PermDroid a framework developed using proposed feature selection approach and machine learning techniques for Android malware detection.

The challenge of developing an Android malware detection framework that can identify malware in real-world apps is difficult for academicians and researchers. The vulnerability lies in the permission model of Android. Therefore, it has attracted the attention of various researchers to develop an Android malware detection model using permission or a set of permissions. Academicians and researchers have used all extracted features in previous studies, resulting in overburdening while creating malware detection models. But, the effectiveness of the machine learning model depends on the relevant features, which help in reducing the value of misclassification errors and have excellent discriminative power. A feature selection framework is proposed in this research paper that helps in selecting the relevant features. In the first stage of the proposed framework, t-test, and univariate logistic regression are implemented on our collected feature data set to classify their capacity for detecting malware. Multivariate linear regression stepwise forward selection and correlation analysis are implemented in the second stage to evaluate the correctness of the features selected in the first stage. Furthermore, the resulting features are used as input in the development of malware detection models using three ensemble methods and a neural network with six different machine-learning algorithms. The developed models' performance is compared using two performance parameters: F-measure and Accuracy. The experiment is performed by using half a million different Android apps. The empirical findings reveal that malware detection model developed using features selected by implementing proposed feature selection framework achieved higher detection rate as compared to the model developed using all extracted features data set. Further, when compared to previously developed frameworks or methodologies, the experimental results indicates that model developed in this study achieved an accuracy of 98.8%.

Machine learning-based predictive modelling for the enhancement of wine quality.

The certification of wine quality is essential to the wine industry. The main goal of this work is to develop a machine learning model to forecast wine quality using the dataset. We utilised samples from the red wine dataset (RWD) with eleven distinct physiochemical properties. With the initial RWD, five machine learning (ML) models were trained and put to the test. The most accurate algorithms are Random Forest (RF) and Extreme Gradient Boosting (XGBoost). Using these two ML approaches, the top three features from a total of eleven features are chosen, and ML analysis is performed on the remaining features. Several graphs are employed to demonstrate the feature importance based on the XGBoost model and RF. Wine quality was predicted using relevant characteristics, often referred to as fundamental elements, that were shown to be essential during the feature selection procedure. When trained and tested without feature selection, with feature selection (RF), and with key attributes, the XGBoost classifier displayed 100% accuracy. In the presence of essential variables, the RF classifier performed better. Finally, to assess the precision of their predictions, the authors trained an RF classifier, validated it, and changed its hyperparameters. To address collinearity and decrease the quantity of predictors without sacrificing model accuracy, we have also used cluster analysis.

Identification of naturally occurring compounds as alternatives to radiation therapy for treatment of small cell lung cancer.

Radiation resistance is one of the major problems in the treatment of small cell lung cancer (SCLC). Most of these patients are given radiation as first-line treatment and it was observed that the initial response in these patients is very good. However, they show relapse in a few months which is also associated with resistance to treatment. Thus, targeting the mechanism by which these cells develop resistance could be an important strategy to improve the survival chances of these patients. From the RNA-Seq data analysis, it was identified that CHEK1 gene was overexpressed. Chk1 protein which is encoded by the CHEK1 gene is an important protein that is involved in radiation resistance in SCLC. It is known to favour the cells to deal with replicative stress. CHEK1 is the major cause for developing radiation resistance in SCLC. Thus, natural compounds that could also serve as potential inhibitors for Chk1 were explored. Accordingly; the compounds were screened based on ADME, docking and MM-GBSA scores. MD simulations were performed for the selected protein-ligand complexes and the results were compared to the co-crystallised ligand, 3-(indol-2-yl)indazole. The results showed that compound INC000033832986 could be a natural alternative to the commercial ligand for the prevention of SCLC.Communicated by Ramaswamy H. Sarma.

Ensemble multimodal deep learning for early diagnosis and accurate classification of COVID-19.

Over the past few years, the awful COVID-19 pandemic effect has become a lethal sickness. The processing of the gathered samples requires extra time due to the use of medical diagnostic equipment, methodologies, and clinical testing procedures for the early diagnosis of infected individuals. An innovative multimodal paradigm for the early diagnosis and precise categorization of COVID-19 is put up as a solution to this issue. To extract distinguishing features from the prepared chest X-ray picture and cough (audio) database, chest X-ray-based and cough-based model are used here. Other public chest X-ray image datasets, and the Coswara cough (audio) dataset containing 92 COVID-19 positive, and 1079 healthy subjects (people) using the deep Uniform-Net, and Convolutional Neural Network (CNN). The weighted sum-rule fusion method and ensemble deep learning algorithms are utilized to further combine the extracted features. For the early diagnosis of patients, the framework offers an accuracy of 98.67%.

