Fibrin drives thromboinflammation and neuropathology in COVID-19.

Life-threatening thrombotic events and neurological symptoms are prevalent in COVID-19 and are persistent in patients with long COVID experiencing post-acute sequelae of SARS-CoV-2 infection1-4. Despite the clinical evidence1,5-7, the underlying mechanisms of coagulopathy in COVID-19 and its consequences in inflammation and neuropathology remain poorly understood and treatment options are insufficient. Fibrinogen, the central structural component of blood clots, is abundantly deposited in the lungs and brains of patients with COVID-19, correlates with disease severity and is a predictive biomarker for post-COVID-19 cognitive deficits1,5,8-10. Here we show that fibrin binds to the SARS-CoV-2 spike protein, forming proinflammatory blood clots that drive systemic thromboinflammation and neuropathology in COVID-19. Fibrin, acting through its inflammatory domain, is required for oxidative stress and macrophage activation in the lungs, whereas it suppresses natural killer cells, after SARS-CoV-2 infection. Fibrin promotes neuroinflammation and neuronal loss after infection, as well as innate immune activation in the brain and lungs independently of active infection. A monoclonal antibody targeting the inflammatory fibrin domain provides protection from microglial activation and neuronal injury, as well as from thromboinflammation in the lung after infection. Thus, fibrin drives inflammation and neuropathology in SARS-CoV-2 infection, and fibrin-targeting immunotherapy may represent a therapeutic intervention for patients with acute COVID-19 and long COVID.

Colorectal Cancer Detection via Metabolites and Machine Learning.

Today, colorectal cancer (CRC) diagnosis is performed using colonoscopy, which is the current, most effective screening method. However, colonoscopy poses risks of harm to the patient and is an invasive process. Recent research has proven metabolomics as a potential, non-invasive detection method, which can use identified biomarkers to detect potential cancer in a patient's body. The aim of this study is to develop a machine-learning (ML) model based on chemical descriptors that will recognize CRC-associated metabolites. We selected a set of metabolites found as the biomarkers of CRC, confirmed that they participate in cancer-related pathways, and used them for training a machine-learning model for the diagnostics of CRC. Using a set of selective metabolites and random compounds, we developed a range of ML models. The best performing ML model trained on Stage 0-2 CRC metabolite data predicted a metabolite class with 89.55% accuracy. The best performing ML model trained on Stage 3-4 CRC metabolite data predicted a metabolite class with 95.21% accuracy. Lastly, the best-performing ML model trained on Stage 0-4 CRC metabolite data predicted a metabolite class with 93.04% accuracy. These models were then tested on independent datasets, including random and unrelated-disease metabolites. In addition, six pathways related to these CRC metabolites were also distinguished: aminoacyl-tRNA biosynthesis; glyoxylate and dicarboxylate metabolism; glycine, serine, and threonine metabolism; phenylalanine, tyrosine, and tryptophan biosynthesis; arginine biosynthesis; and alanine, aspartate, and glutamate metabolism. Thus, in this research study, we created machine-learning models based on metabolite-related descriptors that may be helpful in developing a non-invasive diagnosis method for CRC.

Structure-selected RBM immunogens prime polyclonal memory responses that neutralize SARS-CoV-2 variants of concern.

Successful control of the COVID-19 pandemic depends on vaccines that prevent transmission. The full-length Spike protein is highly immunogenic but the majority of antibodies do not target the virus: ACE2 interface. In an effort to affect the quality of the antibody response focusing it to the receptor-binding motif (RBM) we generated a series of conformationally-constrained immunogens by inserting solvent-exposed RBM amino acid residues into hypervariable loops of an immunoglobulin molecule. Priming C57BL/6 mice with plasmid (p)DNA encoding these constructs yielded a rapid memory response to booster immunization with recombinant Spike protein. Immune sera antibodies bound strongly to the purified receptor-binding domain (RBD) and Spike proteins. pDNA primed for a consistent response with antibodies efficient at neutralizing authentic WA1 virus and three variants of concern (VOC), B.1.351, B.1.617.2, and BA.1. We demonstrate that immunogens built on structure selection can be used to influence the quality of the antibody response by focusing it to a conserved site of vulnerability shared between wildtype virus and VOCs, resulting in neutralizing antibodies across variants.

