Global Startup Heat Map highlights 10 AI Startups advancing Drug Discovery in 2023
Through the Big Data & Artificial Intelligence (AI)-powered StartUs Insights Discovery Platform, which covers over 3 790 000+ startups & scaleups globally, we identified 491 AI startups advancing drug discovery. The Global Startup Heat Map below highlights the 10 AI-based drug discovery startups you should watch in 2023 as well as the geo-distribution of all 491 startups & scaleups we analyzed for this research. Based on the heat map, we see high startup activity in the US, followed by Western Europe. These AI-based drug discovery startups work on solutions ranging from convolutional graph networks to molecular modeling and protein-drug interactions to agile drug development.
As the world’s largest resource for data on emerging companies, the SaaS platform enables you to identify relevant technologies and industry trends quickly & exhaustively. Based on the data from the platform, the Top 5 AI-powered Drug Discovery Startup Hubs are in London, New York City, Cambridge, Boston & San Francisco. The 10 hand-picked startups highlighted in this report are chosen from all over the world and develop solutions for small molecule therapeutics, in vivo guided discovery, druggability prediction, and more.
10 Top AI Startups advancing Drug Discovery in 2023
Innovations in AI-powered drug discovery enable faster and more efficient drug development. For instance, machine learning algorithms analyze vast amounts of biological data and identify potential drug candidates. These algorithms also identify patterns and relationships in data that are difficult for humans to detect, enabling more precise and targeted drug development. Another recent innovation in AI-powered drug discovery is the use of virtual screening tools that simulate the interaction between potential drug candidates and target molecules. This method reduces the time and costs associated with traditional drug discovery methods. Additionally, AI-powered clinical trials allow pharma companies to collect and analyze patient data more efficiently and accurately. This approach helps them identify patient subgroups that may benefit from a particular drug, enabling more personalized medicine approaches.
- Ailynix – Convolutional Graph Networks for Drug Design
- Pangea Botanica – Novel Small Molecule Therapeutics
- DevsHealth – Molecular Modeling
- Vevo Therapeutics – In Vivo Guided Drug Discovery
- Gandeeva Therapeutics – Protein-Drug Interactions
- Cortex Discovery – Molecular Dynamics
- CardiaTec Biosciences – Cardiovascular Disease Drug Targets
- Boltzmann Labs – Novel Small Molecule Discovery
- molab.ai – Absorption, Distribution, Metabolism, Excretion, & Toxicity (ADMET) Prediction
- CarbonSilicon – Druggability Prediction
Ailynix develops Convolutional Graph Networks (CGNs) for Drug Design
US-based startup Ailynix specializes in AI-based drug design and discovery that leverages deep learning and convolutional graph networks. The startup’s platforms use supervised training methods to develop quantitative structure-activity relationship (QSAR)-based computational models for predicting chemical structures. They identify potential drugs from a massive molecule database, enabling further computational searches and refinement. The startup’s platforms thus advance protein-based therapeutic drug discovery using orthosteric, allosteric, and functional data. Consequently, they cater to biotech and pharma companies, contract research organizations (CROs), and university research labs.
Pangea Botanica offers Novel Small Molecule Therapeutics
UK-based startup Pangea Botanica develops PangeAI, an AI-powered platform to accelerate drug discovery and development. It maps the chemical composition of plants and creates a diverse dataset of natural products to match compounds. The platform also predicts chemical properties, modes of action, and synergistic effects. By combining AI, metabolomics, and cheminformatics, PangeAI enables the scalable discovery of nature-inspired therapeutics. It also assists in the proposal of lead candidates for development, thereby enhancing the development of new and existing compounds.
DevsHealth advances Molecular Modeling
Spanish startup DevsHealth makes antiviral and antibiotic treatments using AI and molecular modeling. The startup’s AI optimizes drug design, predicts side effects, and forecasts ADME properties. Additionally, it integrates public-source databases to simplify data handling for massive datasets of gene expression experiments, bioactive compounds, and proteins. Further, DevsHealth leverages real-world data (RWD) and quantum computing to enhance its AI models and predictions, enabling better anti-infective treatments.
