SEGCECO: Subgraph Embedding of Gene expression matrix for prediction of CEll-cell COmmunication.

Recent advances in single-cell RNA sequencing technology have eased analyses of signaling networks of cells. Recently, cell-cell interaction has been studied based on various link prediction approaches on graph-structured data. These approaches have assumptions about the likelihood of node interaction, thus showing high performance for only some specific networks. Subgraph-based methods have solved this problem and outperformed other approaches by extracting local subgraphs from a given network. In this work, we present a novel method, called Subgraph Embedding of Gene expression matrix for prediction of CEll-cell COmmunication (SEGCECO), which uses an attributed graph convolutional neural network to predict cell-cell communication from single-cell RNA-seq data. SEGCECO captures the latent and explicit attributes of undirected, attributed graphs constructed from the gene expression profile of individual cells. High-dimensional and sparse single-cell RNA-seq data make converting the data into a graphical format a daunting task. We successfully overcome this limitation by applying SoptSC, a similarity-based optimization method in which the cell-cell communication network is built using a cell-cell similarity matrix which is learned from gene expression data. We performed experiments on six datasets extracted from the human and mouse pancreas tissue. Our comparative analysis shows that SEGCECO outperforms latent feature-based approaches, and the state-of-the-art method for link prediction, WLNM, with 0.99 ROC and 99% prediction accuracy. The datasets can be found at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE84133 and the code is publicly available at Github https://github.com/sheenahora/SEGCECO and Code Ocean https://codeocean.com/capsule/8244724/tree.

PPPCT: Privacy-Preserving framework for Parallel Clustering Transcriptomics data.

Single-cell transcriptomics data provides crucial insights into patients' health, yet poses significant privacy concerns. Genomic data privacy attacks can have deep implications, encompassing not only the patients' health information but also extending widely to compromise their families'. Moreover, the permanence of leaked data exacerbates the challenges, making retraction an impossibility. While extensive efforts have been directed towards clustering single-cell transcriptomics data, addressing critical challenges, especially in the realm of privacy, remains pivotal. This paper introduces an efficient, fast, privacy-preserving approach for clustering single-cell RNA-sequencing (scRNA-seq) datasets. The key contributions include ensuring data privacy, achieving high-quality clustering, accommodating the high dimensionality inherent in the datasets, and maintaining reasonable computation time for big-scale datasets. Our proposed approach utilizes the map-reduce scheme to parallelize clustering, addressing intensive calculation challenges. Intel Software Guard eXtension (SGX) processors are used to ensure the security of sensitive code and data during processing. Additionally, the approach incorporates a logarithm transformation as a preprocessing step, employs non-negative matrix factorization for dimensionality reduction, and utilizes parallel k-means for clustering. The approach fully leverages the computing capabilities of all processing resources within a secure private cloud environment. Experimental results demonstrate the efficacy of our approach in preserving patient privacy while surpassing state-of-the-art methods in both clustering quality and computation time. Our method consistently achieves a minimum of 7% higher Adjusted Rand Index (ARI) than existing approaches, contingent on dataset size. Additionally, due to parallel computations and dimensionality reduction, our approach exhibits efficiency, converging to very good results in less than 10 seconds for a scRNA-seq dataset with 5000 genes and 6000 cells when prioritizing privacy and under two seconds without privacy considerations. Availability and implementation Code and datasets availability: https://github.com/University-of-Windsor/PPPCT.

A Fecal-Microbial-Extracellular-Vesicles-Based Metabolomics Machine Learning Framework and Biomarker Discovery for Predicting Colorectal Cancer Patients.

