Stem-cell based, machine learning approach for optimizing natural killer cell-based personalized immunotherapy for high-grade ovarian cancer.

Advanced high-grade serous ovarian cancer continues to be a therapeutic challenge for those affected using the current therapeutic interventions. There is an increasing interest in personalized cancer immunotherapy using activated natural killer (NK) cells. NK cells account for approximately 15% of circulating white blood cells. They are also an important element of the tumor microenvironment (TME) and the body's immune response to cancers. In the present study, DeepNEU-C2Rx, a machine learning platform, was first used to create validated artificially induced pluripotent stem cell simulations. These simulations were then used to generate wild-type artificially induced NK cells (aiNK-WT) and TME simulations. Once validated, the aiNK-WT simulations were exposed to artificially induced high-grade serous ovarian cancer represented by aiOVCAR3. Cytolytic activity of aiNK was evaluated in presence and absence of aiOVCAR3 and data were compared with the literature for validation. The TME simulations suggested 26 factors that could be evaluated based on their ability to enhance aiNK-WT cytolytic activity in the presence of aiOVCAR3. The addition of programmed cell death-1 inhibitor leads to significant reinvigoration of aiNK cytolytic activity. The combination of programmed cell death-1 and glycogen synthase kinase 3 inhibitors showed further improvement. Further addition of ascitic fluid factor inhibitors leads to optimal aiNK activation. Our data showed that NK cell simulations could be used not only to pinpoint novel immunotherapeutic targets to reinvigorate the activity of NK cells against cancers, but also to predict the outcome of targeting tumors with specific genetic expression and mutation profiles.

Artificially Induced Pluripotent Stem Cell-Derived Whole-Brain Organoid for Modelling the Pathophysiology of Metachromatic Leukodystrophy and Drug Repurposing.

Metachromatic leukodystrophy (MLD) is a rare neurodegenerative disease that results from a deficiency of the lysosomal enzyme arylsulfatase A (ARSA). Worldwide, there are between one in 40,000 and one in 160,000 people living with the disease. While there are currently no effective treatments for MLD, induced pluripotent stem cell-derived brain organoids have the potential to provide a better understanding of MLD pathogenesis. However, developing brain organoid models is expensive, time consuming and may not accurately reflect disease progression. Using accurate and inexpensive computer simulations of human brain organoids could overcome the current limitations. Artificially induced whole-brain organoids (aiWBO) have the potential to greatly expand our ability to model MLD and guide future wet lab research. In this study, we have upgraded and validated our artificially induced whole-brain organoid platform (NEUBOrg) using our previously validated machine learning platform, DeepNEU (v6.2). Using this upgraded NEUBorg, we have generated aiWBO simulations of MLD and provided a novel approach to evaluate factors associated with MLD pathogenesis, disease progression and new potential therapeutic options.

Lung organoid simulations for modelling and predicting the effect of mutations on SARS-CoV-2 infectivity.

The global pandemic caused by the SARS-CoV-2 virus continues to spread. Infection with SARS- CoV-2 causes COVID-19, a disease of variable severity. Mutation has already altered the SARS-CoV-2 genome from its original reported sequence and continued mutation is highly probable. These mutations can: (i) have no significant impact (they are silent), (ii) result in a complete loss or reduction of infectivity, or (iii) induce increase in infectivity. Physical generation, for research purposes, of viral mutations that could enhance infectivity are controversial and highly regulated. The primary purpose of this project was to evaluate the ability of the DeepNEU machine learning stem-cell simulation platform to enable rapid and efficient assessment of the potential impact of viral loss-of-function (LOF) and gain-of-function (GOF) mutations on SARS-CoV-2 infectivity. Our data suggest that SARS-CoV-2 infection can be simulated in human alveolar type lung cells. Simulation of infection in these lung cells can be used to model and assess the impact of LOF and GOF mutations in the SARS-CoV2 genome. We have also created a four- factor infectivity measure: the DeepNEU Case Fatality Rate (dnCFR). dnCFR can be used to assess infectivity based on the presence or absence of the key viral proteins (NSP3, Spike-RDB, N protein, and M protein). dnCFR was used in this study, not to only assess the impact of different mutations on SARS-CoV2 infectivity, but also to categorize the effects of mutations as loss of infectivity or gain of infectivity events.

