Integrating AI/ML Models for Patient Stratification Leveraging Omics Dataset and Clinical Biomarkers from COVID-19 Patients: A Promising Approach to Personalized Medicine.

The COVID-19 pandemic has presented an unprecedented challenge to the healthcare system. Identifying the genomics and clinical biomarkers for effective patient stratification and management is critical to controlling the spread of the disease. Omics datasets provide a wealth of information that can aid in understanding the underlying molecular mechanisms of COVID-19 and identifying potential biomarkers for patient stratification. Artificial intelligence (AI) and machine learning (ML) algorithms have been increasingly used to analyze large-scale omics and clinical datasets for patient stratification. In this manuscript, we demonstrate the recent advances and predictive accuracies in AI- and ML-based patient stratification modeling linking omics and clinical biomarker datasets, focusing on COVID-19 patients. Our ML model not only demonstrates that clinical features are enough of an indicator of COVID-19 severity and survival, but also infers what clinical features are more impactful, which makes our approach a useful guide for clinicians for prioritization best-fit therapeutics for a given cohort of patients. Moreover, with weighted gene network analysis, we are able to provide insights into gene networks that have a significant association with COVID-19 severity and clinical features. Finally, we have demonstrated the importance of clinical biomarkers in identifying high-risk patients and predicting disease progression.

In Silico Development of Combinatorial Therapeutic Approaches Targeting Key Signaling Pathways in Metabolic Syndrome.

PURPOSE: Dysregulations of key signaling pathways in metabolic syndrome are multifactorial, eventually leading to cardiovascular events. Hyperglycemia in conjunction with dyslipidemia induces insulin resistance and provokes release of proinflammatory cytokines resulting in chronic inflammation, accelerated lipid peroxidation with further development of atherosclerotic alterations and diabetes. We have proposed a novel combinatorial approach using FDA approved compounds targeting IL-17a and DPP4 to ameliorate a significant portion of the clustered clinical risks in patients with metabolic syndrome. In our current research we have modeled the outcomes of metabolic syndrome treatment using two distinct drug classes. METHODS: Targets were chosen based on the clustered clinical risks in metabolic syndrome: dyslipidemia, insulin resistance, impaired glucose control, and chronic inflammation. Drug development platform, BIOiSIM™, was used to narrow down two different drug classes with distinct modes of action and modalities. Pharmacokinetic and pharmacodynamic profiles of the most promising drugs were modeling showing predicted outcomes of combinatorial therapeutic interventions. RESULTS: Preliminary studies demonstrated that the most promising drugs belong to DPP-4 inhibitors and IL-17A inhibitors. Evogliptin was chosen to be a candidate for regulating glucose control with long term collateral benefit of weight loss and improved lipid profiles. Secukinumab, an IL-17A sequestering agent used in treating psoriasis, was selected as a repurposed candidate to address the sequential inflammatory disorders that follow the first metabolic insult. CONCLUSIONS: Our analysis suggests this novel combinatorial therapeutic approach inducing DPP4 and Il-17a suppression has a high likelihood of ameliorating a significant portion of the clustered clinical risk in metabolic syndrome.

Molecular Simulation and Statistical Learning Methods toward Predicting Drug-Polymer Amorphous Solid Dispersion Miscibility, Stability, and Formulation Design.

Amorphous solid dispersions (ASDs) have emerged as widespread formulations for drug delivery of poorly soluble active pharmaceutical ingredients (APIs). Predicting the API solubility with various carriers in the API-carrier mixture and the principal API-carrier non-bonding interactions are critical factors for rational drug development and formulation decisions. Experimental determination of these interactions, solubility, and dissolution mechanisms is time-consuming, costly, and reliant on trial and error. To that end, molecular modeling has been applied to simulate ASD properties and mechanisms. Quantum mechanical methods elucidate the strength of API-carrier non-bonding interactions, while molecular dynamics simulations model and predict ASD physical stability, solubility, and dissolution mechanisms. Statistical learning models have been recently applied to the prediction of a variety of drug formulation properties and show immense potential for continued application in the understanding and prediction of ASD solubility. Continued theoretical progress and computational applications will accelerate lead compound development before clinical trials. This article reviews in silico research for the rational formulation design of low-solubility drugs. Pertinent theoretical groundwork is presented, modeling applications and limitations are discussed, and the prospective clinical benefits of accelerated ASD formulation are envisioned.