Colorectal cancer (CRC) is one of the most common and lethal diseases among all types of cancer, and metabolites play a significant role in the development of this complex disease. This study aimed to identify potential biomarkers and targets in the diagnosis and treatment of CRC using high-throughput metabolomics. Metabolite data extracted from the feces of CRC patients and healthy volunteers were normalized with the median normalization and Pareto scale for multivariate analysis. Univariate ROC analysis, the t-test, and analysis of fold changes (FCs) were applied to identify biomarker candidate metabolites in CRC patients. Only metabolites that overlapped the two different statistical approaches (false-discovery-rate-corrected p-value < 0.05 and AUC > 0.70) were considered in the further analysis. Multivariate analysis was performed with biomarker candidate metabolites based on linear support vector machines (SVM), partial least squares discrimination analysis (PLS-DA), and random forests (RF). The model identified five biomarker candidate metabolites that were significantly and differently expressed (adjusted p-value < 0.05) in CRC patients compared to healthy controls. The metabolites were succinic acid, aminoisobutyric acid, butyric acid, isoleucine, and leucine. Aminoisobutyric acid was the metabolite with the highest discriminatory potential in CRC, with an AUC equal to 0.806 (95% CI = 0.700-0.897), and was down-regulated in CRC patients. The SVM model showed the most substantial discrimination capacity for the five metabolites selected in the CRC screening, with an AUC of 0.985 (95% CI: 0.94-1).

Cell Type Annotation Model Selection: General-Purpose vs. Pattern-Aware Feature Gene Selection in Single-Cell RNA-Seq Data.

With the advances in high-throughput sequencing technology, an increasing amount of research in revealing heterogeneity among cells has been widely performed. Differences between individual cells' functionality are determined based on the differences in the gene expression profiles. Although the observations indicate a great performance of clustering methods, manual annotation of the clusters of cells is a challenge yet to be addressed more scalable and faster. On the other hand, due to the lack of enough labelled datasets, just a few supervised techniques have been used in cell type identification, and they obtained more robust results compared to clustering methods. A recent study showed that a complementary step of feature selection helped support vector machine (SVM) to outperform other classifiers in different scenarios. In this article, we compare and evaluate the performance of two state-of-the-art supervised methods, XGBoost and SVM, with information gain as a feature selection method. The results of the experiments on three standard scRNA-seq datasets indicate that XGBoost automatically annotates cell types in a simpler and more scalable framework. Additionally, it sheds light on the potential use of boosting tree approaches combined with deep neural networks to capture underlying information of single-cell RNA-Seq data more effectively. It can be used to identify marker genes and other applications in biological studies.

Relevance of Fluorodopa PET Scan in Dopamine Responsive Dystonia and Juvenile Parkinsonism: A Systematic Review.

BACKGROUND: Dopamine Responsive Dystonia (DRD) and Juvenile Parkinsonism (JP) are two diseases commonly presenting with parkinsonian symptoms in young patients. Current clinical guidelines offer a diagnostic approach based on molecular analysis. However, developing countries have limitations in terms of accessibility to these tests. We aimed to assess the utility of imaging equipment, usually more available worldwide, to help diagnose and improve patients' quality of life with these diseases. METHODS: We performed a systematic literature review in English using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) and meta-analysis of observational studies in epidemiology (MOOSE) protocols. We only used human clinical trials about dopamine responsive dystonia and juvenile parkinsonism patients in which a fluorodopa (FD) positron emission tomography (PET) scan was performed to identify its use in these diseases. RESULTS: We included six studies that fulfilled our criteria. We found a clear pattern of decreased uptake in the putamen and caudate nucleus in JP cases. At the same time, the results in DRD were comparable to normal subjects, with only a slightly decreased marker uptake in the previously mentioned regions by the FD PET scan. CONCLUSIONS: We found a distinctive pattern for each of these diseases. Identifying these findings with FD PET scans can shorten the delay in making a definitive diagnosis when genetic testing is unavailable, a common scenario in developing countries.

Computationally repurposing drugs for breast cancer subtypes using a network-based approach.