A novel multimodal fusion framework for early diagnosis and accurate classification of COVID-19 patients using X-ray images and speech signal processing techniques.

BACKGROUND AND OBJECTIVE: COVID-19 outbreak has become one of the most challenging problems for human being. It is a communicable disease caused by a new coronavirus strain, which infected over 375 million people already and caused almost 6 million deaths. This paper aims to develop and design a framework for early diagnosis and fast classification of COVID-19 symptoms using multimodal Deep Learning techniques. METHODS: we collected chest X-ray and cough sample data from open source datasets, Cohen and datasets and local hospitals. The features are extracted from the chest X-ray images are extracted from chest X-ray datasets. We also used cough audio datasets from Coswara project and local hospitals. The publicly available Coughvid DetectNow and Virufy datasets are used to evaluate COVID-19 detection based on speech sounds, respiratory, and cough. The collected audio data comprises slow and fast breathing, shallow and deep coughing, spoken digits, and phonation of sustained vowels. Gender, geographical location, age, preexisting medical conditions, and current health status (COVID-19 and Non-COVID-19) are recorded. RESULTS: The proposed framework uses the selection algorithm of the pre-trained network to determine the best fusion model characterized by the pre-trained chest X-ray and cough models. Third, deep chest X-ray fusion by discriminant correlation analysis is used to fuse discriminatory features from the two models. The proposed framework achieved recognition accuracy, specificity, and sensitivity of 98.91%, 96.25%, and 97.69%, respectively. With the fusion method we obtained 94.99% accuracy. CONCLUSION: This paper examines the effectiveness of well-known ML architectures on a joint collection of chest-X-rays and cough samples for early classification of COVID-19. It shows that existing methods can effectively used for diagnosis and suggesting that the fusion learning paradigm could be a crucial asset in diagnosing future unknown illnesses. The proposed framework supports health informatics basis on early diagnosis, clinical decision support, and accurate prediction.

Chest X ray and cough sample based deep learning framework for accurate diagnosis of COVID-19.

All witnessed the terrible effects of the COVID-19 pandemic on the health and work lives of the population across the world. It is hard to diagnose all infected people in real time since the conventional medical diagnosis of COVID-19 patients takes a couple of days for accurate diagnosis results. In this paper, a novel learning framework is proposed for the early diagnosis of COVID-19 patients using hybrid deep fusion learning models. The proposed framework performs early classification of patients based on collected samples of chest X-ray images and Coswara cough (sound) samples of possibly infected people. The captured cough samples are pre-processed using speech signal processing techniques and Mel frequency cepstral coefficient features are extracted using deep convolutional neural networks. Finally, the proposed system fuses extracted features to provide 98.70% and 82.7% based on Chest-X ray images and cough (audio) samples for early diagnosis using the weighted sum-rule fusion method.

Complex entropy based encryption and decryption technique for securing medical images.

During medical picture transmission, the most pressing concern is security. Medical images must be encrypted since they are extremely sensitive. Watermarking, digital fingerprinting/signature, and encoding are some of the available image security techniques. Images and movies, for example, must be highly encrypted and decoded without losing any content information. Medical photos, for example, require extra protection, and protecting medical images is a critical issue when medical images and related patient information are transferred over public networks. This research work proposes a visual encryption strategy to secure medical pictures before being transmitted or stored in the cloud. This technique makes such pictures of unauthorized people unavailable and also maintains confidentiality, a prime safety requirement. The process made use of a pixel shuffling-based encryption technique and a secret key created from the image. In this research, we encrypted the medical image using modified Arnold Map Encryption and generated secret key values. Therefore, the image is encrypted, and henceforth it is decrypted as well. So this work gave us the encrypted image and decrypted image/original image as well. The modified Arnold Map Encryption tries to add more randomness, thus increasing the entropy of the image and thus makes it harder to decrypt. The modified Arnold Map Encryption is also compared to other algorithms such as Hyper Chaotic, Secure Hash Algorithm-13 (SHA-13), Ten Logistic Maps, Bakers Map, HenonMap, Cross Chaos Map, and 2D Logistic Map and shows better results in terms of encryption speed and Number of Pixel Change Rate (NPCR) value.

COVID-19 Risk Prediction for Diabetic Patients Using Fuzzy Inference System and Machine Learning Approaches.

