Targeting the NTF2-like domain of G3BP1: Novel modulators of intracellular granule dynamics.

Stress granule (SG) is a temporary cellular structure that plays a crucial role in the regulation of mRNA and protein sequestration during various cellular stress conditions. SG enables cells to cope with stress more effectively, conserving vital energy and resources. Focusing on the NTF2-like domain of G3BP1, a key protein in SG dynamics, we explore to identify and characterize novel small molecules involved in SG modulation without external stressors. Through in silico molecular docking approach to simulate the interaction between various compounds and the NTF2-like domain of G3BP1, we identified three compounds as potential candidates that could bind to the NTF2-like domain of G3BP1. Subsequent immunofluorescence experiments demonstrated that these compounds induce the formation of SG-like, G3BP1-positive granules. Importantly, the granule formation by these compounds occurs independent from the phosphorylation of eIF2α, a common mechanism in SG formation, suggesting that it might offer a new strategy for influencing SG dynamics implicated in various diseases.

Carnitine acetyltransferase deficiency mediates mitochondrial dysfunction-induced cellular senescence in dermal fibroblasts.

Aging is accompanied by impaired mitochondrial function and accumulation of senescent cells. Mitochondrial dysfunction contributes to senescence by increasing the levels of reactive oxygen species and compromising energy metabolism. Senescent cells secrete a senescence-associated secretory phenotype (SASP) and stimulate chronic low-grade inflammation, ultimately inducing inflammaging. Mitochondrial dysfunction and cellular senescence are two closely related hallmarks of aging; however, the key driver genes that link mitochondrial dysfunction and cellular senescence remain unclear. Here, we aimed to elucidate a novel role of carnitine acetyltransferase (CRAT) in the development of mitochondrial dysfunction and cellular senescence in dermal fibroblasts. Transcriptomic analysis of skin tissues from young and aged participants showed significantly decreased CRAT expression in intrinsically aged skin. CRAT downregulation in human dermal fibroblasts recapitulated mitochondrial changes in senescent cells and induced SASP secretion. Specifically, CRAT knockdown caused mitochondrial dysfunction, as indicated by increased oxidative stress, disruption of mitochondrial morphology, and a metabolic shift from oxidative phosphorylation to glycolysis. Mitochondrial damage induced the release of mitochondrial DNA into the cytosol, which activated the cyclic GMP-AMP synthase (cGAS)-stimulator of interferon genes (STING) and NF-ĸB pathways to induce SASPs. Consistently, fibroblast-specific CRAT-knockout mice showed increased skin aging phenotypes in vivo, including decreased cell proliferation, increased SASP expression, increased inflammation, and decreased collagen density. Our results suggest that CRAT deficiency contributes to aging by mediating mitochondrial dysfunction-induced senescence.

Background-filtered telomerase activity assay with cyclic DNA cleavage amplification.

Overexpression of telomerase incites the abnormal proliferation of cancer cells. Thus, it has been regarded as a cancer biomarker and a potential therapeutic target. Existing assays suggest a promising sensing scheme to detect telomerase activity. However, they are complicated in terms of assay preparation and implementation. We herein report a Quenching-Exempt invader Signal Amplification Test, termed 'QUEST'. The assay leverages on a high turnover, specific cleaving enzyme, flap endonuclease I (FEN1), and graphene oxide (GO) for background (BG) filtering. In response to the target, FEN1 significantly boosts the signal with invader signal amplification. To distinguish the target signal, GO filters out the BG. It captures residual reporter invader probes (RP) to quench undesired signals. QUEST is straightforward without any pre-preparatory steps and washing/separation. Its probe design is simple and cost-effective. With QUEST, we investigated telomerase activities in various cell lines. Notably, we discriminated cancer cell lines from normal cell lines. In addition, a candidate inhibitor for telomerase was screened, which showed the promising potential of QUEST in real applications.

Machine-Learning Algorithms Using Systemic Inflammatory Markers to Predict the Oncologic Outcomes of Colorectal Cancer After Surgery.