'De novo' drug discovery is costly, slow, and with high risk. Repurposing known drugs for treatment of other diseases offers a fast, low-cost/risk and highly-efficient method toward development of efficacious treatments. The emergence of large-scale heterogeneous biomolecular networks, molecular, chemical and bioactivity data, and genomic and phenotypic data of pharmacological compounds is enabling the development of new area of drug repurposing called 'in silico' drug repurposing, i.e., computational drug repurposing (CDR). The aim of CDR is to discover new indications for an existing drug (drug-centric) or to identify effective drugs for a disease (disease-centric). Both drug-centric and disease-centric approaches have the common challenge of either assessing the similarity or connections between drugs and diseases. However, traditional CDR is fraught with many challenges due to the underlying complex pharmacology and biology of diseases, genes, and drugs, as well as the complexity of their associations. As such, capturing highly non-linear associations among drugs, genes, diseases by most existing CDR methods has been challenging. We propose a network-based integration approach that can best capture knowledge (and complex relationships) contained within and between drugs, genes and disease data. A network-based machine learning approach is applied thereafter by using the extracted knowledge and relationships in order to identify single and pair of approved or experimental drugs with potential therapeutic effects on different breast cancer subtypes. Indeed, further clinical analysis is needed to confirm the therapeutic effects of identified drugs on each breast cancer subtype.

Cardiac Cement Embolism After Thoracic Kyphoplasty: Successful Conservative Treatment With 4-Year Follow-Up.

BACKGROUND: The present case report describes a complication after a percutaneous spine surgery technique that is highly uncommon in clinical practice: a bone cement cardiac embolism. This rare complication emphasizes the importance of this case, which is also interesting considering the midterm follow-up. Documented cardiac embolisms published in the literature (which are scarce) describe the acute phase of these cases but lack follow-up. There are no systematic reviews on this topic, only case-by-case presentations, and surgeons are not aware of its real implications. CASE: We report a case of an 84-year-old man who developed sudden thoracic and spinal pain associated with 82% saturation and dyspnea a few hours after 4-level thoracic spine vertebroplasty and kyphoplasty. Imaging revealed multiple bone cement embolisms in his lung and heart. Because the patient was hemodynamically stable, cardiologists recommended conservative treatment with low molecular weight heparin, without embolus removal. At 4-year follow-up, the patient remained asymptomatic. CONCLUSION: Cardiac cement embolization following percutaneous techniques represents a life-threatening situation that should be ruled out if the patient presents symptoms during the early postoperative period. Treatment may vary from conservative to emergency open-heart surgery.

Discovering cell types using manifold learning and enhanced visualization of single-cell RNA-Seq data.

Identifying relevant disease modules such as target cell types is a significant step for studying diseases. High-throughput single-cell RNA-Seq (scRNA-seq) technologies have advanced in recent years, enabling researchers to investigate cells individually and understand their biological mechanisms. Computational techniques such as clustering, are the most suitable approach in scRNA-seq data analysis when the cell types have not been well-characterized. These techniques can be used to identify a group of genes that belong to a specific cell type based on their similar gene expression patterns. However, due to the sparsity and high-dimensionality of scRNA-seq data, classical clustering methods are not efficient. Therefore, the use of non-linear dimensionality reduction techniques to improve clustering results is crucial. We introduce a method that is used to identify representative clusters of different cell types by combining non-linear dimensionality reduction techniques and clustering algorithms. We assess the impact of different dimensionality reduction techniques combined with the clustering of thirteen publicly available scRNA-seq datasets of different tissues, sizes, and technologies. We further performed gene set enrichment analysis to evaluate the proposed method's performance. As such, our results show that modified locally linear embedding combined with independent component analysis yields overall the best performance relative to the existing unsupervised methods across different datasets.

Identification of Enriched Regions in ChIP-Seq Data via a Linear-Time Multi-Level Thresholding Algorithm.