Individuals with pre-existing diabetes seem to be vulnerable to the COVID-19 due to changes in blood sugar levels and diabetes complications. As observed globally, around 20-50% of individuals affected by coronavirus had diabetes. However, there is no recent finding that diabetic patients are more prone to contract COVID-19 than nondiabetic patients. However, a few recent findings have observed that it could be at least twice as likely to die from complications of diabetes. Considering the multifold mortality rate of COVID-19 in diabetic patients, this study proposes a COVID-19 risk prediction model for diabetic patients using a fuzzy inference system and machine learning approaches. This study aimed to estimate the risk level of COVID-19 in diabetic patients without a medical practitioner's advice for timely action and overcoming the multifold mortality rate of COVID-19 in diabetic patients. The proposed model takes eight input parameters, which were found as the most influential symptoms in diabetic patients. With the help of the various state-of-the-art machine learning techniques, fifteen models were built over the rule base. CatBoost classifier gives the best accuracy, recall, precision, F1 score, and kappa score. After hyper-parameter optimization, CatBoost classifier showed 76% accuracy and improvements in the recall, precision, F1 score, and kappa score, followed by logistic regression and XGBoost with 75.1% and 74.7% accuracy. Stratified k-fold cross-validation is used for validation purposes.

Chimeric RNA Design Principles for RNA-Mediated Gene Fusion.

One common genetic alteration in cancer is gene fusion resulting from chromosomal translocations. The mechanisms that create such oncogenic fusion genes are not well understood. Previously, we provided the direct evidence that expression of a designed chimeric RNA can drive the formation of TMPRSS2-ERG gene fusion. Central to this RNA-mediated gene fusion mechanism is a proposed three-way junction formed by RNA/DNA hybrid and the intergenic DNA stem formed by target genes. In this study, we determined the important parameters for chimeric RNA-mediated gene fusion using TMPRSS2-ERG fusion gene as the model. Our results indicate that both the chimeric RNA lengths and the sizes of unpaired bulges play important roles in inducing TMPRSS2-ERG gene fusion. The optimal length of unpaired bulges was about 35 nt, while the optimal chimeric RNA length was about 50 nt for targeting. These observations were consistent regardless of the target locations within TMPRSS2 and ERG genes. These empirically determined parameters provide important insight for searching cellular RNAs that may initiate oncogenic fusion genes. The knowledge could also facilitate the development of useful genomic technology for manipulating mammalian genomes.

RNA-driven JAZF1-SUZ12 gene fusion in human endometrial stromal cells.

Oncogenic fusion genes as the result of chromosomal rearrangements are important for understanding genome instability in cancer cells and developing useful cancer therapies. To date, the mechanisms that create such oncogenic fusion genes are poorly understood. Previously we reported an unappreciated RNA-driven mechanism in human prostate cells in which the expression of chimeric RNA induces specified gene fusions in a sequence-dependent manner. One fundamental question yet to be addressed is whether such RNA-driven gene fusion mechanism is generalizable, or rather, a special case restricted to prostate cells. In this report, we demonstrated that the expression of designed chimeric RNAs in human endometrial stromal cells leads to the formation of JAZF1-SUZ12, a cancer fusion gene commonly found in low-grade endometrial stromal sarcomas. The process is specified by the sequence of chimeric RNA involved and inhibited by estrogen or progesterone. Furthermore, it is the antisense rather than sense chimeric RNAs that effectively drive JAZF1-SUZ12 gene fusion. The induced fusion gene is validated both at the RNA and the genomic DNA level. The ability of designed chimeric RNAs to drive and recapitulate the formation of JAZF1-SUZ12 gene fusion in endometrial cells represents another independent case of RNA-driven gene fusion, suggesting that RNA-driven genomic recombination is a permissible mechanism in mammalian cells. The results could have fundamental implications in the role of RNA in genome stability, and provide important insight in early disease mechanisms related to the formation of cancer fusion genes.

Genome-wide, integrative analysis of circular RNA dysregulation and the corresponding circular RNA-microRNA-mRNA regulatory axes in autism.