Accelerated Repurposing and Drug Development of Pulmonary Hypertension Therapies for COVID-19 Treatment Using an AI-Integrated Biosimulation Platform.

The COVID-19 pandemic has reached over 100 million worldwide. Due to the multi-targeted nature of the virus, it is clear that drugs providing anti-COVID-19 effects need to be developed at an accelerated rate, and a combinatorial approach may stand to be more successful than a single drug therapy. Among several targets and pathways that are under investigation, the renin-angiotensin system (RAS) and specifically angiotensin-converting enzyme (ACE), and Ca2+-mediated SARS-CoV-2 cellular entry and replication are noteworthy. A combination of ACE inhibitors and calcium channel blockers (CCBs), a critical line of therapy for pulmonary hypertension, has shown therapeutic relevance in COVID-19 when investigated independently. To that end, we conducted in silico modeling using BIOiSIM, an AI-integrated mechanistic modeling platform by utilizing known preclinical in vitro and in vivo datasets to accurately simulate systemic therapy disposition and site-of-action penetration of the CCBs and ACEi compounds to tissues implicated in COVID-19 pathogenesis.

Entering the era of computationally driven drug development.

Historically, failure rates in drug development are high; increased sophistication and investment throughout the process has shifted the reasons for attrition, but the overall success rates have remained stubbornly and consistently low. Only 8% of new entities entering clinical testing gain regulatory approval, indicating that significant obstacles still exist for efficient therapeutic development. The continued high failure rate can be partially attributed to the inability to link drug exposure with the magnitude of observed safety and efficacy-related pharmacodynamic (PD) responses; frequently, this is a result of nonclinical models exhibiting poor prediction of human outcomes across a wide range of disease conditions, resulting in faulty evaluation of drug toxicology and efficacy. However, the increasing quality and standardization of experimental methods in preclinical stages of testing has created valuable data sets within companies that can be leveraged to further improve the efficiency and accuracy of preclinical prediction for both pharmacokinetics (PK) and PD. Models of Quantitative structure-activity relationships (QSAR), physiologically based pharmacokinetics (PBPK), and PK/PD relationships have also improved efficiency. Founded on a core understanding of biochemistry and physiological interactions of xenobiotics, these in silico methods have the potential to increase the probability of compound success in clinical trials. Integration of traditional computational methods with machine-learning approaches and existing internal pharma databases stands to make a fundamental impact on the speed and accuracy of predictions during the process of drug development and approval.

Aberrant Retinoblastoma (RB)-E2F Transcriptional Regulation Defines Molecular Phenotypes of Osteosarcoma.

We previously identified two distinct molecular subtypes of osteosarcoma through gene expression profiling. These subtypes are associated with distinct tumor behavior and clinical outcomes. Here, we describe mechanisms that give rise to these molecular subtypes. Using bioinformatic analyses, we identified a significant association between deregulation of the retinoblastoma (RB)-E2F pathway and the molecular subtype with worse clinical outcomes. Xenotransplantation models recapitulated the corresponding behavior for each osteosarcoma subtype; thus, we used cell lines to validate the role of the RB-E2F pathway in regulating the prognostic gene signature. Ectopic RB resets the patterns of E2F regulated gene expression in cells derived from tumors with worse clinical outcomes (molecular phenotype 2) to those comparable with those observed in cells derived from tumors with less aggressive outcomes (molecular phenotype 1), providing a functional association between RB-E2F dysfunction and altered gene expression in osteosarcoma. DNA methyltransferase and histone deacetylase inhibitors similarly reset the transcriptional state of the molecular phenotype 2 cells from a state associated with RB deficiency to one seen with RB sufficiency. Our data indicate that deregulation of RB-E2F pathway alters the epigenetic landscape and biological behavior of osteosarcoma.

Characterization of Clostridium difficile isolates from human fecal samples and retail meat from Pennsylvania.