BACKGROUND: This study aimed to investigate the clinical significance of machine-learning (ML) algorithms based on serum inflammatory markers to predict survival outcomes for patients with colorectal cancer (CRC). METHODS: The study included 941 patients with stages I to III CRC. Based on random forest algorithms using 15 compositions of inflammatory markers, four different prediction scores (DFS score-1, DFS score-2, DFS score-3, and DFS score-4) were developed for the Yonsei cohort (training set, n = 803) and tested in the Ulsan cohort (test set, n = 138). The Cox proportional hazards model was used to determine correlation between prediction scores and disease-free survival (DFS). Harrell's concordance index (C-index) was used to compare the predictive ability of prediction scores for each composition. RESULTS: The multivariable analysis showed the DFS score-4 to be an independent prognostic factor after adjustment for clinicopathologic factors in both the training and test sets (hazard ratio [HR], 8.98; 95% confidence interval [CI] 6.7-12.04; P < 0.001 for the training set and HR, 2.55; 95% CI 1.1-5.89; P = 0.028 for the test set]. With regard to DFS, the highest C-index among single compositions was observed in the lymphocyte-to-C-reactive protein ratio (LCR) (0.659; 95% CI 0.656-0.662), and the C-index of DFS score-4 (0.727; 95% CI 0.724-0.729) was significantly higher than that of LCR in the test set. The C-index of DFS score-3 (0.725; 95% CI 0.723-0.728) was similar to that of DFS score-4, but higher than that of DFS score-2 (0.680; 95% CI 0.676-0.683). CONCLUSIONS: The ML-based approaches showed prognostic utility in predicting DFS. They could enhance clinical use of inflammatory markers in patients with CRC.

Evaluation of nutritional status and clinical depression classification using an explainable machine learning method.

Introduction: Depression is a prevalent disorder worldwide, with potentially severe implications. It contributes significantly to an increased risk of diseases associated with multiple risk factors. Early accurate diagnosis of depressive symptoms is a critical first step toward management, intervention, and prevention. Various nutritional and dietary compounds have been suggested to be involved in the onset, maintenance, and severity of depressive disorders. Despite the challenges to better understanding the association between nutritional risk factors and the occurrence of depression, assessing the interplay of these markers through supervised machine learning remains to be fully explored. Methods: This study aimed to determine the ability of machine learning-based decision support methods to identify the presence of depression using publicly available health data from the Korean National Health and Nutrition Examination Survey. Two exploration techniques, namely, uniform manifold approximation and projection and Pearson correlation, were performed for explanatory analysis among datasets. A grid search optimization with cross-validation was performed to fine-tune the models for classifying depression with the highest accuracy. Several performance measures, including accuracy, precision, recall, F1 score, confusion matrix, areas under the precision-recall and receiver operating characteristic curves, and calibration plot, were used to compare classifier performances. We further investigated the importance of the features provided: visualized interpretation using ELI5, partial dependence plots, and local interpretable using model-agnostic explanations and Shapley additive explanation for the prediction at both the population and individual levels. Results: The best model achieved an accuracy of 86.18% for XGBoost and an area under the curve of 84.96% for the random forest model in original dataset and the XGBoost algorithm with an accuracy of 86.02% and an area under the curve of 85.34% in the quantile-based dataset. The explainable results revealed a complementary observation of the relative changes in feature values, and, thus, the importance of emergent depression risks could be identified. Discussion: The strength of our approach is the large sample size used for training with a fine-tuned model. The machine learning-based analysis showed that the hyper-tuned model has empirically higher accuracy in classifying patients with depressive disorder, as evidenced by the set of interpretable experiments, and can be an effective solution for disease control.

Fire accelerant classification from GC-MS data of suspected arson cases using machine-learning models.

Using a practical GC-MS dataset containing approximately 4000 suspected arson cases, three machine-learning based classification models were developed and their performances were evaluated. All models trained for classifying the data from fire residue into six categories; no fire accelerants detected or else one of fire accelerants was used within gasoline, kerosene, diesel, solvents, or candle. The classification accuracies of the random forest, supporting vector machine, and convolutional neural network model were 0.88, 0.88, and 0.92, respectively. By calculating feature importance of the random forest model, several potential chemical fingerprints of fire accelerants were discovered.

ReBADD-SE: Multi-objective molecular optimisation using SELFIES fragment and off-policy self-critical sequence training.

The discovery of drugs to selectively remove disease-related cells is challenging in computer-aided drug design. Many studies have proposed multi-objective molecular generation methods and demonstrated their superiority using the public benchmark dataset for kinase inhibitor generation tasks. However, the dataset does not contain many molecules that violate Lipinski's rule of five. Thus, it remains unclear whether existing methods are effective in generating molecules violating the rule, such as navitoclax. To address this, we analysed the limitations of existing methods and propose a multi-objective molecular generation method with a novel parsing algorithm for molecular string representation and a modified reinforcement learning method for the efficient training of multi-objective molecular optimisation. The proposed model had success rates of 84% in GSK3b+JNK3 inhibitor generation and 99% in Bcl-2 family inhibitor generation tasks.

