A5084062018- Bioinformatics and Genomic Networks
- Computational Drug Discovery Methods
- Gene Regulatory Network Analysis
- Genetics, Aging, and Longevity in Model Organisms
- Cell Image Analysis Techniques
- Gene expression and cancer classification
- Epigenetics and DNA Methylation
- Histone Deacetylase Inhibitors Research
- Nutritional Studies and Diet
- DNA Repair Mechanisms
- Health, Environment, Cognitive Aging
- Dietary Effects on Health
- Ubiquitin and proteasome pathways
- Protein Tyrosine Phosphatases
- Immune cells in cancer
- Lung Cancer Treatments and Mutations
- Birth, Development, and Health
- Hair Growth and Disorders
- Telomeres, Telomerase, and Senescence
- Machine Learning in Healthcare
- Genomics and Chromatin Dynamics
- Cancer Mechanisms and Therapy
- Effects of Radiation Exposure
- RNA and protein synthesis mechanisms
- Cancer therapeutics and mechanisms
Insilico Medicine (United States)
2015-2025
Insilicos (United States)
2015-2024
Hong Kong Science and Technology Parks Corporation
2020-2022
Johns Hopkins University
2014-2018
Dmitry Rogachev National Research Center of Pediatric Hematology, Oncology and Immunology
2013-2018
Ministry of Health of the Russian Federation
2018
Moscow Institute of Physics and Technology
2013-2014
Institute of Bioorganic Chemistry
2013-2014
Federal Medical-Biological Agency
2014
Syktyvkar State University
2014
Deep learning is rapidly advancing many areas of science and technology with multiple success stories in image, text, voice video recognition, robotics, autonomous driving. In this paper we demonstrate how deep neural networks (DNN) trained on large transcriptional response data sets can classify various drugs to therapeutic categories solely based their profiles. We used the perturbation samples 678 across A549, MCF-7, PC-3 cell lines from LINCS Project linked those 12 use derived MeSH. To...
The increased availability of data and recent advancements in artificial intelligence present the unprecedented opportunities healthcare major challenges for patients, developers, providers regulators. novel deep learning transfer techniques are turning any about person into medical transforming simple facial pictures videos powerful sources predictive analytics. Presently, patients do not have control over access privileges to their records remain unaware true value they have. In this...
Aging | doi:10.18632/aging.100968. Evgeny Putin, Polina Mamoshina, Alexander Aliper, Mikhail Korzinkin, Alexey Moskalev, Kolosov, Ostrovskiy, Charles Cantor, Jan Vijg, Alex Zhavoronkov
Recent advances in deep learning and specifically generative adversarial networks have demonstrated surprising results generating new images videos upon request even using natural language as input. In this paper we present the first application of autoencoders (AAE) for novel molecular fingerprints with a defined set parameters. We developed 7-layer AAE architecture latent middle layer serving discriminator. As an input output uses vector binary concentration molecule. also introduced...
Modern computational approaches and machine learning techniques accelerate the invention of new drugs. Generative models can discover novel molecular structures within hours, while conventional drug discovery pipelines require months work. In this article, we propose a generative architecture, entangled conditional adversarial autoencoder, that generates based on various properties, such as activity against specific protein, solubility, or ease synthesis. We apply proposed model to generate...
Accurate and physiologically meaningful biomarkers for human aging are key to assessing antiaging therapies. Given ethnic differences in health, diet, lifestyle, behavior, environmental exposures, even average rate of biological aging, it stands reason that clocks trained on datasets obtained from specific populations more likely account these potential confounding factors, resulting an enhanced capacity predict chronological age quantify age. Here, we present a deep learning-based...
Amyotrophic lateral sclerosis (ALS) is a severe neurodegenerative disease with ill-defined pathogenesis, calling for urgent developments of new therapeutic regimens. Herein, we applied PandaOmics, an AI-driven target discovery platform, to analyze the expression profiles central nervous system (CNS) samples (237 cases; 91 controls) from public datasets, and direct iPSC-derived motor neurons (diMNs) (135 31 Answer ALS. Seventeen high-confidence eleven novel targets were identified will be...
Differences in DNA repair capacity have been hypothesized to underlie the great range of maximum lifespans among mammals. However, measurements individual activities cells and animals not substantiated such a relationship because utilization pathways animals--depending on habitats, anatomical characteristics, life styles--varies greatly between mammalian species. Recent advances high-throughput genomics, combination with increased knowledge genetic involved genome maintenance, now enable...
