AXXAM

Author name: ASolia

Artificial intelligence in drug discovery

Artificial intelligence in 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

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 »

Potency assays for gene therapy CMC studies

Science Spyglass Development of potency assays for clinical studies on gene therapy candidates Gene therapy has emerged as a promising and powerful treatment modality for numerous human diseases, with Adeno-Associated Virus (AAV) vectors recognized as some of the safest and most widely used delivery systems. For these complex biological medicines, where product testing poses unique challenges, potency assays play a critical role in clinical studies and drug licensing. Leveraging Axxam’s advanced technological platforms, these potency assays can be tailored to meet the specific requirements of various application fields, providing robust solutions to this critical step in the drug development process. AAV vectors have been proven to be particularly successful in ophthalmology. In this field, Axxam has recently developed and validated on behalf of GenSight Biologics a potency assay* to support clinical studies of an AAV-based optogenetic drug, i.e. GS030-DP from GenSight Biologics, for visual restoration in patients with Retinitis Pigmentosa. Explore more about gene therapy and potency assays in the expandable boxes below or scroll down to dive straight into our case study on a potency assay for Retinitis Pigmentosa gene therapy. AAVs as a promising strategy for gene therapy Gene therapy is a therapeutic strategy based on the modification of gene expression within target cells via the employment of viral or non-viral vectors. Up to date, most of the US Food and Drug Administration (FDA)-approved gene therapies are viral based (Wang et al., 2024 Signal Transduct Target Ther). The viral vector approach takes advantage of the natural ability of viruses to infect human cells. Viral pathological genetic sequences are replaced by the desired therapeutic genes and target cells are then infected with the modified viruses, leading to the incorporation of the therapeutic material into the nuclei (Ghoraba et al., 2022 Clin Ophthalmol).   Amongst the viral vectors studied and used for in-vivo gene therapy -which include adenovirus, retrovirus, lentivirus, and herpes simplex virus-, AAV vectors have attracted a significant amount of attention in the field, due to their broad tissue tropism, good safety profile and versatile manufacturing processes. In fact, AAVs are non-pathogenic, do not integrate into the host genome, can sustain long-term gene expression and are often inherently capable of efficient cellular entry thus enhancing transduction efficiency (Wang et al., 2024 Signal Transduct Target Ther).   Notably, the form of AAV used in gene therapy is not the wild-type but a recombinant one (rAAV), which lacks viral DNA and instead contains the recombinant DNA. This will persist as episome in the nucleus of transduced cells and will not be integrated into the host genome, thus it will be diluted over time as cells proliferate and will be eventually lost, which is ideal for some gene therapy applications (Naso et al., 2017 BioDrugs). AAV-based gene therapy for ocular diseases rAAVs have the potential to find several applications in the clinic and are currently being tested in clinical trials for a wide range of human diseases, spamming from ocular and neurological to metabolic, hematological, cardiovascular and oncogenic diseases (Wang et al., 2024 Signal Transduct Target Ther). Amongst them, ophthalmology is certainly the main application field of rAAVs. This is due to several reasons: the eye has special immune features that reduce AAV immunogenicity; the eye is small and compartmentalized, thus being easily accessible and requiring low rAAV doses; many ocular diseases are monogenic and thus are suitable for gene therapy.   Gene therapy for ocular diseases was approved by the FDA in 2017 to treat pediatric patients with an inherited retinal disease. Several studies are currently focusing on other possible gene therapies for a wide range of ocular diseases involving from the cornea to the retina (Wang et al., 2024 Signal Transduct Target Ther; Ghoraba et al., 2022 Clin Ophthalmol).   A specialized approach of gene therapy particularly used in the eye is optogenetics. It consists in delivering genetic information that encodes for light sensitive proteins to non-photoreceptor retinal neurons such as ganglion cells, making them sensitive to light stimulation and bypassing the photoreceptors (Ghoraba et al., 2022 Clin Ophthalmol). This strategy could improve vision in patients with Retinitis Pigmentosa (RP) or other inherited diseases where photoreceptors are damaged. The use of optogenetics to restore vision was initially proposed in 2006 by Pan and colleagues (Bi et al., 2006 Neuron). A decade later, the biopharma company GenSight Biologics developed GS030, an optogenetic treatment candidate combining an AAV2-based gene therapy (GS030-DP) with the use of light-stimulating goggles (GS030-MD). As described in the case study below, Axxam was involved in developing and validating the GS030-DP potency assay, as shown in Gael et al., 2018.Download the poster on GS030-PD Potency assays for assessing biological medicines When developing any kind of pharmaceutical, it is mandatory to establish its potency to comply with authorities’ regulations (e.g. FDA or European Medicines Agency, EMA). A potency assay is a quantitative measure of the biological activity of a drug; more specifically, it measures the ability of the product to elicit a specific response in a disease-relevant context. It is used to evaluate product features associated with its quality and manufacturing controls to assure product identity, purity, stability in all phases of clinical studies.   The first step in potency assay development is the choice of the best experimental method, which depends on the mechanism of action of the candidate product. Then, characteristics to be assessed through the assay are the followings: linearity, precision, accuracy, robustness, repeatability, specificity. In fact, potency assays should be able to detect small variations in drug product potency in a robust and specific manner, suitable to assess batch-to-batch variability and drug stability in long-term storage.   Such evaluations can be particularly challenging in case of biological medicines, such as cell and gene therapy medicinal products and tissue engineered products, which have nucleic acid, viral vectors, viable cells and tissues as starting material (Salmikangas et al., 2023 Front Med). For cells, viability and cell phenotype are important features but alone are not sufficient to address biological activity. For example, if cells are transduced with

