Technological and research advances have produced large volumes of biomedical data. When represented as a network (graph), these data become useful for modeling entities and interactions in ...biological and similar complex systems. In the field of network biology and network medicine, there is a particular interest in predicting results from drug-drug, drug-disease, and protein-protein interactions to advance the speed of drug discovery. Existing data and modern computational methods allow to identify potentially beneficial and harmful interactions, and therefore, narrow drug trials ahead of actual clinical trials. Such automated data-driven investigation relies on machine learning techniques. However, traditional machine learning approaches require extensive preprocessing of the data that makes them impractical for large datasets. This study presents wide range of machine learning methods for predicting outcomes from biomedical interactions and evaluates the performance of the traditional methods with more recent network-based approaches.
We applied a wide range of 32 different network-based machine learning models to five commonly available biomedical datasets, and evaluated their performance based on three important evaluations metrics namely AUROC, AUPR, and F1-score. We achieved this by converting link prediction problem as binary classification problem. In order to achieve this we have considered the existing links as positive example and randomly sampled negative examples from non-existant set. After experimental evaluation we found that Prone, ACT and Formula: see text are the top 3 best performers on all five datasets.
This work presents a comparative evaluation of network-based machine learning algorithms for predicting network links, with applications in the prediction of drug-target and drug-drug interactions, and applied well known network-based machine learning methods. Our work is helpful in guiding researchers in the appropriate selection of machine learning methods for pharmaceutical tasks.
Advanced glycation end products (AGEs) culminate from the non-enzymatic reaction between a free carbonyl group of a reducing sugar and free amino group of proteins. 3-deoxyglucosone (3-DG) is one of ...the dicarbonyl species that rapidly forms several protein-AGE complexes that are believed to be involved in the pathogenesis of several diseases, particularly diabetic complications. In this study, the generation of AGEs (Nε-carboxymethyl lysine and pentosidine) by 3-DG in H1 histone protein was characterized by evaluating extent of side chain modification (lysine and arginine) and formation of Amadori products as well as carbonyl contents using several physicochemical techniques. Results strongly suggested that 3-DG is a potent glycating agent that forms various intermediates and AGEs during glycation reactions and affects the secondary structure of the H1 protein. Structural changes and AGE formation may influence the function of H1 histone and compromise chromatin structures in cases of secondary diabetic complications.
Acute aortic occlusions (AAOs) are rare vascular emergencies associated with high morbidity and mortality. Presenting signs and symptoms vary but typically involve the lower extremities and include ...mottled skin with diminished pedal pulses, paresis, and severe pain. Prompt recognition and imaging are necessary to prevent rapid deterioration, which can lead to loss of limb or death. Treatment includes surgical or endovascular interventions based on patient-associated risk factors and clot location.We present a 76-year-old female who arrived at the emergency department with an AAO involving the infrarenal abdominal aorta and bilateral common iliac arteries. Efficient physical examination and utilization of computed tomography with angiography of the abdomen and pelvis allowed for the appropriate recognition of the AAO and subsequent successful surgical embolectomy. This case report underscores the importance of an expeditious clinical and radiographic evaluation in patients presenting with lower extremity pain and weakness.
Advanced glycation end-products (AGEs) are heterogeneous group of compounds, known to be implicated in diabetic complications. One of the consequences of the Maillard reaction is attributed to the ...production of reactive intermediate products such as α-oxoaldehydes. 3-deoxyglucosone (3-DG), an α-oxoaldehyde has been found to be involved in accelerating vascular damage during diabetes. In the present study, calf thymus histone H3 was treated with 3-deoxyglucosone to investigate the generation of AGEs (Nε-carboxymethyllysine, pentosidine), by examining the degree of side chain modifications and formation of different intermediates and employing various physicochemical techniques. The results clearly indicate the formation of AGEs and structural changes upon glycation of H3 by 3-deoxyglucosone, which may hamper the normal functioning of H3 histone, that may compromise the veracity of chromatin structures and function in secondary complications of diabetes.
Methylation of histone H3 lysine 4 (H3K4) by Set1 complex/COMPASS is a hallmark of eukaryotic chromatin, but it remains poorly understood how this post-translational modification contributes to the ...regulation of biological processes like the cell cycle. Here, we report a H3K4 methylation-dependent pathway in Saccharomyces cerevisiae that governs toxicity toward benomyl, a microtubule destabilizing drug. Benomyl-sensitive growth of wild-type cells required mono- and dimethylation of H3K4 and Pho23, a PHD-containing subunit of the Rpd3L complex. Δset1 and Δpho23 deletions suppressed defects associated with ipl1-2 aurora kinase mutant, an integral component of the spindle assembly checkpoint during mitosis. Benomyl resistance of Δset1 strains was accompanied by deregulation of all four tubulin genes and the phenotype was suppressed by tub2-423 and Δtub3 mutations, establishing a genetic link between H3K4 methylation and microtubule function. Most interestingly, sine wave fitting and clustering of transcript abundance time series in synchronized cells revealed a requirement for Set1 for proper cell-cycle-dependent gene expression and Δset1 cells displayed delayed entry into S phase. Disruption of G1/S regulation in Δmbp1 and Δswi4 transcription factor mutants duplicated both benomyl resistance and suppression of ipl1-2 as was observed with Δset1 Taken together our results support a role for H3K4 methylation in the coordination of cell-cycle progression and proper assembly of the mitotic spindle during mitosis.
PDF
