DCGAN-DTA: Predicting drug-target binding affinity with deep convolutional generative adversarial networks.

BACKGROUND: In recent years, there has been a growing interest in utilizing computational approaches to predict drug-target binding affinity, aiming to expedite the early drug discovery process. To address the limitations of experimental methods, such as cost and time, several machine learning-based techniques have been developed. However, these methods encounter certain challenges, including the limited availability of training data, reliance on human intervention for feature selection and engineering, and a lack of validation approaches for robust evaluation in real-life applications. RESULTS: To mitigate these limitations, in this study, we propose a method for drug-target binding affinity prediction based on deep convolutional generative adversarial networks. Additionally, we conducted a series of validation experiments and implemented adversarial control experiments using straw models. These experiments serve to demonstrate the robustness and efficacy of our predictive models. We conducted a comprehensive evaluation of our method by comparing it to baselines and state-of-the-art methods. Two recently updated datasets, namely the BindingDB and PDBBind, were used for this purpose. Our findings indicate that our method outperforms the alternative methods in terms of three performance measures when using warm-start data splitting settings. Moreover, when considering physiochemical-based cold-start data splitting settings, our method demonstrates superior predictive performance, particularly in terms of the concordance index. CONCLUSION: The results of our study affirm the practical value of our method and its superiority over alternative approaches in predicting drug-target binding affinity across multiple validation sets. This highlights the potential of our approach in accelerating drug repurposing efforts, facilitating novel drug discovery, and ultimately enhancing disease treatment. The data and source code for this study were deposited in the GitHub repository, https://github.com/mojtabaze7/DCGAN-DTA . Furthermore, the web server for our method is accessible at https://dcgan.shinyapps.io/bindingaffinity/ .

Emerging opportunities of using large language models for translation between drug molecules and indications.

A drug molecule is a substance that changes an organism's mental or physical state. Every approved drug has an indication, which refers to the therapeutic use of that drug for treating a particular medical condition. While the Large Language Model (LLM), a generative Artificial Intelligence (AI) technique, has recently demonstrated effectiveness in translating between molecules and their textual descriptions, there remains a gap in research regarding their application in facilitating the translation between drug molecules and indications (which describes the disease, condition or symptoms for which the drug is used), or vice versa. Addressing this challenge could greatly benefit the drug discovery process. The capability of generating a drug from a given indication would allow for the discovery of drugs targeting specific diseases or targets and ultimately provide patients with better treatments. In this paper, we first propose a new task, the translation between drug molecules and corresponding indications, and then test existing LLMs on this new task. Specifically, we consider nine variations of the T5 LLM and evaluate them on two public datasets obtained from ChEMBL and DrugBank. Our experiments show the early results of using LLMs for this task and provide a perspective on the state-of-the-art. We also emphasize the current limitations and discuss future work that has the potential to improve the performance on this task. The creation of molecules from indications, or vice versa, will allow for more efficient targeting of diseases and significantly reduce the cost of drug discovery, with the potential to revolutionize the field of drug discovery in the era of generative AI.

Systems Biology for Drug Target Discovery in Acute Myeloid Leukemia.

Combining new therapeutics with all-trans-retinoic acid (ATRA) could improve the efficiency of acute myeloid leukemia (AML) treatment. Modeling the process of ATRA-induced differentiation based on the transcriptomic profile of leukemic cells resulted in the identification of key targets that can be used to increase the therapeutic effect of ATRA. The genome-scale transcriptome analysis revealed the early molecular response to the ATRA treatment of HL-60 cells. In this study, we performed the transcriptomic profiling of HL-60, NB4, and K562 cells exposed to ATRA for 3-72 h. After treatment with ATRA for 3, 12, 24, and 72 h, we found 222, 391, 359, and 1032 differentially expressed genes (DEGs) in HL-60 cells, as well as 641, 1037, 1011, and 1499 DEGs in NB4 cells. We also found 538 and 119 DEGs in K562 cells treated with ATRA for 24 h and 72 h, respectively. Based on experimental transcriptomic data, we performed hierarchical modeling and determined cyclin-dependent kinase 6 (CDK6), tumor necrosis factor alpha (TNF-alpha), and transcriptional repressor CUX1 as the key regulators of the molecular response to the ATRA treatment in HL-60, NB4, and K562 cell lines, respectively. Mapping the data of TMT-based mass-spectrometric profiling on the modeling schemes, we determined CDK6 expression at the proteome level and its down-regulation at the transcriptome and proteome levels in cells treated with ATRA for 72 h. The combination of therapy with a CDK6 inhibitor (palbociclib) and ATRA (tretinoin) could be an alternative approach for the treatment of acute myeloid leukemia (AML).