A study was conducted to determine the prevalence of Clostridium difficile and characterize C. difficile isolates from human stool and retail grocery meat samples. Human stool samples (n=317) were obtained from a clinical laboratory and meat samples (n=303) were collected from 8 retail grocery stores from October 2011 through September 2012 from Centre County of Pennsylvania and were examined for C. difficile. C. difficile was isolated from 16.7% of stool samples (n=317) and 6.9%, 11.5%, 14.5%, and 7.8% of beef (n=72), pork (n=78), turkey (n=76), and chicken (n=77) samples, respectively. Six different toxin gene profiles were detected in all human and meat isolates of C. difficile based on the presence or absence of toxin genes tcdA, tcdB, and cdtA and cdtB. Interestingly, 75.6% of the human C. difficile isolates lacked any deletion in the tcdC gene (139-bp), whereas a 39-bp deletion was observed in 61.3% of the C. difficile strains isolated from meat samples. C. difficile from meat samples were more susceptible to clindamycin, moxifloxacin, vancomycin, and metronidazole than C. difficile isolates from human samples. Twenty-five different ribotypes were identified in human and meat C. difficile isolates. In conclusion, significant genotypic and phenotypic differences were observed between human and meat isolates of C. difficile; however, a few C. difficile isolates from meat-in particular ribotypes 078, PA01, PA05, PA16, and PA22 with unique profiles (toxin gene, tcdC gene size and antimicrobial resistance profiles)-were similar to human C. difficile isolates.

White button mushrooms increase microbial diversity and accelerate the resolution of Citrobacter rodentium infection in mice.

The effect of feeding C57BL/6 mice white button (WB) mushrooms or control (CTRL) diets for 6 wk was determined on the bacterial microflora, urinary metabolome, and resistance to a gastrointestinal (GI) pathogen. Feeding mice a diet containing 1 g WB mushrooms/100 g diet resulted in changes in the microflora that were evident at 2 wk and stabilized after 4 wk of WB feeding. Compared with CTRL-fed mice, WB feeding (1 g/100 g diet) increased the diversity of the microflora and reduced potentially pathogenic (e.g., Clostridia) bacteria in the GI tract. Bacteria from the Bacteroidetes phylum increased and the Firmicutes phylum decreased in mushroom-fed mice compared with CTRL. The changes in the microflora were also reflected in the urinary metabolome that showed a metabolic shift in the WB-fed compared with the CTRL-fed mice. The WB feeding and changes in the microbiome were associated with fewer inflammatory cells and decreased colitis severity in the GI mucosa following Citrobacter rodentium infection compared with CTRL. Paradoxically, the clearance of C. rodentium infection did not differ even though Ifn-γ and Il-17 were higher in the colons of the WB-fed mice compared with CTRL. Adding modest amounts of WB mushrooms (1 g/100 g diet) to the diet changed the composition of the normal flora and the urinary metabolome of mice and these changes resulted in better control of inflammation and resolution of infection with C. rodentium.

An AI Approach to Generating MIDD Assets Across the Drug Development Continuum.

Model-informed drug development involves developing and applying exposure-based, biological, and statistical models derived from preclinical and clinical data sources to inform drug development and decision-making. Discrete models are generated from individual experiments resulting in a single model expression that is utilized to inform a single stage-gate decision. Other model types provide a more holistic view of disease biology and potentially disease progression depending on the appropriateness of the underlying data sources for that purpose. Despite this awareness, most data integration and model development approaches are still reliant on internal (within company) data stores and traditional structural model types. An AI/ML-based MIDD approach relies on more diverse data and is informed by past successes and failures including data outside a host company (external data sources) that may enhance predictive value and enhance data generated by the sponsor to reflect more informed and timely experimentation. The AI/ML methodology also provides a complementary approach to more traditional modeling efforts that support MIDD and thus yields greater fidelity in decision-making. Early pilot studies support this assessment but will require broader adoption and regulatory support for more evidence and refinement of this paradigm. An AI/ML-based approach to MIDD has the potential to transform regulatory science and the current drug development paradigm, optimize information value, and increase candidate and eventually product confidence with respect to safety and efficacy. We highlight early experiences with this approach using the AI compute platforms as representative examples of how MIDD can be facilitated with an AI/ML approach.

Driving success in personalized medicine through AI-enabled computational modeling.

The development of successful drugs is expensive and time-consuming because of high clinical attrition rates. This is caused partially by the rupture seen in the translatability of the drug from the bench to the clinic in the context of personalized medicine. Artificial intelligence (AI)-driven platforms integrated with mechanistic modeling have become instrumental in accelerating the drug development process by leveraging data ubiquitously across the various phases. AI can counter the deficiencies and ambiguities that arise during the classical drug development process while reducing human intervention and bridging the translational gap in discovering the connections between drugs and diseases.

