Predicting RNA splicing from DNA sequence using Pangolin

Zeng, Teng; Li, Yi

doi:10.1101/2021.07.06.451243

Cited by 4 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, end-to-end prediction is generally recommended to leverage the full power of Deep Learning. Others have shown that Deep Learning can effectively directly predict transitions such as splice sites [Zeng and Li, 2022, Zhang et al, 2016, Wang et al, 2019. It is conceptually possible to encode a full gene structure as a series of transition tokens and positions, and then predict structure with a many-to-many model architecture such as those used for large language modeling [Brown et al, 2020, Vaswani et al, 2017.…”

Section: Discussionmentioning

confidence: 99%

Helixer–de novoPrediction of Primary Eukaryotic Gene Models Combining Deep Learning and a Hidden Markov Model

Holst

Bolger

Günther

et al. 2023

Preprint

View full text Add to dashboard Cite

Gene structural annotation is a critical step in obtaining biological knowledge from genome sequences yet remains a major challenge in genomics projects. Current de novo Hidden Markov Models are limited in their capacity to model biological complexity; while current pipelines are resource-intensive and their results vary in quality with the available extrinsic data. Here, we build on our previous work in applying Deep Learning to gene calling to make a fully applicable, fast and user friendly tool for predicting primary gene models from DNA sequence alone. The quality is state-of-the-art, with predictions scoring closer by most measures to the references than to predictions from other de novo tools. Helixer's predictions can be used as is or could be integrated in pipelines to boost quality further. Moreover, there is substantial potential for further improvements and advancements in gene calling with Deep Learning. Helixer is open source and available at https://github.com/weberlab-hhu/Helixer A web interface is available at https://www.plabipd.de/helixer_main.html

show abstract

Section: Discussionmentioning

confidence: 99%

Helixer–de novoPrediction of Primary Eukaryotic Gene Models Combining Deep Learning and a Hidden Markov Model

Holst

Bolger

Günther

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Currently, we only applied SpliceBERT to predict splice sites and branchpoints independent of tissue or cell types, while tissue/cell typespecific alternative splicing cannot be ignored because they contributed a lot to transcriptomic and proteomic diversity (43). In fact, predicting tissue/cell type-specific splicing is still challenging solely from sequences (10,44). We may combine additional tasks like tissuespecific splice site strength (10) and RNA binding protein binding sites (45) to improve the model's ability for tissue-specific prediction.…”

Section: Discussionmentioning

confidence: 99%

“…In fact, predicting tissue/cell type-specific splicing is still challenging solely from sequences (10,44). We may combine additional tasks like tissuespecific splice site strength (10) and RNA binding protein binding sites (45) to improve the model's ability for tissue-specific prediction.…”

Section: Discussionmentioning

confidence: 99%

“…SPANR (3) is a Bayesian network model for predicting the Percent Spliced In (PSI or Ψ) of alternatively spliced exons. More recently, deep learning models like MMSplice (8), SpliceAI (9) and Pangolin (10) employed deep convolutional neural networks (CNN) to predict alternative splicing events, splice sites or splice site usage. These methods achieved superior performance as compared to earlier ones and have been widely utilized to analyze aberrant RNA splicing events caused by genetic variants.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-supervised learning on millions of pre-mRNA sequences improves sequence-based RNA splicing prediction

Chen

Zhou

Ding

et al. 2023

Preprint

View full text Add to dashboard Cite

RNA splicing is an important post-transcriptional process of gene expression in eukaryotic organisms. Here, we developed a novel language model, SpliceBERT, pre-trained on the precursor messenger RNA sequences of 72 vertebrates to improve sequence-based modelling of RNA splicing. SpliceBERT is capable of generating embeddings that preserve the evolutionary information of nucleotides and functional characteristics of splice sites. Moreover, the pre-trained model can be utilized to prioritize potential splice-disrupting variants in an unsupervised manner based on genetic variants' impact on the output of SpliceBERT for sequence context. Benchmarked on a multi-species splice site and a human branchpoint prediction task, SpliceBERT outperformed not only conventional baseline models but also other language models pretrained only on the human genome. Our study highlighted the importance of unsupervised learning with genomic sequences of multiple species and indicated that language models were promising approaches to decipher the determinants of RNA splicing.

show abstract

“…Splicing patterns are directly influenced by the nucleotide sequences surrounding splice sites [29]. This has enabled the development of many algorithms to predict alternative splicing from RNA-seq [30][31][32] or DNA sequence [33][34][35][36][37]. Beyond human clinical applications, methods that require only DNA sequence can be leveraged to understand alternative splicing in extant species for which acquiring RNA-seq data may be difficult to impossible or in extinct taxa, such as archaic hominins.…”

Section: Introductionmentioning

confidence: 99%

Resurrecting the Alternative Splicing Landscape of Archaic Hominins using Machine Learning

Brand

Colbran

Capra

2022

Preprint

View full text Add to dashboard Cite

Alternative splicing contributes to adaptation and divergence in many species. However, it has not been possible to directly compare splicing between modern and archaic hominins. Here, we unmask the recent evolution of this previously unobservable regulatory mechanism by applying SpliceAI, a machine-learning algorithm that identifies splice altering variants (SAVs), to high-coverage genomes from three Neanderthals and a Denisovan. We discover 5,950 putative archaic SAVs, of which 2,343 are archaic-specific and 3,607 also occur in modern humans via introgression (237) or shared ancestry (3,370). Archaic-specific SAVs are enriched in genes that contribute to many traits potentially relevant to hominin phenotypic divergence, such as perspiration, platelet volume, and spinal rigidity. Compared to shared SAVs, archaic-specific SAVs occur in sites under weaker selection and are more common in genes with tissue-specific expression. Further underscoring the importance of negative selection on SAVs, Neanderthal lineages with low effective population sizes are enriched for SAVs compared to Denisovan and shared SAVs. Finally, we find that nearly all introgressed SAVs in humans were shared across Neanderthals, suggesting that older SAVs were more tolerated in modern human genomes. Our results reveal the splicing landscape of archaic hominins and identify potential contributions of splicing to phenotypic differences among hominins.

show abstract

Predicting RNA splicing from DNA sequence using Pangolin

Cited by 4 publications

References 34 publications

Helixer–de novoPrediction of Primary Eukaryotic Gene Models Combining Deep Learning and a Hidden Markov Model

Helixer–de novoPrediction of Primary Eukaryotic Gene Models Combining Deep Learning and a Hidden Markov Model

Self-supervised learning on millions of pre-mRNA sequences improves sequence-based RNA splicing prediction

Resurrecting the Alternative Splicing Landscape of Archaic Hominins using Machine Learning

Contact Info

Product

Resources

About