Circular RNAs (circRNAs), a class of long noncoding RNAs, are known to be enriched in mammalian neural tissues. Although a wide range of dysregulation of gene expression in autism spectrum disorder (ASD) have been reported, the role of circRNAs in ASD remains largely unknown. Here, we performed genome-wide circRNA expression profiling in postmortem brains from individuals with ASD and controls and identified 60 circRNAs and three coregulated modules that were perturbed in ASD. By integrating circRNA, microRNA, and mRNA dysregulation data derived from the same cortex samples, we identified 8170 ASD-associated circRNA-microRNA-mRNA interactions. Putative targets of the axes were enriched for ASD risk genes and genes encoding inhibitory postsynaptic density (PSD) proteins, but not for genes implicated in monogenetic forms of other brain disorders or genes encoding excitatory PSD proteins. This reflects the previous observation that ASD-derived organoids show overproduction of inhibitory neurons. We further confirmed that some ASD risk genes (NLGN1, STAG1, HSD11B1, VIP, and UBA6) were regulated by an up-regulated circRNA (circARID1A) via sponging a down-regulated microRNA (miR-204-3p) in human neuronal cells. Particularly, alteration of NLGN1 expression is known to affect the dynamic processes of memory consolidation and strengthening. To the best of our knowledge, this is the first systems-level view of circRNA regulatory networks in ASD cortex samples. We provided a rich set of ASD-associated circRNA candidates and the corresponding circRNA-microRNA-mRNA axes, particularly those involving ASD risk genes. Our findings thus support a role for circRNA dysregulation and the corresponding circRNA-microRNA-mRNA axes in ASD pathophysiology.

Validating Gene Fusion as the Source of Chimeric RNAs.

While chimeric RNAs may be generated by transcription-mediated mechanisms such as "trans-splicing" and "read-through/splicing" (Zhang et al., Cancer Discov 2:598-607, 2012; Zaphiropoulos, Front Genet 2:92, 2011; Li et al., Cell Cycle 8:218-222, 2009; Jividen and Li, Genes Chromosomes Cancer 53:963-971, 2014; Jia et al., Trends Cancer 2:475-484, 2016), most highly expressed chimeric RNA species identified so far are usually transcribed directly from fusion genes. Fusion genes, formed by joining two parental genes as a result of chromosomal rearrangements, are hallmarks of many types of cancer. Various methods can be deployed for confirming a particular fusion gene as the original source of transcribed chimeric RNA. In this chapter, we discuss commonly used methodologies such as genomic DNA breakpoint mapping and fluorescent in situ hybridization useful for confirming gene fusion events. In addition, we highlight the development of new technologies such as de novo whole-genome optical mapping suitable for global analysis of genomic arrangements. The advantages and disadvantages of each of these technologies are presented and compared.

Comparison of de-novo assembly tools for plasmid metagenome analysis.

BACKGROUND: With the advent of next-generation sequencing techniques, culture-independent metagenome approaches have now made it possible to predict possible presence of genes in the environmental bacteria most of which may be non-cultivable. Short reads obtained from the deep sequencing can be assembled into long contigs some of which include plasmids. Plasmids are the circular double stranded DNA in bacteria and known as one of the major carriers of antibiotic resistance genes. OBJECTIVE: Metagenomic analyses, especially focused on plasmids, could help us predict dissemination mechanisms of antibiotic resistance genes in the environment. However, with the availability of a myriad of metagenomic assemblers, the selection of the most appropriate metagenome assembler for the plasmid metagenome study might be challenging. Therefore, in this study, we compared five open source assemblers to suggest most effective way of plasmid metagenome analysis. METHODS: IDBA-UD, MEGAHIT, SPAdes, SOAPdenovo2, and Velvet are compared for conducting plasmid metagenome analyses using two water samples. RESULTS: Our results clearly showed that abundance and types of antibiotic resistance genes on plasmids varied depending on the selection of assembly tools. IDBA-UD and MEGAHIT demonstrated the overall best assembly statistics with high N50 values with higher portion of longer contigs. CONCLUSION: These two assemblers also detected more diverse plasmids. Among the two, MEGAHIT showed more memory efficient assembly, therefore we suggest that the use of MEGAHIT for plasmid metagenome analysis may offer more diverse plasmids with less computer resource required. Here, we also summarized a fundamental plasmid metagenome work flow, especially for antibiotic resistance gene investigation.

Tethered Balloon Technology in Design Solutions for Rescue and Relief Team Emergency Communication Services.

