Automated design of multi-target ligands by generative deep learning.

Generative deep learning models enable data-driven de novo design of molecules with tailored features. Chemical language models (CLM) trained on string representations of molecules such as SMILES have been successfully employed to design new chemical entities with experimentally confirmed activity on intended targets. Here, we probe the application of CLM to generate multi-target ligands for designed polypharmacology. We capitalize on the ability of CLM to learn from small fine-tuning sets of molecules and successfully bias the model towards designing drug-like molecules with similarity to known ligands of target pairs of interest. Designs obtained from CLM after pooled fine-tuning are predicted active on both proteins of interest and comprise pharmacophore elements of ligands for both targets in one molecule. Synthesis and testing of twelve computationally favored CLM designs for six target pairs reveals modulation of at least one intended protein by all selected designs with up to double-digit nanomolar potency and confirms seven compounds as designed dual ligands. These results corroborate CLM for multi-target de novo design as source of innovation in drug discovery.

Polypharmacology prediction: the long road toward comprehensively anticipating small-molecule selectivity to de-risk drug discovery.

INTRODUCTION: Small molecules often bind to multiple targets, a behavior termed polypharmacology. Anticipating polypharmacology is essential for drug discovery since unknown off-targets can modulate safety and efficacy - profoundly affecting drug discovery success. Unfortunately, experimental methods to assess selectivity present significant limitations and drugs still fail in the clinic due to unanticipated off-targets. Computational methods are a cost-effective, complementary approach to predict polypharmacology. AREAS COVERED: This review aims to provide a comprehensive overview of the state of polypharmacology prediction and discuss its strengths and limitations, covering both classical cheminformatics methods and bioinformatic approaches. The authors review available data sources, paying close attention to their different coverage. The authors then discuss major algorithms grouped by the types of data that they exploit using selected examples. EXPERT OPINION: Polypharmacology prediction has made impressive progress over the last decades and contributed to identify many off-targets. However, data incompleteness currently limits most approaches to comprehensively predict selectivity. Moreover, our limited agreement on model assessment challenges the identification of the best algorithms - which at present show modest performance in prospective real-world applications. Despite these limitations, the exponential increase of multidisciplinary Big Data and AI hold much potential to better polypharmacology prediction and de-risk drug discovery.

Systematic Investigation of Dual-Target-Directed Ligands.

Multitarget-directed ligands (MTDLs) are compounds rationally designed to affect multiple targets, aiming for a better therapeutic profile. For over 20 years, MTDLs have garnered increasing attention, the idea being that their full potential would have been achieved, thanks to unprecedented target combinations and advanced medicinal chemistry strategies. This study presents a literature mining effort resulting in a data set of dual-target-directed ligands (DTDLs), the fundamental example of MTDLs. We used this data set to evaluate the rationale behind target selection and the chemical novelty of DTDLs targeting specific protein combinations. Our analysis focused on DTDL targets in terms of biological function, disease association, structure, and chemogenomic traits. We also compared DTDLs with single-target compounds. We found that well-known target pathology associations often guide DTDL design, leveraging existing chemical scaffolds and binding pocket similarities. These findings highlight the current state of the field and suggest substantial untapped potential for rational polypharmacology.

Multitargeted polypharmacotherapy for cancer treatment. theoretical concepts and proposals.

INTRODUCTION: The pharmacological treatment of cancer has evolved from cytotoxic to molecular targeted therapy. The median survival gains of 124 drugs approved by the FDA from 2003 to 2021 is 2.8 months. Targeted therapy is based on the somatic mutation theory, which has some paradoxes and limitations. While efforts of targeted therapy must continue, we must study newer approaches that could advance therapy and affordability for patients. AREAS COVERED: This work briefly overviews how cancer therapy has evolved from cytotoxic chemotherapy to current molecular-targeted therapy. The limitations of the one-target, one-drug approach considering cancer as a robust system and the basis for multitargeting approach with polypharmacotherapy using repurposing drugs. EXPERT OPINION: Multitargeted polypharmacotherapy for cancer with repurposed drugs should be systematically investigated in preclinical and clinical studies. Remarkably, most of these proposed drugs already have a long history in the clinical setting, and their safety is known. In principle, the risk of their simultaneous administration should not be greater than that of a first-in-human phase I study as long as the protocol is developed with strict vigilance to detect early possible side effects from their potential interactions. Research on cancer therapy should go beyond the prevailing paradigm targeted therapy.