CRISPR/Cas13a-assisted AMP generation for SARS-CoV-2 RNA detection using a personal glucose meter.

Herein, we described a washing- and label-free clustered regularly interspaced short palindromic repeats (CRISPR)/LwaCas13a-based RNA detection method utilizing a personal glucose meter (PGM), which relies on the trans-cleavage activity of CRISPR/Cas13a and kinase reactions. In principle, the presence of target RNA activates the trans-cleavage of CRISPR/Cas13a, generating 2',3'-cyclic phosphate adenosine, which is converted to adenosine monophosphate (AMP) by the T4 polynucleotide kinase. Subsequently, the AMP is converted to adenosine diphosphate (ADP) through phosphorylation by a myokinase; ADP is then used as a substrate in the cascade enzymatic reaction promoted by pyruvate kinase and hexokinase. The overall reaction leads to the continuous conversion of glucose to glucose-6-phosphate, resulting in a reduction of glucose concentration proportional to the level of target RNA, which can therefore be indirectly measured with a PGM. By employing this novel strategy, severe acute respiratory syndrome coronavirus-2 RNA can be successfully detected with excellent specificity. In addition, we were able to overcome non-specific responses of CRISPR/Cas13a and distinguish single nucleotide polymorphisms by introducing a single-base mismatch in the complementary RNA. Our study provides an alternative coronavirus disease 2019 detection technology that is affordable, accessible, and portable with a fast turnaround time and excellent selectivity.

Predicting progression to dementia with "comprehensive visual rating scale" and machine learning algorithms.

Background and Objective: Identifying biomarkers for predicting progression to dementia in patients with mild cognitive impairment (MCI) is crucial. To this end, the comprehensive visual rating scale (CVRS), which is based on magnetic resonance imaging (MRI), was developed for the assessment of structural changes in the brains of patients with MCI. This study aimed to investigate the use of the CVRS score for predicting dementia in patients with MCI over a 2-year follow-up period using various machine learning (ML) algorithms. Methods: We included 197 patients with MCI who were followed up more than once. The data used for this study were obtained from the Japanese-Alzheimer's Disease Neuroimaging Initiative study. We assessed all the patients using their CVRS scores, cortical thickness data, and clinical data to determine their progression to dementia during a follow-up period of over 2 years. ML algorithms, such as logistic regression, random forest (RF), XGBoost, and LightGBM, were applied to the combination of the dataset. Further, feature importance that contributed to the progression from MCI to dementia was analyzed to confirm the risk predictors among the various variables evaluated. Results: Of the 197 patients, 108 (54.8%) showed progression from MCI to dementia. Tree-based classifiers, such as XGBoost, LightGBM, and RF, achieved relatively high performance. In addition, the prediction models showed better performance when clinical data and CVRS score (accuracy 0.701-0.711) were used than when clinical data and cortical thickness (accuracy 0.650-0.685) were used. The features related to CVRS helped predict progression to dementia using the tree-based models compared to logistic regression. Conclusions: Tree-based ML algorithms can predict progression from MCI to dementia using baseline CVRS scores combined with clinical data.

Washing-Free and Label-Free Onsite Assay for Inorganic Pyrophosphatase Activity Using a Personal Glucose Meter.

In this study, we demonstrated a personal glucose meter-based method for washing-free and label-free inorganic pyrophosphatase (PPase) detection, which relies on the cascade enzymatic reaction (CER) promoted by hexokinase and pyruvate kinase. In principle, the absence of target PPase enables adenosine triphosphate sulfurylase to catalyze the conversion of pyrophosphate (PPi) to ATP, a substrate of CER, which results in the significant reduction of glucose levels by the effective CER process. In contrast, the PPi cleavage activity works in the presence of target PPase by decomposing PPi to orthophosphate (Pi). Therefore, the CER process cannot be effectively executed, leading to the maintenance of the initial high glucose level that may be measured by a portable personal glucose meter. Based on this novel strategy, a quantitative evaluation of the PPase activity may be achieved in a dynamic linear range of 1.5-25 mU/mL with a detection limit of 1.18 mU/mL. Compared with the previous PPase detection methods, this method eliminates the demand for expensive and bulky analysis equipment as well as a complex washing step. More importantly, the diagnostic capability of this method was also successfully verified by reliably detecting PPase present in an undiluted human serum sample with an excellent recovery ratio of 100 ± 2%.

