Eugene Izumchenko

// Polina Mamoshina 1,2 , Lucy Ojomoko 1 , Yury Yanovich 3 , Alex Ostrovski 3 , Alex Botezatu 3 , Pavel Prikhodko 3 , Eugene Izumchenko 4 , Alexander Aliper 1 , Konstantin Romantsov 1 , Alexander Zhebrak 1 , Iraneus Obioma Ogu 5 and Alex Zhavoronkov 1,6 1 Pharmaceutical Artificial Intelligence Department, Insilico Medicine, Inc., Emerging Technology Centers, Johns Hopkins University at Eastern, Baltimore, Maryland, USA 2 Department of Computer Science, University of Oxford, Oxford, United Kingdom 3 The Bitfury Group, Amsterdam, Netherlands 4 Department of Otolaryngology-Head & Neck Surgery, Johns Hopkins University School of Medicine, Baltimore, MD, USA 5 Africa Blockchain Artificial Intelligence for Healthcare Initiative, Insilico Medicine, Inc, Abuja, Nigeria 6 The Biogerontology Research Foundation, London, United Kingdom Correspondence to: Alex Zhavoronkov, email: // Keywords : artificial intelligence; deep learning; data management; blockchain; digital health Received : October 19, 2017 Accepted : November 02, 2017 Published : November 09, 2017 Abstract The increased availability of data and recent advancements in artificial intelligence present the unprecedented opportunities in healthcare and major challenges for the patients, developers, providers and regulators. The novel deep learning and transfer learning techniques are turning any data about the person into medical data transforming simple facial pictures and videos into powerful sources of data for predictive analytics. Presently, the patients do not have control over the access privileges to their medical records and remain unaware of the true value of the data they have. In this paper, we provide an overview of the next-generation artificial intelligence and blockchain technologies and present innovative solutions that may be used to accelerate the biomedical research and enable patients with new tools to control and profit from their personal data as well with the incentives to undergo constant health monitoring. We introduce new concepts to appraise and evaluate personal records, including the combination-, time- and relationship-value of the data. We also present a roadmap for a blockchain-enabled decentralized personal health data ecosystem to enable novel approaches for drug discovery, biomarker development, and preventative healthcare. A secure and transparent distributed personal data marketplace utilizing blockchain and deep learning technologies may be able to resolve the challenges faced by the regulators and return the control over personal data including medical records back to the individuals.

In the past 3 years, altered expression of the HEF1/CAS-L/NEDD9 scaffolding protein has emerged as contributing to cancer metastasis in multiple cancer types. However, whereas some studies have identified elevated NEDD9 expression as prometastatic, other work has suggested a negative role in tumor progression. We here show that the Nedd9-null genetic background significantly limits mammary tumor initiation in the MMTV-polyoma virus middle T genetic model. Action of NEDD9 is tumor cell intrinsic, with immune cell infiltration, stroma, and angiogenesis unaffected. The majority of the late-appearing mammary tumors of MMTV-polyoma virus middle T;Nedd9(-/-) mice are characterized by depressed activation of proteins including AKT, Src, FAK, and extracellular signal-regulated kinase, emphasizing an important role of NEDD9 as a scaffolding protein for these prooncogenic proteins. Analysis of cells derived from primary Nedd9(+/+) and Nedd9(-/-) tumors showed persistently reduced FAK activation, attachment, and migration, consistent with a role for NEDD9 activation of FAK in promoting tumor aggressiveness. This study provides the first in vivo evidence of a role for NEDD9 in breast cancer progression and suggests that NEDD9 expression may provide a biomarker for tumor aggressiveness.

1alpha,25-dihydroxyvitamin D(3) (1,25D(3)) is a powerful differentiation agent, which has potential for treatment of myeloid leukemias and other types of cancer, but the calcemia produced by pharmacologically active doses precludes the use of this agent in the clinic. We have shown that carnosic acid, the major rosemary polyphenol, enhances the differentiating and antiproliferative effects of low concentrations of 1,25D(3) in human myeloid leukemia cell lines (HL60, U937). Here we translated these findings to in vivo conditions using a syngeneic mouse leukemia tumor model. To this end, we first demonstrated that as in HL60 cells, differentiation of WEHI-3B D(-) murine myelomonocytic leukemia cells induced by 1 nM 1,25D(3) or its low-calcemic analog, 1,25-dihydroxy-16-ene-5,6-trans-cholecalciferol (Ro25-4020), can be synergistically potentiated by carnosic acid (10 microM) or the carnosic acid-rich ethanolic extract of rosemary leaves. This effect was accompanied by cell cycle arrest in G0 + G1 phase and a marked inhibition of cell growth. In the in vivo studies, i.p. injections of 2 microg Ro25-4020 in Balb/c mice bearing WEHI-3B D(-) tumors produced a significant delay in tumor appearance and reduction in tumor size, without significant toxicity. Another analog, 1,25-dihydroxy-16,23Z-diene-20-epi-26,27-hexafluoro-19-nor-cholecalciferol (Ro26-3884) administered at the same dose was less effective than Ro25-4020 and profoundly toxic. Importantly, combined treatment with 1% dry rosemary extract (mixed with food) and 1 microg Ro25-4020 resulted in a strong cooperative antitumor effect, without inducing hypercalcemia. These results indicate for the first time that a plant polyphenolic preparation and a vitamin D derivative can cooperate not only in inducing leukemia cell differentiation in vitro, but also in the antileukemic activity in vivo. These data may suggest novel protocols for chemoprevention or differentiation therapy of myeloid leukemia.

Successful drug development in oncology is grossly suboptimal, manifested by the very low percentage of new agents being developed that ultimately succeed in clinical approval. This poor success is in part due to the inability of standard cell-line xenograft models to accurately predict clinical success and to tailor chemotherapy specifically to a group of patients more likely to benefit from the therapy. Patient-derived xenografts (PDXs) maintain the histopathological architecture and molecular features of human tumors, and offer a potential solution to maximize drug development success and ultimately generate better outcomes for patients. Although imperfect in mimicking all aspects of human cancer, PDXs are a more predictable platform for preclinical evaluation of treatment effect and in selected cases can guide therapeutic decision making in the clinic. This article summarizes the current status of PDX models, challenges associated with modeling human cancer, and various approaches that have been applied to overcome these challenges and improve the clinical relevance of PDX cancer models.