DERIVATION AND VALIDATION OF A MACHINE LEARNING MODEL FOR THE PREVENTION OF UNPLANNED DIALYSIS.

BACKGROUND: Approximately half of all patients with advanced chronic kidney disease (CKD) who progress to kidney failure initiate dialysis in an unplanned fashion which is associated with high morbidity, mortality, and healthcare costs. A novel prediction model designed to identify advanced CKD patients who are at high risk for developing kidney failure over short time frames (6-12 months) may help reduce the rates of unplanned dialysis and improve the quality of transitions from CKD to kidney failure. METHODS: We performed a retrospective study employing machine learning random forest algorithms incorporating routinely collected age and sex data along with time-varying trends in laboratory measurements to derive and validate six- and 12-month kidney failure risk prediction models in the advanced CKD population. The models were comprehensively characterized in three independent cohorts in Ontario, Canada - derived in a cohort of 1,849 consecutive advanced CKD patients (mean [standard deviation] age 66 [15] years, eGFR 19 [7] mL/min/1.73m2), and validated in two external advanced CKD cohorts (n=1,356; age 69 [14] years, eGFR 22 [7] mL/min/1.73m2). RESULTS: Across all cohorts, 55% of patients experienced kidney failure, of which 35% involved unplanned dialysis. The six- and 12-month models demonstrated excellent discrimination with area under the receiver operating characteristic curve of 0.88 (95%CI: 0.87-0.89) and 0.87 (95%CI: 0.86-0.87) along with high probabilistic accuracy with Brier scores of 0.10 (95%CI 0.09-0.10) and 0.14 (95%CI 0.13-0.14), respectively. The models were also well-calibrated and delivered timely alerts on a significant number of patients who ultimately initiated dialysis in an unplanned fashion. Similar results were found upon external validation testing. CONCLUSION: These machine-learning models using routinely collected patient data accurately predict near-future kidney failure risk among the advanced CKD population, and retrospectively deliver advanced warning on a substantial proportion of unplanned dialysis events. Optimal implementation strategies still need to be elucidated.

Simulating whole-body vibration for neonatal patients on a tire-coupled road simulator.

Exposure to excessive whole-body vibration is linked to health issues and may result in increased rates of mortality and morbidity in infants. Newborn infants requiring specialized treatment at neonatal intensive care units often require transportation by road ambulance to specialized care centers, exposing the infants to potentially harmful vibration and noise. A standardized Neonatal Patient Transport System (NPTS) has been deployed in Ontario, Canada, that provides life saving equipment to patients and safe operation for the clinical care staff. However, there is evidence that suggests patients may experience a higher amplitude of vibration at certain frequencies when compared with the vehicle vibration. In a multi-year collaborative project, we seek to create a standardized test procedure to evaluate the levels of vibration and the effectiveness of mitigation strategies. Previous studies have looked at laboratory vibration testing of a transport system or transport incubator and were limited to single degree of freedom excitation, neglecting the combined effects of rotational motion. This study considers laboratory testing of a full vehicle and patient transport system on an MTS Model 320 Tire-Coupled Road Simulator. The simulation of road profiles and discrete events on a tire-coupled road simulator allows for the evaluation of the vibration levels of the transport system and the exploration of mitigation strategies in a controlled setting. The tire-coupled simulator can excite six degrees-of-freedom motion of the transport system for vibration evaluation in three orthogonal directions including the contributions of the three rotational degrees of freedom. The vibration data measured on the transport system during the tire-coupled testing are compared to corresponding road test data to assess the accuracy of the vibration environment replication. Three runs of the same drive file were conducted during the laboratory testing, allowing the identification of anomalies and evaluation of the repeatability. The tire-coupled full vehicle testing revealed a high level of accuracy in re-creating the road sections and synthesized random profiles. The simulation of high amplitude discrete events, such as speed hump traverses, were highly repeatable, yet yielded less accurate results with respect to the peak amplitudes at the patient. The resulting accelerations collected at the input to the manikin (sensor located under the mattress) matched well between the real-world and road simulator. The sensors used during testing included series 3741B uni-axial and series 356A01 tri-axial accelerometers by PCB Piezotronics. These results indicate a tire-coupled road simulator can be used to accurately evaluate vibration levels and assess the benefits of future mitigation strategies in a controlled setting with a high level of repeatability.

Species-specific microRNA discovery and target prediction in the soybean cyst nematode.

