A potent new-scaffold androgen receptor antagonist discovered on the basis of a MIEC-SVM model

A Unified Deep Graph Model for Identifying the Molecular Categories of Ligands Targeting Nuclear Receptors

To fulfill functions for differentially regulating the downstream signaling pathways, functional ligands (i.e., agonists or antagonists) targeting nuclear receptors (NRs) are designed to stabilize different conformations (active or inactive) of the proteins. However, in practical applications, it is usually difficult to determine the molecular category of an NR ligand because these molecules all bind in the same location of an NR protein, namely, the ligand-binding pocket (LBP). Considering that ligands with different properties (agonists or antagonists) prefer to bind with differential conformations of NRs, it is possible to identify the molecular type of a given ligand through the differential binding environment (active or inactive conformations) of the protein-ligand interaction. Therefore, in this study, we established a unified model (NRIGN) based on the deep graphic architecture to discriminate agonists and antagonists targeting 26 successful or in-clinical-trial NR targets. Our result shows that NRIGN achieves an excellent prediction accuracy (ACC >0.95) and is robust enough to be applied in various real-world scenarios, such as predicting the molecular type of ligands in crystallized NR structures, ligands with multiple NR activities, and ligands with their types altered by target mutations. The proposed model is expected to promote rational design of drugs targeting NR proteins.

Enhancing PI3Kγ inhibitor discovery: a machine learning-based virtual screening approach integrating pharmacophores, docking, and molecular descriptors

PI3Kγ is a lipid kinase that is expressed primarily in leukocytes and plays a significant role in tumors, inflammation, and autoimmune diseases. Consequently, considerable attention has been given to the development of pharmacological inhibitors of PI3Kγ. Recently, machine learning-based virtual screening approaches have been increasingly applied in new drug discovery research, potentially providing innovative strategies for the development of PI3Kγ inhibitors. Thus, in this study, we developed a naïve Bayesian classification (NBC) model that integrates molecular descriptors, molecular fingerprints, molecular docking, and pharmacophore models for virtual screening of the PI3Kγ protein. The validation results indicated that the optimal model demonstrated significant potential for differentiating between active and inactive compounds, as well as a reliable ability to identify true PI3Kγ inhibitors with defined biological activity. Additionally, the optimal NBC model provided favorable and unfavorable fragments for PI3Kγ inhibitors, which will help guide the design and discovery of novel PI3Kγ inhibitors. Finally, the optimal NBC model was employed to perform virtual screening on the ChEMBL database, resulting in the identification of several compounds with high potential as PI3Kγ inhibitors. We anticipate that the developed machine learning-based virtual screening approach will offer valuable insights and guidance for the development of novel PI3Kγ inhibitors.

Discovery of 5-Nitro-N-(3-(trifluoromethyl)phenyl) Pyridin-2-amine as a Novel Pure Androgen Receptor Antagonist against Antiandrogen Resistance

The transformation of clinical androgen receptor (AR) antagonists into agonists driven by AR mutations poses a significant challenge in treating prostate cancer (PCa). Novel anti-AR therapeutics combating mutation-induced resistance are required. Herein, by combining structure-based virtual screening and biological evaluation, a high-affinity agonist E10 was first discovered. Then guided by the representative conformation of State 1 at the free energy landscape, the structural optimization of E10 was performed, and pure AR antagonists EL15 (IC50 = 0.94 μM) and EF2 (IC50 = 0.30 μM) were successfully identified. Both can antagonize wild-type and variant drug-resistant ARs. Therein, EF2 demonstrated potent inhibition of the AR pathway and effectively suppressed tumor growth in a C4-2B xenograft mouse model following oral administration. Further molecular dynamics simulation and mutagenesis studies revealed atomic insights into the mode of action of EF2 which may serve as a novel lead compound for developing therapeutics against AR-driven PCa.

Data-centric challenges with the application and adoption of artificial intelligence for drug discovery

INTRODUCTION

Artificial intelligence (AI) is exhibiting tremendous potential to reduce the massive costs and long timescales of drug discovery. There are however important challenges currently limiting the impact and scope of AI models.