The actions taken at the initial times of a disaster are critical. Catastrophe occurs because of terrorist acts or natural hazards which have the potential to disrupt the infrastructure of wireless communication networks. Therefore, essential emergency functions such as search, rescue, and recovery operations during a catastrophic event will be disabled. We propose tethered balloon technology to provide efficient emergency communication services and reduce casualty mortality and morbidity for disaster recovery. The tethered balloon is an actively developed research area and a simple solution to support the performance, facilities, and services of emergency medical communication. The most critical requirement for rescue and relief teams is having a higher quality of communication services which enables them to save people's lives. Using our proposed technology, it has been reported that the performance of rescue and relief teams significantly improved. OPNET Modeler 14.5 is used for a network simulated with the help of ad hoc tools (Disaster Med Public Health Preparedness. 2019;13:203-210).

RNA-mediated gene fusion in mammalian cells.

One of the hallmarks of cancer is the formation of oncogenic fusion genes as a result of chromosomal translocations. Fusion genes are presumed to form before fusion RNA expression. However, studies have reported the presence of fusion RNAs in individuals who were negative for chromosomal translocations. These observations give rise to "the cart before the horse" hypothesis, in which the genesis of a fusion RNA precedes the fusion gene. The fusion RNA then guides the genomic rearrangements that ultimately result in a gene fusion. However, RNA-mediated genomic rearrangements in mammalian cells have never been demonstrated. Here we provide evidence that expression of a chimeric RNA drives formation of a specified gene fusion via genomic rearrangement in mammalian cells. The process is: (i) specified by the sequence of chimeric RNA involved, (ii) facilitated by physiological hormone levels, (iii) permissible regardless of intrachromosomal (TMPRSS2-ERG) or interchromosomal (TMPRSS2-ETV1) fusion, and (iv) can occur in normal cells before malignant transformation. We demonstrate that, contrary to "the cart before the horse" model, it is the antisense rather than sense chimeric RNAs that effectively drive gene fusion, and that this disparity can be explained by transcriptional conflict. Furthermore, we identified an endogenous RNA AZI1 that functions as the "initiator" RNA to induce TMPRSS2-ERG fusion. RNA-driven gene fusion demonstrated in this report provides important insight in early disease mechanisms, and could have fundamental implications in the biology of mammalian genome stability, as well as gene-editing technology via mechanisms native to mammalian cells.

The role of HGF-MET pathway and CCDC66 cirRNA expression in EGFR resistance and epithelial-to-mesenchymal transition of lung adenocarcinoma cells.

BACKGROUND: Epithelial-to-mesenchymal transition (EMT) has, in recent years, emerged as an important tumor cell behavior associated with high metastatic potential and drug resistance. Interestingly, protein SUMOylation and hepatocyte growth factor could respectively reduce the effect of small molecule inhibitors on tyrosine kinase activity of mutated epidermal growth factor receptor of lung adenocarcinomas (LADC). The actual mechanism is yet to be resolved. METHODS: Immunohistochemistry was used to stain proteins in LADC specimens. Protein expression was confirmed by Western blotting. In vitro, expression of proteins was determined by Western blotting and immunocytochemistry. Levels of circular RNA were determined by reverse transcription-polymerase chain reaction. RESULTS: SAE2 and cirRNA CCDC66 were highly expressed in LADC. Expression of SAE2 was mainly regulated by EGFR; however, expression of cirRNA CCDC66 was positively regulated by FAK and c-Met but negatively modulated by nAchR7α. EGFR-resistant H1975 also highly expressed cirRNA CCDC66. Immediate response of hypoxia increased phosphorylated c-Met, SAE2, and epithelial-to-mesenchymal transition. Either activation of FAK or silencing of nAchR7α increased cirRNA CCDC66. CONCLUSIONS: HGF/c-Met regulates expression of SAE2 and cirRNA CCDC66 to increase EMT and drug resistance of LADC cells. Multimodality drugs concurrently aiming at these targets would probably provide more benefits for cancer patients.

Metagenomic analysis reveals the prevalence and persistence of antibiotic- and heavy metal-resistance genes in wastewater treatment plant.

The increased antibiotic resistance among microorganisms has resulted into growing interest for investigating the wastewater treatment plants (WWTPs) as they are reported to be the major source in the dissemination of antibiotic resistance genes (ARGs) and heavy metal resistance genes (HMRGs) in the environment. In this study, we investigated the prevalence and persistence of ARGs and HMRGs as well as bacterial diversity and mobile genetic elements (MGEs) in influent and effluent at the WWTP in Gwangju, South Korea, using high-throughput sequencing based metagenomic approach. A good number of broad-spectrum of resistance genes (both ARG and HMRG) were prevalent and likely persistent, although large portion of them were successfully removed at the wastewater treatment process. The relative abundance of ARGs and MGEs was higher in effluent as compared to that of influent. Our results suggest that the resistance genes with high abundance and bacteria harbouring ARGs and MGEs are likely to persist more through the treatment process. On analyzing the microbial community, the phylum Proteobacteria, especially potentially pathogenic species belonging to the genus Acinetobacter, dominated in WWTP. Overall, our study demonstrates that many ARGs and HMRGs may persist the treatment processes in WWTPs and their association to MGEs may contribute to the dissemination of resistance genes among microorganisms in the environment.