Development of a Diagnostic Model for Pancreatic Ductal Adenocarcinoma Using Machine Learning and Blood-Based miRNAs.

INTRODUCTION: Pancreatic ductal adenocarcinoma (PDAC) has the lowest survival rate among all major cancers due to a lack of symptoms in early stages, early detection tools, and optimal therapies for late-stage patients. Thus, effective and non-invasive diagnostic tests are greatly needed. Recently, circulating miRNAs have been reported to be altered in PDAC. They are promising biomarkers because of stability in the blood, ease of non-invasive detection, and convenient screening methods. This study aimed to use blood-based miRNA biomarkers and various analysis methods in the development of a machine-learning (ML) model for PDAC. METHODS: Blood-based miRNAs associated with PDAC were collected from open sources. miRNA sequences, targeted genes, and involved pathways were used to construct a set of descriptors for an ML model. RESULTS: Bioinformatics analysis revealed that most genes in pancreatic cancer and insulin signaling pathways were targeted by the PDAC-related miRNAs. The best-performing ML model with the Random Forest classifier was able to achieve an accuracy of 88.4%. Model evaluations of an independent PDAC-associated miRNAs test set had 100% accuracy while non-cancer miRNAs had 52.4% accuracy, indicating specificity to PDAC. CONCLUSIONS: Our results suggest an ML model developed using blood-based miRNA biomarkers' target gene, pathway, and sequence features could be potentially implicated in PDAC diagnostics.

Laryngeal cancer diagnosis via miRNA-based decision tree model.

PURPOSE: Laryngeal cancer (LC) is the most common head and neck cancer, which often goes undiagnosed due to the inaccessible nature of current diagnosis methods in some parts of the world. Many recent studies have shown that microRNAs (miRNAs) are crucial biomarkers for a variety of cancers. METHODS: In this study, we create a decision tree model for the diagnosis of laryngeal cancer using a created series of miRNA attributes, such as sequence-based characteristics, predicted miRNA target genes, and gene pathways. This series of attributes is extracted from both differentially expressed blood-based miRNAs in laryngeal cancer and random, non-associated with cancer miRNAs. RESULTS: Several machine-learning (ML) algorithms were tested in the ML model, and the Hoeffding Tree classifier yields the highest accuracy (86.8%) in miRNAs-based recognition of laryngeal cancer. Furthermore, our model is validated with the independent laryngeal cancer datasets and can accurately diagnose laryngeal cancer with 86% accuracy. We also explored the biological relationships of the attributes used in our model to understand their relationship with cancer proliferation or suppression pathways. CONCLUSION: Our study demonstrates that the proposed model and an inexpensive miRNA testing strategy have the potential to serve as an additional method for diagnosing laryngeal cancer.

piRNA in Machine-Learning-Based Diagnostics of Colorectal Cancer.

Objective biomarkers are crucial for early diagnosis to promote treatment and raise survival rates for diseases. With the smallest non-coding RNAs-piwi-RNAs (piRNAs)-and their transcripts, we sought to identify if these piRNAs could be used as biomarkers for colorectal cancer (CRC). Using previously published data from serum samples of patients with CRC, 13 differently expressed piRNAs were selected as potential biomarkers. With this data, we developed a machine learning (ML) algorithm and created 1020 different piRNA sequence descriptors. With the Naïve Bayes Multinomial classifier, we were able to isolate the 27 most influential sequence descriptors and achieve an accuracy of 96.4%. To test the validity of our model, we used data from piRBase with known associations with CRC that we did not use to train the ML model. We were able to achieve an accuracy of 85.7% with these new independent data. To further validate our model, we also tested data from unrelated diseases, including piRNAs with a correlation to breast cancer and no proven correlation to CRC. The model scored 44.4% on these piRNAs, showing that it can identify a difference between biomarkers of CRC and biomarkers of other diseases. The final results show that our model is an effective tool for diagnosing colorectal cancer. We believe that in the future, this model will prove useful for colorectal cancer and other diseases diagnostics.