Chromatin immunoprecipitation (ChIP-Seq) has emerged as a superior alternative to microarray technology as it provides higher resolution, less noise, greater coverage and wider dynamic range. While ChIP-Seq enables probing of DNA-protein interaction over the entire genome, it requires the use of sophisticated tools to recognize hidden patterns and extract meaningful data. Over the years, various attempts have resulted in several algorithms making use of different heuristics to accurately determine individual peaks corresponding to unique DNA-protein. However, finding all the significant peaks with high accuracy in a reasonable time is still a challenge. In this work, we propose the use of Multi-level thresholding algorithm, which we call LinMLTBS, used to identify the enriched regions on ChIP-Seq data. Although various suboptimal heuristics have been proposed for multi-level thresholding, we emphasize on the use of an algorithm capable of obtaining an optimal solution, while maintaining linear-time complexity. Testing various algorithm on various ENCODE project datasets shows that our approach attains higher accuracy relative to previously proposed peak finders while retaining a reasonable processing speed.

Radiological and histopathological assessment of bone infiltration in soft tissue sarcomas.

BACKGROUND: Deep soft tissue sarcomas are frequently in contact with bone. The therapeutic decision of a composite resection strategy may be challenging, which is usually based on clinical and radiological criteria. The aims of the study were to evaluate the overall frequency of bone and periosteal infiltration in these patients in whom composite resection was indicated, and evaluate the role of magnetic resonance imaging and bone scintigraphy in this scenario. METHODS: Forty-nine patients with a composite surgical resection (soft tissue sarcoma and bone), treated at a single institution between 2006 and 2018, were retrospectively included. Presurgical planning of the resection limits was based on clinical and imaging findings (magnetic resonance imaging and bone scintigraphy). Magnetic resonance imaging was performed in all patients (100%) and bone scintigraphy in 41 (83.7% of the cases). According to magnetic resonance imaging results, patients were divided into two groups: Group A, in which the tumor is adjacent to the bone without evidence of infiltration (n = 24, 48,9%), and Group B, patients with evidence of bone involvement by magnetic resonance imaging (n = 25, 51,1%). BS showed a pathological deposit in 28 patients (68.3%). Histological analysis of the resection specimen was preceded to identify bone and periosteal infiltration. For the analysis of the diagnostic validity of imaging tests, histological diagnosis was considered as the gold standard in the evaluation of STS bone infiltration. RESULTS: Histological bone infiltration was identified in 49% of patients and isolated periosteal infiltration in 14.3%. In terms of diagnostic accuracy, magnetic resonance imaging and bone scintigraphy sensitivity values were 92% and 90%, and their specificity values were 91.7% and 52.4%, respectively. CONCLUSIONS: The incidence of bone and periosteal infiltration of soft tissue sarcomas in contact with bone is high. Presurgical bone assessment by MRI has proven to be a sensitive and specific tool in the diagnosis of bone infiltration. Due to its high negative predictive value, BS is a useful test to rule out it. In those cases, in which there is suspicion of bone infiltration not confirmed by MRI, new diagnostic protocols should be established in order to avoid inappropriate resections.

Vertebral metastasis of renal carcinoma at diagnosis: mechanical and clinical evaluation: surgical management / Metástasis vertebral de carcinoma renal en el momento del diagnóstico: evaluación mecánica y clínica: manejo quirúrgico

Renal cell carcinoma accounts for 2-3% of all malignant neoplasms. Metastatic disease of the spine is common and 50% of bone metastases are already present at the time of primary diagnosis. Bone metastases from renal cell carcinoma are difficult to manage, especially vertebral localization.A 48-year-old woman was diagnosed with renal cell carcinoma in the context of low back pain. The patient presented two skeleton metastases at diagnosis (T11 and 5th rib). The patient received neoadjuvant treatment with cabozantinib, followed by removal of the renal tumor. Radiotherapy was administered for the lumbar lesion. In spite of the radiotherapy treatment, increased low back pain limiting mobility and ambulation. MRI showed an occupation of the spinal canal, without neurological lesion. The SINS scale revealed a score of 14 (vertebral instability). The patient's prognosis was greater than 12 months according to the Tokuhashi score. Based on clinical and mechanical criteria, surgical treatment of the vertebral lesion was decided. T11 vertebrectomy was performed, the reconstruction was made with an expandable cage, and T8 a L2 posterior spinal arthrodesis. A partial resection of the fifth rib was performed in order to remove the whole macroscopic tumor. After 3 months, she was diagnosed with a local infection, treated by irrigation, debridement and antibiotherapy, with good evolution. At 1-year follow-up, she has no low back pain or functional limitation. Follow-up chest-abdomen-pelvis computed CT scan showed absence of disease progression, furthermore, the vertebral arthrodesis shows fusion signs. At the time of this report, there are no clinical or radiological data of infection