Connective Tissue Growth Factor: Regulation, Diseases, and Drug Discovery.

In drug discovery, selecting targeted molecules is crucial as the target could directly affect drug efficacy and the treatment outcomes. As a member of the CCN family, CTGF (also known as CCN2) is an essential regulator in the progression of various diseases, including fibrosis, cancer, neurological disorders, and eye diseases. Understanding the regulatory mechanisms of CTGF in different diseases may contribute to the discovery of novel drug candidates. Summarizing the CTGF-targeting and -inhibitory drugs is also beneficial for the analysis of the efficacy, applications, and limitations of these drugs in different disease models. Therefore, we reviewed the CTGF structure, the regulatory mechanisms in various diseases, and drug development in order to provide more references for future drug discovery.

Elucidating the semantics-topology trade-off for knowledge inference-based pharmacological discovery.

Leveraging AI for synthesizing the deluge of biomedical knowledge has great potential for pharmacological discovery with applications including developing new therapeutics for untreated diseases and repurposing drugs as emergent pandemic treatments. Creating knowledge graph representations of interacting drugs, diseases, genes, and proteins enables discovery via embedding-based ML approaches and link prediction. Previously, it has been shown that these predictive methods are susceptible to biases from network structure, namely that they are driven not by discovering nuanced biological understanding of mechanisms, but based on high-degree hub nodes. In this work, we study the confounding effect of network topology on biological relation semantics by creating an experimental pipeline of knowledge graph semantic and topological perturbations. We show that the drop in drug repurposing performance from ablating meaningful semantics increases by 21% and 38% when mitigating topological bias in two networks. We demonstrate that new methods for representing knowledge and inferring new knowledge must be developed for making use of biomedical semantics for pharmacological innovation, and we suggest fruitful avenues for their development.

Multicriteria decision making attributes and estimation of physicochemical properties of kidney cancer drugs via topological descriptors.

Based on topological descriptors, QSPR analysis is an incredibly helpful statistical method for examining many physical and chemical properties of compounds without demanding costly and time-consuming laboratory tests. Firstly, we discuss and provide research on kidney cancer drugs using topological indices and done partition of the edges of kidney cancer drugs which are based on the degree. Secondly, we examine the attributes of nineteen drugs casodex, eligard, mitoxanrone, rubraca, and zoladex, etc and among others, using linear QSPR model. The study in the article not only demonstrates a good correlation between TIs and physical characteristics with the QSPR model being the most suitable for predicting complexity, enthalpy, molar refractivity, and other factors and a best-fit model is attained in this study. This theoretical approach might benefit chemists and professionals in the pharmaceutical industry to forecast the characteristics of kidney cancer therapies. This leads towards new opportunities to paved the way for drug discovery and the formation of efficient and suitable treatment options in therapeutic targeting. We also employed multicriteria decision making techniques like COPRAS and PROMETHEE-II for ranking of said disease treatment drugs and physicochemical characteristics.

Computational drug repositioning with attention walking.

