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

The use of artificial intelligence in induced pluripotent stem cell-based technology over 10-year period: A systematic scoping review

BACKGROUND

Stem cell research, particularly in the domain of induced pluripotent stem cell (iPSC) technology, has shown significant progress. The integration of artificial intelligence (AI), especially machine learning (ML) and deep learning (DL), has played a pivotal role in refining iPSC classification, monitoring cell functionality, and conducting genetic analysis. These enhancements are broadening the applications of iPSC technology in disease modelling, drug screening, and regenerative medicine. This review aims to explore the role of AI in the advancement of iPSC research.

METHODS

In December 2023, data were collected from three electronic databases (PubMed, Web of Science, and Science Direct) to investigate the application of AI technology in iPSC processing.

RESULTS

This systematic scoping review encompassed 79 studies that met the inclusion criteria. The number of research studies in this area has increased over time, with the United States emerging as a leading contributor in this field. AI technologies have been diversely applied in iPSC technology, encompassing the classification of cell types, assessment of disease-specific phenotypes in iPSC-derived cells, and the facilitation of drug screening using iPSC. The precision of AI methodologies has improved significantly in recent years, creating a foundation for future advancements in iPSC-based technologies.

CONCLUSIONS

Our review offers insights into the role of AI in regenerative and personalized medicine, highlighting both challenges and opportunities. Although still in its early stages, AI technologies show significant promise in advancing our understanding of disease progression and development, paving the way for future clinical applications.

Induced Pluripotent Stem Cell-Based Drug Screening by Use of Artificial Intelligence

Induced pluripotent stem cells (iPSCs) are terminally differentiated somatic cells that differentiate into various cell types. iPSCs are expected to be used for disease modeling and for developing novel treatments because differentiated cells from iPSCs can recapitulate the cellular pathology of patients with genetic mutations. However, a barrier to using iPSCs for comprehensive drug screening is the difficulty of evaluating their pathophysiology. Recently, the accuracy of image analysis has dramatically improved with the development of artificial intelligence (AI) technology. In the field of cell biology, it has become possible to estimate cell types and states by examining cellular morphology obtained from simple microscopic images. AI can evaluate disease-specific phenotypes of iPS-derived cells from label-free microscopic images; thus, AI can be utilized for disease-specific drug screening using iPSCs. In addition to image analysis, various AI-based methods can be applied to drug development, including phenotype prediction by analyzing genomic data and virtual screening by analyzing structural formulas and protein-protein interactions of compounds. In the future, combining AI methods may rapidly accelerate drug discovery using iPSCs. In this review, we explain the details of AI technology and the application of AI for iPSC-based drug screening.

Moving Towards Induced Pluripotent Stem Cell-based Therapies with Artificial Intelligence and Machine Learning

The advent of induced pluripotent stem cell (iPSC) technology, which allows to transform one cell type into another, holds the promise to produce therapeutic cells and organs on demand. Realization of this objective is contingent on the ability to demonstrate quality and safety of the cellular product for its intended use. Bottlenecks and backlogs to the clinical use of iPSCs have been fully outlined and a need has emerged for safer and standardized protocols to trigger cell reprogramming and functional differentiation. Amidst great challenges, in particular associated with lengthy culture time and laborious cell characterization, a demand for faster and more accurate methods for the validation of cell identity and function at different stages of the iPSC manufacturing process has risen. Artificial intelligence-based methods are proving helpful for these complex tasks and might revolutionize the way iPSCs are managed to create surrogate cells and organs. Here, we briefly review recent progress in artificial intelligence approaches for evaluation of iPSCs and their derivatives in experimental studies.

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.

Cell Transdifferentiation and Reprogramming in Disease Modeling: Insights into the Neuronal and Cardiac Disease Models and Current Translational Strategies

Cell transdifferentiation and reprogramming approaches in recent times have enabled the manipulation of cell fate by enrolling exogenous/artificial controls. The chemical/small molecule and regulatory components of transcription machinery serve as potential tools to execute cell transdifferentiation and have thereby uncovered new avenues for disease modeling and drug discovery. At the advanced stage, one can believe these methods can pave the way to develop efficient and sensitive gene therapy and regenerative medicine approaches. As we are beginning to learn about the utility of cell transdifferentiation and reprogramming, speculations about its applications in translational therapeutics are being largely anticipated. Although clinicians and researchers are endeavoring to scale these processes, we lack a comprehensive understanding of their mechanism(s), and the promises these offer for targeted and personalized therapeutics are scarce. In the present report, we endeavored to provide a detailed review of the original concept, methods and modalities enrolled in the field of cellular transdifferentiation and reprogramming. A special focus is given to the neuronal and cardiac systems/diseases towards scaling their utility in disease modeling and drug discovery.

Quality evaluation of induced pluripotent stem cell colonies by fusing multi-source features

BACKGROUND AND OBJECTIVE

Induced pluripotent stem cells (iPSCs) have great potential as the basis of regenerative medicine. In this paper, we propose an automatic quality evaluation model based on multi-source feature ensemble learning to divide the iPSC colonies into three categories: good, medium and bad.

METHODS

First, we obtained iPSCs samples using a Sendai virus reprogramming method. Second, we collected the bright field-images of iPSC colonies and processed them with adaptive gamma transform and data enhancement. The evaluation for the iPSC colony quality was further verified with living cell fluorescent staining, currently accepted as the optimal biological method. Third, multi-source features were extracted using three deep convolutional neural networks (DCNNs) and four traditional feature descriptors. Finally, we utilized a support vector machine (SVM) to perform classification. Before feeding into the SVM, the features were processed by principal component analysis algorithm to save computational cost and training time.

RESULTS

Experimental results on the collected iPSC dataset (46,500 images) show that the proposed method could obtain 95.55% classification accuracy.