El carcinoma de células renales representa el 2-3% de todas las neoplasias malignas. La enfermedad metastásica de la columna vertebral es frecuente y el 50% de las metástasis óseas ya están presentes en el momento del diagnóstico. Las metástasis óseas del carcinoma de células renales son difíciles de manejar, especialmente en localización vertebral.Una mujer de 48 años fue diagnosticada de carcinoma de células renales en el contexto de un dolor lumbar. La paciente presentaba dos metástasis óseas en el momento del diagnóstico (T11 y 5ª costilla). Inicialmente recibió tratamiento neoadyuvante con cabozantinib, seguido de la extirpación quirúrgica del tumor renal. Se administró radioterapia para la lesión lumbar. A pesar del tratamiento radioterápico, aumentó el dolor lumbar con limitación para la movilidad y la deambulación. La RM mostró una ocupación del canal espinal, sin lesión neurológica. La escala SINS reveló una puntuación de 14 (inestabilidad vertebral). El pronóstico de la paciente era superior a 12 meses según la puntuación de Tokuhashi. Basándose en criterios clínicos y mecánicos, se decidió el tratamiento quirúrgico de la lesión vertebral. Se realizó una vertebrectomía de T11, para la reconstrucción se usó una caja extensible, junto con una artrodesis vertebral T8-L2. Se realizó una resección parcial de la quinta costilla para eliminar todo el tumor macroscópico. A los 3 meses de la cirugía la paciente fue diagnosticada de infección local, tratada mediante irrigación, desbridamiento y antibioterapia, con buena evolución. Al año de seguimiento, no presenta dolor lumbar ni limitación funcional. La tomografía computarizada de tórax-abdomen-pelvis de seguimiento mostró ausencia de progresión de la enfermedad, además, la artrodesis vertebral muestra signos de fusión. En el momento de este informe, no hay datos clínicos ni radiológicos de infección.

The Circadian Clock Gene, Bmal1, Regulates Intestinal Stem Cell Signaling and Represses Tumor Initiation.

BACKGROUND & AIMS: Circadian rhythms are daily physiological oscillations driven by the circadian clock: a 24-hour transcriptional timekeeper that regulates hormones, inflammation, and metabolism. Circadian rhythms are known to be important for health, but whether their loss contributes to colorectal cancer is not known. We tested the nonredundant clock gene Bmal1 in intestinal homeostasis and tumorigenesis, using the Apcmin model of colorectal cancer. METHODS: Bmal1 mutant, epithelium-conditional Bmal1 mutant, and photoperiod (day/night cycle) disrupted mice bearing the Apcmin allele were assessed for tumorigenesis. Tumors and normal nontransformed tissue were characterized. Intestinal organoids were assessed for circadian transcription rhythms by RNA sequencing, and in vivo and organoid assays were used to test Bmal1-dependent proliferation and self-renewal. RESULTS: Loss of Bmal1 or circadian photoperiod increases tumor initiation. In the intestinal epithelium the clock regulates transcripts involved in regeneration and intestinal stem cell signaling. Tumors have no self-autonomous clock function and only weak clock function in vivo. Apcmin clock-disrupted tumors show high Yes-associated protein 1 (Hippo signaling) activity but show low Wnt (Wingless and Int-1) activity. Intestinal organoid assays show that loss of Bmal1 increases self-renewal in a Yes-associated protein 1-dependent manner. CONCLUSIONS: Bmal1 regulates intestinal stem cell pathways, including Hippo signaling, and the loss of circadian rhythms potentiates tumor initiation. Transcript profiling: GEO accession number: GSE157357.

