AXXAM

info@axxam.com

Author name: ASolia

Parkinson’s disease cellular models

α-synuclein assays in Parkinson’s drug discovery

Leave a Comment / Blog, In-vitro Assays /

Science Spyglass α-synuclein assays for Parkinson’s disease: Advanced cellular platforms for next-generation drug discovery Understanding and targeting α-synuclein aggregation is a key challenge in Parkinson’s disease drug discovery. At Axxam, we develop multiparametric cellular models to study aggregation, proteostasis, and neuronal function in physiologically relevant systems. Get in touch with our experts In this spyglass article: Growing importance of α-synuclein in neurodegenerative diseases Challenges in the α-synuclein therapeutic landscape Axxam’s platform to quantify α-synuclein aggregation Picture of iPSC-dopaneurons (FUJIFILM Cellular Dynamics) stained with b-II tubulin (neurons and neurites-green) and Hoechst for nuclei (blue) – representative of a single fov of a 384-well. Find this article interesting? Register for our webinar to discover more about how our α-synuclein assay platform supports Parkinson’s disease programs. α-Synuclein and Organelles: Key Players in the Neurodegeneration Puzzle 16 April 2026, 16:00 CEST / 10:00 EDT / 07:00 PDT Register for the webinar α-synuclein importance in neurodegeneration Neurodegenerative diseases such as Parkinson’s disease (PD), Alzheimer’s disease, amyotrophic lateral sclerosis (ALS), and frontotemporal dementia are characterized by progressive neuronal dysfunction associated with protein aggregation and organelle dysfunction. Among the proteins involved, α-synuclein (α-syn) has emerged as a central driver of Parkinson’s disease. Under physiological conditions, α-synuclein plays a role in synaptic vesicle trafficking and neurotransmitter release. However, pathological misfolding leads to toxic oligomers and fibrillar aggregates that accumulate in Lewy bodies and contribute to neuronal degeneration1. Increasing evidence highlights the role of cellular organelles in regulating protein homeostasis, particularly: lysosomes mitochondria autophagic pathways These systems maintain cellular proteostasis and prevent accumulation of misfolded proteins. In Parkinson’s disease, dysfunction of these organelles, especially lysosomal impairment, strongly contributes to α-synuclein aggregation and toxicity2. Consequently, targeting pathways involved in lysosomal function, autophagy, and protein clearance has become a promising therapeutic strategy. Despite strong biological rationale, a major limitation remains the lack of robust and physiologically relevant cellular assays capable of modeling α-synuclein aggregation and its modulation by pharmacological compounds. Challenges in α-synuclein drug discovery Traditional biochemical assays detect fibril formation in-vitro but fail to capture the complexity of cellular environments influencing aggregation, trafficking, and clearance. Conversely, many cellular models rely on overexpression systems, often leading to non-physiological phenotypes. This creates a gap between early screening assays and disease-relevant biology, slowing the identification of effective drug candidates. Next generation assays are therefore required to: Measure α-synuclein aggregation in physiological conditions using human-relevant neuronal models Capture organellar and pathway involvement, influencing aggregation, such as lysosomes and autophagy Provide quantitative and scalable readouts suitable for compound screening Advanced phenotypic and functional assays combined with disease-relevant cell systems allow the development of multiparametric cellular platforms capable of capturing the complexity of neurodegenerative processes. Request a consultation with our team Axxam’s platform to study Parkinson’s disease in-vitro To support Parkinson’s disease drug discovery efforts targeting α-synuclein, Axxam has developed an integrated cellular workflow capturing multiple aspects of Parkinson’s disease biology in human systems. The workflow includes high-content imaging assays that enable visualization and