Effects of Magnesium, Calcium, and Aluminum Chelation on Fluoroquinolone Absorption Rate and Bioavailability: A Computational Study.

Fluoroquinolones (FQs) are a widespread class of broad-spectrum antibiotics prescribed as a first line of defense, and, in some cases, as the only treatment against bacterial infection. However, when administered orally, reduced absorption and bioavailability can occur due to chelation in the gastrointestinal tract (GIT) with multivalent metal cations acquired from diet, coadministered compounds (sucralfate, didanosine), or drug formulation. Predicting the extent to which this interaction reduces in vivo antibiotic absorption and systemic exposure remains desirable yet challenging. In this study, we focus on quinolone interactions with magnesium, calcium and aluminum as found in dietary supplements, antacids (Maalox) orally administered therapies (sucralfate, didanosine). The effect of FQ-metal complexation on absorption rate was investigated through a combined molecular and pharmacokinetic (PK) modeling study. Quantum mechanical calculations elucidated FQ-metal binding energies, which were leveraged to predict the magnitude of reduced bioavailability via a quantitative structure-property relationship (QSPR). This work will help inform clinical FQ formulation design, alert to possible dietary effects, and shed light on drug-drug interactions resulting from coadministration at an earlier stage in the drug development pipeline.

In Silico Simulation of the Systemic Drug Exposure Following the Topical Application of Opioid Analgesics in Patients with Cutaneous Lesions.

The use of opioid analgesics in treating severe pain is frequently associated with putative adverse effects in humans. Topical agents that are shown to have high efficacy with a favorable safety profile in clinical settings are great alternatives for pain management of multimodal analgesia. However, the risk of side effects induced by transdermal absorption and systemic exposure is of great concern as they are challenging to predict. The present study aimed to use "BIOiSIM" an artificial intelligence-integrated biosimulation platform to predict the transdermal disposition of opioid analgesics. The model successfully predicted their exposure following the topical application of central opioid agonist buprenorphine and peripheral agonist oxycodone in healthy human subjects with simulation of intra-skin exposure in subjects with burns and pressure wounds. The predicted plasma levels of analgesics were used to evaluate the safety of the therapeutic pain control in patients with the dermal structural impairments caused by acute (burns) or chronic cutaneous lesions (pressure wounds) with topical opioid analgesics.

A hybrid modeling approach for assessing mechanistic models of small molecule partitioning in vivo using a machine learning-integrated modeling platform.

Prediction of the first-in-human dosing regimens is a critical step in drug development and requires accurate quantitation of drug distribution. Traditional in vivo studies used to characterize clinical candidate's volume of distribution are error-prone, time- and cost-intensive and lack reproducibility in clinical settings. The paper demonstrates how a computational platform integrating machine learning optimization with mechanistic modeling can be used to simulate compound plasma concentration profile and predict tissue-plasma partition coefficients with high accuracy by varying the lipophilicity descriptor logP. The approach applied to chemically diverse small molecules resulted in comparable geometric mean fold-errors of 1.50 and 1.63 in pharmacokinetic outputs for direct tissue:plasma partition and hybrid logP optimization, with the latter enabling prediction of tissue permeation that can be used to guide toxicity and efficacy dosing in human subjects. The optimization simulations required to achieve these results were parallelized on the AWS cloud and generated outputs in under 5 h. Accuracy, speed, and scalability of the framework indicate that it can be used to assess the relevance of other mechanistic relationships implicated in pharmacokinetic-pharmacodynamic phenomena with a lower risk of overfitting datasets and generate large database of physiologically-relevant drug disposition for further integration with machine learning models.

Scalable in silico Simulation of Transdermal Drug Permeability: Application of BIOiSIM Platform.