Inhibition of matrix metalloproteinase expression by selective clearing of senescent dermal fibroblasts attenuates ultraviolet-induced photoaging.

Photoaging mainly occurs due to ultraviolet (UV) radiation, and is accompanied by increased secretion of matrix metalloproteinases (MMPs) and degradation of collagen. UV radiation induces cell senescence in the skin; however, the role of senescent cells in photoaging remains unclear. Therefore, to elucidate the role of senescent cells in photoaging, we evaluated the effect of senolytics in a photoaging mouse model and investigated the underlying mechanism of their antiaging effect. Both UV-induced senescent human dermal fibroblasts and a photoaging mouse model, ABT-263 and ABT-737, demonstrated senolytic effects on senescent fibroblasts. Moreover, we found that several senescence-associated secretory phenotype factors, such as IL-6, CCL5, CCL7, CXCL12, and SCF, induced MMP-1 expression in dermal fibroblasts, which decreased after treatment with ABT-263 and ABT-737 in vivo and in vitro. Both senolytic drugs attenuated the induction of MMPs and decreased collagen density in the photoaging mouse model. Our data suggest that senolytic agents reduce UV-induced photoaging, making strategies for targeting senescent dermal fibroblasts promising options for the treatment of photoaging.

A natural compound harmine decreases melanin synthesis through regulation of the DYRK1A/NFATC3 pathway.

BACKGROUND: Melanin plays important roles in determining human skin color and protecting human skin cells against harmful ultraviolet light. However, abnormal hyperpigmentation in some areas of the skin may become aesthetically unpleasing, resulting in the need for effective agents or methods to regulate undesirable hyperpigmentation. OBJECTIVE: We investigated the effect of harmine, a natural harmala alkaloid belonging to the beta-carboline family, on melanin synthesis and further explored the signaling pathways involved in its mechanism of action. METHODS: Human MNT-1 melanoma cells and human primary melanocytes were treated with harmine, chemical inhibitors, small interfering RNAs, or mammalian expression vectors. Cell viability, melanin content, and expression of various target molecules were assessed. RESULTS: Harmine decreased melanin synthesis and tyrosinase expression in human MNT-1 melanoma cells. Inhibition of DYRK1A, a harmine target, decreased melanin synthesis and tyrosinase expression. Further studies revealed that nuclear translocation of NFATC3, a potential DYRK1A substrate, was induced via the harmine/DYRK1A pathway and that NFATC3 knockdown increased melanin synthesis and tyrosinase expression. Suppression of melanin synthesis and tyrosinase expression via the harmine/DYRK1A pathway was significantly attenuated by NFATC3 knockdown. Furthermore, harmine also decreased melanin synthesis and tyrosinase expression through regulation of NFATC3 in human primary melanocytes. CONCLUSION: Our results indicate that harmine decreases melanin synthesis through regulation of the DYRK1A/NFATC3 pathway and suggest that the DYRK1A/NFATC3 pathway may be a potential target for the development of depigmenting agents.

A spatiotemporal analysis of opioid poisoning mortality in Ohio from 2010 to 2016.

Opioid-related deaths have severely increased since 2000 in the United States. This crisis has been declared a public health emergency, and among the most affected states is Ohio. We used statewide vital statistic data from the Ohio Department of Health (ODH) and demographics data from the U.S. Census Bureau to analyze opioid-related mortality from 2010 to 2016. We focused on the characterization of the demographics from the population of opioid-related fatalities, spatiotemporal pattern analysis using Moran's statistics at the census-tract level, and comorbidity analysis using frequent itemset mining and association rule mining. We found higher rates of opioid-related deaths in white males aged 25-54 compared to the rest of Ohioans. Deaths tended to increasingly cluster around Cleveland, Columbus and Cincinnati and away from rural regions as time progressed. We also found relatively high co-occurrence of cardiovascular disease, anxiety or drug abuse history, with opioid-related mortality. Our results demonstrate that state-wide spatiotemporal and comorbidity analysis of the opioid epidemic could provide novel insights into how the demographic characteristics, spatiotemporal factors, and/or health conditions may be associated with opioid-related deaths in the state of Ohio.

Radiomics Features of 18F-Fluorodeoxyglucose Positron-Emission Tomography as a Novel Prognostic Signature in Colorectal Cancer.