Machine-learning-based virtual screening to repurpose drugs for treatment of Candida albicans infection.

BACKGROUND: Approximately 30% of Candida genus isolates are resistant to all currently available antifungal drugs and it is highly important to develop new treatments. Additionally, many current drugs are toxic and cause unwanted side effects. 1,3-beta-glucan synthase is an essential enzyme that builds the cell walls of Candida. OBJECTIVES: Targeting CaFKS1, a subunit of the synthase, could be used to fight Candida. METHODS: In the present study, a machine-learning model based on chemical descriptors was trained to recognise drugs that inhibit CaFKS1. The model attained 96.72% accuracy for classifying between active and inactive drug compounds. Descriptors for FDA-approved and other drugs were calculated, and the model was used to predict the potential activity of these drugs against CaFKS1. RESULTS: Several drugs, including goserelin and icatibant, were detected as active with high confidence. Many of the drugs, interestingly, were gonadotrophin-releasing hormone (GnRH) antagonists or agonists. A literature search found that five of the predicted drugs inhibit Candida experimentally. CONCLUSIONS: This study yields promising drugs to be repurposed to combat Candida albicans infection. Future steps include testing the drugs on fungal cells in vitro.

Potential SARS-CoV-2 protease Mpro inhibitors: repurposing FDA-approved drugs.

Using as a template the crystal structure of the SARS-CoV-2 main protease, we developed a pharmacophore model of functional centers of the protease inhibitor-binding pocket. With this model, we conducted data mining of the conformational database of FDA-approved drugs. This search brought 64 compounds that can be potential inhibitors of the SARS-CoV-2 protease. The conformations of these compounds undergone 3D fingerprint similarity clusterization. Then we conducted docking of possible conformers of these drugs to the binding pocket of the protease. We also conducted the same docking of random compounds. Free energies of the docking interaction for the selected compounds were clearly lower than random compounds. Three of the selected compounds were carfilzomib, cyclosporine A, and azithromycin-the drugs that already are tested for COVID-19 treatment. Among the selected compounds are two HIV protease inhibitors and two hepatitis C protease inhibitors. We recommend testing of the selected compounds for treatment of COVID-19.

Finding distinctions between oral cancer and periodontitis using saliva metabolites and machine learning.

OBJECTIVE: The aim of this research is the study of metabolic pathways related to oral cancer and periodontitis along with development of machine-learning model for elucidation of these diseases based on saliva metabolites of patients. METHODS: Data mining, metabolomic pathways analysis, study of metabolite-gene networks related to these diseases. Machine-learning and deep-learning methods for development of the model for recognition of oral cancer versus periodontitis, using patients' saliva. RESULTS: The most accurate classifications between oral cancer and periodontitis were performed using neural networks, logistic regression and stochastic gradient descent confirmed by the separate 10-fold cross-validations. The best results were achieved by the deep-learning neural network with the TensorFlow program. Accuracy of the resulting model was 79.54%. The other methods, which did not rely on deep learning, were able to achieve comparable, although slightly worse results with respect to accuracy. CONCLUSION: Our results demonstrate a possibility to distinguish oral cancer from periodontal disease by analysis the saliva metabolites of a patient, using machine-learning methods. These findings may be useful in the development of a non-invasive method to aid care providers in determining between oral cancer and periodontitis quickly and effectively.

ANKRD9 is a metabolically-controlled regulator of IMPDH2 abundance and macro-assembly.