The soybean cyst nematode (SCN) is a devastating pathogen for economic and food security considerations. Although the SCN genome has recently been sequenced, the presence of any miRNA has not been systematically explored and reported. This paper describes the development of a species-specific SCN miRNA discovery pipeline and its application to the SCN genome. Experiments on well-documented model nematodes (Caenorhabditis elegans and Pristionchus pacificus) are used to tune the pipeline's hyperparameters and confirm its recall and precision. Application to the SCN genome identifies 3342 high-confidence putative SCN miRNA. Prediction specificity within SCN is confirmed by applying the pipeline to RNA hairpins from known exonic regions of the SCN genome (i.e., sequences known to not be miRNA). Prediction recall is confirmed by building a positive control set of SCN miRNA, based on a limited deep sequencing experiment. Interestingly, a number of novel miRNA are predicted to be encoded within the intronic regions of effector genes, known to be involved in SCN parasitism, suggesting that these miRNA may also be involved in the infection process or virulence. Beyond miRNA discovery, gene targets within SCN are predicted for all high-confidence novel miRNA using a miRNA:mRNA target prediction system. Lastly, cross-kingdom miRNA targeting is investigated, where putative soybean mRNA targets are identified for novel SCN miRNA. All predicted miRNA and gene targets are made available in appendix and through a Borealis DataVerse open repository ( https://borealisdata.ca/dataset.xhtml?persistentId=doi:10.5683/SP3/30DEXA ).

Short Timeframe Prediction of Kidney Failure among Patients with Advanced Chronic Kidney Disease.

BACKGROUND: Development of a short timeframe (6-12 months) kidney failure risk prediction model may serve to improve transitions from advanced chronic kidney disease (CKD) to kidney failure and reduce rates of unplanned dialysis. The optimal model for short timeframe kidney failure risk prediction remains unknown. METHODS: This retrospective study included 1757 consecutive patients with advanced CKD (mean age 66 years, estimated glomerular filtration rate 18 mL/min/1.73 m2). We compared the performance of Cox regression models using (a) baseline variables alone, (b) time-varying variables and machine learning models, (c) random survival forest, (d) random forest classifier in the prediction of kidney failure over 6/12/24 months. Performance metrics included area under the receiver operating characteristic curve (AUC-ROC) and maximum precision at 70% recall (PrRe70). Top-performing models were applied to 2 independent external cohorts. RESULTS: Compared to the baseline Cox model, the machine learning and time-varying Cox models demonstrated higher 6-month performance [Cox baseline: AUC-ROC 0.85 (95% CI 0.84-0.86), PrRe70 0.53 (95% CI 0.51-0.55); Cox time-varying: AUC-ROC 0.88 (95% CI 0.87-0.89), PrRe70 0.62 (95% CI 0.60-0.64); random survival forest: AUC-ROC 0.87 (95% CI 0.86-0.88), PrRe70 0.61 (95% CI 0.57-0.64); random forest classifier AUC-ROC 0.88 (95% CI 0.87-0.89), PrRe70 0.62 (95% CI 0.59-0.65)]. These trends persisted, but were less pronounced, at 12 months. The random forest classifier was the highest performing model at 6 and 12 months. At 24 months, all models performed similarly. Model performance did not significantly degrade upon external validation. CONCLUSIONS: When predicting kidney failure over short timeframes among patients with advanced CKD, machine learning incorporating time-updated data provides enhanced performance compared with traditional Cox models.

P-TarPmiR accurately predicts plant-specific miRNA targets.

microRNAs (miRNAs) are small non-coding ribonucleic acids that post-transcriptionally regulate gene expression through the targeting of messenger RNA (mRNAs). Most miRNA target predictors have focused on animal species and prediction performance drops substantially when applied to plant species. Several rule-based miRNA target predictors have been developed in plant species, but they often fail to discover new miRNA targets with non-canonical miRNA-mRNA binding. Here, the recently published TarDB database of plant miRNA-mRNA data is leveraged to retrain the TarPmiR miRNA target predictor for application on plant species. Rigorous experiment design across four plant test species demonstrates that animal-trained predictors fail to sustain performance on plant species, and that the use of plant-specific training data improves accuracy depending on the quantity of plant training data used. Surprisingly, our results indicate that the complete exclusion of animal training data leads to the most accurate plant-specific miRNA target predictor indicating that animal-based data may detract from miRNA target prediction in plants. Our final plant-specific miRNA prediction method, dubbed P-TarPmiR, is freely available for use at http://ptarpmir.cu-bic.ca . The final P-TarPmiR method is used to predict targets for all miRNA within the soybean genome. Those ranked predictions, together with GO term enrichment, are shared with the research community.