The aim of this study was to investigate the prognostic value of radiomics signatures derived from 18F-fluorodeoxyglucose (18F-FDG) positron-emission tomography (PET) in patients with colorectal cancer (CRC). From April 2008 to Jan 2014, we identified CRC patients who underwent 18F-FDG-PET before starting any neoadjuvant treatments and surgery. Radiomics features were extracted from the primary lesions identified on 18F-FDG-PET. Patients were divided into a training and validation set by random sampling. A least absolute shrinkage and selection operator Cox regression model was applied for prognostic signature building with progression-free survival (PFS) using the training set. Using the calculated radiomics score, a nomogram was developed, and its clinical utility was assessed in the validation set. A total of 381 patients with surgically resected CRC patients (training set: 228 vs. validation set: 153) were included. In the training set, a radiomics signature labeled as a rad_score was generated using two PET-derived features, such as gray-level run length matrix long-run emphasis (GLRLM_LRE) and gray-level zone length matrix short-zone low-gray-level emphasis (GLZLM_SZLGE). Patients with a high rad_score in the training and validation set had a shorter PFS. Multivariable analysis revealed that the rad_score was an independent prognostic factor in both training and validation sets. A radiomics nomogram, developed using rad_score, nodal stage, and lymphovascular invasion, showed good performance in the calibration curve and comparable predictive power with the staging system in the validation set. Textural features derived from 18F-FDG-PET images may enable detailed stratification of prognosis in patients with CRC.

Ultraviolet irradiation-induced inhibition of histone deacetylase 4 increases the expression of matrix metalloproteinase-1 but decreases that of type I procollagen via activating JNK in human dermal fibroblasts.

BACKGROUND: Ultraviolet (UV) irradiation is the main contributing factor for skin aging. UV irradiation induces epigenetic changes in skin. It increases the activity of histone acetylases (HATs) but decreases that of histone deacetylases (HDACs). OBJECTIVE: We aimed to investigate alterations in all classes of HDACs and sirtuins (SIRTs) in response to UV irradiation, and determine the HDACs regulating the expressions of matrix metalloproteinase 1 (MMP-1) and type I procollagen. METHODS: Primary human dermal fibroblasts were UV irradiated. HDAC4 was knocked-down or overexpressed to investigate its effect on the expression of MMP-1 and type I procollagen. The mRNA and protein levels were analyzed by quantitative real-time polymerase chain reaction and western blotting. RESULTS: Among 11 HDACs and 7 SIRTs, we found that the expression of HDAC4, HDAC5, HDAC6, HDAC7, HDAC8, HDAC11, SIRT2, and SIRT3 were significantly and consistently reduced by UV at both mRNA and protein levels. Among these, the reduction of HDAC4 was responsible for the basal and UV-induced increase in the expression of MMP-1 and decrease in that of type I procollagen. Furthermore, the reduced HDAC4 could activate c-Jun N-terminal kinase (JNK), resulting in an increase in MMP-1 and decrease in type I procollagen. CONCLUSIONS: UV treatment decreases the expression of HDACs and SIRTs in dermal fibroblasts; in particular, the UV-induced reduction in the expression of HDAC4 might play an important role in regulating the expression of MMP-1 and type I procollagen.

Myeloid-Derived Suppressor Cell Subsets Drive Glioblastoma Growth in a Sex-Specific Manner.

Myeloid-derived suppressor cells (MDSC) that block antitumor immunity are elevated in glioblastoma (GBM) patient blood and tumors. However, the distinct contributions of monocytic (mMDSC) versus granulocytic (gMDSC) subsets have yet to be determined. In mouse models of GBM, we observed that mMDSCs were enriched in the male tumors, whereas gMDSCs were elevated in the blood of females. Depletion of gMDSCs extended survival only in female mice. Using gene-expression signatures coupled with network medicine analysis, we demonstrated in preclinical models that mMDSCs could be targeted with antiproliferative agents in males, whereas gMDSC function could be inhibited by IL1ß blockade in females. Analysis of patient data confirmed that proliferating mMDSCs were predominant in male tumors and that a high gMDSC/IL1ß gene signature correlated with poor prognosis in female patients. These findings demonstrate that MDSC subsets differentially drive immune suppression in a sex-specific manner and can be leveraged for therapeutic intervention in GBM. SIGNIFICANCE: Sexual dimorphism at the level of MDSC subset prevalence, localization, and gene-expression profile constitutes a therapeutic opportunity. Our results indicate that chemotherapy can be used to target mMDSCs in males, whereas IL1 pathway inhibitors can provide benefit to females via inhibition of gMDSCs.See related commentary by Gabrilovich et al., p. 1100.This article is highlighted in the In This Issue feature, p. 1079.