Members of a large family of Ankyrin Repeat Domain (ANKRD) proteins regulate numerous cellular processes by binding to specific protein targets and modulating their activity, stability, and other properties. The same ANKRD protein may interact with different targets and regulate distinct cellular pathways. The mechanisms responsible for switches in the ANKRDs' behavior are often unknown. We show that cells' metabolic state can markedly alter interactions of an ANKRD protein with its target and the functional outcomes of this interaction. ANKRD9 facilitates degradation of inosine monophosphate dehydrogenase 2 (IMPDH2), the rate-limiting enzyme in GTP biosynthesis. Under basal conditions ANKRD9 is largely segregated from the cytosolic IMPDH2 in vesicle-like structures. Upon nutrient limitation, ANKRD9 loses its vesicular pattern and assembles with IMPDH2 into rodlike filaments, in which IMPDH2 is stable. Inhibition of IMPDH2 activity with ribavirin favors ANKRD9 binding to IMPDH2 rods. The formation of ANKRD9/IMPDH2 rods is reversed by guanosine, which restores ANKRD9 associations with the vesicle-like structures. The conserved Cys109Cys110 motif in ANKRD9 is required for the vesicle-to-rods transition as well as binding and regulation of IMPDH2. Oppositely to overexpression, ANKRD9 knockdown increases IMPDH2 levels and prevents formation of IMPDH2 rods upon nutrient limitation. Taken together, the results suggest that a guanosine-dependent metabolic switch determines the mode of ANKRD9 action toward IMPDH2.

Deep-learning- and pharmacophore-based prediction of RAGE inhibitors.

The receptor for advanced glycation end products (RAGE) has been identified as a therapeutic target in a host of pathological diseases, including Alzheimer's disease. RAGE is a target with no crystallographic data on inhibitors in complex with RAGE, multiple hypothesized binding modes, and small amounts of activity data. The main objective of this study was to demonstrate the efficacy of deep-learning (DL) techniques on small bioactivity datasets, and to identify candidate inhibitors of RAGE. We applied transfer learning in the form of a semi-supervised molecular representation in order to address small dataset problems. To validate the candidate inhibitors, we examined them using more computationally expensive pharmacophore-modeling and docking techniques. We created a strong classifier of RAGE activity, producing 79 candidate inhibitors. These candidates agreed with docking models and were shown to have no significant statistical difference from pharmacophore-based results. The transfer-learning techniques used allow DL to generalize chemical features from small bioactivity datasets to a broader library of compounds with high accuracy. Furthermore, the DL model is able to handle multiple binding modes without explicit instructions. Our results demonstrate the potential of a broad family of DL techniques on bioactivity predictions.

Bovine leukemia virus relation to human breast cancer: Meta-analysis.

Bovine leukemia virus (BLV) is a virus that infects cattle around the world and is very similar to the human T-cell leukemia virus (HTLV), which causes adult T-cell leukemia/lymphoma (ATL). Recently, presence of BLV DNA and protein was demonstrated in commercial bovine products and in humans. BLV DNA is generally found at higher rates in humans who have or will develop breast cancer, according to research done with subjects from several countries. These findings have led to a hypothesis that BLV transmission plays a role in breast cancer oncogenesis in humans. Here we summarize the current knowledge in the field.

Prediction of Premature Termination Codon Suppressing Compounds for Treatment of Duchenne Muscular Dystrophy Using Machine Learning.

A significant percentage of Duchenne muscular dystrophy (DMD) cases are caused by premature termination codon (PTC) mutations in the dystrophin gene, leading to the production of a truncated, non-functional dystrophin polypeptide. PTC-suppressing compounds (PTCSC) have been developed in order to restore protein translation by allowing the incorporation of an amino acid in place of a stop codon. However, limitations exist in terms of efficacy and toxicity. To identify new compounds that have PTC-suppressing ability, we selected and clustered existing PTCSC, allowing for the construction of a common pharmacophore model. Machine learning (ML) and deep learning (DL) models were developed for prediction of new PTCSC based on known compounds. We conducted a search of the NCI compounds database using the pharmacophore-based model and a search of the DrugBank database using pharmacophore-based, ML and DL models. Sixteen drug compounds were selected as a consensus of pharmacophore-based, ML, and DL searches. Our results suggest notable correspondence of the pharmacophore-based, ML, and DL models in prediction of new PTC-suppressing compounds.