NEUBOrg: Artificially Induced Pluripotent Stem Cell-Derived Brain Organoid to Model and Study Genetics of Alzheimer's Disease Progression.

Alzheimer's disease (AD) is the most common type of neurodegenerative diseases. There are over 44 million people living with the disease worldwide. While there are currently no effective treatments for AD, induced pluripotent stem cell-derived brain organoids have the potential to provide a better understanding of Alzheimer's pathogenesis. Nevertheless, developing brain organoid models is expensive, time consuming and often does not reflect disease progression. Using accurate and inexpensive computer simulations of human brain organoids can overcome the current limitations. Induced whole brain organoids (aiWBO) will greatly expand our ability to model AD and can guide wet lab research. In this study, we have successfully developed and validated artificially induced a whole brain organoid platform (NEUBOrg) using our previously validated machine learning platform, DeepNEU (v6.1). Using NEUBorg platform, we have generated aiWBO simulations of AD and provided a novel approach to test genetic risk factors associated with AD progression and pathogenesis.

Viral pandemic preparedness: A pluripotent stem cell-based machine-learning platform for simulating SARS-CoV-2 infection to enable drug discovery and repurposing.

Infection with the SARS-CoV-2 virus has rapidly become a global pandemic for which we were not prepared. Several clinical trials using previously approved drugs and drug combinations are urgently under way to improve the current situation. A vaccine option has only recently become available, but worldwide distribution is still a challenge. It is imperative that, for future viral pandemic preparedness, we have a rapid screening technology for drug discovery and repurposing. The primary purpose of this research project was to evaluate the DeepNEU stem-cell based platform by creating and validating computer simulations of artificial lung cells infected with SARS-CoV-2 to enable the rapid identification of antiviral therapeutic targets and drug repurposing. The data generated from this project indicate that (a) human alveolar type lung cells can be simulated by DeepNEU (v5.0), (b) these simulated cells can then be infected with simulated SARS-CoV-2 virus, (c) the unsupervised learning system performed well in all simulations based on available published wet lab data, and (d) the platform identified potentially effective anti-SARS-CoV2 combinations of known drugs for urgent clinical study. The data also suggest that DeepNEU can identify potential therapeutic targets for expedited vaccine development. We conclude that based on published data plus current DeepNEU results, continued development of the DeepNEU platform will improve our preparedness for and response to future viral outbreaks. This can be achieved through rapid identification of potential therapeutic options for clinical testing as soon as the viral genome has been confirmed.

DeepNEU: Artificially Induced Stem Cell (aiPSC) and Differentiated Skeletal Muscle Cell (aiSkMC) Simulations of Infantile Onset POMPE Disease (IOPD) for Potential Biomarker Identification and Drug Discovery.

Infantile onset Pompe disease (IOPD) is a rare and lethal genetic disorder caused by the deletion of the acid alpha-glucosidase (GAA) gene. This gene encodes an essential lysosomal enzyme that converts glycogen to glucose. While enzyme replacement therapy helps some, our understanding of disease pathophysiology is limited. In this project we develop computer simulated stem cells (aiPSC) and differentiated skeletal muscle cells (aiSkMC) to empower IOPD research and drug discovery. Our Artificial Intelligence (AI) platform, DeepNEU v3.6 was used to generate aiPSC and aiSkMC simulations with and without GAA expression. These simulations were validated using peer reviewed results from the recent literature. Once the aiSkMC simulations (IOPD and WT) were validated they were used to evaluate calcium homeostasis and mitochondrial function in IOPD. Lastly, we used aiSkMC IOPD simulations to identify known and novel biomarkers and potential therapeutic targets. The aiSkMC simulations of IOPD correctly predicted genotypic and phenotypic features that were reported in recent literature. The probability that these features were accurately predicted by chance alone using the binomial test is 0.0025. The aiSkMC IOPD simulation correctly identified L-type calcium channels (VDCC) as a biomarker and confirmed the positive effects of calcium channel blockade (CCB) on calcium homeostasis and mitochondrial function. These published data were extended by the aiSkMC simulations to identify calpain(s) as a novel potential biomarker and therapeutic target for IOPD. This is the first time that computer simulations of iPSC and differentiated skeletal muscle cells have been used to study IOPD. The simulations are robust and accurate based on available published literature. We also demonstrated that the IOPD simulations can be used for potential biomarker identification leading to targeted drug discovery. We will continue to explore the potential for calpain inhibitors with and without CCB as effective therapy for IOPD.