quantification of α-synuclein aggregation in human cells. These assays provide robust and scalable ways to monitor how α-synuclein accumulates and how candidate compounds may influence this process. To increase physiological relevance, aggregation analysis can be extended to human iPSC-derived dopaminergic neurons, the neuronal population most affected in Parkinson’s disease. Studying α-synuclein pathology in these cells enables evaluation of therapeutic strategies in a context that more closely reflects human disease biology. Explore our iPSC-based assay models However, Parkinson’s disease involves more than neuronal dysfunction alone. Increasing evidence highlights the important role of astrocytes and other glial cells in regulating neuronal health and maintaining proteostasis in the brain. Astrocytes contribute to protein clearance pathways and may influence the propagation or removal of pathological α-synuclein species. Incorporating these cellular interactions is therefore essential for understanding disease mechanisms and identifying effective therapeutic interventions. Beyond protein aggregation itself, Axxam’s platform also explores cellular pathways that regulate proteostasis and organelle function, particularly lysosomal activity and mitochondria responsible for maintaining protein homeostasis. This platform enhances profiling of disease phenotypes by also integrating Cell Painting, a high-content image-based profiling technique, which enables automated, quantitative analysis of organelle morphology, cellular and neurite network structures providing a holistic view of the model. Cell Painting on FUJIFILM Cellular Dynamics iPSC-derived neurons. Learn more about our cell painting expertise Functional cellular assays are complemented by electrophysiological approaches that provide direct insights into neuronal and organelle physiology. Multielectrode array (MEA) recordings allow the monitoring of neuronal network activity in dopaminergic neuron cultures, revealing how disease mechanisms or pharmacological interventions affect neuronal communication. Electrophysiological recordings from isolated lysosomes enable the investigation of ion channel activity within lysosomal membranes, an emerging area of interest in Parkinson’s disease biology. Access our expertise in electrophysiology and MEA technologies By integrating these complementary layers of information, the platform connects: α-synuclein aggregation organelle and proteostasis pathways neuronal and electrophysiological functional responses This integrated approach moves beyond single-endpoint assays and provides a broader and more mechanistic view of Parkinson’s disease biology, supporting target validation, mechanism-of-action studies, and compound screening in physiologically relevant systems. Bridging biology and drug discovery An integrated and multiparametric assay platform, such as the one we developed at Axxam, offers new opportunities to bridge the gap between target biology and therapeutic discovery. By combining: quantitative imaging human-relevant neuronal models functional electrophysiology advanced phenotypic profiling approaches (including Cell Painting) to capture high-dimensional cellular signatures researchers can gain deeper insight into disease mechanisms and compound activity. Get in touch with our experts References Pitton R. et al. Alpha-Synuclein Neurobiology in Parkinson’s Disease: A Comprehensive Review of Its Role, Mechanisms, and Therapeutic Perspectives. Brain Sci. 2025, 15, 1260. Bayati A et al. Alpha-synuclein, autophagy-lysosomal pathway, and Lewy bodies: Mutations, propagation, aggregation, and the formation of inclusions. J Biol Chem. 2024 Oct;300(10):107742. Related content α-Synuclein and Organelles: Key Players in the Neurodegeneration Puzzle 16 April 2026, 16:00 CEST / 10:00 EDT / 07:00 PDT Register for the webinar Human neuron models for scalable drug discovery of Parkinson’s disease α-synuclein aggregation assays enabling disease-relevant evaluation for hit-to-lead validation, target identification, and functional studies Download