Recognition of early and late stages of bladder cancer using metabolites and machine learning.

INTRODUCTION: Bladder cancer (BCa) is one of the most common and aggressive cancers. It is the sixth most frequently occurring cancer in men and its rate of occurrence increases with age. The current method of BCa diagnosis includes a cystoscopy and biopsy. This process is expensive, unpleasant, and may have severe side effects. Recent growth in the power and accessibility of machine-learning software has allowed for the development of new, non-invasive diagnostic methods whose accuracy and sensitivity are uncompromising to function. OBJECTIVES: The goal of this research was to elucidate the biomarkers including metabolites and corresponding genes for different stages of BCa, show their distinguishing and common features, and create a machine-learning model for classification of stages of BCa. METHODS: Sets of metabolites for early and late stages, as well as common for both stages were analyzed using MetaboAnalyst and Ingenuity® Pathway Analysis (IPA®) software. Machine-learning methods were utilized in the development of a binary classifier for early- and late-stage metabolites of BCa. Metabolites were quantitatively characterized using EDragon 1.0 software. The two modeling methods used are Multilayer Perceptron (MLP) and Stochastic Gradient Descent (SGD) with a logistic regression loss function. RESULTS: We explored metabolic pathways related to early-stage BCa (Galactose metabolism and Starch and sucrose metabolism) and to late-stage BCa (Glycine, serine, and threonine metabolism, Arginine and proline metabolism, Glycerophospholipid metabolism, and Galactose metabolism) as well as those common to both stages pathways. The central metabolite impacting the most cancerogenic genes (AKT, EGFR, MAPK3) in early stage is D-glucose, while late-stage BCa is characterized by significant fold changes in several metabolites: glycerol, choline, 13(S)-hydroxyoctadecadienoic acid, 2'-fucosyllactose. Insulin was also seen to play an important role in late stages of BCa. The best performing model was able to predict metabolite class with an accuracy of 82.54% and the area under precision-recall curve (PRC) of 0.84 on the training set. The same model was applied to three separate sets of metabolites obtained from public sources, one set of the late-stage metabolites and two sets of the early-stage metabolites. The model was better at predicting early-stage metabolites with accuracies of 72% (18/25) and 95% (19/20) on the early sets, and an accuracy of 65.45% (36/55) on the late-stage metabolite set. CONCLUSION: By examining the biomarkers present in the urine samples of BCa patients as compared with normal patients, the biomarkers associated with this cancer can be pinpointed and lead to the elucidation of affected metabolic pathways that are specific to different stages of cancer. Development of machine-learning model including metabolites and their chemical descriptors made it possible to achieve considerable accuracy of prediction of stages of BCa.

A novel small molecule inhibitor of p32 mitochondrial protein overexpressed in glioma.

BACKGROUND: The mitochondrial protein p32 is a validated therapeutic target of cancer overexpressed in glioma. Therapeutic targeting of p32 with monoclonal antibody or p32-binding LyP-1 tumor-homing peptide can limit tumor growth. However, these agents do not specifically target mitochondrial-localized p32 and would not readily cross the blood-brain barrier to target p32-overexpressing gliomas. Identifying small molecule inhibitors of p32 overexpressed in cancer is a more rational therapeutic strategy. Thus, in this study we employed a pharmacophore modeling strategy to identify small molecules that could bind and inhibit mitochondrial p32. METHODS: A pharmacophore model of C1q and LyP-1 peptide association with p32 was used to screen a virtual compound library. A primary screening assay for inhibitors of p32 was developed to identify compounds that could rescue p32-dependent glutamine-addicted glioma cells from glutamine withdrawal. Inhibitors from this screen were analyzed for direct binding to p32 by fluorescence polarization assay and protein thermal shift. Affect of the p32 inhibitor on glioma cell proliferation was assessed by Alamar Blue assay, and affect on metabolism was examined by measuring lactate secretion. RESULTS: Identification of a hit compound (M36) validates the pharmacophore model. M36 binds directly to p32 and inhibits LyP-1 tumor homing peptide association with p32 in vitro. M36 effectively inhibits the growth of p32 overexpressing glioma cells, and sensitizes the cells to glucose depletion. CONCLUSIONS: This study demonstrates a novel screening strategy to identify potential inhibitors of mitochondrial p32 protein overexpressed in glioma. High throughput screening employing this strategy has potential to identify highly selective, potent, brain-penetrant small molecules amenable for further drug development.

