PlayMolecule Glimpse: Understanding Protein-Ligand Property Predictions with Interpretable Neural Networks

Integrating single-cell and multi-omic approaches reveals Euphorbiae Humifusae Herba-dependent mitochondrial dysfunction in non-small-cell lung cancer

Euphorbiae Humifusae Herba (EHH) is a pivotal therapeutic agent with diverse pharmacological effects. However, a substantial gap exists in understanding its pharmacological properties and anti-tumour mechanisms. This study aimed to address this gap by exploring EHH's pharmacological properties, identifying NSCLC therapy-associated protein targets, and elucidating how EHH induces mitochondrial disruption in NSCLC cells, offering insights into novel NSCLC treatment strategies. String database was utilized to explore protein-protein interactions. Subsequently, single-cell analysis and multi-omics further unveiled the impact of EHH-targeted genes on the immune microenvironment of NSCLC, as well as their influence on immunotherapeutic responses. Finally, both in vivo and in vitro experiments elucidated the anti-tumour mechanisms of EHH, specifically through the assessment of mitochondrial ROS levels and alterations in mitochondrial membrane potential. EHH exerts its influence through engagement with a cluster of 10 genes, including the apoptotic gene CASP3. This regulatory impact on the immune milieu within NSCLC holds promise as an indicator for predicting responses to immunotherapy. Besides, EHH demonstrated the capability to induce mitochondrial ROS generation and perturbations in mitochondrial membrane potential in NSCLC cells, ultimately leading to mitochondrial dysfunction and consequent apoptosis of tumour cells. EHH induces mitochondrial disruption in NSCLC cells, leading to cell apoptosis to inhibit the progress of NSCLC.

Machine Learning for Sequence and Structure-Based Protein-Ligand Interaction Prediction

Developing new drugs is too expensive and time -consuming. Accurately predicting the interaction between drugs and targets will likely change how the drug is discovered. Machine learning-based protein-ligand interaction prediction has demonstrated significant potential. In this paper, computational methods, focusing on sequence and structure to study protein-ligand interactions, are examined. Therefore, this paper starts by presenting an overview of the data sets applied in this area, as well as the various approaches applied for representing proteins and ligands. Then, sequence-based and structure-based classification criteria are subsequently utilized to categorize and summarize both the classical machine learning models and deep learning models employed in protein-ligand interaction studies. Moreover, the evaluation methods and interpretability of these models are proposed. Furthermore, delving into the diverse applications of protein-ligand interaction models in drug research is presented. Lastly, the current challenges and future directions in this field are addressed.

Navigating the Expansive Landscapes of Soft Materials: A User Guide for High-Throughput Workflows

Synthetic polymers are highly customizable with tailored structures and functionality, yet this versatility generates challenges in the design of advanced materials due to the size and complexity of the design space. Thus, exploration and optimization of polymer properties using combinatorial libraries has become increasingly common, which requires careful selection of synthetic strategies, characterization techniques, and rapid processing workflows to obtain fundamental principles from these large data sets. Herein, we provide guidelines for strategic design of macromolecule libraries and workflows to efficiently navigate these high-dimensional design spaces. We describe synthetic methods for multiple library sizes and structures as well as characterization methods to rapidly generate data sets, including tools that can be adapted from biological workflows. We further highlight relevant insights from statistics and machine learning to aid in data featurization, representation, and analysis. This Perspective acts as a "user guide" for researchers interested in leveraging high-throughput screening toward the design of multifunctional polymers and predictive modeling of structure-property relationships in soft materials.

Leveraging decagonal in-silico strategies for uncovering IL-6 inhibitors with precision

Interleukin-6 upregulation leads to various acute phase reactions such as local inflammation and systemic inflammation in many diseases like cancer, multiple sclerosis, rheumatoid arthritis, anemia, and Alzheimer's disease stimulating JAK/STAT3, Ras/MAPK, PI3K-PKB/Akt pathogenic pathways. Since no small molecules are available in the market against IL-6 till now, we have designed a class of small bioactive 1,3 - indanedione (IDC) molecules for inhibiting IL-6 using a decagonal approach computational studies. The IL-6 mutations were mapped in the IL-6 protein (PDB ID: 1ALU) from thorough pharmacogenomic and proteomics studies. The protein-drug interaction networking analysis for 2637 FFDA-approved drugs with IL-6 protein using Cytoscape software showed that 14 drugs have prominent interactions with IL-6. Molecular docking studies showed that the designed compound IDC-24 (-11.8 kcal/mol) and methotrexate (-5.20) bound most strongly to the 1ALU south asian population mutated protein. MMGBSA results indicated that IDC-24 (-41.78 kcal/mol) and methotrexate (-36.81 kcal/mol) had the highest binding energy when compared to the standard molecules LMT-28 (-35.87 kcal/mol) and MDL-A (-26.18 kcal/mol). These results we substantiated by the molecular dynamic studies in which the compound IDC-24 and the methotrexate had the highest stability. Further, the MMPBSA computations produced energies of -28 kcal/mol and -14.69 kcal/mol for IDC-24 and LMT-28. KDeep absolute binding affinity computations revealed energies of -5.81 kcal/mol and -4.74 kcal/mol for IDC-24 and LMT-28 respectively. Finally, our decagonal approach established the compound IDC-24 from the designed 1,3-indanedione library and methotrexate from protein drug interaction networking as suitable HITs against IL-6.