α-synuclein assays in Parkinson’s drug discovery Read More »

GLP-1 receptor assay: drug discovery in the metabolic field

Leave a Comment / Blog, In-vitro Assays /

Science Spyglass GLP-1 receptor assay: drug discovery in the metabolic disorders field Metabolic disorders, particularly type 2 diabetes and obesity, represent a major global health burden. In the United States alone, over 30 million people live with type 2 diabetes, and one-third of the population is affected by obesity. These conditions are closely linked to increased cardiovascular risk and long-term health complications. As their prevalence continues to rise, there is an urgent need for effective and innovative pharmacological interventions to manage and treat these chronic diseases. In this article, we explore how metabolism is regulated, highlight the key cellular players, and introduce the tools developed by Axxam to study these mechanisms, focusing in particular on the GLP-1 (glucagon-like peptide-1) receptor assay. Hormonal regulation of metabolism: the role of enteroendocrine cells and incretins Metabolic regulation is tightly controlled by a complex network of hormones, many of which are secreted by enteroendocrine cells (EECs), specialized sensory cells that make up about 1% of the gut epithelium. These cells detect the presence of nutrients in the intestinal lumen via chemosensory G protein-coupled receptors (GPCRs) and taste receptors, and in response, release hormones that influence digestion, appetite, and glucose metabolism. Besides nutrient availability, this process is regulated also by other stimuli, including mechanical stretch, and neural signals. Key hormones released by EECs include GLP-1, GIP, cholecystokinin (CCK), ghrelin, and peptide YY (PYY). Among them, GLP-1 and GIP (gastric inhibitory polypeptide) are known as incretins, gut-derived hormones that enhance glucose-dependent insulin secretion, playing a pivotal role in maintaining glucose homeostasis and serve as important therapeutic targets for type 2 diabetes and obesity. The GLP-1 receptor: a key target in glucose and appetite regulation The glucagon-like peptide-1 receptor (GLP-1R) is a GPCR found primarily in pancreatic β-cells, brain, heart, kidney, and the gastrointestinal tract. It plays a key role in regulating blood sugar by enhancing insulin secretion in response to glucose and reducing glucagon secretion, which helps lower blood glucose levels. GLP-1R is activated by the hormone GLP-1, released from EECs after eating. Activation of this receptor also slows gastric emptying, promotes satiety, and reduces food intake, contributing to weight management and appetite control. From a therapeutic perspective, GLP-1 receptor agonists — drugs that mimic the endogenous hormone GLP-1 — are used to treat type 2 diabetes and obesity by improving insulin secretion, lowering blood sugar, and supporting weight reduction. While peptide-based GLP-1 receptor agonists such as Exenatide, Liraglutide, Dulaglutide, and Semaglutide have demonstrated strong efficacy, there remains significant interest in developing next-generation therapies. One key challenge is that these biologics typically require injection, which can limit patient compliance and convenience. To address this, researchers are exploring alternative routes of administration, including oral, transdermal, and inhalable formulations. In parallel, there is growing focus on small molecule GLP-1R agonists, which have the potential to be administered orally, produced more cost-effectively, and offer improved stability and pharmacokinetic profiles. These advancements