Vevo Therapeutics enables In Vivo Guided Drug Discovery
US-based startup Vevo Therapeutics creates Mosaic, a platform to generate high-resolution, single-cell in vivo data at scale. It measures both phenotypic and transcriptomic changes in cell states to capture general rules of drug efficacy as well as drug-induced changes in gene expression. The platform also utilizes proprietary methods for pooling cells from multiple patients in one tumor and single-cell RNA profiling to determine drug action. Mosaic also studies drug-cell interactions in vivo, uncovering previously undetectable mechanisms of action and resistance that current in vitro models overlook.
Gandeeva Therapeutics captures Protein-Drug Interactions
Canadian startup Gandeeva Therapeutics offers a drug discovery platform that leverages AI and cryogenic electron microscopy. Its modules include SPOTLIGHT to identify validated targets, HYPERFOCUS which maps druggable sites, and CRYO-CADD which generates structural insights. The platform combines technologies in chemistry, biology, imaging, and machine learning to visualize, measure, and capture protein-protein and protein-drug interactions at high speed and resolution. As a result, the startup accelerates drug discovery by targeting disease-relevant proteins and influencing their function.
Cortex Discovery advances Molecular Dynamics
Cortex Discovery is a German startup that provides deep learning-based solutions to make accurate simulations of ligand-protein binding. The startup’s technology models the chemical processes of interactions between targets and drug-like molecules. This allows for the generalization of a wider range of compound classes and new targets without existing experimental data. Moreover, Cortex Discovery’s technology predicts on-target interactions (hit discovery), off-target interactions (polypharmacology), and drug metabolism and toxicity (ADMET profiling). Consequently, it finds applications in the discovery of drugs for life extension and age-related disorders.
CardiaTec Biosciences offers Cardiovascular Disease Drug Targets
UK-based startup CardiaTec Biosciences applies AI and large-scale multi-omics data to develop cardiovascular disease drug targets. The startup’s AI-driven multi-omics analysis platform uncovers relationships across various biological layers, including gene variation, methylation, expression, proteomics, and metabolomics. The platform also features patient stratification and biomarker identification to facilitate the transition towards personalized medicine, improving patient care.
Boltzmann Labs aids Novel Small Molecule Discovery
Indian startup Boltzmann Labs makes a chemistry studio for discovering novel small molecules and exploring chemical spaces with generative AI. The startup’s studio, BoltChem, creates QSAR property models using machine learning and deep learning. Its AI-based synthesis planning tool, ReBolt, also simplifies reaction pathway design. Additionally, the startup’s BoltBio, a target identification platform, utilizes multi-omics analysis, knowledge graphs, and neural networks to accelerate treatment for rare and common diseases.
molab.ai creates an ADMET Prediction Engine
German startup molab.ai advances drug and compound discovery through ADMET predictions and a compound optimization suite. The startup’s prediction engine provides highly accurate ADMET property predictions with reliable confidence indicators and actionable recommendations for novel molecules. The engine also performs robustly in unfamiliar chemical space, outperforming physics-based models and other AI solutions. Besides, the compound optimization suite offers suggestions for novel and alternative molecular structures optimal for better binding affinity and synthetic accessibility.
CarbonSilicon facilitates Druggability Prediction
Chinese startup CarbonSilicon offers a drug discovery workflow leveraging AI-generated content (AIGC), self-supervised pre-training, reinforcement learning, and physics-based modeling. The startup’s activity prediction solution, Inno-Docking, provides complete protein preparation, ligand preparation, and intelligent setting of docking parameters. Additionally, Inno-Rescoring features AI-scoring functions to evaluate protein-ligand binding affinity. CarbonSilicon’s comprehensive druggability assessment involves three computational modules Inno-ADMET for ADMET properties, ChemFH to filter frequent hit compounds, and Inno-SA to predict substructure-related toxicity. The startup’s solutions thus enable medicinal chemists to find potential drug candidates more efficiently and easily.
Discover All Emerging Pharma Startups
The pharma startups showcased in this report are only a small sample of all startups we identified through our data-driven startup scouting approach. Download our free Pharma Innovation Report for a broad overview of the industry or get in touch for quick & exhaustive research on the latest technologies & emerging solutions that will impact your company in 2023!