imprinted locus, both of which show biallelic expression in the mouse, but their imprinting status in cattle is still unknown. In this study, we examined the allelic expression of ZNF597 and NAA60 in adult bovine placental and somatic tissues. By comparing the mRNA-based genotypes with the genomic DNA-based genotypes, we identified monoallelic expression of ZNF597 in the placenta and in seven other tissues, including the cerebrum, heart, liver, spleen, lung, kidney, and muscle. Nevertheless, analysis revealed biallelic expression of the NAA60 gene in these tissues. Moreover, we tested the imprinting status of ZNF597 and confirmed that the maternal allele is expressed in the bovine placenta. To determine the role of DNA methylation in regulating monoallelic/imprinted expression of bovine ZNF597, the methylation status of two CpG-enriched regions in the bovine ZNF597-NAA60 locus was analyzed using the bisulfite sequencing method. Differentially methylated regions were detected on ten CpG loci in the bovine ZNF597 promoter region. In summary, the bovine ZNF597 gene is a maternally expressed gene, and its expression is regulated by DNA methylation, whereas the NAA60 gene is not imprinted in cattle.