INTRODUCTION: Transdermal drug delivery is gaining popularity as an alternative to traditional routes of administration. It can increase patient compliance because of its painless and noninvasive nature, aid compounds in bypassing presystemic metabolic effects, and reduce the likelihood of adverse effects through decreased systemic exposure. In silico physiological modeling is critical to predicting dermal exposure for a therapeutic and assessing the impact of different formulations on transdermal disposition. METHODS: The present study aimed at developing a physiologically based transdermal platform, "BIOiSIM", that could be globally applied to a wide variety of compounds to predict their transdermal disposition. The platform integrates a 16-compartment model of compound pharmacokinetics and was used to simulate and predict drug exposure of three chemically and biologically distinct drug-like compounds. Machine learning optimization was composed of two components: exhaustive search algorithm (coarse-tuning) and descent (fine-tuning) integrated with the platform used to quantitatively determine parameters influencing pharmacokinetics (eg permeability, kperm) of test compounds. RESULTS: The model successfully predicted drug exposure (AUC, Cmax and Tmax) following transdermal application of morphine, buprenorphine and nicotine in human subjects, mostly with less than two-fold absolute average fold error (AAFE). The model was further able to successfully characterize the relationship between observed systemic exposure and intended pharmacological effect. The predicted systemic concentration of morphine and plasma levels of endogenous pain biomarkers were used to estimate the effectiveness of a given therapeutic regimen. CONCLUSION: BIOiSIM marks a novel approach to in silico prediction that will enable leveraging of machine learning technology in the pharmaceutical space. The approach to model development outlined results in scalable, accurate models and enables the generation of large parameter/coefficient datasets from in vivo clinical data that can be used in future work to train quantitative structure activity relationship (QSAR) models for predicting likelihood of compound utility as a transdermally administered therapeutic.

CRISPR/Cas9-Based Positive Screens for Cancer-Related Traits.

Since the advent of large-scale, detailed descriptive cancer genomics studies at the beginning of the century, such as The Cancer Genome Atlas (TCGA), labs around the world have been working to make this data useful. Data like these can be made more useful by comparison with complementary functional genomic data. One new example is the application of CRISPR/Cas9-based library screening for cancer-related traits in cell lines. Such screens can reveal genome-wide suppressors of tumorigenesis and metastasis. Here we describe the use of widely available lentiviral libraries for such screens in cultured cell lines.

Comparative Transcriptome Analysis Quantifies Immune Cell Transcript Levels, Metastatic Progression, and Survival in Osteosarcoma.

Overall survival of patients with osteosarcoma (OS) has improved little in the past three decades, and better models for study are needed. OS is common in large dog breeds and is genetically inducible in mice, making the disease ideal for comparative genomic analyses across species. Understanding the level of conservation of intertumor transcriptional variation across species and how it is associated with progression to metastasis will enable us to more efficiently develop effective strategies to manage OS and to improve therapy. In this study, transcriptional profiles of OS tumors and cell lines derived from humans (n = 49), mice (n = 103), and dogs (n = 34) were generated using RNA sequencing. Conserved intertumor transcriptional variation was present in tumor sets from all three species and comprised gene clusters associated with cell cycle and mitosis and with the presence or absence of immune cells. Further, we developed a novel gene cluster expression summary score (GCESS) to quantify intertumor transcriptional variation and demonstrated that these GCESS values associated with patient outcome. Human OS tumors with GCESS values suggesting decreased immune cell presence were associated with metastasis and poor survival. We validated these results in an independent human OS tumor cohort and in 15 different tumor data sets obtained from The Cancer Genome Atlas. Our results suggest that quantification of immune cell absence and tumor cell proliferation may better inform therapeutic decisions and improve overall survival for OS patients.Significance: This study offers new tools to quantify tumor heterogeneity in osteosarcoma, identifying potentially useful prognostic biomarkers for metastatic progression and survival in patients. Cancer Res; 78(2); 326-37. ©2017 AACR.

Understanding the Osteosarcoma Pathobiology: A Comparative Oncology Approach.

Osteosarcoma is an aggressive primary bone tumor in humans and is among the most common cancer afflicting dogs. Despite surgical advancements and intensification of chemo- and targeted therapies, the survival outcome for osteosarcoma patients is, as of yet, suboptimal. The presence of metastatic disease at diagnosis or its recurrence after initial therapy is a major factor for the poor outcomes. It is thought that most human and canine patients have at least microscopic metastatic lesions at diagnosis. Osteosarcoma in dogs occurs naturally with greater frequency and shares many biological and clinical similarities with osteosarcoma in humans. From a genetic perspective, osteosarcoma in both humans and dogs is characterized by complex karyotypes with highly variable structural and numerical chromosomal aberrations. Similar molecular abnormalities have been observed in human and canine osteosarcoma. For instance, loss of TP53 and RB regulated pathways are common. While there are several oncogenes that are commonly amplified in both humans and dogs, such as MYC and RAS, no commonly activated proto-oncogene has been identified that could form the basis for targeted therapies. It remains possible that recurrent aberrant gene expression changes due to gene amplification or epigenetic alterations could be uncovered and these could be used for developing new, targeted therapies. However, the remarkably high genomic complexity of osteosarcoma has precluded their definitive identification. Several advantageous murine models of osteosarcoma have been generated. These include spontaneous and genetically engineered mouse models, including a model based on forward genetics and transposon mutagenesis allowing new genes and genetic pathways to be implicated in osteosarcoma development. The proposition of this review is that careful comparative genomic studies between human, canine and mouse models of osteosarcoma may help identify commonly affected and targetable pathways for alternative therapies for osteosarcoma patients. Translational research may be found through a path that begins in mouse models, and then moves through canine patients, and then human patients.