Reciprocal perspective as a super learner improves drug-target interaction prediction (MUSDTI).

The identification of novel drug-target interactions (DTI) is critical to drug discovery and drug repurposing to address contemporary medical and public health challenges presented by emergent diseases. Historically, computational methods have framed DTI prediction as a binary classification problem (indicating whether or not a drug physically interacts with a given protein target); however, framing the problem instead as a regression-based prediction of the physiochemical binding affinity is more meaningful. With growing databases of experimentally derived drug-target interactions (e.g. Davis, Binding-DB, and Kiba), deep learning-based DTI predictors can be effectively leveraged to achieve state-of-the-art (SOTA) performance. In this work, we formulated a DTI competition as part of the coursework for a senior undergraduate machine learning course and challenged students to generate component DTI models that might surpass SOTA models and effectively combine these component models as part of a meta-model using the Reciprocal Perspective (RP) multi-view learning framework. Following 6 weeks of concerted effort, 28 student-produced component deep-learning DTI models were leveraged in this work to produce a new SOTA RP-DTI model, denoted the Meta Undergraduate Student DTI (MUSDTI) model. Through a series of experiments we demonstrate that (1) RP can considerably improve SOTA DTI prediction, (2) our new double-cold experimental design is more appropriate for emergent DTI challenges, (3) that our novel MUSDTI meta-model outperforms SOTA models, (4) that RP can improve upon individual models as an ensembling method, and finally, (5) RP can be utilized for low computation transfer learning. This work introduces a number of important revelations for the field of DTI prediction and sequence-based, pairwise prediction in general.

Assessing sequence-based protein-protein interaction predictors for use in therapeutic peptide engineering.

Engineering peptides to achieve a desired therapeutic effect through the inhibition of a specific target activity or protein interaction is a non-trivial task. Few of the existing in silico peptide design algorithms generate target-specific peptides. Instead, many methods produce peptides that achieve a desired effect through an unknown mechanism. In contrast with resource-intensive high-throughput experiments, in silico screening is a cost-effective alternative that can prune the space of candidates when engineering target-specific peptides. Using a set of FDA-approved peptides we curated specifically for this task, we assess the applicability of several sequence-based protein-protein interaction predictors as a screening tool within the context of peptide therapeutic engineering. We show that similarity-based protein-protein interaction predictors are more suitable for this purpose than the state-of-the-art deep learning methods publicly available at the time of writing. We also show that this approach is mostly useful when designing new peptides against targets for which naturally-occurring interactors are already known, and that deploying it for de novo peptide engineering tasks may require gathering additional target-specific training data. Taken together, this work offers evidence that supports the use of similarity-based protein-protein interaction predictors for peptide therapeutic engineering, especially peptide analogs.

Machine Learning Study of Metabolic Networks vs ChEMBL Data of Antibacterial Compounds.

Antibacterial drugs (AD) change the metabolic status of bacteria, contributing to bacterial death. However, antibiotic resistance and the emergence of multidrug-resistant bacteria increase interest in understanding metabolic network (MN) mutations and the interaction of AD vs MN. In this study, we employed the IFPTML = Information Fusion (IF) + Perturbation Theory (PT) + Machine Learning (ML) algorithm on a huge dataset from the ChEMBL database, which contains >155,000 AD assays vs >40 MNs of multiple bacteria species. We built a linear discriminant analysis (LDA) and 17 ML models centered on the linear index and based on atoms to predict antibacterial compounds. The IFPTML-LDA model presented the following results for the training subset: specificity (Sp) = 76% out of 70,000 cases, sensitivity (Sn) = 70%, and Accuracy (Acc) = 73%. The same model also presented the following results for the validation subsets: Sp = 76%, Sn = 70%, and Acc = 73.1%. Among the IFPTML nonlinear models, the k nearest neighbors (KNN) showed the best results with Sn = 99.2%, Sp = 95.5%, Acc = 97.4%, and Area Under Receiver Operating Characteristic (AUROC) = 0.998 in training sets. In the validation series, the Random Forest had the best results: Sn = 93.96% and Sp = 87.02% (AUROC = 0.945). The IFPTML linear and nonlinear models regarding the ADs vs MNs have good statistical parameters, and they could contribute toward finding new metabolic mutations in antibiotic resistance and reducing time/costs in antibacterial drug research.