Traumatic recurrent hip dislocation associated with femoral head fracturere constructed with iliac crest autograft / Luxación recurrente de cadera asociada a fractura de cabeza femoral reconstruida con autoinjerto de cresta iliaca

Hip femoral head fractures are extremely uncommon, but likely associated with traumatic hip dislocations. Both lesions require emergent treatment to avoid further complications.19-year-old male patient was received after a high-energy motor vehicle accident with severe brain and thoraco-abdominal trauma and a displaced femoral head fracture with posterior hip dislocation with no acetabular fracture. An emergent open reduction and internal fixation with 2 headless screws was performed, as well as posterior capsule repair. After 1 month as an inpatient in Intensive Care Unit, he sustained a new episode of posterior hip dislocation. Consequently, a second successful surgical reduction was obtained, and hip stability was achieved by posterior reconstruction with iliac crest autograft fixed with cannulated screw and posterior structure repair. Two years later, he was able to walk independently and he does not present any signs of degenerative joint disease nor avascular necrosis.

Las fracturas de la cabeza femoral son extremadamente raras y están asociadas comúnmente con una luxación de cadera traumática. Ambas lesiones requieren tratamiento urgente con el objetivo de evitar complicaciones posteriores. Un paciente varón de 19 años fue trasladado tras un accidente de tráfico de alta energía en el que sufrió un traumatismo craneoencefálico y toracoabdominal grave, además de una fractura de cabeza femoral desplazada junto a una luxación posterior de cadera sin afectación acetabular. De manera urgente, fue intervenido mediante una reducción abierta y fijación interna de la fractura con dos tornillos canulados sin cabeza y reparación de la cápsula articular posterior. Tras un mes de ingreso en la unidad de cuidados intensivos, sufrió un nuevo episodio de luxación posterior de cadera. Debido a ello, se realiza una segunda intervención quirúrgica con reducción abierta y en la que se obtiene una adecuada estabilidad de la cadera mediante reconstrucción posterior con la adición de autoinjerto tricortical de cresta ilíaca y reparación capsular posterior. Después de dos años de seguimiento, el paciente deambula de manera independiente, sin dolor y sin signos degenerativos ni de necrosis avascular en las pruebas de imagen.

Mortality after distal femur fractures in the elderly.

INTRODUCTION: the frequency of distal femur fractures in the elderly is rapidly increasing. A study of these fractures was conducted in our center in order to evaluate the comorbidities and the mortality associated with this entity. MATERIAL AND METHODS: all the distal femur fractures by low energy in patients over 65 years old at a tertiary center were included, between January 2010 and December 2016. Baseline characteristics, the type of fracture, comorbidities, and functional status before admission, were collected. The relationship of each of these variables to the final functional class, immediate and late complications and mortality during the follow-up. Fifty-nine patients were included, with a median age of 85.3 years (IQR 78.6-91.6). Fifty-one patients were women. In 10 patients, the fractures were atraumatic (postural change mainly in non-walking patients), and in 54 of the cases were treated surgically (6 with retrograde intramedullary nailing and 48 with lateral locking plate). The median time to surgery was 4.5 days (IQR 2-6) and 14 patients were operated within 48 hours. The median follow-up was 26.3 months. RESULTS: fourteen patients died during the first year of follow-up. Factors independently associated with death during the first year after the fracture were: conservative treatment, and the inability to ambulate before the episode. The absence of certain comorbidities, such as chronic heart disease, and cancer, and an age under 80 years, behaved as protective factors. CONCLUSION: low-energy distal femur fractures comprise a severe injury in the elderly and are associated with high mortality. Surgical treatment showed better outcomes in terms of survival, with no significant differences depending on the type of fracture, the type of implant or the median time to surgery.

iSOM-GSN: an integrative approach for transforming multi-omic data into gene similarity networks via self-organizing maps.