Polypharmacology-Driven Discovery and Design of Highly Selective, Dual and Multitargeting Inhibitors of Mycobacterium tuberculosis - A Review.

The increasing demand for novel antitubercular agents has been the main 'force' of many TB research efforts due to the uncontrolled growing number of drug-resistant strains of M. tuberculosis in the clinical setting. Many strategies have been employed to address the drug-resistant issue, including a trend that is gaining attention, which is the design and discovery of Mtb inhibitors that are either dual- or multitargeting. The multiple-target design concept is not new in medicinal chemistry. With a growing number of newly discovered Mtb proteins, numerous targets are now available for developing new biochemical/cell-based assays and computer-aided drug design (CADD) protocols. To describe the achievements and overarching picture of this field in anti- infective drug discovery, we provide in this review small molecules that exhibit profound inhibitory activity against the tubercle bacilli and are identified to trace two or more Mtb targets. This review also presents emerging design methodologies for developing new anti-TB agents, particularly tailored to structure-based CADD.

KinomeMETA: a web platform for kinome-wide polypharmacology profiling with meta-learning.

Kinase-targeted inhibitors hold promise for new therapeutic options, with multi-target inhibitors offering the potential for broader efficacy while minimizing polypharmacology risks. However, comprehensive experimental profiling of kinome-wide activity is expensive, and existing computational approaches often lack scalability or accuracy for understudied kinases. We introduce KinomeMETA, an artificial intelligence (AI)-powered web platform that significantly expands the predictive range with scalability for predicting the polypharmacological effects of small molecules across the kinome. By leveraging a novel meta-learning algorithm, KinomeMETA efficiently utilizes sparse activity data, enabling rapid generalization to new kinase tasks even with limited information. This significantly expands the repertoire of accurately predictable kinases to 661 wild-type and clinically-relevant mutant kinases, far exceeding existing methods. Additionally, KinomeMETA empowers users to customize models with their proprietary data for specific research needs. Case studies demonstrate its ability to discover new active compounds by quickly adapting to small dataset. Overall, KinomeMETA offers enhanced kinome virtual profiling capabilities and is positioned as a powerful tool for developing new kinase inhibitors and advancing kinase research. The KinomeMETA server is freely accessible without registration at https://kinomemeta.alphama.com.cn/.

Toward structure-multiple activity relationships (SMARts) using computational approaches: A polypharmacological perspective.

In the current era of biological big data, which are rapidly populating the biological chemical space, in silico polypharmacology drug design approaches help to decode structure-multiple activity relationships (SMARts). Current computational methods can predict or categorize multiple properties simultaneously, which aids the generation, identification, curation, prioritization, optimization, and repurposing of molecules. Computational methods have generated opportunities and challenges in medicinal chemistry, pharmacology, food chemistry, toxicology, bioinformatics, and chemoinformatics. It is anticipated that computer-guided SMARts could contribute to the full automatization of drug design and drug repurposing campaigns, facilitating the prediction of new biological targets, side and off-target effects, and drug-drug interactions.

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.

Molecular hybridization: a powerful tool for multitarget drug discovery.

INTRODUCTION: The current drug discovery paradigm of 'one drug, multiple targets' has gained attention from both the academic medicinal chemistry community and the pharmaceutical industry. This is in response to the urgent need for effective agents to treat multifactorial chronic diseases. The molecular hybridization strategy is a useful tool that has been widely explored, particularly in the last two decades, for the design of multi-target drugs. AREAS COVERED: This review examines the current state of molecular hybridization in guiding the discovery of multitarget small molecules. The article discusses the design strategies and target selection for a multitarget polypharmacology approach to treat various diseases, including cancer, Alzheimer's disease, cardiac arrhythmia, endometriosis, and inflammatory diseases. EXPERT OPINION: Although the examples discussed highlight the importance of molecular hybridization for the discovery of multitarget bioactive compounds, it is notorious that the literature has focused on specific classes of targets. This may be due to a deep understanding of the pharmacophore features required for target binding, making targets such as histone deacetylases and cholinesterases frequent starting points. However, it is important to encourage the scientific community to explore diverse combinations of targets using the molecular hybridization strategy.