Drug repositioning aims to identify new therapeutic indications for approved medications. Recently, the importance of computational drug repositioning has been highlighted because it can reduce the costs, development time, and risks compared to traditional drug discovery. Most approaches in this area use networks for systematic analysis. Inferring drug-disease associations is then defined as a link prediction problem in a heterogeneous network composed of drugs and diseases. In this article, we present a novel method of computational drug repositioning, named drug repositioning with attention walking (DRAW). DRAW proceeds as follows: first, a subgraph enclosing the target link for prediction is extracted. Second, a graph convolutional network captures the structural features of the labeled nodes in the subgraph. Third, the transition probabilities are computed using attention mechanisms and converted into random walk profiles. Finally, a multi-layer perceptron takes random walk profiles and predicts whether a target link exists. As an experiment, we constructed two heterogeneous networks with drug-drug similarities based on chemical structures and anatomical therapeutic chemical classification (ATC) codes. Using 10-fold cross-validation, DRAW achieved an area under the receiver operating characteristic (ROC) curve of 0.903 and outperformed state-of-the-art methods. Moreover, we demonstrated the results of case studies for selected drugs and diseases to further confirm the capability of DRAW to predict drug-disease associations.

De novo generation of multi-target compounds using deep generative chemistry.

Polypharmacology drugs-compounds that inhibit multiple proteins-have many applications but are difficult to design. To address this challenge we have developed POLYGON, an approach to polypharmacology based on generative reinforcement learning. POLYGON embeds chemical space and iteratively samples it to generate new molecular structures; these are rewarded by the predicted ability to inhibit each of two protein targets and by drug-likeness and ease-of-synthesis. In binding data for >100,000 compounds, POLYGON correctly recognizes polypharmacology interactions with 82.5% accuracy. We subsequently generate de-novo compounds targeting ten pairs of proteins with documented co-dependency. Docking analysis indicates that top structures bind their two targets with low free energies and similar 3D orientations to canonical single-protein inhibitors. We synthesize 32 compounds targeting MEK1 and mTOR, with most yielding >50% reduction in each protein activity and in cell viability when dosed at 1-10 µM. These results support the potential of generative modeling for polypharmacology.

Reductionism and proxy failure: From neuroscience to target-based drug discovery.

Reductionist methodologies reduce phenomena to some of their lower-level components. Researchers gradually shift their focus away from observing the actual object of study toward investigating and optimizing such lower-level proxies. Following reductionism, these proxies progressively diverge further from the original object of study. We vividly illustrate this in the evolution of target-based drug discovery from rational and phenotypic drug discovery.

Quantifying Antibody-Dependent Cellular Cytotoxicity in a Tumor Spheroid Model: Application for Drug Discovery.

Monoclonal antibody-based immunotherapy targeting tumor antigens is now a mainstay of cancer treatment. One of the clinically relevant mechanisms of action of the antibodies is antibody-dependent cellular cytotoxicity (ADCC), where the antibody binds to the cancer cells and engages the cellular component of the immune system, e.g., natural killer (NK) cells, to kill the tumor cells. The effectiveness of these therapies could be improved by identifying adjuvant compounds that increase the sensitivity of the cancer cells or the potency of the immune cells. In addition, undiscovered drug interactions in cancer patients co-medicated for previous conditions or cancer-associated symptoms may determine the success of the antibody therapy; therefore, such unwanted drug interactions need to be eliminated. With these goals in mind, we created a cancer ADCC model and describe here a simple protocol to find ADCC-modulating drugs. Since 3D models such as cancer cell spheroids are superior to 2D cultures in predicting in vivo responses of tumors to anticancer therapies, spheroid co-cultures of EGFP-expressing HER2+ JIMT-1 breast cancer cells and the NK92.CD16 cell lines were set up and induced with Trastuzumab, a monoclonal antibody clinically approved against HER2-positive breast cancer. JIMT-1 spheroids were allowed to form in cell-repellent U-bottom 96-well plates. On day 3, NK cells and Trastuzumab were added. The spheroids were then stained with Annexin V-Alexa 647 to measure apoptotic cell death, which was quantitated in the peripheral zone of the spheroids with an automated microscope. The applicability of our assay to identify ADCC-modulating molecules is demonstrated by showing that Sunitinib, a receptor tyrosine kinase inhibitor approved by the FDA against metastatic cancer, almost completely abolishes ADCC. The generation of the spheroids and image acquisition and analysis pipelines are compatible with high-throughput screening for ADCC-modulating compounds in cancer cell spheroids.

