RBPSpot: Learning on appropriate contextual information for RBP binding sites discovery.
Ontology highlight
ABSTRACT:
SUBMITTER: Sharma NK
PROVIDER: S-EPMC8605353 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Circular RNAs (circRNAs), with their crucial roles in gene regulation and disease development, have become rising stars in the RNA world. To understand the regulatory function of circRNAs, many studies focus on the interactions between circRNAs and RNA-binding proteins (RBPs). Recently, the abundant CLIP-seq experimental data has enabled the large-scale identification and analysis of circRNA-RBP interactions, whereas, as far as we know, no computational tool based on machine learning has been proposed yet. We develop CRIP (CircRNAs Interact with Proteins) for the prediction of RBP-binding sites on circRNAs using RNA sequences alone. CRIP consists of a stacked codon-based encoding scheme and a hybrid deep learning architecture, in which a convolutional neural network (CNN) learns high-level abstract features and a recurrent neural network (RNN) learns long dependency in the sequences. We construct 37 data sets including sequence fragments of binding sites on circRNAs, and each set corresponds to an RBP. The experimental results show that the new encoding scheme is superior to the existing feature representation methods for RNA sequences, and the hybrid network outperforms conventional classifiers by a large margin, where both the CNN and RNN components contribute to the performance improvement.
| S-EPMC6859861 | biostudies-literature
Project description:Neuronal activity generates DNA double-strand breaks (DSBs) at specific loci in vitro and this facilitates the rapid transcriptional induction of early response genes (ERGs). Physiological neuronal activity, including exposure of mice to learning behaviors, also cause the formation of DSBs, yet the distribution of these breaks and their relation to brain function remains unclear. Here, following contextual fear conditioning (CFC) in mice, we profiled the locations of DSBs genome-wide in the medial prefrontal cortex and hippocampus using γH2AX ChIP-Seq. Remarkably, we found that DSB formation is widespread in the brain compared to cultured primary neurons and they are predominately involved in synaptic processes. We observed increased DNA breaks at genes induced by CFC in neuronal and non-neuronal nuclei. Activity-regulated and proteostasis-related transcription factors appear to govern some of these gene expression changes across cell types. Finally, we find that glia but not neurons have a robust transcriptional response to glucocorticoids, and many of these genes are sites of DSBs. Our results indicate that learning behaviors cause widespread DSB formation in the brain that are associated with experience-driven transcriptional changes across both neuronal and glial cells.
| S-EPMC8248687 | biostudies-literature
Project description:Originally discovered in the bacteriophage Mu DNA inversion system gin, Fis (Factor for Inversion Stimulation) regulates many genetic systems. To determine the base frequency conservation required for Fis to locate its binding sites, we collected a set of 60 experimentally defined wild-type Fis DNA binding sequences. The sequence logo for Fis binding sites showed the significance and likely kinds of base contacts, and these are consistent with available experimental data. Scanning with an information theory based weight matrix within fis, nrd, tgt/sec and gin revealed Fis sites not previously identified, but for which there are published footprinting and biochemical data. DNA mobility shift experiments showed that a site predicted to be 11 bases from the proximal Salmonella typhimurium hin site and a site predicted to be 7 bases from the proximal P1 cin site are bound by Fis in vitro. Two predicted sites separated by 11 bp found within the nrd promoter region, and one in the tgt/sec promoter, were also confirmed by gel shift analysis. A sequence in aldB previously reported to be a Fis site, for which information theory predicts no site, did not shift. These results demonstrate that information analysis is useful for predicting Fis DNA binding.
| S-EPMC147151 | biostudies-other
Project description:Exploration permits acquisition of the most relevant information during learning. However, the specific information needed, the influences of this information on decision making, and the relevant neural mechanisms remain poorly understood. We modeled distinct information types available during contextual association learning and used model-based fMRI in conjunction with manipulation of exploratory decision making to identify neural activity associated with information-based decisions. We identified hippocampal-prefrontal contributions to advantageous decisions based on immediately available novel information, distinct from striatal contributions to advantageous decisions based on the sum total available (accumulated) information. Furthermore, network-level interactions among these regions during exploratory decision making were related to learning success. These findings link strategic exploration decisions during learning to quantifiable information and advance understanding of adaptive behavior by identifying the distinct and interactive nature of brain-network contributions to decisions based on distinct information types.