Flexible scaffold-based cheminformatics approach for polypharmacological drug design.

Effective treatments for complex central nervous system (CNS) disorders require drugs with polypharmacology and multifunctionality, yet designing such drugs remains a challenge. Here, we present a flexible scaffold-based cheminformatics approach (FSCA) for the rational design of polypharmacological drugs. FSCA involves fitting a flexible scaffold to different receptors using different binding poses, as exemplified by IHCH-7179, which adopted a "bending-down" binding pose at 5-HT2AR to act as an antagonist and a "stretching-up" binding pose at 5-HT1AR to function as an agonist. IHCH-7179 demonstrated promising results in alleviating cognitive deficits and psychoactive symptoms in mice by blocking 5-HT2AR for psychoactive symptoms and activating 5-HT1AR to alleviate cognitive deficits. By analyzing aminergic receptor structures, we identified two featured motifs, the "agonist filter" and "conformation shaper," which determine ligand binding pose and predict activity at aminergic receptors. With these motifs, FSCA can be applied to the design of polypharmacological ligands at other receptors.

Kinome-Wide Virtual Screening by Multi-Task Deep Learning.

Deep learning is a machine learning technique to model high-level abstractions in data by utilizing a graph composed of multiple processing layers that experience various linear and non-linear transformations. This technique has been shown to perform well for applications in drug discovery, utilizing structural features of small molecules to predict activity. Here, we report a large-scale study to predict the activity of small molecules across the human kinome-a major family of drug targets, particularly in anti-cancer agents. While small-molecule kinase inhibitors exhibit impressive clinical efficacy in several different diseases, resistance often arises through adaptive kinome reprogramming or subpopulation diversity. Polypharmacology and combination therapies offer potential therapeutic strategies for patients with resistant diseases. Their development would benefit from a more comprehensive and dense knowledge of small-molecule inhibition across the human kinome. Leveraging over 650,000 bioactivity annotations for more than 300,000 small molecules, we evaluated multiple machine learning methods to predict the small-molecule inhibition of 342 kinases across the human kinome. Our results demonstrated that multi-task deep neural networks outperformed classical single-task methods, offering the potential for conducting large-scale virtual screening, predicting activity profiles, and bridging the gaps in the available data.

Medicinal Polypharmacology in the Clinic - Translating the Polypharmacolome into Therapeutic Benefit.

Drugs with multiple targets, often annotated as 'unselective', 'promiscuous', 'multitarget', or 'polypharmacological', are widely considered in both academic and industrial research as a high risk due to the likelihood of adverse effects. However, retrospective analyses have shown that particularly approved drugs bear rich polypharmacological profiles. This raises the question whether our perception of the specificity paradigm ('one drug-one target concept') is correct - and if specifically multitarget drugs should be developed instead of being rejected. These questions provoke a paradigm shift - regarding the development of polypharmacological drugs not as a 'waste of investment', but acknowledging the existence of a 'lack of investment'. This perspective provides an insight into modern drug development highlighting latest drug candidates that have not been assessed in a broader polypharmacology-based context elsewhere embedded in a historic framework of classical and modern approved multitarget drugs. The article shall be an inspiration to the scientific community to re-consider current standards, and more, to evolve to a better understanding of polypharmacology from a challenge to an opportunity.

AI for targeted polypharmacology: The next frontier in drug discovery.