The Canonical Poly (A) Polymerase PAP1 Polyadenylates Non-Coding RNAs and Is Essential for snoRNA Biogenesis in Trypanosoma brucei.

The parasite Trypanosoma brucei is the causative agent of African sleeping sickness and is known for its unique RNA processing mechanisms that are common to all the kinetoplastidea including Leishmania and Trypanosoma cruzi. Trypanosomes possess two canonical RNA poly (A) polymerases (PAPs) termed PAP1 and PAP2. PAP1 is encoded by one of the only two genes harboring cis-spliced introns in this organism, and its function is currently unknown. In trypanosomes, all mRNAs, and non-coding RNAs such as small nucleolar RNAs (snoRNAs) and long non-coding RNAs (lncRNAs), undergo trans-splicing and polyadenylation. Here, we show that the function of PAP1, which is located in the nucleus, is to polyadenylate non-coding RNAs, which undergo trans-splicing and polyadenylation. Major substrates of PAP1 are the snoRNAs and lncRNAs. Under the silencing of either PAP1 or PAP2, the level of snoRNAs is reduced. The dual polyadenylation of snoRNA intermediates is carried out by both PAP2 and PAP1 and requires the factors essential for the polyadenylation of mRNAs. The dual polyadenylation of the precursor snoRNAs by PAPs may function to recruit the machinery essential for snoRNA processing.

Noncoding Effects of Circular RNA CCDC66 Promote Colon Cancer Growth and Metastasis.

Circular RNA (circRNA) is a class of noncoding RNA whose functions remain mostly unknown. Recent studies indicate circRNA may be involved in disease pathogenesis, but direct evidence is scarce. Here, we characterize the functional role of a novel circRNA, circCCDC66, in colorectal cancer. RNA-Seq data from matched normal and tumor colon tissue samples identified numerous circRNAs specifically elevated in cancer cells, several of which were verified by quantitative RT-PCR. CircCCDC66 expression was elevated in polyps and colon cancer and was associated with poor prognosis. Gain-of-function and loss-of-function studies in colorectal cancer cell lines demonstrated that circCCDC66 controlled multiple pathological processes, including cell proliferation, migration, invasion, and anchorage-independent growth. In-depth characterization revealed that circCCDC66 exerts its function via regulation of a subset of oncogenes, and knockdown of circCCDC66 inhibited tumor growth and cancer invasion in xenograft and orthotopic mouse models, respectively. Taken together, these findings highlight a novel oncogenic function of circRNA in cancer progression and metastasis. Cancer Res; 77(9); 2339-50. ©2017 AACR.

Genome-wide analysis of small nucleolar RNAs of Leishmania major reveals a rich repertoire of RNAs involved in modification and processing of rRNA.

Trypanosomatids are protozoan parasites and the causative agent of infamous infectious diseases. These organisms regulate their gene expression mainly at the post-transcriptional level and possess characteristic RNA processing mechanisms. In this study, we analyzed the complete repertoire of Leishmania major small nucleolar (snoRNA) RNAs by performing RNA-seq analysis on RNAs that were affinity-purified using the C/D snoRNA core protein, SNU13, and the H/ACA core protein, NHP2. This study revealed a large collection of C/D and H/ACA snoRNAs, organized in gene clusters generally containing both snoRNA types. Abundant snoRNAs were identified and predicted to guide trypanosome-specific rRNA cleavages. The repertoire of snoRNAs was compared to that of the closely related Trypanosoma brucei, and 80% of both C/D and H/ACA molecules were found to have functional homologues. The comparative analyses elucidated how snoRNAs evolved to generate molecules with analogous functions in both species. Interestingly, H/ACA RNAs have great flexibility in their ability to guide modifications, and several of the RNA species can guide more than one modification, compensating for the presence of single hairpin H/ACA snoRNA in these organisms. Placing the predicted modifications on the rRNA secondary structure revealed hypermodification regions mostly in domains which are modified in other eukaryotes, in addition to trypanosome-specific modifications.