Ensemble-Based Virtual Screening Led to the Discovery of Novel Lead Molecules as Potential NMBAs.

Neuromuscular blocking agents (NMBAs) are routinely used during anesthesia to relax skeletal muscle. Nicotinic acetylcholine receptors (nAChRs) are ligand-gated ion channels; NMBAs can induce muscle paralysis by preventing the neurotransmitter acetylcholine (ACh) from binding to nAChRs situated on the postsynaptic membranes. Despite widespread efforts, it is still a great challenge to find new NMBAs since the introduction of cisatracurium in 1995. In this work, an effective ensemble-based virtual screening method, including molecular property filters, 3D pharmacophore model, and molecular docking, was applied to discover potential NMBAs from the ZINC15 database. The results showed that screened hit compounds had better docking scores than the reference compound d-tubocurarine. In order to further investigate the binding modes between the hit compounds and nAChRs at simulated physiological conditions, the molecular dynamics simulation was performed. Deep analysis of the simulation results revealed that ZINC257459695 can stably bind to nAChRs' active sites and interact with the key residue Asp165. The binding free energies were also calculated for the obtained hits using the MM/GBSA method. In silico ADMET calculations were performed to assess the pharmacokinetic properties of hit compounds in the human body. Overall, the identified ZINC257459695 may be a promising lead compound for developing new NMBAs as an adjunct to general anesthesia, necessitating further investigations.

Streamlining Computational Fragment-Based Drug Discovery through Evolutionary Optimization Informed by Ligand-Based Virtual Prescreening.

Recent advances in computational methods provide the promise of dramatically accelerating drug discovery. While mathematical modeling and machine learning have become vital in predicting drug-target interactions and properties, there is untapped potential in computational drug discovery due to the vast and complex chemical space. This paper builds on our recently published computational fragment-based drug discovery (FBDD) method called fragment databases from screened ligand drug discovery (FDSL-DD). FDSL-DD uses in silico screening to identify ligands from a vast library, fragmenting them while attaching specific attributes based on predicted binding affinity and interaction with the target subdomain. In this paper, we further propose a two-stage optimization method that utilizes the information from prescreening to optimize computational ligand synthesis. We hypothesize that using prescreening information for optimization shrinks the search space and focuses on promising regions, thereby improving the optimization for candidate ligands. The first optimization stage assembles these fragments into larger compounds using genetic algorithms, followed by a second stage of iterative refinement to produce compounds with enhanced bioactivity. To demonstrate broad applicability, the methodology is demonstrated on three diverse protein targets found in human solid cancers, bacterial antimicrobial resistance, and the SARS-CoV-2 virus. Combined, the proposed FDSL-DD and a two-stage optimization approach yield high-affinity ligand candidates more efficiently than other state-of-the-art computational FBDD methods. We further show that a multiobjective optimization method accounting for drug-likeness can still produce potential candidate ligands with a high binding affinity. Overall, the results demonstrate that integrating detailed chemical information with a constrained search framework can markedly optimize the initial drug discovery process, offering a more precise and efficient route to developing new therapeutics.

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.

FraHMT: A Fragment-Oriented Heterogeneous Graph Molecular Generation Model for Target Proteins.