In drug discovery, targeted polypharmacology, i.e., targeting multiple molecular targets with a single drug, is redefining therapeutic design to address complex diseases. Pre-selected pharmacological profiles, as exemplified in kinase drugs, promise enhanced efficacy and reduced toxicity. Historically, many of such drugs were discovered serendipitously, limiting predictability and efficacy, but currently artificial intelligence (AI) offers a transformative solution. Machine learning and deep learning techniques enable modeling protein structures, generating novel compounds, and decoding their polypharmacological effects, opening an avenue for more systematic and predictive multi-target drug design. This review explores the use of AI in identifying synergistic co-targets and delineating them from anti-targets that lead to adverse effects, and then discusses advances in AI-enabled docking, generative chemistry, and proteochemometric modeling of proteome-wide compound interactions, in the context of polypharmacology. We also provide insights into challenges ahead.

Investigating Polypharmacology through Targeting Known Human Neutrophil Elastase Inhibitors to Proteinase 3.

Using a combination of multisite λ-dynamics (MSλD) together with in vitro IC50 assays, we evaluated the polypharmacological potential of a scaffold currently in clinical trials for inhibition of human neutrophil elastase (HNE), targeting cardiopulmonary disease, for efficacious inhibition of Proteinase 3 (PR3), a related neutrophil serine proteinase. The affinities we observe suggest that the dihydropyrimidinone scaffold can serve as a suitable starting point for the establishment of polypharmacologically targeting both enzymes and enhancing the potential for treatments addressing diseases like chronic obstructive pulmonary disease.

Recent advances in multitarget-directed ligands via in silico drug discovery.

To combat multifactorial refractory diseases, such as cancer, cardiovascular, and neurodegenerative diseases, multitarget drugs have become an emerging area of research aimed at 'synthetic lethality' (SL) relationships associated with drug-resistance mechanisms. In this review, we discuss the in silico design of dual and triple-targeted ligands, strategies by which specific 'warhead' groups are incorporated into a parent compound or scaffold with primary inhibitory activity against one target to develop one small molecule that inhibits two or three molecular targets in an effort to increase potency against multifactorial diseases. We also discuss the analytical exploration of structure-activity relationships (SARs), physicochemical properties, polypharmacology, scaffold feature extraction of US Food and Drug Administration (FDA)-approved multikinase inhibitors (MKIs), and updates regarding the clinical status of dual-targeted chemotypes.

Medicinal polypharmacology: Exploration and exploitation of the polypharmacolome in modern drug development.

At the core of complex and multifactorial human diseases, such as cancer, metabolic syndrome, or neurodegeneration, are multiple players that cross-talk in robust biological networks which are intrinsically resilient to alterations. These multifactorial diseases are characterized by sophisticated feedback mechanisms which manifest cellular imbalance and resistance to drug therapy. By adhering to the specificity paradigm ("one target-one drug concept"), research focused for many years on drugs with very narrow mechanisms of action. This narrow focus promoted therapy ineffectiveness and resistance. However, modern drug discovery has evolved over the last years, increasingly emphasizing integral strategies for the development of clinically effective drugs. These integral strategies include the controlled engagement of multiple targets to overcome therapy resistance. Apart from the additive or even synergistic effects in therapy, multitarget drugs harbor molecular-structural attributes to explore orphan targets of which intrinsic substrates/physiological role(s) and/or modulators are unknown for future therapy purposes. We designated this multidisciplinary and translational research field between medicinal chemistry, chemical biology, and molecular pharmacology as 'medicinal polypharmacology'. Medicinal polypharmacology emerged as alternative approach to common single-targeted pharmacology stretching from basic drug and target identification processes to clinical evaluation of multitarget drugs, and the exploration and exploitation of the 'polypharmacolome' is at the forefront of modern drug development research.

Calcium channel blockers' contribution to overcoming Current drug discovery challenges in Alzheimer's disease.

INTRODUCTION: Alzheimer's disease (AD) is a progressive, irreversible, and multifactorial brain disorder that gradually and insidiously destroys individual's memory, thinking, and other cognitive abilities. AREAS COVERED: In this perspective, the authors examine the complex and multifactorial nature of Alzheimer's disease and believe that the best approach to develop new drugs is the MTDL strategy, which obviously faces several challenges. These challenges include identifying the key combination of targets and their suitability for coordinated actions, as well as developing an acceptable pharmacokinetic and toxicological profile to deliver a drug candidate. EXPERT OPINION: Since calcium plays a crucial role in the pathology of AD, a polypharmacological approach with calcium channel blockers reinforced by activities targeting other factors involved in AD is a serious option in our opinion. This is exemplified by a phase III clinical trial using a drug combination approach with Losartan, Amlodipine (a calcium channel blocker), and Atorvastatin, as well as several MTDL-based calcium channel blockade approaches with a promising in vitro and in vivo profile.