Generation and Reactions of ε-Carbonyl Cations via Group 13 Catalysis.

The generation of ε-carbonyl cations and their reactions with nucleophiles is accomplished readily without transition metal cation stabilization, using the ε-bromide dienoate or dienone starting materials and GaCl3 or InCl3 catalysis. Arene nucleophiles are somewhat more straightforward than allyltrimethylsilane, but allyltrimethylsilane and propiophenone trimethysilyl enol ether each react successfully with InCl3 catalysis. The viability of these cations is supported by DFT calculations.

Sex differences in developmental patterns of neocortical astroglia: A mouse translatome database.

Astroglial cells are key players in the development and maintenance of neurons and neuronal networks. Astroglia express steroid hormone receptors and show rapid responses to hormonal manipulations. However, despite important sex differences in the cortex and hippocampus, few studies have examined sex differences in astroglial cells in telencephalic development. To characterize the cortical astroglial translatome in male and female mice across postnatal development, we use translating ribosome affinity purification together with RNA sequencing and immunohistochemistry to phenotype astroglia at six developmental time points. Overall, we find two distinct astroglial phenotypes between early (P1-P7) and late development (P14-adult), independent of sex. We also find sex differences in gene expression patterns across development that peak at P7 and appear to result from males reaching a mature astroglial phenotype earlier than females. These developmental sex differences could have an impact on the construction of neuronal networks and windows of vulnerability to perturbations and disease.

Fluorescein isothiocyanate, a platform for the selective and sensitive detection of S-Nitrosothiols and hydrogen sulfide.

Here we show that the fluorescence of fluorescein isothiocyanate (FITC) is not altered by its reaction with primary amines. However, the fluorescence is rapidly quenched upon reaction with small molecular weight thiols including cysteine, glutathione, homocysteine, dithiothreitol, and sulfide. We have taken advantage of the thiol-dependent quenching of FITC to devise a sulfide specific assay by utilizing polydimethylsiloxane (PDMS) membranes that are permeable to hydrogen sulfide but not to larger charged thiols. In addition, we have discovered that the fluorescein dithiocarbamate (FDTC) formed by the reaction with sulfide can specifically react with S-nitrosothiols (RSNO) to regenerate FITC, thus serving as a specific, fluorogenic reagent to detect picomol levels of RSNO. FDTC was tested as an intracellular RSNO-sensor in germinating tomato seedlings (Solanum lycopersicum) via epifluorescence microscopy. Control plant roots exposed to FDTC showed low intracellular fluorescence which increased ∼3-fold upon exposure to extracellular S-nitrosoglutathione and ∼4-fold in the presence of N6022, a S-nitrosoglutathione reductase (GSNOR) inhibitor, demonstrating that FDTC can be used to visualize intracellular RSNO levels.

Alkynedicobalt mediated vinylogous Nazarov reactions.

The SnCl4 mediated reactions of cross conjugated aryl enynone-Co2(CO)6 and dienynone-Co2(CO)6 complexes afford benzocycloheptynone complexes or cycloheptenynone complexes in a thermal vinylogous Nazarov process. The rate of ring closure is strongly dependent on the ketone α-substituent.

Bottle-Feeding Intervention Detection in the NICU.

Video-based monitoring of patients in the neonatal intensive care unit (NICU) has great potential for improving patient care. Video-based detection of clinical events, such as bottle feeding, would represent a step towards semi-automated charting of clinical events. Recording such events contemporaneously would address the limitations associated with retrospective charting. Such a system could also support oral feeding assessment tools, as the patient's feeding skills and nutrition are pivotal in monitoring their growth. We therefore leverage transfer learning using a pretrained VGG-16 model to classify images obtained during an intervention, to determine if a bottle-feeding event is occurring. Additionally, we explore a data expansion technique by extracting similar-feature images from publicly available sources to supplement our dataset of real NICU patients to address data scarcity. This work also visualizes and quantifies the gap between the source domain (ImageNet data subset) and target domain (NICU dataset), thereby illustrating the impact of expanding our training set for knowledge transfer proficiency. Results show an increase of over 18% in sensitivity after data expansion. Analysis of network activation maps indicates that data expansion is able to reduce the distance between the source and target domains.