aim to expand therapeutic options, enhance accessibility, and improve long-term adherence in the management of metabolic disorders. Finally, beyond their role in controlling metabolic processes, GLP-1 receptor agonists also show promising potential benefits in treating cardiovascular and neurodegenerative diseases. Axxam’s GLP-1 receptor assay: a tool for metabolic drug discovery At Axxam, we have developed and optimized a GLP-1 recombinant assay using a CHO (Chinese Hamster Ovary) cell line. This GLP-1 receptor assay is ideal for studying receptor activation mediated by small molecules. The GLP-1 receptor pathway involves GLP-1 binding to its receptor (GLP-1R), which activates G-proteins, leading to increased cyclic adenosine monophosphate (cAMP) levels and subsequent activation of protein kinase A (PKA). This pathway primarily influences insulin secretion and glucagon inhibition in pancreatic beta and alpha cells, respectively. In our assay, we employ the HTRF® cAMP Gs HiRange detection kit from Revvity as the readout for the measurement of the cAMP levels produced upon GLP1 receptor activation. Talk with our experts The cAMP kit operates on a competitive format involving a specific antibody labeled with cryptate (donor) and cAMP coupled to d2 (acceptor). This setup enables direct characterization of all types of compounds acting on Gs-coupled receptors in either adherent or suspension cells. Native cAMP produced by the cells competes with the d2-labeled cAMP for binding to monoclonal anti-cAMP Eu3+ cryptate. Source: www.revvity.com The assay has been validated with both GLP-1 (7-36), the endogenous physiological full agonist secreted by intestinal L-cells, and its metabolite GLP1 (9-36) which is a weaker partial agonist. The EC50 of GLP1 (7-36) is in the expected 2 digits pM range (25-60pM), while its metabolite shows a potency which is 4 logs lower and falls into the low µM range. We also tested the effect of the known covalent allosteric modulator BETP, which – as expected – significantly potentiated the activity of GLP-1 (9-36) on the GLP-1 receptor. This GLP-1 receptor assay is suitable for compound profiling studies as well as high throughput screening campaigns with proven high sensitivity to the GLP-1 (7-36) reference ligand and robustness. The GLP-1 receptor assay is also suitable for testing natural compounds and extracts, supporting the development of nutraceuticals and functional food products aimed at improving metabolic health. Axxam’s GLP-1 secretion assay: metabolic drug discovery from a different perspective Studies have shown that fatty acids and other endogenous ligands may engage with relevant GPCRs, including GPR40, GPR120, GPR119 and TGR5, to promote GLP-1 secretion. Taking into account the above-mentioned considerations on cost and safety aspects, oral small molecule agonists stimulating endogenous GLP-1 secretion by intestinal L-cells may offer a promising alternative for developing new treatments for Type 2 diabetes and obesity. As a novel method for identifying compounds that promote the release of the physiological agonist GLP-1, we have developed and optimized a GLP-1 secretion assay. We employ NCI-H716 * and STC-1 cell lines, well-characterized models respectively for human and murine intestinal L-cells. To detect GLP-1 secretion from enteroendocrine cell supernatants, we exploit a reporter cell line that expresses the recombinant GLP-1 receptor in combination with the chAMPion reporter system in a CHO background. This cell line expresses a

GLP-1 receptor assay: drug discovery in the metabolic field Read More »