Differential network analysis of ROS1 inhibitors reveals lorlatinib polypharmacology through co-targeting PYK2.

Multiple tyrosine kinase inhibitors (TKIs) are often developed for the same indication. However, their relative overall efficacy is frequently incompletely understood and they may harbor unrecognized targets that cooperate with the intended target. We compared several ROS1 TKIs for inhibition of ROS1-fusion-positive lung cancer cell viability, ROS1 autophosphorylation and kinase activity, which indicated disproportionately higher cellular potency of one TKI, lorlatinib. Quantitative chemical and phosphoproteomics across four ROS1 TKIs and differential network analysis revealed that lorlatinib uniquely impacted focal adhesion signaling. Functional validation using pharmacological probes, RNA interference, and CRISPR-Cas9 knockout uncovered a polypharmacology mechanism of lorlatinib by dual targeting ROS1 and PYK2, which form a multiprotein complex with SRC. Rational multi-targeting of this complex by combining lorlatinib with SRC inhibitors exhibited pronounced synergy. Taken together, we show that systems pharmacology-based differential network analysis can dissect mixed canonical/non-canonical polypharmacology mechanisms across multiple TKIs enabling the design of rational drug combinations.

KinomeMETA: meta-learning enhanced kinome-wide polypharmacology profiling.

Kinase inhibitors are crucial in cancer treatment, but drug resistance and side effects hinder the development of effective drugs. To address these challenges, it is essential to analyze the polypharmacology of kinase inhibitor and identify compound with high selectivity profile. This study presents KinomeMETA, a framework for profiling the activity of small molecule kinase inhibitors across a panel of 661 kinases. By training a meta-learner based on a graph neural network and fine-tuning it to create kinase-specific learners, KinomeMETA outperforms benchmark multi-task models and other kinase profiling models. It provides higher accuracy for understudied kinases with limited known data and broader coverage of kinase types, including important mutant kinases. Case studies on the discovery of new scaffold inhibitors for membrane-associated tyrosine- and threonine-specific cdc2-inhibitory kinase and selective inhibitors for fibroblast growth factor receptors demonstrate the role of KinomeMETA in virtual screening and kinome-wide activity profiling. Overall, KinomeMETA has the potential to accelerate kinase drug discovery by more effectively exploring the kinase polypharmacology landscape.

Ligand recognition and G-protein coupling of trace amine receptor TAAR1.

Trace-amine-associated receptors (TAARs), a group of biogenic amine receptors, have essential roles in neurological and metabolic homeostasis1. They recognize diverse endogenous trace amines and subsequently activate a range of G-protein-subtype signalling pathways2,3. Notably, TAAR1 has emerged as a promising therapeutic target for treating psychiatric disorders4,5. However, the molecular mechanisms underlying its ability to recognize different ligands remain largely unclear. Here we present nine cryo-electron microscopy structures, with eight showing human and mouse TAAR1 in a complex with an array of ligands, including the endogenous 3-iodothyronamine, two antipsychotic agents, the psychoactive drug amphetamine and two identified catecholamine agonists, and one showing 5-HT1AR in a complex with an antipsychotic agent. These structures reveal a rigid consensus binding motif in TAAR1 that binds to endogenous trace amine stimuli and two extended binding pockets that accommodate diverse chemotypes. Combined with mutational analysis, functional assays and molecular dynamic simulations, we elucidate the structural basis of drug polypharmacology and identify the species-specific differences between human and mouse TAAR1. Our study provides insights into the mechanism of ligand recognition and G-protein selectivity by TAAR1, which may help in the discovery of ligands or therapeutic strategies for neurological and metabolic disorders.