DeepNEU: cellular reprogramming comes of age - a machine learning platform with application to rare diseases research.

BACKGROUND: Conversion of human somatic cells into induced pluripotent stem cells (iPSCs) is often an inefficient, time consuming and expensive process. Also, the tendency of iPSCs to revert to their original somatic cell type over time continues to be problematic. A computational model of iPSCs identifying genes/molecules necessary for iPSC generation and maintenance could represent a crucial step forward for improved stem cell research. The combination of substantial genetic relationship data, advanced computing hardware and powerful nonlinear modeling software could make the possibility of artificially-induced pluripotent stem cells (aiPSC) a reality. We have developed an unsupervised deep machine learning technology, called DeepNEU that is based on a fully-connected recurrent neural network architecture with one network processing layer for each input. DeepNEU was used to simulate aiPSC systems using a defined set of reprogramming transcription factors. Genes/proteins that were reported to be essential in human pluripotent stem cells (hPSC) were used for system modelling. RESULTS: The Mean Squared Error (MSE) function was used to assess system learning. System convergence was defined at MSE < 0.001. The markers of human iPSC pluripotency (N = 15) were all upregulated in the aiPSC final model. These upregulated/expressed genes in the aiPSC system were entirely consistent with results obtained for iPSCs. CONCLUSION: This research introduces and validates the potential use of aiPSCs as computer models of human pluripotent stem cell systems. Disease-specific aiPSCs have the potential to improve disease modeling, prototyping of wet lab experiments, and prediction of genes relevant and necessary for aiPSC production and maintenance for both common and rare diseases in a cost-effective manner.

Novel anti-cancer drug COTI-2 synergizes with therapeutic agents and does not induce resistance or exhibit cross-resistance in human cancer cell lines.

Emerging drug-resistance and drug-associated toxicities are two major factors limiting successful cancer therapy. Combinations of chemotherapeutic drugs have been used in the clinic to improve patient outcome. However, cancer cells can acquire resistance to drugs, alone or in combination. Resistant tumors can also exhibit cross-resistance to other chemotherapeutic agents, resulting in sub-optimal treatment and/or treatment failure. Therefore, developing novel oncology drugs that induce no or little acquired resistance and with a favorable safety profile is essential. We show here that combining COTI-2, a novel clinical stage agent, with multiple chemotherapeutic and targeted agents enhances the activity of these drugs in vitro and in vivo. Importantly, no overt toxicity was observed in the combination treatment groups in vivo. Furthermore, unlike the tested chemotherapeutic drugs, cancer cells did not develop resistance to COTI-2. Finally, some chemo-resistant tumor cell lines only showed mild cross-resistance to COTI-2 while most remained sensitive to it.

Correction: COTI-2, a novel small molecule that is active against multiple human cancer cell lines in vitro and in vivo.

[This corrects the article DOI: 10.18632/oncotarget.9133.].

COTI-2, a novel small molecule that is active against multiple human cancer cell lines in vitro and in vivo.

Identification of novel anti-cancer compounds with high efficacy and low toxicity is critical in drug development. High-throughput screening and other such strategies are generally resource-intensive. Therefore, in silico computer-aided drug design has gained rapid acceptance and popularity. We employed our proprietary computational platform (CHEMSAS®), which uses a unique combination of traditional and modern pharmacology principles, statistical modeling, medicinal chemistry, and machine-learning technologies to discover and optimize novel compounds that could target various cancers. COTI-2 is a small molecule candidate anti-cancer drug identified using CHEMSAS. This study describes the in vitro and in vivo evaluation of COTI-2. Our data demonstrate that COTI-2 is effective against a diverse group of human cancer cell lines regardless of their tissue of origin or genetic makeup. Most treated cancer cell lines were sensitive to COTI-2 at nanomolar concentrations. When compared to traditional chemotherapy or targeted-therapy agents, COTI-2 showed superior activity against tumor cells, in vitro and in vivo. Despite its potent anti-tumor efficacy, COTI-2 was safe and well-tolerated in vivo. Although the mechanism of action of COTI-2 is still under investigation, preliminary results indicate that it is not a traditional kinase or an Hsp90 inhibitor.