AXXVirtual for drug discovery

AXXVirtual: a chemistry-driven virtual library for drug discovery

Leave a Comment / Blog, Compound Libraries /

Science Spyglass Building AXXVirtual: a chemistry-driven virtual library for drug discovery In the same way as in high-throughput screening (HTS), the quality of the screened library plays a crucial role in the success of virtual screening. While virtual screening enables the exploration of much broader and more diverse chemical spaces, many virtual libraries are populated with molecules that, while computationally attractive, are difficult — or even impossible — to synthesize. For many drug discovery programs, this stage represents a major bottleneck: synthesis can be slow, unpredictable, and resource-intensive, delaying the confirmation of biological activity and the chemical exploration of the promising compounds. This is precisely the gap that the AXXVirtual library was designed to overcome. Beyond ensuring high-quality, drug-like chemical space, this 185 million non-commercial small molecule library was built with synthesis feasibility at its core. Every AXXVirtual compound can be produced in just 2–3 steps from readily available building blocks. This unique design guarantees that virtual hits are not just theoretical possibilities but tangible molecules, accessible within controlled and predictable timelines. As a result, AXXVirtual enables researchers to reach in vitro confirmation faster, accelerating the path from virtual screening to validated hits. Developed through a structured four-stage process, the compounds were rigorously selected by applying strict rules and filters to guarantee drug-like properties and structural diversity, thereby enabling efficient downstream development. This article walks you through the principles behind building a high-quality virtual library for drug discovery and shows how these concepts were applied in the design of the 185 million compound AXXVirtual library. Want to explore AXXVirtual for your projects? Get in touch Designing for the real lab: the synthetic accessibility Synthetic feasibility has become a key parameter in the design of virtual libraries, ensuring that computational efforts translate into compounds that can be readily produced for downstream testing [1, 2]. The core of this approach lies in relying on synthetic routes based on established reaction classes that have demonstrated their value over decades — including, for instance, amide coupling and the Suzuki–Miyaura reaction. Despite the emergence of new methodologies, these reactions remain the backbone of medicinal chemistry due to their efficiency, reproducibility, scalability, and high yields [3]. Built on the concepts previously described, the AXXVirtual compounds have been designed to be synthesized through twelve synthetic routes, each consisting of two to three steps, employing nine reliable reactions. The building blocks, more than 12.000 in total, were selected from the inventory of a trusted partner and are immediately available, eliminating delays from external orders. In addition, the reagents have been carefully selected to ensure clean reactions, minimizing side products and regioisomer formation. This thoughtful combination of proven chemistry and readily available reagents enables a fast and efficient synthesis, allowing the preparation of 100-120 compounds within just two to three weeks. To maintain these standards, the library is regularly updated in line with the partner’s inventory, making AXXVirtual a dynamic and continuously evolving library. Designing smarter: AI-powered properties and synthetic feasibility prediction Artificial intelligence (AI) is playing an increasingly important role in the landscape of virtual libraries for drug discovery by enabling more accurate and efficient predictions of molecular properties and synthetic accessibility. Today, a variety of machine learning models are employed to predict molecular properties with increasing accuracy and speed. These models rely heavily on large and curated training sets – databases of molecules with known experimental properties – to identify patterns and relationships between molecular features, such as size, chemical groups, and shape, and their observed behaviors, such as solubility and toxicity. Unlike simple rule-based methods, machine learning adapts to the complexity and the variability inherent in chemical data and this allows it to capture subtle influences and nonlinear effects that traditional rules often miss. For synthetic accessibility, tools like RAscore (Retrosynthetic Accessibility Score) [8] are widely used. RAscore is a machine learning classifier trained on the outcomes of the retrosynthetic planning software AiZynthFinder. Instead of running a full retrosynthetic analysis for each molecule — which is impractical when dealing with millions of compounds — RAscore provides a rapid estimate of whether a compound is likely to be synthesizable using known building blocks and reaction rules. Applying RAscore to evaluate AXXVirtual compounds, we found that the vast majority (96%) scored above 0.8 on the 0-to-1 scale, confirming their high synthetic accessibility. This result further highlights the robustness of the chemistry underpinning our library. Designing for success: from synthesizable to developable molecules While synthetic accessibility defines what can be built, drug-likeness defines what is worth pursuing. Virtual libraries should not only contain compounds that are synthetically feasible, but also exhibit molecular properties that make them suitable candidates for future development. This includes properties that impact solubility, permeability, metabolic stability, and safety. The concept of drug-likeness is grounded in the empirical observation of properties shared by orally bioavailable drugs. Large-scale analyses of marketed drugs and clinical candidates have revealed that certain molecular properties – such as moderate size and balanced lipophilicity – are associated with favorable pharmacokinetic behavior. These findings led to the formulation of guidelines, with Lipinski’s Rule of Five (Ro5) [4] and Veber’s rules [5] being among the most well-known and widely adopted. In parallel with physicochemical profiling, the quality of chemical libraries, including virtual ones, must be ensured by excluding compounds known to cause assay interference or unreliable readouts. A major class of such problematic molecules is represented by PAINS (Pan-Assay Interference compoundS), which are chemical structures prone to react nonspecifically with numerous biological targets rather than specifically affecting one desired target [6]. Rhodanines exemplify the extent of the problem. More than 2.000 rhodanines have been reported to have biological activity in over 400 papers. However, a publication by Bristol-Myers Squibb points out that these compounds undergo light-induced reactions that irreversibly modify proteins. It is hard to imagine how such a mechanism could be optimized to produce a drug or a useful tool [7]. At Axxam, more than 20 years of experience with physical libraries have given us deep insight into selecting the right compounds