Improved Prediction of miRNA-Disease Associations Based on Matrix Completion with Network Regularization.

The identification of potential microRNA (miRNA)-disease associations enables the elucidation of the pathogenesis of complex human diseases owing to the crucial role of miRNAs in various biologic processes and it yields insights into novel prognostic markers. In the consideration of the time and costs involved in wet experiments, computational models for finding novel miRNA-disease associations would be a great alternative. However, computational models, to date, are biased towards known miRNA-disease associations; this is not suitable for rare miRNAs (i.e., miRNAs with a few known disease associations) and uncommon diseases (i.e., diseases with a few known miRNA associations). This leads to poor prediction accuracies. The most straightforward way of improving the performance is by increasing the number of known miRNA-disease associations. However, due to lack of information, increasing attention has been paid to developing computational models that can handle insufficient data via a technical approach. In this paper, we present a general framework-improved prediction of miRNA-disease associations (IMDN)-based on matrix completion with network regularization to discover potential disease-related miRNAs. The success of adopting matrix factorization is demonstrated by its excellent performance in recommender systems. This approach considers a miRNA network as additional implicit feedback and makes predictions for disease associations relevant to a given miRNA based on its direct neighbors. Our experimental results demonstrate that IMDN achieved excellent performance with reliable area under the receiver operating characteristic (ROC) area under the curve (AUC) values of 0.9162 and 0.8965 in the frameworks of global and local leave-one-out cross-validations (LOOCV), respectively. Further, case studies demonstrated that our method can not only validate true miRNA-disease associations but also suggest novel disease-related miRNA candidates.

Combinatorial feature embedding based on CNN and LSTM for biomedical named entity recognition.

With the rapid advancement of technology and the necessity of processing large amounts of data, biomedical Named Entity Recognition (NER) has become an essential technique for information extraction in the biomedical field. NER, which is a sequence-labeling task, has been performed using various traditional techniques including dictionary-, rule-, machine learning-, and deep learning-based methods. However, as existing biomedical NER models are insufficient to handle new and unseen entity types from the growing biomedical data, the development of more effective and accurate biomedical NER models is being widely researched. Among biomedical NER models utilizing deep learning approaches, there have been only a few studies involving the design of high-level features in the embedding layer. In this regard, herein, we propose a deep learning NER model that effectively represents biomedical word tokens through the design of a combinatorial feature embedding. The proposed model is based on Bidirectional Long Short-Term Memory (bi-LSTM) with Conditional Random Field (CRF) and enhanced by integrating two different character-level representations extracted from a Convolutional Neural Network (CNN) and bi-LSTM. Additionally, an attention mechanism is applied to the model to focus on the relevant tokens in the sentence, which alleviates the long-term dependency problem of the LSTM model and allows effective recognition of entities. The proposed model was evaluated on two benchmark datasets, the JNLPBA and NCBI-Disease, and a comparative analysis with the existing models is performed. The proposed model achieved a relatively higher performance with an F1-score of 86.93% in case of NCBI-Disease, and a competitive performance for the JNLPBA with an F1-score of 75.31%.

IMIPMF: Inferring miRNA-disease interactions using probabilistic matrix factorization.

Recently, increasing evidence have reported that microRNAs (miRNAs) play key roles in a variety of biological processes. Therefore, the identification of novel miRNA-disease associations can shed new light on disease etiology and pathogenesis. Till now, various computational methods have been proposed to predict potential miRNA-disease associations by reducing the experimental costs and time consumption. However, most existing methods are highly dependent on known miRNA-disease associations. Therefore, the prediction of new miRNAs (i.e., miRNAs without known associated diseases) and new diseases (i.e., diseases without known associated miRNAs) has become challenging. In this paper, we present IMIPMF, a novel method for predicting miRNA-disease associations using probabilistic matrix factorization (PMF), which is a machine learning technique that is widely used in recommender systems. Predicting the rating scores that a user may assign to each item in a recommender system is analogous to predicting miRNA-disease associations. By applying PMF, our model not only identifies novel miRNA-disease associations, but also overcomes the common problem of incompatibility with miRNAs without any known associated disease, which was a limitation of most previous computational methods. We demonstrated that our proposed model achieved a high performance with a reliable AUC value of 0.891 by performing 5-fold cross-validation. Overall, IMIPMF is a high-performance machine-learning-based model for predicting miRNA-disease associations, although it only considers known miRNA-disease associations and miRNA expression data.