Leverage our AI models for drug discovery, customize your own, or run your data on our cutting-edge platforms.
Novel molecules from scaffolds of interest unknown from previous studies through generative AI.
Tolerable, safe and plausible molecules on drug discovery targets.
Cutting-edge AI neural networks to predict bioactivity on organisms, human cell lines, permeability, solubility, toxicology and ADME.
Cutting-edge AI neural networks to predict molecular docking against targets and inhibitory activity.
MedFacts aims to revolutionize drug discovery through cutting-edge AI technology. By integrating deep learning and drug discovery expertise, we uncover novel therapeutic molecules more efficiently than traditional methods.
Our proprietary AI models leverage large biomedical datasets to generate innovative, data-driven insights for drug development.
We are committed to transparency, ethical standards, and a fact-based approach that ensures our research leads to meaningful health solutions.
Our mission is to accelerate drug discovery, reduce development costs, and bring life-saving treatments to patients faster, making a global impact in healthcare.
Our tailored AI models drive not only discovery but also offer comprehensive optimization solutions to enhance drug profiles and competitive market positioning.
Leverage our cutting-edge AI to generate novel candidates with promising therapeutic potential.
Boost the biological activity of existing molecules.
Uncover new therapeutic uses for known molecules.
Gain a competitive edge by understanding the limitations of rival drugs.
MedGEN_PAP leverages our proprietary generative AI to rapidly identify and synthesize a library of novel antibiotics against multiresistant bacteria, significantly accelerating the pathway from discovery to preclinical development. Designed for adaptability, it promises to efficiently counteract emerging bacterial resistances, securing a future-proof solution in antibiotic therapy.
+10x
Harnessing MedGEN’s advanced generative AI and reinforcement learning, our platform achieves a 10x increase in the generation of novel antibiotic compounds. This acceleration not only enhances drug discovery but also maximizes potential for groundbreaking therapeutic solutions.
30%
MedBIO’s relational graph convolutional networks predict complex biological interactions with a minimum 30% competitive advantage over traditional models. This precision enhances molecule design with optimal bioactivity and safety profiles, speeding progression from concept to clinical trials.
-2x
MedTOX’s AI reduces the number of drug candidates needed for toxicity testing by at least twofold, ensuring not only stringent safety but also high therapeutic efficacy, significantly cutting both time and development costs.
-3x
MedDOCK employs advanced simulations and relational graph analysis to improve drug-target interactions, requiring at least three times fewer candidates for testing. This efficiency enhances our ability to develop potent inhibitors against resistant bacterial strains, saving substantial time and resources.
+$2b
Addressing the $2 billion market for E. coli-resistant bacteria, our AI platforms set new standards in drug discovery and development, outperforming existing technologies in speed, accuracy, and cost-effectiveness. Also, targeting K. pneumoniae-resistant bacteria also heads up to this market potential.
Pneumonia
Our AI platforms develop more potent antibiotics with lower MIC values than current treatments like Zevtera and Fetroja, effectively broadening treatment efficacy against resistant pneumonia strains. This results in candidates suited for wider clinical use and better patient outcomes.
Track MedFacts programmes currently underway and completed.
Status: Underway
Start date: October 2025
Provision end date: September 2026
Grant: 23027
Call: Aviso N.º 21/C16-i02/2025 - Concurso no âmbito da medida "Vouchers para Startups - Novos produtos digitais/tecnológicos"
This project focuses on applying MedFacts proprietary AI workflows to antibiotic preclinical discovery. The programme combines generative design, prioritization and in-silico evaluation pipelines to speed the identification of promising candidates against high-priority resistant bacteria.
At execution level, MedGEN_PAP supports faster triage of candidate compounds, improves evidence-based selection for follow-up studies, and strengthens translation from digital discovery to preclinical validation.
Close