Scientists used AI-driven PandaOmics platform to analyze gene expression datasets from DNA repair diseases, identifying biomarkers associated with treatment response. The study focused on genes that stratify cancer patients by survival outcomes, providing potential targets for personalized therapies.
Researchers at Insilico Medicine used their proprietary AI-driven target discovery engine, PandaOmics, to identify 17 high-confidence and 11 novel therapeutic targets for ALS. These targets were further validated in various model systems, including a c9ALS Drosophila model, and showed strong functional correlations to ALS. The study's ...
Researchers at Insilico Medicine have used AI to identify potential targets that are implicated in multiple age-related diseases and also play a role in the basic biology of aging. The study resulted in the identification of 69 high-confidence targets with potential high druggability.
Insilico Medicine will present its latest results in modern and next-generation AI for generative chemistry at ACS Spring 2021. The company's Chemistry42 platform facilitates the discovery of novel small molecule leads in several therapeutic areas, integrating AI techniques with computational and medicinal chemistry methods.
Insilico Medicine introduces Molecular Sets (MOSES), a benchmarking platform for generative chemistry models, enabling easy comparison and evaluation of new models against existing approaches. The platform provides a curated dataset, metrics, and baselines for assessing model performance.
Insilico Medicine will showcase its latest AI advancements in drug discovery and productive longevity at the Leveraging Intelligent Tech for Drug Development Forum. The company's work on AI-generated molecular structures, synthetic biological data, and clinical trial prediction has garnered significant attention and funding.
A new study discovered that GULP1 is a key regulator of the NRF2-KEAP1 signaling axis in urothelial carcinoma. GULP1 knockdown led to increased tumor growth and resistance to cisplatin treatment.
A new deep learning-based aging clock uses whole genome sequencing data from thousands of gut bacteria to predict human biological age. The study shows that the age of the host is a significant contributor to gut community dynamics, with microflora succession patterns associated with age progression.
Researchers developed a machine learning algorithm to predict six major clinical forms of drug-induced cardiac toxicity from gene expression data. The model demonstrated generalizability and was validated on an independent dataset, with potential applications in enhancing pharmaceutical industry safety evaluation.
Researchers at Insilico Medicine developed a new AI model that combines generative biology and chemistry to generate novel molecular structures for a desired transcriptional response. The Bidirectional Adversarial Autoencoder can be used for virtual screening, discovering new molecular structures and predicting transcriptional responses.
The company has proposed a new family of prior distributions: TRIP, which improves Fréchet Inception Distance for GANs and Evidence Lower Bound for VAEs. The model was experimentally validated in cells and animals, demonstrating its potential for accelerating drug discovery.
A new AI system, Generative Tensorial Reinforcement Learning (GENTRL), was used to generate six novel inhibitors of DDR1 kinase target in just 21 days. Four compounds showed activity in biochemical assays, and one lead candidate demonstrated favorable pharmacokinetics in mice.
Researchers at Insilico Medicine have developed a new molecular descriptor, MCE-18, which estimates molecular complexity and defines the evolution of small molecules in medicinal chemistry. The study reveals that modern drug development is becoming more qualitative and smarter, with higher degrees of 3D complexity.
Researchers call for new models to value human life data, allowing patients to own and profit from their health information. This shift could lead to increased engagement in the healthcare system, driven by blockchain technology and AI-based data analysis.
Researchers discovered a new candidate gene, unpaired 1, that contributes to lifespan regulation in Drosophila melanogaster. Overexpression of this gene increased lifespan in nervous tissue and fat body, but decreased lifespan in intestine.
A new study published by the Moskalev Lab has revealed how overexpressing the pro-longevity gene Gclc in Drosophila melanogaster leads to life extension and changes in the thorax's transcriptome, including genes involved in metabolism, immune system, and circadian rhythmicity.
Researchers from Peking University and Insilico Medicine are collaborating on AI-powered drug discovery methods, aiming to accelerate pharmaceutical research and development. The project will focus on various applications of AI in drug discovery, including target identification, compound generation, and personalized medicine.
A recent study published in Scientific Reports found that smokers demonstrate a higher aging ratio and are predicted to be twice as old as their chronological age compared to nonsmokers. The study used blood biochemistry and artificial intelligence to analyze the impact of smoking on biological age.
A recent paper by Insilico Medicine introduces deep learning for aging research, revealing age as a key biological feature that can be predicted using various data types. The study also outlines the potential applications of this technology, including personalized immunotherapies and vaccinations.
A new study published by Insilico Medicine using artificial intelligence has identified potential FP2 blockers, which could lead to the development of new antimalarial drugs. The research provides insights into the properties of E64 approaches and their interaction with falcipain-2, a key target for malaria treatment.
The special issue brings together contributions from top academics and industry experts, highlighting the use of generative chemistry and GANs for de-novo molecular design. Experimental validation of generated molecules demonstrates high activity and selectivity in a novel inhibitor of Janus Kinase 3.
Researchers at Insilico Medicine developed an Entangled Conditional Adversarial Autoencoder (ECAAE) that generates molecular structures based on various properties. The generated molecule demonstrated high activity and selectivity against a specific protein, laying the foundation for AI-powered drug discovery.
Researchers at Johns Hopkins and Insilico Medicine discovered novel epigenetically silenced genes in ovarian cancer, including methylation of the GULP1 gene. GULP1 expression is associated with late-stage disease and poor overall survival, suggesting its potential as a biomarker.
Researchers developed a deep-learning model to predict biological age of muscles and estimate the importance of genetic and epigenetic factors driving muscle aging. The study identified tissue-specific biomarkers of aging, which can be used to track the effectiveness of interventions.