Potency assays for gene therapy CMC studies Read More »

Axxam in oncology drug discovery

Empowering oncology drug discovery

Science Spyglass Empowering oncology drug discovery with Axxam’s tailored solutions At Axxam, we are committed to advancing oncology drug discovery by applying a range of approaches designed to define molecular targets or disease mechanisms and to identify small molecule hits and lead candidates as starting points for drug development in cancer research. We offer tailored assays and screening solutions, addressing many of the biological mechanisms underlying complex cancer hallmarks: Advanced assays for biomolecular interactions: Our assay designs are based on the current structural understanding of crucial molecular mechanisms driving cancer progression, such as protein-protein or protein-DNA/RNA interactions. This enables us to identify even weakly active small molecules. Biophysical methods for drug interaction validation: We utilize techniques such as thermal shift analysis and microscale thermophoresis to confirm and explore the interactions between compounds and their targets, ensuring precise and reliable results in oncology drug discovery. Covalent binder compound collection: We have recently expanded our chemical libraries to include a library of covalent binders named AXXCovalent, with the aim of identifying lead candidates also for notoriously difficult-to-target proteins. Targeted protein degradation: Axxam has developed assays to explore targeted protein degradation, particularly to address so-called “undruggable” targets like transcription factors and intrinsically disordered proteins. We have also partnered with Symeres to generate a PROTAC (proteolysis-targeting chimeras) platform enabling the identification of degraders that act via the proteasome. Cellular platform techniques: Axxam uses advanced cellular assays to monitor pharmacological effects of compounds on epigenetic and transcriptional mechanisms, splicing processes, and signaling pathways. These assays are performed in physiologically relevant cell types as well as within native cellular environments. High-content screening with 2D and 3D models: Axxam employs high-content screening techniques to monitor changes in the cell phenotypes, both in traditional 2D cultures and more complex 3D tumor spheroids to better simulate the tumor environment. Mass spectrometry-based target identification: Through our collaboration with Momentum Biotechnologies, we employ affinity selection mass spectrometry to identify novel small molecule binders testing our AXXDiversity compound collection, targeting both protein and RNA targets. Contact us Back

Empowering oncology drug discovery Read More »

Scroll to Top