A de novo compound targeting α-synuclein improves deficits in models of Parkinson's disease.

Abnormal accumulation and propagation of the neuronal protein α-synuclein has been hypothesized to underlie the pathogenesis of Parkinson's disease, dementia with Lewy bodies and multiple system atrophy. Here we report a de novo-developed compound (NPT100-18A) that reduces α-synuclein toxicity through a novel mechanism that involves displacing α-synuclein from the membrane. This compound interacts with a domain in the C-terminus of α-synuclein. The E83R mutation reduces the compound interaction with the 80-90 amino acid region of α-synuclein and prevents the effects of NPT100-18A. In vitro studies showed that NPT100-18A reduced the formation of wild-type α-synuclein oligomers in membranes, reduced the neuronal accumulation of α-synuclein, and decreased markers of cell toxicity. In vivo studies were conducted in three different α-synuclein transgenic rodent models. Treatment with NPT100-18A ameliorated motor deficits in mThy1 wild-type α-synuclein transgenic mice in a dose-dependent manner at two independent institutions. Neuropathological examination showed that NPT100-18A decreased the accumulation of proteinase K-resistant α-synuclein aggregates in the CNS and was accompanied by the normalization of neuronal and inflammatory markers. These results were confirmed in a mutant line of α-synuclein transgenic mice that is prone to generate oligomers. In vivo imaging studies of α-synuclein-GFP transgenic mice using two-photon microscopy showed that NPT100-18A reduced the cortical synaptic accumulation of α-synuclein within 1 h post-administration. Taken together, these studies support the notion that altering the interaction of α-synuclein with the membrane might be a feasible therapeutic approach for developing new disease-modifying treatments of Parkinson's disease and other synucleinopathies.

Discovery of substituted 4-aminoquinazolines as selective Toll-like receptor 4 ligands.

The Toll-like receptors (TLRs) are critical components of the innate immune system that regulate immune recognition in part through NF-κB activation. A human cell-based high throughput screen (HTS) revealed substituted 4-aminoquinazolines to be small molecular weight activators of NF-κB. The most potent hit compound predominantly stimulated through the human TLR4/MD2 complex, and had less activity with the mouse TLR4/MD2. There was no activity with other TLRs and the TLR4 activation was MD-2 dependent and CD14 independent. Synthetic modifications of the quinazoline scaffold at the 2 and 4 positions revealed trends in structure-activity relationships with respect to TLR dependent production of the NF-κB associated cytokine IL-8 in human peripheral blood mononuclear cells, as well as IL-6 in mouse antigen presenting cells. Furthermore, the hit compound in this series also activated the interferon signaling pathway resulting in type I interferon production. Substitution at the O-phenyl moiety with groups such as bromine, chlorine and methyl resulted in enhanced immunological activity. Computational studies indicated that the 4-aminoquinazoline compounds bind primarily to human MD-2 in the TLR4/MD-2 complex. These small molecules, which preferentially stimulate human rather than mouse innate immune cells, may be useful as adjuvants or immunotherapeutic agents.

Implementation of Machine Learning-Based System for Early Diagnosis of Feline Mammary Carcinomas through Blood Metabolite Profiling.