AREAS COVERED

In this perspective, the authors discuss a range of data issues (bias, inconsistency, skewness, irrelevance, small size, high dimensionality), how they challenge AI models, and which issue-specific mitigations have been effective. Next, they point out the challenges faced by uncertainty quantification techniques aimed at enhancing and trusting the predictions from these AI models. They also discuss how conceptual errors, unrealistic benchmarks and performance misestimation can confound the evaluation of models and thus their development. Lastly, the authors explain how human bias, whether from AI experts or drug discovery experts, constitutes another challenge that can be alleviated by gaining more prospective experience.

EXPERT OPINION

AI models are often developed to excel on retrospective benchmarks unlikely to anticipate their prospective performance. As a result, only a few of these models are ever reported to have prospective value (e.g. by discovering potent and innovative drug leads for a therapeutic target). The authors have discussed what can go wrong in practice with AI for drug discovery. The authors hope that this will help inform the decisions of editors, funders investors, and researchers working in this area.

Machine learning-based cell death marker for predicting prognosis and identifying tumor immune microenvironment in prostate cancer

Background

Prostate cancer (PCa) incidence and mortality rates are rising, necessitating precise prognostic tools to guide personalized treatment. Dysregulation of programmed cell death pathways in tumor suppression and cancer development has garnered increasing attention, providing a new research direction for identifying biomarkers and potential therapeutic targets.

Methods

Integrating multiple database resources, we constructed and optimized a prognostic signature based on the expression of programmed cell death-related genes (PCDRG) using ten machine learning algorithms. Model performance and prognostic effects were further evaluated. We analyzed the relationships between signature and clinicopathological features, somatic mutations, drug sensitivity, and the tumor immune microenvironment, and constructed a nomogram. The expression level of PCDRGs were evaluated and compared.

Results

Of 1560 PCDRGs, 149 were differentially expressed in PCa, with 34 associated with biochemical recurrence. The PCDRG-derived index (PCDI), constructed using the random forest algorithm, exhibited optimal prognostic performance, successfully stratifying PCa patients into two groups with significant prognostic differences. Patients with high PCDI scores exhibited poorer survival and lower immunotherapy benefit. PCDI was closely associated with the infiltration of specific immune cells, particularly positive correlations with macrophages and T helper cells, and negative correlations with neutrophils, suggesting that PCDI may influence the tumor immune microenvironment, thereby affecting patient prognosis and treatment response. PCDI was associated with age, pathological stage, somatic mutations, and drug sensitivity. The PCDI-based nomogram demonstrated excellent performance in predicting biochemical recurrence in PCa patients. Finally, the differential expression of these PCDRGs was verified based on cell lines and PCa patient expression profile data.

Conclusion

This study developed an effective prognostic indicator for prostate cancer, PCDI, using machine learning approaches. PCDI reflects the link between aberrant programmed cell death pathways and disease progression and treatment response.

RLpMIEC: High-Affinity Peptide Generation Targeting Major Histocompatibility Complex-I Guided and Interpreted by Interaction Spectrum-Navigated Reinforcement Learning

Major histocompatibility complex (MHC) plays a vital role in presenting epitopes (short peptides from pathogenic proteins) to T-cell receptors (TCRs) to trigger the subsequent immune responses. Vaccine design targeting MHC generally aims to find epitopes with a high binding affinity for MHC presentation. Nevertheless, to find novel epitopes usually requires high-throughput screening of bulk peptide database, which is time-consuming, labor-intensive, more unaffordable, and very expensive. Excitingly, the past several years have witnessed the great success of artificial intelligence (AI) in various fields, such as natural language processing (NLP, e.g., GPT-4), protein structure prediction and engineering (e.g., AlphaFold2), and so on. Therefore, herein, we propose a deep reinforcement-learning (RL)-based generative algorithm, RLpMIEC, to quantitatively design peptide targeting MHC-I systems. Specifically, RLpMIEC combines the energetic spectrum (namely, the molecular interaction energy component, MIEC) based on the peptide-MHC interaction and the sequence information to generate peptides with strong binding affinity and precise MIEC spectra to accelerate the discovery of candidate peptide vaccines. RLpMIEC performs well in all the generative capability evaluations and can generate peptides with strong binding affinities and precise MIECs and, moreover, with high interpretability, demonstrating its powerful capability in participation for accelerating peptide-based vaccine development.