| S-EPMC4081497 | biostudies-literature
Project description:Kaposi's sarcoma-associated herpesvirus (KSHV) is tightly linked to at least two lymphoproliferative disorders, primary effusion lymphoma (PEL) and multicentric Castleman's disease (MCD). However, the development of KSHV-mediated lymphoproliferative disease is not fully understood. Here, we generated two recombinant KSHV viruses deleted for the first RBP-Jκ binding site (RTA(1st)) and all three RBP-Jκ binding sites (RTA(all)) within the RTA promoter. Our results showed that RTA(1st) and RTA(all) recombinant viruses possess increased viral latency and a decreased capability for lytic replication in HEK 293 cells, enhancing colony formation and proliferation of infected cells. Furthermore, recombinant RTA(1st) and RTA(all) viruses showed greater infectivity in human peripheral blood mononuclear cells (PBMCs) relative to wt KSHV. Interestingly, KSHV BAC36 wt, RTA(1st) and RTA(all) recombinant viruses infected both T and B cells and all three viruses efficiently infected T and B cells in a time-dependent manner early after infection. Also, the capability of both RTA(1st) and RTA(all) recombinant viruses to infect CD19+ B cells was significantly enhanced. Surprisingly, RTA(1st) and RTA(all) recombinant viruses showed greater infectivity for CD3+ T cells up to 7 days. Furthermore, studies in Telomerase-immortalized human umbilical vein endothelial (TIVE) cells infected with KSHV corroborated our data that RTA(1st) and RTA(all) recombinant viruses have enhanced ability to persist in latently infected cells with increased proliferation. These recombinant viruses now provide a model to explore early stages of primary infection in human PBMCs and development of KSHV-associated lymphoproliferative diseases.
| S-EPMC3257303 | biostudies-other
Project description:BackgroundX-ray images are commonly used to assess the bone destruction of rheumatoid arthritis. The purpose of this study is to propose an automatic-bone-destruction-evaluation system fully utilizing deep neural networks (DNN). This system detects all target joints of the modified Sharp/van der Heijde score (SHS) from a hand X-ray image. It then classifies every target joint as intact (SHS = 0) or non-intact (SHS ≥ 1).MethodsWe used 226 hand X-ray images of 40 rheumatoid arthritis patients. As for detection, we used a DNN model called DeepLabCut. As for classification, we built four classification models that classify the detected joint as intact or non-intact. The first model classifies each joint independently, whereas the second model does it while comparing the same contralateral joint. The third model compares the same joint group (e.g., the proximal interphalangeal joints) of one hand and the fourth model compares the same joint group of both hands. We evaluated DeepLabCut's detection performance and classification models' performances. The classification models' performances were compared to three orthopedic surgeons.ResultsDetection rates for all the target joints were 98.0% and 97.3% for erosion and joint space narrowing (JSN). Among the four classification models, the model that compares the same contralateral joint showed the best F-measure (0.70, 0.81) and area under the curve of the precision-recall curve (PR-AUC) (0.73, 0.85) regarding erosion and JSN. As for erosion, the F-measure and PR-AUC of this model were better than the best of the orthopedic surgeons.ConclusionsThe proposed system was useful. All the target joints were detected with high accuracy. The classification model that compared the same contralateral joint showed better performance than the orthopedic surgeons regarding erosion.
| S-EPMC9528108 | biostudies-literature
Project description:Neuronal activity generates DNA double-strand breaks (DSBs) in vitro and in vivo, and these breaks facilitate the rapid transcriptional induction of immediate early genes (IEGs). Yet the locations of these DSBs in vivo and their relation to brain function remains unclear. Here, following contextual fear conditioning in mice, we profiled the locations of DSBs genome-wide along with transcriptomic changes in neurons and glia in two brain regions. Interestingly, while DSB-susceptible genes induced by fear learning in neurons are predominately involved in synaptic processes, we also observe increased DNA breaks at genes upregulated in glia. Both activity-regulated and proteostasis-related transcription factors appear to govern these gene expression changes across cell types. Finally, we find that glia but not neurons have a robust transcriptional response to glucocorticoids, and these are sites of DSBs. Overall, our data show that fear learning rapidly induces transcriptional changes at genes important for brain function, including stress-responsive genes in glia, and this correlates with hotspots of DSBs.