Abstract Signalling pathway activation analysis is a powerful approach for extracting biologically relevant features from large-scale transcriptomic and proteomic data. However, modern pathway-based methods often fail to provide stable signatures of specific phenotype or reliable disease biomarkers. In the present study, we introduce in silico Pathway Activation Network Decomposition Analysis (iPANDA) as scalable robust method biomarker identification using gene expression The iPANDA...
There is an association between smoking and cancer, cardiovascular disease all-cause mortality. However, currently, there are no affordable informative tests for assessing the effects of on rate biological aging. In this study we demonstrate first time that status can be predicted using blood biochemistry cell count results andthe recent advances in artificial intelligence (AI). By employing age-prediction models developed supervised deep learning techniques, found smokers exhibited higher...
Aging | doi:10.18632/aging.203960. Frank W. Pun, Geoffrey Ho Duen Leung, Hoi Wing Bonnie Hei Man Liu, Xi Long, Ivan V. Ozerov, Ju Wang, Feng Ren, Alexander Aliper, Evgeny Izumchenko, Alexey Moskalev, João Pedro de Magalhães, Alex Zhavoronkov
Hypoxia-inducible factor prolyl hydroxylase (PHD) inhibitors have been approved for treating renal anemia yet failed clinical testing inflammatory bowel disease because of a lack efficacy. Here we used multimodel multimodal generative artificial intelligence platform to design an orally gut-restricted selective PHD1 and PHD2 inhibitor that exhibits favorable safety pharmacokinetic profiles in preclinical studies. ISM012-042 restores intestinal barrier function alleviates gut inflammation...
Fibroblast growth factor receptors (FGFRs) are established oncogenic drivers in various solid tumors. However, the approved FGFR inhibitors face challenges with acquired resistance and dose-limiting adverse effects associated FGFR1/4 inhibition, limiting therapeutic efficacy. Herein, we systematically explored linker electrophile moieties based on pyrrolopyrazine carboxamide core identified aniline α-fluoroacrylamide as an effective covalent warhead. Compound 10 potently inhibited FGFR2...
Cyclin-dependent kinases 12 and 13 (CDK12/13) safeguard genomic integrity by preferentially regulating gene expression in the DNA damage response (DDR). The CDK12/13-mediated upregulation of DDR genes pathways significantly contributes to both tumorigenesis development resistance antitumor therapies. Thus, functional inhibition CDK12/13 offers an attractive strategy combat carcinogenesis, particularly for refractory treatment-resistant cancers. Here, we report discovery compound 12b as a...
Aging is now at the forefront of major challenges faced globally, creating an immediate need for safe, widescale interventions to reduce burden chronic disease and extend human healthspan.Metformin rapamycin are two FDA-approved mTOR inhibitors proposed this purpose, exhibiting significant anti-cancer anti-aging properties beyond their current clinical applications.However, each faces issues with approval off-label, prophylactic use due adverse effects.Here, we initiate effort identify...
// Nikolay M. Borisov 1, 2 , Nadezhda V. Terekhanova 3 Alexander Aliper Larisa S. Venkova Philip Yu Smirnov Sergey Roumiantsev Mikhail B. Korzinkin Alex A. Zhavoronkov 3, 4 Anton Buzdin 1 Pathway Pharmaceuticals, Wan Chai, Hong Kong, Kong SAR Laboratory of Systems Biology, A.I. Burnasyan Federal Medical Biophysical Center, Moscow, 123182, Russia Bioinformatics, D. Rogachyov Research Center Pediatric Hematology, Oncology and Immunology, 117198, Group for Genomic Regulation Cell Signaling...
Significance We identified a human-specific endogenous retroviral insert (hsERV) that acts as an enhancer for human PRODH , hsERV_PRODH. encodes proline dehydrogenase, which is involved in neuromediator synthesis the CNS. show hsERV_PRODH synergistically with CpG island of and regulated by methylation. detected high expression hippocampus, was correlated undermethylated state this enhancer. regulatory elements provide neuron-specific transcription hippocampal cells, mechanism activity...
For the past several decades, research in understanding molecular basis of human aging has progressed significantly with analysis premature syndromes. Progerin, an altered form lamin A, been identified as cause Hutchinson-Gilford Progeria Syndrome (HGPS), and may be a contributing causative factor normal aging. However, question whether HGPS actually recapitulates process at cellular organismal level, or simply mimics phenotype is widely debated. In present study we analyzed publicly...
High throughput technologies opened a new era in biomedicine by enabling massive analysis of gene expression at both RNA and protein levels. Unfortunately, data obtained different experiments are often poorly compatible, even for the same biologic samples. Here, using experimental bioinformatic investigation major platforms, we show that aggregation level molecular pathways helps to diminish cross- intra-platform bias otherwise clearly seen individual genes. We created mathematical model...