Imprinting defects at human 14q32 locus alters gene expression and is associated with the pathobiology of osteosarcoma.

Osteosarcoma is the most common primary bone malignancy affecting children and adolescents. Although several genetic predisposing conditions have been associated with osteosarcoma, our understanding of its pathobiology is rather limited. Here we show that, first, an imprinting defect at human 14q32-locus is highly prevalent (87%) and specifically associated with osteosarcoma patients < 30 years of age. Second, the average demethylation at differentially methylated regions (DMRs) in the 14q32-locus varied significantly compared to genome-wide demethylation. Third, the 14q32-locus was enriched in both H3K4-me3 and H3K27-me3 histone modifications that affected expression of all imprinted genes and miRNAs in this region. Fourth, imprinting defects at 14q32 - DMRs are present in triad DNA samples from affected children and their biological parents. Finally, imprinting defects at 14q32-DMRs were also observed at higher frequencies in an Rb1/Trp53 mutation-induced osteosarcoma mouse model. Further analysis of normal and tumor tissues from a Sleeping Beauty mouse model of spontaneous osteosarcoma supported the notion that these imprinting defects may be a key factor in osteosarcoma pathobiology. In conclusion, we demonstrate that imprinting defects at the 14q32 locus significantly alter gene expression, may contribute to the pathogenesis of osteosarcoma, and could be predictive of survival outcomes.

Slit-Robo GTPase-Activating Protein 2 as a metastasis suppressor in osteosarcoma.

Osteosarcoma is the most common primary bone tumor, with metastatic disease responsible for most treatment failure and patient death. A forward genetic screen utilizing Sleeping Beauty mutagenesis in mice previously identified potential genetic drivers of osteosarcoma metastasis, including Slit-Robo GTPase-Activating Protein 2 (Srgap2). This study evaluates the potential role of SRGAP2 in metastases-associated properties of osteosarcoma cell lines through Srgap2 knockout via the CRISPR/Cas9 nuclease system and conditional overexpression in the murine osteosarcoma cell lines K12 and K7M2. Proliferation, migration, and anchorage independent growth were evaluated. RNA sequencing and immunohistochemistry of human osteosarcoma tissue samples were used to further evaluate the potential role of the Slit-Robo pathway in osteosarcoma. The effects of Srgap2 expression modulation in the murine OS cell lines support the hypothesis that SRGAP2 may have a role as a suppressor of metastases in osteosarcoma. Additionally, SRGAP2 and other genes in the Slit-Robo pathway have altered transcript levels in a subset of mouse and human osteosarcoma, and SRGAP2 protein expression is reduced or absent in a subset of primary tumor samples. SRGAP2 and other axon guidance proteins likely play a role in osteosarcoma metastasis, with loss of SRGAP2 potentially contributing to a more aggressive phenotype.

MicroRNAs as potential target in human bone and soft tissue sarcoma therapeutics.

Sarcomas are highly aggressive heterogeneous tumors that are mesenchymal in origin. There have been vast advancements on identifying diagnostic markers for sarcomas including chromosomal translocations, but very little progress has been made to identify targeted therapies against them. The tumor heterogeneity, genetic complexity and the lack of drug studies make it challenging to recognize the potential targets and also accounts for the inadequate treatments in sarcomas. In recent years, microRNAs that are a part of small non-coding RNAs have shown promising results as potential diagnostic and prognostic biomarkers in multiple sarcoma types. This review focuses on the current knowledge of the microRNAs that are deregulated in sarcomas, and an insight on the strategies to target these microRNAs that are essential for developing improved therapies for various human sarcomas.