2021-05-31 | GSE155095 | GEO
Project description:BackgroundDetermining protein-protein interactions and their binding affinity are important in understanding cellular biological processes, discovery and design of novel therapeutics, protein engineering, and mutagenesis studies. Due to the time and effort required in wet lab experiments, computational prediction of binding affinity from sequence or structure is an important area of research. Structure-based methods, though more accurate than sequence-based techniques, are limited in their applicability due to limited availability of protein structure data.ResultsIn this study, we propose a novel machine learning method for predicting binding affinity that uses protein 3D structure as privileged information at training time while expecting only protein sequence information during testing. Using the method, which is based on the framework of learning using privileged information (LUPI), we have achieved improved performance over corresponding sequence-based binding affinity prediction methods that do not have access to privileged information during training. Our experiments show that with the proposed framework which uses structure only during training, it is possible to achieve classification performance comparable to that which is obtained using structure-based features. Evaluation on an independent test set shows improved performance over the PPA-Pred2 method as well.ConclusionsThe proposed method outperforms several baseline learners and a state-of-the-art binding affinity predictor not only in cross-validation, but also on an additional validation dataset, demonstrating the utility of the LUPI framework for problems that would benefit from classification using structure-based features. The implementation of LUPI developed for this work is expected to be useful in other areas of bioinformatics as well.
| S-EPMC6238365 | biostudies-literature
Project description:Humans can learn and store multiple visuomotor mappings (dual-adaptation) when feedback for each is provided alternately. Moreover, learned context cues associated with each mapping can be used to switch between the stored mappings. However, little is known about the associative learning between cue and required visuomotor mapping, and how learning generalises to novel but similar conditions. To investigate these questions, participants performed a rapid target-pointing task while we manipulated the offset between visual feedback and movement end-points. The visual feedback was presented with horizontal offsets of different amounts, dependent on the targets shape. Participants thus needed to use different visuomotor mappings between target location and required motor response depending on the target shape in order to "hit" it. The target shapes were taken from a continuous set of shapes, morphed between spiky and circular shapes. After training we tested participants performance, without feedback, on different target shapes that had not been learned previously. We compared two hypotheses. First, we hypothesised that participants could (explicitly) extract the linear relationship between target shape and visuomotor mapping and generalise accordingly. Second, using previous findings of visuomotor learning, we developed a (implicit) Bayesian learning model that predicts generalisation that is more consistent with categorisation (i.e. use one mapping or the other). The experimental results show that, although learning the associations requires explicit awareness of the cues' role, participants apply the mapping corresponding to the trained shape that is most similar to the current one, consistent with the Bayesian learning model. Furthermore, the Bayesian learning model predicts that learning should slow down with increased numbers of training pairs, which was confirmed by the present results. In short, we found a good correspondence between the Bayesian learning model and the empirical results indicating that this model poses a possible mechanism for simultaneously learning multiple visuomotor mappings.
| S-EPMC4376781 | biostudies-literature
Project description:RNA binding proteins (RBPs) are critical for the post-transcriptional control of RNAs and play vital roles in a myriad of biological processes, such as RNA localization and gene regulation. Therefore, computational methods that are capable of accurately identifying RBPs are highly desirable and have important implications for biomedical and biotechnological applications. Here, we propose a two-stage deep transfer learning-based framework, termed RBP-TSTL, for accurate prediction of RBPs. In the first stage, the knowledge from the self-supervised pre-trained model was extracted as feature embeddings and used to represent the protein sequences, while in the second stage, a customized deep learning model was initialized based on an annotated pre-training RBPs dataset before being fine-tuned on each corresponding target species dataset. This two-stage transfer learning framework can enable the RBP-TSTL model to be effectively trained to learn and improve the prediction performance. Extensive performance benchmarking of the RBP-TSTL models trained using the features generated by the self-supervised pre-trained model and other models trained using hand-crafting encoding features demonstrated the effectiveness of the proposed two-stage knowledge transfer strategy based on the self-supervised pre-trained models. Using the best-performing RBP-TSTL models, we further conducted genome-scale RBP predictions for Homo sapiens, Arabidopsis thaliana, Escherichia coli, and Salmonella and established a computational compendium containing all the predicted putative RBPs candidates. We anticipate that the proposed RBP-TSTL approach will be explored as a useful tool for the characterization of RNA-binding proteins and exploration of their sequence-structure-function relationships.
| S-EPMC9294422 | biostudies-literature