CONCLUSIONS

Our study could provide a method to efficiently and quickly judge the biological quality of a single iPSC colony or populations and facilitate the large-scale iPSC manufacturing.

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.

Reprogramming of Differentiated Mammalian and Human Retinal Pigment Epithelium: Current Achievements and Prospects

Abstract

Impairment of the homeostatic and functional integrity of the retina and retinal pigment epithelium (RPE) is the main cause of some degenerative diseases of the human eye, which are accompanied by loss of eyesight. Despite the significant progress made over the past decades in the development of new methods for treatment for this pathology, there are still several complications when using surgical methods for correction of eyesight and so far insurmountable limitations in the applications of modern approaches, such as gene therapy and genetic engineering. One of the promising approaches to the treatment of degenerative diseases of the retina may be an approach based on the application of regenerative capacities of its endogenous cells with high plasticity, in particular, of RPE cells and Müller glia. Currently, vertebrate RPE cells are of great interest as a source of new photoreceptors and other neurons in the degrading retina in vivo. In this regard, the possibilities of their direct reprogramming by genetic, epigenetic, and chemical methods and their combination are being investigated. This review focuses on research in gene-directed reprogramming of vertebrate RPE cells into retinal neurons, with detailed analysis of the genes used as the main reprogramming factors, comparative analysis, and extrapolation of experimental data from animals to humans. Also, this review covers studies on the application of alternative approaches to gene-directed reprogramming, such as chemical-mediated reprogramming with the use of cocktails of therapeutic low-molecular-weight compounds and microRNAs. In general, the research results indicate the complexity of the process for direct reprogramming of human RPE cells into retinal neurons. However, taking into account the results of direct reprogramming of vertebrate cells and the accessibility of human RPE cells for various vectors that deliver a variety of molecules to cells, such as transcription factors, chimeric endonucleases, recombinant proteins, and low-weight molecular compounds, the most optimal combination of factors for the successful conversion of human RPE cells to retinal neurons can be suggested.

Machine Learning Applied to Diagnosis of Human Diseases: A Systematic Review

Human healthcare is one of the most important topics for society. It tries to find the correct effective and robust disease detection as soon as possible to patients receipt the appropriate cares. Because this detection is often a difficult task, it becomes necessary medicine field searches support from other fields such as statistics and computer science. These disciplines are facing the challenge of exploring new techniques, going beyond the traditional ones. The large number of techniques that are emerging makes it necessary to provide a comprehensive overview that avoids very particular aspects. To this end, we propose a systematic review dealing with the Machine Learning applied to the diagnosis of human diseases. This review focuses on modern techniques related to the development of Machine Learning applied to diagnosis of human diseases in the medical field, in order to discover interesting patterns, making non-trivial predictions and useful in decision-making. In this way, this work can help researchers to discover and, if necessary, determine the applicability of the machine learning techniques in their particular specialties. We provide some examples of the algorithms used in medicine, analysing some trends that are focused on the goal searched, the algorithm used, and the area of applications. We detail the advantages and disadvantages of each technique to help choose the most appropriate in each real-life situation, as several authors have reported. The authors searched Scopus, Journal Citation Reports (JCR), Google Scholar, and MedLine databases from the last decades (from 1980s approximately) up to the present, with English language restrictions, for studies according to the objectives mentioned above. Based on a protocol for data extraction defined and evaluated by all authors using PRISMA methodology, 141 papers were included in this advanced review.

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.

Videira P, Valadão G. Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

The amount of data collected and managed in (bio)medicine is ever-increasing. Thus, there is a need to rapidly and efficiently collect, analyze, and characterize all this information. Artificial intelligence (AI), with an emphasis on deep learning, holds great promise in this area and is already being successfully applied to basic research, diagnosis, drug discovery, and clinical trials. Rare diseases (RDs), which are severely underrepresented in basic and clinical research, can particularly benefit from AI technologies. Of the more than 7000 RDs described worldwide, only 5% have a treatment. The ability of AI technologies to integrate and analyze data from different sources (e.g., multi-omics, patient registries, and so on) can be used to overcome RDs’ challenges (e.g., low diagnostic rates, reduced number of patients, geographical dispersion, and so on). Ultimately, RDs’ AI-mediated knowledge could significantly boost therapy development. Presently, there are AI approaches being used in RDs and this review aims to collect and summarize these advances. A section dedicated to congenital disorders of glycosylation (CDG), a particular group of orphan RDs that can serve as a potential study model for other common diseases and RDs, has also been included.

Using transcription factors for direct reprogramming of neurons in vitro

Cell therapy offers great promises in replacing the neurons lost due to neurodegenerative diseases or injuries. However, a key challenge is the cellular source for transplantation which is often limited by donor availability. Direct reprogramming provides an exciting avenue to generate specialized neuron subtypes in vitro, which have the potential to be used for autologous transplantation, as well as generation of patient-specific disease models in the lab for drug discovery and testing gene therapy. Here we present a detailed review on transcription factors that promote direct reprogramming of specific neuronal subtypes with particular focus on glutamatergic, GABAergic, dopaminergic, sensory and retinal neurons. We will discuss the developmental role of master transcriptional regulators and specification factors for neuronal subtypes, and summarize their use in promoting direct reprogramming into different neuronal subtypes. Furthermore, we will discuss up-and-coming technologies that advance the cell reprogramming field, including the use of computational prediction of reprogramming factors, opportunity of cellular reprogramming using small chemicals and microRNA, as well as the exciting potential for applying direct reprogramming in vivo as a novel approach to promote neuro-regeneration within the body. Finally, we will highlight the clinical potential of direct reprogramming and discuss the hurdles that need to be overcome for clinical translation.