Insilico Medicine introduces a novel deep neural network architecture called Reinforced Adversarial Neural Computer (RANC) for de novo molecular design. RANC outperforms other methods in generating unique structures and passing medical chemistry filters.
The Adversarial Threshold Neural Computer (ATNC) model, a proof-of-concept, combines Generative Adversarial Networks (GANs) with Reinforcement Learning (RL) to generate novel small organic molecules. The GAN-RL architecture demonstrated the ability to produce valid and unique molecular structures, paving the way for future drug discovery.
Researchers propose roadmap for making humans resistant to radiation and stress damage, with a focus on radioresistance. The strategies aim to maximize productive life years in space, addressing challenges like high-LET radiation.
The researchers developed a new class of bifunctional immunotherapeutic agents called Y-traps, which can target and disable multiple immune suppressive molecules. These Y-traps were found to be effective in inhibiting tumor growth and activating antitumor immunity, even against cancers that do not respond to existing immunotherapies.
A novel deep-learning based hematological human aging clock predicts the biological age of individual patients with high accuracy. The model outperforms chronological age in predicting all-cause mortality, highlighting population-specific patterns of aging.
A new study uses deep learning methods to identify genes involved in embryonic development, fetal transition, and cancer. The research may lead to innovative strategies for induced tissue regeneration and cancer treatment.
Researchers from Insilico Medicine and BitFury Group present a blockchain-based life data interchange system to decentralize and accelerate biomedical research. The system utilizes deep learning technologies to analyze human life data, reducing biases and democratizing healthcare access.
A new model proposes returning control over human life data to patients, accelerating biomedical research through a secure and transparent distributed personal data marketplace utilizing blockchain and deep learning technologies. This approach can resolve challenges faced by regulators and improve patient satisfaction.
Insilico Medicine showcases its use of artificial intelligence to identify disease targets, generate molecular structures, and track interventions for metabesity. The company aims to prevent metabolic-rooted disorders such as diabetes and dementia.
A new AI model called druGAN enables the generation of novel molecules with desired properties, surpassing previous GAN-based approaches. The model uses reinforcement learning to generate effective molecular graphs, paving the way for improved pharmaceuticals.
Researchers found that SMAD4 loss is associated with cetuximab resistance and induction of MAPK/JNK activation in HPV-negative head and neck squamous cell carcinoma (HNSCC) patients. The study suggests that targeting pro-survival pathways may be a novel strategy for overcoming cetuximab resistance.
Insilico Medicine will showcase its latest AI advancements in aging research and personal health data management. The company aims to apply deep learning to improve biomarker development, predict chronological age, and provide geroprotectors for various diseases.
Scientists have applied iPANDA, a novel approach for analyzing high-throughput transcriptomic datasets, to identify the earliest signaling harbingers of malignant transition in OSCC. The study reveals that dysregulation of these signaling networks occurs even before precancerous cells invade and acquire malignant potential.
Insilico Medicine will showcase its pioneering work in applying deep learning techniques to drug discovery, biomarker development, and aging research. The company's presentation highlights the applications of Generative Adversarial Networks (GANs) in oncology and infectious diseases.
Scientists at InSilico Medicine developed a proof-of-concept AI model using Generative Adversarial Autoencoders (AAEs) to generate molecular fingerprints of cancer-killing molecules. The study demonstrates the potential for AI to accelerate pharmaceutical R&D and improve clinical trial success rates.
Insilico Medicine developed a novel tool, iPANDA, to derive new insights from gene expression repositories. The method combines precalculated gene coexpression data with gene importance factors for obtaining pathway activation scores, producing highly consistent sets of biologically relevant biomarkers.
The article presents a comprehensive overview of in silico drug repurposing methods, highlighting the advantages and disadvantages of various techniques. The authors emphasize the potential of incorporating deep learning approaches into modular workflows, which can accelerate development and reduce costs.
Insilico Medicine will present new research data on geroprotectors, small molecules that mimic the young healthy state in old human tissues. The results are a result of a multi-year research program with multiple in silico predictions made using algorithms validated using data from many age-related diseases.
Researchers utilized Regeneration Intelligence to evaluate signaling pathways in lung and liver fibrosis and glaucoma, identifying potential biomarkers and therapeutic targets. The study suggests that pathway signatures may play a role in aging-related diseases.
Insilico Medicine scientists will present advances in deep learning for biomarker development and drug discovery at the ISFA-Columbia University Actuarial Science Workshop. The workshop aims to integrate deep learning with actuarial science to assess risk in finance, insurance, and other industries.
Scientists from Insilico Medicine used deep neural networks to predict therapeutic use of large numbers of drugs from gene expression data, achieving 54.6% accuracy in class prediction. The study also found that many misclassified drugs had dual use, suggesting potential for drug repurposing.
Insilico Medicine presents research on applying deep learning to biomarker development and cosmetics applications at INNOCOS World Beauty Innovation Summit. The company's app RYNKL evaluates anti-aging interventions using machine learning methods, minimizing animal testing.
InSilico Medicine presents recent advances in applying signaling pathway activation analysis and deep learning to drug discovery and age-related diseases. The company's mission is to extend healthy human longevity through faster and more effective diagnostics and cures.
The paper calls for creating a task force to evaluate the classification of aging as a disease in ICD-11. Classifying aging as a disease could help shift the focus from treatment to prevention, attracting more resources to aging research and business cases for pharmaceutical companies.
A new method for testing human induced pluripotent stem cells (iPSCs) has been developed, allowing for the evaluation of their differentiation potential. This approach uses pathway activation profiling to identify impaired iPSC lines and predict in vitro differentiation capabilities.
A new algorithm developed by InSilico Medicine has the potential to improve the effectiveness of targeted therapy for cancer patients. The algorithm predicts whether a specific drug will work for an individual patient based on activation of intracellular regulatory pathways.