AXXVirtual: a chemistry-driven virtual library for drug discovery Read More »

Generative AI for PPI modulators

Designing PPI modulators with Generative AI

Leave a Comment / Blog, Compound Libraries /

Science Spyglass Designing a library of PPI modulators with Generative Artificial Intelligence Why Generative AI for PPI Modulators? Protein–protein interactions (PPIs) play a central role in the regulation of cellular signaling, structural organization, and enzymatic function. Dysregulation of specific PPIs has been implicated in a wide range of pathologies, including oncogenesis, neurodegenerative disorders, and infectious diseases. Despite their biological relevance, PPIs have long posed a challenge for small-molecule drug discovery due to their typically large, shallow, and hydrophobic binding interfaces that often involve dispersed hot spots making it difficult to achieve high-affinity and selective binding with conventional small molecules. However, advances in structural biology and computational modeling have begun to redefine the tractability of PPIs. Among the most promising developments in this space is the application of generative artificial intelligence (Generative AI), which offers powerful new capabilities to explore chemical space and maximize the chance of binding at protein-protein interfaces. Figure 1. Example of protein-protein interaction (PPI) molecules binding at the interface of two protein units. Below we describe our application of Generative AI in designing a library of PPI modulators, called the AXXPPI library. Furthermore, important AI concepts are briefly described at the end of the article. Ready to accelerate your drug discovery with the AXXPPI library? Contact us Data curation for PPI modulator design High-quality data is foundational to the success of any machine learning–driven drug discovery project, and this is especially true when targeting complex systems like protein–protein interactions. Accurate, well-curated datasets enable models to learn meaningful structure–activity relationships and generate chemically plausible, target-relevant molecules. For this project, we assembled a diverse and representative dataset of known PPI modulators by integrating compounds from several specialized sources, including 2P2Idb, iPPI-DB, Timbal, ChEMBL, and peer-reviewed literature. Each entry was carefully curated to ensure correct annotation of bioactivity, target interface, and molecular structure, enabling downstream modeling to focus on truly relevant chemical features. This rigorous data preparation step is essential not only for training robust models but also for minimizing bias and improving the translational relevance of the predicted molecules. Finetuning a pretrained drug-like model To explore the chemical space of PPI modulators, we employed de novo molecular generation using state-of-the-art generative modeling frameworks. As a starting point, we utilized a model pretrained on large, drug-like chemical libraries, which had learned the general rules of chemical syntax and structure.  Figure 2. Schematic representation of ideal molecules (yellow spheres) within focused (light grey) and general (dark grey) chemical space. To adapt this model to PPI-relevant scaffolds and molecular features, we applied a transfer learning strategy by fine-tuning it on our curated dataset of known PPI modulators. This domain-specific refinement enabled the generative algorithm to focus on structural motifs, physicochemical properties, and topologies commonly found in PPI-active compounds within the drug-like space. Nevertheless, further optimization of the fine-tuned model is required to directly incorporate additional design constraints such as synthetic tractability without compromising its ability to generate functionally relevant modulators with promising pharmacological profiles. De novo generation of optimized molecules To further guide the de novo generation of PPI modulators toward synthetically tractable and functionally relevant chemical space, we implemented reinforcement learning (RL) with multi-objective optimization. A key component of our reward strategy was a machine learning classifier specifically trained to distinguish PPI modulators from non-PPI compounds, providing a probabilistic measure of PPI-likeness for generated molecules. In addition to this classifier, we incorporated the Synthetic Accessibility Score (SAS) to penalize impractical structures. The reinforcement learning algorithm ranked generated molecules based on Pareto efficiency across multiple objectives, ensuring a balance between synthetic tractability and predicted biological relevance. In this framework, the pretrained generative model served as the agent, i.e., the network being actively optimized, while the fine-tuned model acted as the prior, i.e. a non-trainable reference that contributes mutations and maintains the generation of chemically valid and PPI-relevant scaffolds. This setup allowed us to efficiently navigate the multi-dimensional objective space and converge on high-quality candidate structures with an optimal trade-off between desirability and diversity. Figure 3. Evaluation of the Machine Learning Classifier’s ability to discriminate known PPIs (not used during the training process – light green) from random compounds (light grey). Filtering, evaluation and synthesis Once molecules are generated, they must undergo a rigorous filtering and prioritization process before synthesis. This workflow follows a funnel-like approach, where large numbers of candidate compounds are progressively narrowed down.   Figure 4. Filtering funnel to select a dataset of molecules to be synthesized. Initially, molecules are removed if they violate medicinal chemistry filters such as REOS or contain undesirable reactive groups. Additional filtering ensures that selected compounds are sufficiently distinct from the training set to avoid rediscovery, while also maximizing chemical diversity. Finally, compounds are evaluated for predicted ADMET properties to ensure acceptable pharmacokinetic and safety profiles. Only a small, carefully selected subset of molecules meeting all these criteria proceeds to synthesis and experimental validation. Use of the PPI library in Axxam HTS A focused PPI compound library is a valuable resource for high-throughput screening (HTS) campaigns targeting challenging biological interfaces. Unlike traditional approaches to PPI-focused libraries, which often rely on large and lipophilic chemotypes with limited drug-like properties to disrupt or stabilize PPIs, our strategy was to combine the structural features required for engaging protein–protein interfaces with careful optimization of physicochemical and developability parameters. The result is a collection of compounds that retain the 3D topologies and interaction patterns relevant for PPI modulation, while maintaining chemical tractability and favorable drug-like characteristics. This makes the library uniquely positioned to deliver high-quality starting points for hit discovery campaigns in the PPI space, increasing their chance for success. PPI-focused libraries are particularly valuable in therapeutic areas where dysregulated protein–protein interactions play a central role in pathogenic interactions. Key areas include: Oncology: Numerous cancer pathways are driven by aberrant PPIs, such as p53–MDM2, BCL-2 family interactions, and β-catenin–TCF. These interactions regulate cell cycle progression, apoptosis, and transcription, making them prime targets for small-molecule inhibitors that can restore normal signaling or induce cell death in tumor cells. Neurodegenerative diseases:

Designing PPI modulators with Generative AI Read More »

Artificial intelligence in drug discovery

Artificial intelligence in drug discovery

Leave a Comment / Blog, Integrated Drug Discovery /

Science Spyglass How artificial intelligence is supporting the small molecule drug discovery process Faster and more efficient The discovery of new small molecule drug candidates has always been a complex, time-consuming, and costly endeavor. For decades, scientists have worked tirelessly to identify new chemical compounds that interact with specific biomolecules in the human body in therapeutically meaningful ways. Today, artificial intelligence in drug discovery is driving a major transformation of the process, providing scientists with powerful new tools to accelerate their work. In simple terms, artificial intelligence (AI) refers to machines or computer programs that can perform tasks that usually require human intelligence, such as recognizing patterns, learning from experience, or making decisions. Machine learning (ML) is a specific type of AI that uses data to learn and improve over time without being explicitly programmed for every scenario. Let’s explore how AI and ML are revolutionizing small molecule drug discovery and why it matters. Let’s talk science and strategy: Schedule a call with our experts Enter artificial intelligence: smarter and faster drug discovery This is where AI and ML come in. These technologies can process vast amounts of data quickly and identify patterns that humans might miss. Artificial intelligence in drug discovery can perform a wide range of tasks, including: Identify novel therapeutic targets: AI can integrate vast biological datasets to uncover new disease-related targets that may be overlooked by traditional methods. Predict the molecular architecture of protein receptors: AI predicts protein structure directly from the amino acid sequence, bypassing time-consuming and costly experiments. Predict how molecules behave: AI models estimate how a particular molecule might interact with a protein in the body, helping researchers decide whether it’s worth testing. Design new molecules: ML can generate entirely new chemical structures that have the potential to become effective drugs. Prioritize candidates for synthesis: AI and ML models assess ADME (absorption, distribution, metabolism, and excretion) properties, toxicity, and stability to help select the most promising compounds for experimental validation. Improve efficiency: By automating early steps in drug discovery, AI reduces the time and cost to bring a new drug to market. Let’s break down each of these contributions. 1. Identifying novel targets AI plays an increasingly important role in target identification, the critical first step in the drug discovery process. By integrating and analyzing large-scale omics datasets, including genomic, transcriptomic, proteomic, and clinical data, AI systems can detect complex biological patterns that point to previously unrecognized disease drivers. These insights can reveal novel, high-potential therapeutic targets and enable researchers to stratify diseases more precisely. This data-driven approach goes beyond what traditional target discovery methods can achieve, particularly in areas like oncology, rare diseases, and multifactorial conditions. AI models can also prioritize targets based on predicted druggability and relevance to patient subgroups, ultimately helping de-risk early discovery efforts. Discover Axxam approach to target identification and validation 2. Predicting protein (receptor) structure AI helps predict protein structures by analyzing amino acid sequences and determining how they fold into a unique 3D shape. This structural information is essential, as a protein’s shape defines its role in the body and forms the receptor site where small molecule drugs can bind. These interactions rely on shape complementarity and non-covalent molecular forces within specific binding pockets. AI-based systems used to predict protein structures are trained on thousands of known examples; one such system is AlphaFold. These systems identify folding patterns and structural motifs, enabling them to predict the 3D conformation of proteins from their amino acid sequences with remarkable speed and accuracy. In essence, by acting like an intelligent puzzle solver, AI dramatically accelerates structural biology. The significance of this breakthrough was recognized by the Nobel Prize in Chemistry awarded to the developers of AlphaFold. 3. Predicting molecular behavior At the heart of many diseases is a faulty protein. Scientists aim to find molecules that can bind to these proteins to inhibit or activate their function. The ability of small molecules to recognize and bind to specific pockets on the protein receptors relies on factors such as shape complementarity, molecular interaction forces, and thermodynamic considerations. Traditionally, this challenge is addressed through High-Throughput Screening (HTS), where hundreds of thousands of compounds are tested experimentally using suitable bioassays, extensive compound libraries, and laboratory automation platforms. In contrast, by digitally simulating these molecular interactions, AI enables the virtual screening of vast compound libraries, including molecules that have not been synthesized yet. This dramatically expands the search space and can potentially save time and resources. At some point, however, predictions need to be confirmed by real experiments for which compounds need to be purchased and prepared for testing or potentially synthesized from scratch.  Importantly, HTS and AI-based virtual screening are not mutually exclusive approaches and can be used in a complementary fashion in modern hit discovery. Insights obtained from virtual screening can guide HTS efforts by focusing experimental resources on the most promising compounds. Conversely, HTS can uncover active compounds that might be missed by current models, providing valuable data that can be fed back into AI algorithms to improve future predictions. When combined strategically, AI and HTS create a powerful workflow that enhances both speed and success rates of identifying high-quality hits. Leverage the best of both worlds: Discover virtual screening and HTS at Axxam 4. Designing new molecules from scratch One of the most exciting applications of artificial intelligence in drug discovery is its ability to design new molecules. Generative AI acts as a virtual chemist, rapidly inventing novel synthesizable molecules and organizing them into virtual libraries to speed up drug discovery. Designing new molecules: AI models extract chemical rules and patterns from large datasets of known compounds and reactions. They use this knowledge to generate new molecular structures that align with specific goals, such as targeting a particular protein or exhibiting desired properties. Ensuring synthetic accessibility: Generative AI can predict whether a proposed molecule can realistically be synthesized using available chemical building blocks and known reactions. Some AI systems, like SynFormer, even generate the synthetic pathways alongside the molecules, ensuring that the designs

Artificial intelligence in drug discovery Read More »

Neuroscience drug screening

Next generation neuroscience drug screening

Leave a Comment / Blog, In-vitro Assays, Innovative Biology, Integrated Drug Discovery /