MOTIVATION: One of the main challenges in applying graph convolutional neural networks (CNNs) on gene-interaction data is the lack of understanding of the vector space to which they belong, and also the inherent difficulties involved in representing those interactions on a significantly lower dimension, viz Euclidean spaces. The challenge becomes more prevalent when dealing with various types of heterogeneous data. We introduce a systematic, generalized method, called iSOM-GSN, used to transform 'multi-omic' data with higher dimensions onto a 2D grid. Afterwards, we apply a CNN to predict disease states of various types. Based on the idea of Kohonen's self-organizing map, we generate a 2D grid for each sample for a given set of genes that represent a gene similarity network. RESULTS: We have tested the model to predict breast and prostate cancer using gene expression, DNA methylation and copy number alteration. Prediction accuracies in the 94-98% range were obtained for tumor stages of breast cancer and calculated Gleason scores of prostate cancer with just 14 input genes for both cases. The scheme not only outputs nearly perfect classification accuracy, but also provides an enhanced scheme for representation learning, visualization, dimensionality reduction and interpretation of multi-omic data. AVAILABILITY AND IMPLEMENTATION: The source code and sample data are available via a Github project at https://github.com/NaziaFatima/iSOM_GSN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Prediction of tumor location in prostate cancer tissue using a machine learning system on gene expression data.

BACKGROUND: Finding the tumor location in the prostate is an essential pathological step for prostate cancer diagnosis and treatment. The location of the tumor - the laterality - can be unilateral (the tumor is affecting one side of the prostate), or bilateral on both sides. Nevertheless, the tumor can be overestimated or underestimated by standard screening methods. In this work, a combination of efficient machine learning methods for feature selection and classification are proposed to analyze gene activity and select them as relevant biomarkers for different laterality samples. RESULTS: A data set that consists of 450 samples was used in this study. The samples were divided into three laterality classes (left, right, bilateral). The aim of this work is to understand the genomic activity in each class and find relevant genes as indicators for each class with nearly 99% accuracy. The system identified groups of differentially expressed genes (RTN1, HLA-DMB, MRI1) that are able to differentiate samples among the three classes. CONCLUSION: The proposed method was able to detect sets of genes that can identify different laterality classes. The resulting genes are found to be strongly correlated with disease progression. HLA-DMB and EIF4G2, which are detected in the set of genes can detect the left laterality, were reported earlier to be in the same pathway called Allograft rejection SuperPath.

A Hierarchical Machine Learning Model to Discover Gleason Grade-Specific Biomarkers in Prostate Cancer.

(1) Background:One of the most common cancers that affect North American men and men worldwide is prostate cancer. The Gleason score is a pathological grading system to examine the potential aggressiveness of the disease in the prostate tissue. Advancements in computing and next-generation sequencing technology now allow us to study the genomic profiles of patients in association with their different Gleason scores more accurately and effectively. (2) Methods: In this study, we used a novel machine learning method to analyse gene expression of prostate tumours with different Gleason scores, and identify potential genetic biomarkers for each Gleason group. We obtained a publicly-available RNA-Seq dataset of a cohort of 104 prostate cancer patients from the National Center for Biotechnology Information's (NCBI) Gene Expression Omnibus (GEO) repository, and categorised patients based on their Gleason scores to create a hierarchy of disease progression. A hierarchical model with standard classifiers in different Gleason groups, also known as nodes, was developed to identify and predict nodes based on their mRNA or gene expression. In each node, patient samples were analysed via class imbalance and hybrid feature selection techniques to build the prediction model. The outcome from analysis of each node was a set of genes that could differentiate each Gleason group from the remaining groups. To validate the proposed method, the set of identified genes were used to classify a second dataset of 499 prostate cancer patients collected from cBioportal. (3) Results: The overall accuracy of applying this novel method to the first dataset was 93.3%; the method was further validated to have 87% accuracy using the second dataset. This method also identified genes that were not previously reported as potential biomarkers for specific Gleason groups. In particular, PIAS3 was identified as a potential biomarker for Gleason score 4 + 3 = 7, and UBE2V2 for Gleason score 6. (4) Insight: Previous reports show that the genes predicted by this newly proposed method strongly correlate with prostate cancer development and progression. Furthermore, pathway analysis shows that both PIAS3 and UBE2V2 share similar protein interaction pathways, the JAK/STAT signaling process.