The molecular generation task stands as a pivotal step in the domains of computational chemistry and drug discovery, aiming to computationally generate molecular structures for specific properties. In contrast to previous models that focused primarily on SMILES strings or molecular graphs, our model placed a special emphasis on the substructure information on molecules, enabling the model to learn richer chemical rules and structure features from fragments and chemical reaction information on molecules. To accomplish this, we fragmented the molecules to construct heterogeneous graph representations based on atom and fragment information. Then our model mapped the heterogeneous graph data into a latent vector space by using an encoder and employed a self-regressive generative model as a decoder for molecular generation. Additionally, we performed transfer learning on the model using a small set of ligand molecules known to be active against the target protein to generate molecules that bind better to the target protein. Experimental results demonstrate that our model is highly competitive with state-of-the-art models. It can generate valid and diverse molecules with favorable physicochemical properties and drug-likeness. Importantly, they produce novel molecules with high docking scores against the target proteins.

FEP Augmentation as a Means to Solve Data Paucity Problems for Machine Learning in Chemical Biology.

In the realm of medicinal chemistry, the primary objective is to swiftly optimize a multitude of chemical properties of a set of compounds to yield a clinical candidate poised for clinical trials. In recent years, two computational techniques, machine learning (ML) and physics-based methods, have evolved substantially and are now frequently incorporated into the medicinal chemist's toolbox to enhance the efficiency of both hit optimization and candidate design. Both computational methods come with their own set of limitations, and they are often used independently of each other. ML's capability to screen extensive compound libraries expediently is tempered by its reliance on quality data, which can be scarce especially during early-stage optimization. Contrarily, physics-based approaches like free energy perturbation (FEP) are frequently constrained by low throughput and high cost by comparison; however, physics-based methods are capable of making highly accurate binding affinity predictions. In this study, we harnessed the strength of FEP to overcome data paucity in ML by generating virtual activity data sets which then inform the training of algorithms. Here, we show that ML algorithms trained with an FEP-augmented data set could achieve comparable predictive accuracy to data sets trained on experimental data from biological assays. Throughout the paper, we emphasize key mechanistic considerations that must be taken into account when aiming to augment data sets and lay the groundwork for successful implementation. Ultimately, the study advocates for the synergy of physics-based methods and ML to expedite the lead optimization process. We believe that the physics-based augmentation of ML will significantly benefit drug discovery, as these techniques continue to evolve.

The Prediction of LptA and LptC Protein-Protein Interactions and Virtual Screening for Potential Inhibitors.

Antibiotic resistance in Gram-negative bacteria remains one of the most pressing challenges to global public health. Blocking the transportation of lipopolysaccharides (LPS), a crucial component of the outer membrane of Gram-negative bacteria, is considered a promising strategy for drug discovery. In the transportation process of LPS, two components of the LPS transport (Lpt) complex, LptA and LptC, are responsible for shuttling LPS across the periplasm to the outer membrane, highlighting their potential as targets for antibacterial drug development. In the current study, a protein-protein interaction (PPI) model of LptA and LptC was constructed, and a molecular screening strategy was employed to search a protein-protein interaction compound library. The screening results indicated that compound 18593 exhibits favorable binding free energy with LptA and LptC. In comparison with the molecular dynamics (MD) simulations on currently known inhibitors, compound 18593 shows more stable target binding ability at the same level. The current study suggests that compound 18593 may exhibit an inhibitory effect on the LPS transport process, making it a promising hit compound for further research.

AI is a viable alternative to high throughput screening: a 318-target study.

High throughput screening (HTS) is routinely used to identify bioactive small molecules. This requires physical compounds, which limits coverage of accessible chemical space. Computational approaches combined with vast on-demand chemical libraries can access far greater chemical space, provided that the predictive accuracy is sufficient to identify useful molecules. Through the largest and most diverse virtual HTS campaign reported to date, comprising 318 individual projects, we demonstrate that our AtomNet® convolutional neural network successfully finds novel hits across every major therapeutic area and protein class. We address historical limitations of computational screening by demonstrating success for target proteins without known binders, high-quality X-ray crystal structures, or manual cherry-picking of compounds. We show that the molecules selected by the AtomNet® model are novel drug-like scaffolds rather than minor modifications to known bioactive compounds. Our empirical results suggest that computational methods can substantially replace HTS as the first step of small-molecule drug discovery.

[The revolution of AI in drug development]. / L'intelligence artificielle, une révolution dans le développement des médicaments.