Reaction of Alkynyl- and Alkenyltrifluoroborates with Propargyldicobalt Cations: Alkynylation, Alkenylation, and Cyclopropanation Product Pathways.

The Lewis acid-mediated Nicholas reactions of propargyl acetate-Co2(CO)6 complexes with a series of potassium alkynyltrifluoroborates and potassium alkenyltrifluoroborates are described. Alkynyltrifluoroborates directly alkynylate the intermediate propargyldicobalt cations. In contrast, alkenyltrifluoroborates proceed through one of the three modes of dominant reactivity: C-2-substituted alkenyltrifluorobrates directly alkenylate, predominantly with the retention of stereochemistry. C-1-substituted alkenyltrifluoroborates alkenylate at C-2. Potassium vinyltrifluoroborate incorporates a cyclopropane at the site propargyl to alkynedicobalt. Computational analysis of these systems explains the differential modes of reactivity of alkenyltrifluoroborates and outlines the probable mechanisms for the formation of each product.

RGB-D scene analysis in the NICU.

Continuity of care is achieved in the neonatal intensive care unit (NICU) through careful documentation of all events of clinical significance, including clinical interventions and routine care events (e.g., feeding, diaper change, weighing, etc.). As a step towards automating this documentation process, we propose a scene recognition algorithm that can automatically identify key features in a single image of the patient environment, paired with a rule-based sentence generator to caption the scene. Color and depth video were obtained from 29 newborn patients from the Children's Hospital of Eastern Ontario (CHEO) using an Intel RealSense SR300 RGB-D camera and manual bedside event annotation. Image processing techniques are implemented to classify two lighting conditions: brightness level and phototherapy. A deep neural network is developed for three image classification tasks: on-going intervention, bed occupancy, and patient coverage. Transfer learning is leveraged in the feature extraction layers, such that weights learned from a generic data-rich task are applied to the clinical domain where data collection is complex and costly. Different depth fusion techniques are implemented and compared among classification tasks, where the depth and color data are fused as an RGB-D image (image fusion) or separately at various layers in the network (network fusion). Promising results were obtained with >84% sensitivity and >73% F1 measure across all context variables despite the large class imbalance. RGBD-based models are shown to outperform RGB models on most tasks. In general, a 4-channel image fusion and network fusion at the 11th layer of the VGG-16 architecture were preferred. Ultimately, achieving complete scene understanding through multimodal computer vision could form the basis for a semi-automated charting system to assist clinical staff.

Human-Soybean Allergies: Elucidation of the Seed Proteome and Comprehensive Protein-Protein Interaction Prediction.

The soybean crop, Glycine max (L.) Merr., is consumed by humans, Homo sapiens, worldwide. While the respective bodies of literature and -omics data for each of these organisms are extensive, comparatively few studies investigate the molecular biological processes occurring between the two. We are interested in elucidating the network of protein-protein interactions (PPIs) involved in human-soybean allergies. To this end, we leverage state-of-the-art sequence-based PPI predictors amenable to predicting the enormous comprehensive interactome between human and soybean. A network-based analytical approach is proposed, leveraging similar interaction profiles to identify candidate allergens and proteins involved in the allergy response. Interestingly, the predicted interactome can be explored from two complementary perspectives: which soybean proteins are predicted to interact with specific human proteins and which human proteins are predicted to interact with specific soybean proteins. A total of eight proteins (six specific to the human proteome and two to the soy proteome) have been identified and supported by the literature to be involved in human health, specifically related to immunological and neurological pathways. This study, beyond generating the most comprehensive human-soybean interactome to date, elucidated a soybean seed interactome and identified several proteins putatively consequential to human health.

The formation of benzoxacin-3-ones via intramolecular Nicholas reactions and synthesis of 8-membered heliannuols.

The γ-carbonyl cations generated from propargyl ether-Co2(CO)6 complexes undergo intramolecular Nicholas reactions to give dehydrobenzoxacin-3-one-Co2(CO)6 complexes in good yields. Reductive decomplexation and subsequent manipulation allows the synthesis of (±)-heliannuol K methyl ether and the formal syntheses of (±)-heliannuol K, (±)-heliannuol A, and (-)-heliannuol L.

Multi-schema computational prediction of the comprehensive SARS-CoV-2 vs. human interactome.

