LncDLSM: Identification of Long Non-coding RNAs with Deep Learning-based Sequence Model.

Long non-coding RNAs (LncRNAs) serve a vital role in regulating gene expressions and other biological processes. Differentiation of lncRNAs from protein-coding transcripts helps researchers dig into the mechanism of lncRNA formation and its downstream regulations related to various diseases. Previous works have been proposed to identify lncRNAs, including traditional bio-sequencing and machine learning approaches. Considering the tedious work of biological characteristic-based feature extraction procedures and inevitable artifacts during bio-sequencing processes, those lncRNA detection methods are not always satisfactory. Hence, in this work, we presented lncDLSM, a deep learning-based framework differentiating lncRNA from other protein-coding transcripts without dependencies on prior biological knowledge. lncDLSM is a helpful tool for identifying lncRNAs compared with other biological feature-based machine learning methods and can be applied to other species by transfer learning achieving satisfactory results. Further experiments showed that different species display distinct boundaries among distributions corresponding to the homology and the specificity among species, respectively. An online web server is provided to the community for easy use and efficient identification of lncRNA, available at http://39.106.16.168/lncDLSM.

Low-molecular-weight heparin inhibits hypoxic pulmonary hypertension and vascular remodeling in guinea pigs.

RATIONALE: We have shown previously that antiproliferative unfractionated heparins block hypoxia-induced pulmonary arterial hypertension (PAH) and vascular remodeling, and hypothesized that low-molecular-weight heparins (LMWHs) would too. OBJECTIVES: To determine the potential role and mechanisms of dalteparin and enoxaparin (two LMWHs) in inhibiting hypoxic PAH and vascular remodeling. METHODS: Male Hartley guinea pigs were exposed for 10 days to normobaric 10% oxygen with dalteparin (5 mg/kg), enoxaparin (5 mg/kg), or with an equivalent volume of normal saline solution. Normoxic control animals (n = 5) received room air for 10 days. Bovine pulmonary artery smooth-muscle cells (PASMCs) were grown in 10% fetal bovine serum without heparin, with dalteparin (1 microg/mL) or with enoxaparin (1 microg/mL). MEASUREMENTS: Pulmonary arterial pressure (PAP), cardiac index, right ventricular heart weight divided by left ventricular plus septum weight (RV/LV+S), hematocrit, percentage of wall thickness of intraacinar vessels (%WT-IA), percentage of wall thickness of terminal bronchiole vessels (%WT-TA), and the percentage of thick-walled vessels (%Thick) were determined. In PASMCs, expression of p27 and cell growth were compared because in mice whole heparin depends on p27 for its antiproliferative action. MAIN RESULTS: In hypoxic animals, hematocrit, PAP, total pulmonary vascular resistance index, RV/LV+S, %WT-IA, %WT-TA, and %Thick all rose significantly vs normoxic control animals (p < 0.05); cardiac index was unchanged. Dalteparin but not enoxaparin significantly reduced PAP, total pulmonary vascular resistance index, and RV/LV + S (p < 0.05 vs hypoxia alone); inhibited PASMC growth; and upregulated p27 expression. Enoxaparin moderately reduced vascular remodeling, which did not translate into less pulmonary hypertension. CONCLUSIONS: Not all LMWHs are the same. Dalteparin was more effective than enoxaparin in inhibiting pulmonary hypertension and vascular remodeling in hypoxic guinea pigs.