Artificial intelligence and machine learning enable the construction of predictive models, which are currently used to assist in decision-making throughout the process of drug discovery and development. These computational models can be used to represent the heterogeneity of a disease, identify therapeutic targets, design and optimize drug candidates, and evaluate the efficacy of these drugs on virtual patients or digital twins. By combining detailed patient characteristics with the prediction of potential drug-candidate properties, artificial intelligence promotes the emergence of a "computational" precision medicine, allowing for more personalized treatments, better tailored to patient specificities with the aid of such predictive models. Based on such new capabilities, a mixed reality approach to the development of new drugs is being adopted by the pharmaceutical industry, which integrates the outputs of predictive virtual models with real-world empirical studies.

Title: L'intelligence artificielle, une révolution dans le développement des médicaments. Abstract: L'intelligence artificielle (IA) et l'apprentissage automatique produisent des modèles prédictifs qui aident à la prise de décisions dans le processus de découverte de nouveaux médicaments. Cette modélisation par ordinateur permet de représenter l'hétérogénéité d'une maladie, d'identifier des cibles thérapeutiques, de concevoir et optimiser des candidats-médicaments et d'évaluer ces médicaments sur des patients virtuels, ou des jumeaux numériques. En facilitant à la fois une connaissance détaillée des caractéristiques des patients et en prédisant les propriétés de multiples médicaments possibles, l'IA permet l'émergence d'une médecine de précision « computationnelle ¼ offrant des traitements parfaitement adaptés aux spécificités des patients.

MolProphet: A One-Stop, General Purpose, and AI-Based Platform for the Early Stages of Drug Discovery.

Artificial intelligence (AI) is an effective tool to accelerate drug discovery and cut costs in discovery processes. Many successful AI applications are reported in the early stages of small molecule drug discovery. However, most of those applications require a deep understanding of software and hardware, and focus on a single field that implies data normalization and transfer between those applications is still a challenge for normal users. It usually limits the application of AI in drug discovery. Here, based on a series of robust models, we formed a one-stop, general purpose, and AI-based drug discovery platform, MolProphet, to provide complete functionalities in the early stages of small molecule drug discovery, including AI-based target pocket prediction, hit discovery and lead optimization, and compound targeting, as well as abundant analyzing tools to check the results. MolProphet is an accessible and user-friendly web-based platform that is fully designed according to the practices in the drug discovery industry. The molecule screened, generated, or optimized by the MolProphet is purchasable and synthesizable at low cost but with good drug-likeness. More than 400 users from industry and academia have used MolProphet in their work. We hope this platform can provide a powerful solution to assist each normal researcher in drug design and related research areas. It is available for everyone at https://www.molprophet.com/.

A probabilistic knowledge graph for target identification.

Early identification of safe and efficacious disease targets is crucial to alleviating the tremendous cost of drug discovery projects. However, existing experimental methods for identifying new targets are generally labor-intensive and failure-prone. On the other hand, computational approaches, especially machine learning-based frameworks, have shown remarkable application potential in drug discovery. In this work, we propose Progeni, a novel machine learning-based framework for target identification. In addition to fully exploiting the known heterogeneous biological networks from various sources, Progeni integrates literature evidence about the relations between biological entities to construct a probabilistic knowledge graph. Graph neural networks are then employed in Progeni to learn the feature embeddings of biological entities to facilitate the identification of biologically relevant target candidates. A comprehensive evaluation of Progeni demonstrated its superior predictive power over the baseline methods on the target identification task. In addition, our extensive tests showed that Progeni exhibited high robustness to the negative effect of exposure bias, a common phenomenon in recommendation systems, and effectively identified new targets that can be strongly supported by the literature. Moreover, our wet lab experiments successfully validated the biological significance of the top target candidates predicted by Progeni for melanoma and colorectal cancer. All these results suggested that Progeni can identify biologically effective targets and thus provide a powerful and useful tool for advancing the drug discovery process.