Background: Feline mammary carcinoma (FMC) is a prevalent and fatal carcinoma that predominantly affects unspayed female cats. FMC is the third most common carcinoma in cats but is still underrepresented in research. Current diagnosis methods include physical examinations, imaging tests, and fine-needle aspiration. The diagnosis through these methods is sometimes delayed and unreliable, leading to increased chances of mortality. Objectives: The objective of this study was to identify the biomarkers, including blood metabolites and genes, related to feline mammary carcinoma, study their relationships, and develop a machine learning (ML) model for the early diagnosis of the disease. Methods: We analyzed the blood metabolites of felines with mammary carcinoma using the pathway analysis feature in MetaboAnalyst software, v. 5.0. We utilized machine-learning (ML) methods to recognize FMC using the blood metabolites of sick patients. Results: The metabolic pathways that were elucidated to be associated with this disease include alanine, aspartate and glutamate metabolism, Glutamine and glutamate metabolism, Arginine biosynthesis, and Glycerophospholipid metabolism. Furthermore, we also elucidated several genes that play a significant role in the development of FMC, such as ERBB2, PDGFA, EGFR, FLT4, ERBB3, FIGF, PDGFC, PDGFB through STRINGdb, a database of known and predicted protein-protein interactions, and MetaboAnalyst 5.0. The best-performing ML model was able to predict metabolite class with an accuracy of 85.11%. Conclusion: Our findings demonstrate that the identification of the biomarkers associated with FMC and the affected metabolic pathways can aid in the early diagnosis of feline mammary carcinoma.

Parkinson's Disease Diagnosis Using miRNA Biomarkers and Deep Learning.

BACKGROUND: The current standard for Parkinson's disease (PD) diagnosis is often imprecise and expensive. However, the dysregulation patterns of microRNA (miRNA) hold potential as a reliable and effective non-invasive diagnosis of PD. METHODS: We use data mining to elucidate new miRNA biomarkers and then develop a machine-learning (ML) model to diagnose PD based on these biomarkers. RESULTS: The best-performing ML model, trained on filtered miRNA dysregulated in PD, was able to identify miRNA biomarkers with 95.65% accuracy. Through analysis of miRNA implicated in PD, thousands of descriptors reliant on gene targets were created that can be used to identify novel biomarkers and strengthen PD diagnosis. CONCLUSIONS: The developed ML model based on miRNAs and their genomic pathway descriptors achieved high accuracies for the prediction of PD.

Using Machine Learning and miRNA for the Diagnosis of Esophageal Cancer.

BACKGROUND: Esophageal cancer (EC) remains a global health challenge, often diagnosed at advanced stages, leading to high mortality rates. Current diagnostic tools for EC are limited in their efficacy. This study aims to harness the potential of microRNAs (miRNAs) as novel, noninvasive diagnostic biomarkers for EC. Our objective was to determine the diagnostic accuracy of miRNAs, particularly in distinguishing miRNAs associated with EC from control miRNAs. METHODS: We applied machine learning (ML) techniques in WEKA (Waikato Environment for Knowledge Analysis) and TensorFlow Keras to a dataset of miRNA sequences and gene targets, assessing the predictive power of several classifiers: naïve Bayes, multilayer perceptron, Hoeffding tree, random forest, and random tree. The data were further subjected to InfoGain feature selection to identify the most informative miRNA sequence and gene target descriptors. The ML models' abilities to distinguish between miRNA implicated in EC and control group miRNA was then tested. RESULTS: Of the tested WEKA classifiers, the top 3 performing ones were random forest, Hoeffding tree, and naïve Bayes. The TensorFlow Keras neural network model was subsequently trained and tested, the model's predictive power was further validated using an independent dataset. The TensorFlow Keras gave an accuracy 0.91. The WEKA best algorithm (naïve Bayes) model yielded an accuracy of 0.94. CONCLUSIONS: The results demonstrate the potential of ML-based miRNA classifiers in diagnosing EC. However, further studies are necessary to validate these findings and explore the full clinical potential of this approach.