Biology subjects

Gandhi, S.

Publications and source records attributed to Gandhi, S..

3 recordsLinked to original sources

bioRxiv2018

cDeepbind: A context sensitive deep learning model of RNA-protein binding

MotivationDetermining RNA binding protein(RBP) binding specificity is crucial for understanding many cellular processes and genetic disorders. RBP binding is known to be affected by both the sequence and structure of RNAs. Deep learning can be used to learn generalizable representations of raw data and has improved state of the art in several fields such as image classification, speech recognition and even genomics. Previous work on RBP binding has either used shallow models that combine sequence and structure or deep models that use only the sequence. Here we combine both abilities by augmenting and refining the original Deepbind architecture to capture structural information and obtain significantly better performance.\n\nResultsWe propose two deep architectures, one a lightweight convolutional network for transcriptome wide inference and another a Long Short-Term Memory(LSTM) network that is suitable for small batches of data. We incorporate computationally predicted secondary structure features as input to our models and show its effectiveness in boosting prediction performance. Our models achieved significantly higher correlations on held out in-vitro test data compared to previous approaches, and generalise well to in-vivo CLIP-SEQ data achieving higher median AUCs than other approaches. We analysed the output from our model for VTS1 and CPO and provided intuition into its working. Our models confirmed known secondary structure preferences for some proteins as well as found new ones where secondary structure might play a role. We also demonstrated the strengths of our model compared to other approaches such as the ability to combine information from long distances along the input.\n\nAvailabilitySoftware and models are available at https://github.com/shreshthgandhi/cDeepbind\n\nContactljlee@psi.toronto.edu, frey@psi.toronto.edu

genomics↗

bioRxiv2018

COSSMO: Predicting Competitive Alternative Splice Site Selection using Deep Learning

MotivationAlternative splice site selection is inherently competitive and the probability of a given splice site to be used also depends strongly on the strength of neighboring sites. Here we present a new model named Competitive Splice Site Model (COSSMO), which explicitly models these competitive effects and predict the PSI distribution over any number of putative splice sites. We model an alternative splicing event as the choice of a 3 acceptor site conditional on a fixed upstream 5 donor site, or the choice of a 5 donor site conditional on a fixed 3 acceptor site. We build four different architectures that use convolutional layers, communication layers, LSTMS, and residual networks, respectively, to learn relevant motifs from sequence alone. We also construct a new dataset from genome annotations and RNA-Seq read data that we use to train our model.\n\nResultsCOSSMO is able to predict the most frequently used splice site with an accuracy of 70% on unseen test data, and achieve an R2 of 60% in modeling the PSI distribution. We visualize the motifs that COSSMO learns from sequence and show that COSSMO recognizes the consensus splice site sequences as well as many known splicing factors with high specificity.\n\nAvailabilityOur dataset is available from http://cossmo.deepgenomics.com.\n\nContactfrey@deepgenomics.com\n\nSupplementary informationSupplementary data are available at Bioinformatics online.

bioinformatics↗

bioRxiv2017

Study of the mitotic chromatin shows involvement of histone modifications in bookmarking and reveals nucleosome deposition patterns

Mitosis encompasses key molecular changes including chromatin condensation, nuclear envelope breakdown, and reduced transcription levels. Immediately after mitosis, the interphase chromatin structure is reestablished and transcription resumes. The reestablishment of the interphase chromatin is probably achieved by bookmarking, i.e., the retention of at least partial information during mitosis. Yet, while recent studies demonstrate that chromatin accessibility is generally preserved during mitosis and is only locally modulated, the exact details of the bookmarking process and its components are still unclear. To gain a deeper understanding of the mitotic bookmarking process, we merged proteomics, immunofluorescence, and ChIP-seq approaches to study the mitotic and interphase genomic organization of human cells. We focused on key histone modifications and employed HeLa-S3 cells as a model system. Generally, we observed a global concordance between the genomic organization of histone modifications in interphase and mitosis, yet the abundance of the two types of modifications we investigated was different. Whereas histone methylation patterns remain highly similar, histone acetylation patterns show a general reduction while maintaining their genomic organization. These results demonstrate that the epigenomic landscape can serve as a major component of the mitotic bookmarking process. Next, to further investigate mitosis-associated chromatin changes, we followed up on previous studies that showed that nucleosome depleted regions (NDRs) become occupied by a nucleosome during mitosis. Surprisingly, we observed that the nucleosome introduced into the NDR during mitosis encompasses a distinctive set of histone modifications, differentiating it from the surrounding nucleosomes. We show that the nucleosomes near the NDR appear to both shift into the NDR during mitosis and adopt a unique modification pattern. HDAC inhibition by the small molecule TSA reverts this pattern. These results provide evidence for a mitotic deposition and change in the modifications of the nucleosomes surrounding the NDR. Altogether, by merging multiple approaches, our study provides evidence to support a model where mitotic bookmarking is achieved by histone modifications and uncovers new insights into the deposition of nucleosomes during mitosis.

genomics↗