Science Spyglass Next generation neuroscience drug screening Tessara’s RealBrain® neural micro-tissues validate compound effects in Axxam’s High-Content Imaging workflow Application note Axxam S.p.A. – Milan (Italy) Tessara Therapeutics Pty Ltd. – Melbourne (Australia) Keywords: chemotherapy induced neuropathy (CIPN), induced pluripotent stem cell (iPSC), neurotoxicity, high content imaging, mini brain, organoids, drug discovery, neural micro-tissues, neurodegenerative diseases. Introduction The use of three-dimensional (3D) biology has revolutionized the way to model and study complex biological processes, surpassing the traditional two-dimensional (2D) approaches. While 2D cell cultures have been the standard for many years, they fail to capture the intricate cell-to-cell and cell-to-matrix interactions that occur in vivo. In contrast, 3D biology offers a more physiologically relevant environment, allowing for the study of cellular behaviors in a context that mimics in vivo conditions more closely. The growing need for non-animal models in biomedical research is also driving the shift toward 3D systems. Indeed, in 2022, the U.S. FDA made headlines by endorsing non-animal testing methods for drug discovery and development, emphasizing the importance of human-relevant models for in vitro drug discovery. Whilst the global life science community has begun rapidly expanding and adopting 3D human tissue models such as spheroids and organoids, a number of limitations have arisen. Spheroids for example are reproducible, but like 2D cultures, the structure of their neural networks is markedly different from the human brain. Organoids can mimic brain complexity but have lacked reproducibility and have been difficult and slow to manufacture. In response to this demand and to facilitate the uptake of 3D models that can better meet the requirements of a preclinical drug discovery pipeline, a new technology from Tessara Therapeutics was introduced. Tessara’s 3D models combined with Axxam’s workflow Based in Melbourne Australia, Tessara is a world leader in 3D cell-based models of the brain. In a world-first innovation, Tessara has developed its RealBrain® neural micro-tissue technology and 3D cell-based models that replicate the biological complexity of the human brain in a reproducible manner. Tessara has validated and recently launched two brain models: the ArtiBrain™ model (healthy human brain), and the ADBrain™ model (sporadic Alzheimer’s disease (AD), representing ~98% of all AD cases). Tessara has developed this platform with commercial scale manufacturing processes, delivering models that are predictive, reproducible at scale and cost-effective. Combining these relevant in vitro models with suitable approaches to fully harness their potential could be transformative for the drug discovery field. In this context, high-content screening (HCS) and image-based readouts represent ideal tools for exploring the dynamic behaviours of cells and networks within 3D environments. Through image-based analysis, researchers can explore the complex biology of 3D systems in unprecedented detail across multiplecellular parameters, generating vast datasets from complex biological systems, facilitating the identification of subtle phenotypic changes that would be missed in traditional screening methods. This technology pipeline enables a deeper understanding of drug responses, toxicity, and mechanisms of action in more relevant biological contexts, offering greater translational value for pre-clinical studies. Incorporating these advanced technologies into research pipelines is transforming the drug discovery and disease modeling field. Generation of Tessara’s RealBrain® neural micro-tissues Tessara’s RealBrain® drug screening platform is based on manufactured human mimetic brain micro-tissues that closely recapitulate neural physiology and pathophysiology. RealBrain® neural micro-tissues are generated by encapsulating primary or induced pluripotent stem cell (iPSC)-derived neural precursor cells in a proprietary hydrogel matrix composed of chemically defined biomaterials. The RealBrain® hydrogel provides the optimal micro-environment to activate endogenous cellular programs of neuro-development in vitro. Over three weeks of maturation, the developing neural and glial cells remodel their micro-environment, migrate in 3 dimensions, form a complex network and replace the synthetic hydrogel with their own cell-secreted extracellular matrix (ECM). The resulting RealBrain® neural micro-tissues closely model human neurophysiology – they respond to neurotransmitters, feature a genetic profile representative of human brain tissue, and under controlled conditions can develop the complex pathological hallmarks of Alzheimer’s disease. These neural micro-tissues are also compatible with all standard laboratory workflows, from immunocytochemistry and confocal microscopy that doesn’t require the use of any clearance protocols, through to genomics and proteomics applications and other functional assays such as calcium imaging. Imaging the RealBrain® micro-tissues with Axxam’s High Content Imaging workflow In this study, we employed an automated high-content confocal imaging system (Opera Phenix Plus, Revvity) to acquire detailed 3D images of RealBrain® micro-tissues, stained with fluorescent markers to visualize neuronal cells (β-III Tubulin), glial cells (GFAP) and cell nuclei (DAPI) (Figure 1); these images illustrate the structural organization and neuronal differentiation within the brain micro-tissue. Figure 1 Representative images of a brain micro-tissue acquired by High Content Microscopy (Opera Phenix Plus, Revvity). (A) Brightfield image showing the overall morphology of the microo-tissue. (B) DAPI staining (blue) highlighting cell nuclei distribution. (C) βIII-Tubulin staining (green) marking neuronal structures. (D) Merged image combining DAPI and βIII-Tubulin signals, providing a composite view of the organoid’s neuronal architecture. Using two different acquisition setups and z-stack acquisitions we were able to capture multiple optical slices, enabling comprehensive 3D reconstruction of the neural micro-tissues at different levels of resolution (Figure 2). Figure 2 High-resolution 3D imaging of microtissues acquired through z-stack acquisition, enabling detailed visualization of cellular structures at different depths. Left panel: A volumetric reconstruction of the microtissue, showcasing its overall morphology and spatial distribution of cellular components. Right panel: Cross-sectional view highlighting internal structural organization, revealing intricate cellular networks and fiber orientations. Neuronal cells are stained by βIII-Tubulin (green) whilst glial cells are marked by GFAP staining (red). Key parameters such as z-stack step size, magnification, field of view, and laser intensities were carefully optimized to ensure both signal clarity and high-quality micro-tissue reconstruction. We balanced acquisition time and resolution to maintain both data quality and efficiency. The resulting images were analyzed using Harmony software (Revvity), where we developed a customized pipeline to visualize cellular features and extract multiparametric data. To assess the impact of magnification on data quality, we compared two settings: 20X (high magnification) and 5X (low magnification) (Figure 3). Figure 3 Examples of acquisition parameters

Next generation neuroscience drug screening Read More »

Scroll to Top