A Machine Learning Approach for Identifying Gene Biomarkers Guiding the Treatment of Breast Cancer.

Genomic profiles among different breast cancer survivors who received similar treatment may provide clues about the key biological processes involved in the cells and finding the right treatment. More specifically, such profiling may help personalize the treatment based on the patients' gene expression. In this paper, we present a hierarchical machine learning system that predicts the 5-year survivability of the patients who underwent though specific therapy; The classes are built on the combination of two parts that are the survivability information and the given therapy. For the survivability information part, it defines whether the patient survives the 5-years interval or deceased. While the therapy part denotes the therapy has been taken during that interval, which includes hormone therapy, radiotherapy, or surgery, which totally forms six classes. The Model classifies one class vs. the rest at each node, which makes the tree-based model creates five nodes. The model is trained using a set of standard classifiers based on a comprehensive study dataset that includes genomic profiles and clinical information of 347 patients. A combination of feature selection methods and a prediction method are applied on each node to identify the genes that can predict the class at that node, the identified genes for each class may serve as potential biomarkers to the class's treatment for better survivability. The results show that the model identifies the classes with high-performance measurements. An exhaustive analysis based on relevant literature shows that some of the potential biomarkers are strongly related to breast cancer survivability and cancer in general.

Transcriptomics Signature from Next-Generation Sequencing Data Reveals New Transcriptomic Biomarkers Related to Prostate Cancer.

Prostate cancer is one of the most common types of cancer among Canadian men. Next-generation sequencing using RNA-Seq provides large amounts of data that may reveal novel and informative biomarkers. We introduce a method that uses machine learning techniques to identify transcripts that correlate with prostate cancer development and progression. We have isolated transcripts that have the potential to serve as prognostic indicators and may have tremendous value in guiding treatment decisions. Analysis of normal versus malignant prostate cancer data sets indicates differential expression of the genes HEATR5B, DDC, and GABPB1-AS1 as potential prostate cancer biomarkers. Our study also supports PTGFR, NREP, SCARNA22, DOCK9, FLVCR2, IK2F3, USP13, and CLASP1 as potential biomarkers to predict prostate cancer progression, especially between stage II and subsequent stages of the disease.

Working Below Skill Level as Risk Factor for Distress Among Latin American Migrants Living in Germany: A Cross-Sectional Study.

About 84,710 Latin American migrants currently live in Germany. Knowledge about their work situation in relation to their skill level and its association with mental health is limited. Therefore, the aims of this study were to assess the prevalence of working below skill level and its association with the prevalence of distress in Latin Americans living in Germany. This cross-sectional study included a convenience sample of 282 Latin American migrants living in Germany. Participants were recruited by a short online (Facebook, personal contacts) or interview-based questionnaire from November 2015 to April 2016. Questions included skill level, job category (categorized by ISCO 2008 code), socio-demographics, violence at the workplace and distress. The latter was assessed by Goldberg's General Health Questionnaire using a cut-off of 4/5. Descriptive statistics were followed by logistic regression analyses adjusting for potential confounders. About half of the study population reported symptoms of distress (45%). 63% of the population worked below skill level. 12-months prevalence of violence at the workplace was 14%. After adjustment, working below skill level was statistically significantly related to distress (odds ratio 2.80; 95% confidence interval 1.58-4.95). Working below skill level is common in Latin American migrants in Germany and may result in poor psychosocial well-being.