Optimizing molecular potential models by imposing kinetic constraints with path reweighting

Empirical force fields employed in molecular dynamics simulations of complex systems are often optimized to reproduce experimentally determined structural and thermodynamic properties. In contrast, experimental knowledge about the interconversion rates between metastable states in such systems is hardly ever incorporated in a force field due to a lack of an efficient approach. Here, we introduce such a framework based on the relationship between dynamical observables, such as rate constants, and the underlying molecular model parameters using the statistical mechanics of trajectories. Given a prior ensemble of molecular dynamics trajectories produced with imperfect force field parameters, the approach allows for the optimal adaption of these parameters such that the imposed constraint of equally predicted and experimental rate constant is obeyed. To do so, the method combines the continuum path ensemble maximum caliber approach with path reweighting methods for stochastic dynamics. When multiple solutions are found, the method selects automatically the combination that corresponds to the smallest perturbation of the entire path ensemble, as required by the maximum entropy principle. To show the validity of the approach, we illustrate the method on simple test systems undergoing rare event dynamics. Next to simple 2D potentials, we explore particle models representing molecular isomerization reactions and protein-ligand unbinding. Besides optimal interaction parameters, the methodology gives physical insights into what parts of the model are most sensitive to the kinetics. We discuss the generality and broad implications of the methodology.

Design of human immunodeficiency virus-1 neutralizing peptides targeting CD4-binding site: An integrative computational biologics approach

Peptide therapeutics have recently gained momentum in antiviral therapy due to their increased potency and cost-effectiveness. Interaction of the HIV-1 envelope gp120 with the host CD4 receptor is a critical step for viral entry, and therefore the CD4-binding site (CD4bs) of gp120 is a potential hotspot for blocking HIV-1 infection. The present study aimed to design short peptides from well-characterized CD4bs targeting broadly neutralizing antibodies (bNAbs), which could be utilized as bNAb mimetics for viral neutralization. Co-crystallized structures of HIV-1 gp120 in complex with CD4bs-directed bNAbs were used to derive hexameric peptides using the Rosetta Peptiderive protocol. Based on empirical insights into co-crystallized structures, peptides derived from the heavy chain alone were considered. The peptides were docked with both HIV-1 subtype B and C gp120, and the stability of the peptide–antigen complexes was validated using extensive Molecular Dynamics (MD) simulations. Two peptides identified in the study demonstrated stable intermolecular interactions with SER365, GLY366, and GLY367 of the PHE43 cavity in the CD4 binding pocket, and with ASP368 of HIV-1 gp120, thereby mimicking the natural interaction between ASP368gp120 and ARG59CD4–RECEPTOR. Furthermore, the peptides featured favorable physico-chemical properties for virus neutralization suggesting that these peptides may be highly promising bNAb mimetic candidates that may be taken up for experimental validation.

Scoring Functions for Protein-Ligand Binding Affinity Prediction using Structure-Based Deep Learning: A Review

The rapid and accurate in silico prediction of protein-ligand binding free energies or binding affinities has the potential to transform drug discovery. In recent years, there has been a rapid growth of interest in deep learning methods for the prediction of protein-ligand binding affinities based on the structural information of protein-ligand complexes. These structure-based scoring functions often obtain better results than classical scoring functions when applied within their applicability domain. Here we review structure-based scoring functions for binding affinity prediction based on deep learning, focussing on different types of architectures, featurization strategies, data sets, methods for training and evaluation, and the role of explainable artificial intelligence in building useful models for real drug-discovery applications.

Atom typing using graph representation learning: How do models learn chemistry?

Atom typing is the first step for simulating molecules using a force field. Automatic atom typing for an arbitrary molecule is often realized by rule-based algorithms, which have to manually encode rules for all types defined in this force field. These are time-consuming and force field-specific. In this study, a method that is independent of a specific force field based on graph representation learning is established for automatic atom typing. The topology adaptive graph convolution network (TAGCN) is found to be an optimal model. The model does not need manual enumeration of rules but can learn the rules just through training using typed molecules prepared during the development of a force field. The test on the CHARMM general force field gives a typing correctness of 91%. A systematic error of typing by TAGCN is its inability of distinguishing types in rings or acyclic chains. It originates from the fundamental structure of graph neural networks and can be fixed in a trivial way. More importantly, analysis of the rationalization processes of these models using layer-wise relation propagation reveals how TAGCN encodes rules learned during training. Our model is found to be able to type using the local chemical environments, in a way highly in accordance with chemists’ intuition.