BACKGROUND: Understanding the disease pathogenesis of the novel coronavirus, denoted SARS-CoV-2, is critical to the development of anti-SARS-CoV-2 therapeutics. The global propagation of the viral disease, denoted COVID-19 ("coronavirus disease 2019"), has unified the scientific community in searching for possible inhibitory small molecules or polypeptides. A holistic understanding of the SARS-CoV-2 vs. human inter-species interactome promises to identify putative protein-protein interactions (PPI) that may be considered targets for the development of inhibitory therapeutics. METHODS: We leverage two state-of-the-art, sequence-based PPI predictors (PIPE4 & SPRINT) capable of generating the comprehensive SARS-CoV-2 vs. human interactome, comprising approximately 285,000 pairwise predictions. Three prediction schemas (all, proximal, RP-PPI) are leveraged to obtain our highest-confidence subset of PPIs and human proteins predicted to interact with each of the 14 SARS-CoV-2 proteins considered in this study. Notably, the use of the Reciprocal Perspective (RP) framework demonstrates improved predictive performance in multiple cross-validation experiments. RESULTS: The all schema identified 279 high-confidence putative interactions involving 225 human proteins, the proximal schema identified 129 high-confidence putative interactions involving 126 human proteins, and the RP-PPI schema identified 539 high-confidence putative interactions involving 494 human proteins. The intersection of the three sets of predictions comprise the seven highest-confidence PPIs. Notably, the Spike-ACE2 interaction was the highest ranked for both the PIPE4 and SPRINT predictors with the all and proximal schemas, corroborating existing evidence for this PPI. Several other predicted PPIs are biologically relevant within the context of the original SARS-CoV virus. Furthermore, the PIPE-Sites algorithm was used to identify the putative subsequence that might mediate each interaction and thereby inform the design of inhibitory polypeptides intended to disrupt the corresponding host-pathogen interactions. CONCLUSION: We publicly released the comprehensive sets of PPI predictions and their corresponding PIPE-Sites landscapes in the following DataVerse repository: https://www.doi.org/10.5683/SP2/JZ77XA. The information provided represents theoretical modeling only and caution should be exercised in its use. It is intended as a resource for the scientific community at large in furthering our understanding of SARS-CoV-2.

Automatic 1D 1H NMR Metabolite Quantification for Bioreactor Monitoring.

High-throughput metabolomics can be used to optimize cell growth for enhanced production or for monitoring cell health in bioreactors. It has applications in cell and gene therapies, vaccines, biologics, and bioprocessing. NMR metabolomics is a method that allows for fast and reliable experimentation, requires only minimal sample preparation, and can be set up to take online measurements of cell media for bioreactor monitoring. This type of application requires a fully automated metabolite quantification method that can be linked with high-throughput measurements. In this review, we discuss the quantifier requirements in this type of application, the existing methods for NMR metabolomics quantification, and the performance of three existing quantifiers in the context of NMR metabolomics for bioreactor monitoring.

Predicting Metabolic Reaction Networks with Perturbation-Theory Machine Learning (PTML) Models.

BACKGROUND: Checking the connectivity (structure) of complex Metabolic Reaction Networks (MRNs) models proposed for new microorganisms with promising properties is an important goal for chemical biology. OBJECTIVE: In principle, we can perform a hand-on checking (Manual Curation). However, this is a challenging task due to the high number of combinations of pairs of nodes (possible metabolic reactions). RESULTS: The CPTML linear model obtained using the LDA algorithm is able to discriminate nodes (metabolites) with the correct assignation of reactions from incorrect nodes with values of accuracy, specificity, and sensitivity in the range of 85-100% in both training and external validation data series. METHODS: In this work, we used Combinatorial Perturbation Theory and Machine Learning techniques to seek a CPTML model for MRNs >40 organisms compiled by Barabasis' group. First, we quantified the local structure of a very large set of nodes in each MRN using a new class of node index called Markov linear indices fk. Next, we calculated CPT operators for 150000 combinations of query and reference nodes of MRNs. Last, we used these CPT operators as inputs of different ML algorithms. CONCLUSION: Meanwhile, PTML models based on Bayesian network, J48-Decision Tree and Random Forest algorithms were identified as the three best non-linear models with accuracy greater than 97.5%. The present work opens the door to the study of MRNs of multiple organisms using PTML models.