RNAsamba: neural network-based assessment of the protein-coding potential of RNA sequences
AP Camargo, V Sourkov, GAG Pereira… - NAR genomics and …, 2020 - academic.oup.com
The advent of high-throughput sequencing technologies made it possible to obtain large
volumes of genetic information, quickly and inexpensively. Thus, many efforts are devoted to …
volumes of genetic information, quickly and inexpensively. Thus, many efforts are devoted to …
Igloo: Slicing the features space to represent sequences
V Sourkov - arXiv preprint arXiv:1807.03402, 2018 - arxiv.org
Historically, Recurrent neural networks (RNNs) and its variants such as LSTM and GRU and
more recently Transformers have been the standard go-to components when processing …
more recently Transformers have been the standard go-to components when processing …
[PDF][PDF] Igloo: Slicing the features space to represent long sequences
V Sourkov - arXiv preprint arXiv:1807.03402, 2018 - researchgate.net
Up until recently Recurrent neural networks (RNNs) have been the standard go-to component
when processing sequential data with neural networks. Issues relative to vanishing …
when processing sequential data with neural networks. Issues relative to vanishing …
RNAsamba: coding potential assessment using ORF and whole transcript sequence information
AP Camargo, V Sourkov, MF Carazzolle - BioRxiv, 2019 - biorxiv.org
Motivation The advent of high-throughput sequencing technologies made it possible to obtain
large volumes of genetic information, quickly and inexpensively. Thus, many efforts are …
large volumes of genetic information, quickly and inexpensively. Thus, many efforts are …
Research in Computational Molecular Biology
I Pe'er - Springer
This volume contains 17 extended abstracts and 23 short abstracts representing a total of
40 proceedings papers presented at the 26th International Conference on Research in …
40 proceedings papers presented at the 26th International Conference on Research in …
Neural cdes for long time series via the log-ode method
Neural Controlled Differential Equations (Neural CDEs) are the continuous-time analogue of
an RNN, just as Neural ODEs are analogous to ResNets. However just like RNNs, training …
an RNN, just as Neural ODEs are analogous to ResNets. However just like RNNs, training …
Adaptive attention for sparse-based long-sequence transformer
Recently, Transformers have been widely used in various fields and have achieved remarkable
results. But it is still difficult for Transformer-based models to process longer sequences …
results. But it is still difficult for Transformer-based models to process longer sequences …
Sparse universal transformer
The Universal Transformer (UT) is a variant of the Transformer that shares parameters across
its layers. Empirical evidence shows that UTs have better compositional generalization …
its layers. Empirical evidence shows that UTs have better compositional generalization …
LA VIE LITTÉRAIRE SOVIÉTIQUE
Z SCHAKOVSKOY - Revue des Deux Mondes (1829-1971), 1963 - JSTOR
… dans les lettres soviétiques, Alexandre Sourkov, faisant le point de … Pour Sourkov aussi, les
années soixante marquent un … par un dogmatique impénitent, Vsevolod Kotchetov, a paru, en …
années soixante marquent un … par un dogmatique impénitent, Vsevolod Kotchetov, a paru, en …
Exploring the Transcriptional and Translational Features Using Deep Neural Networks for mRNAs Classification
A Kefi, M Chukhman, V Karintha… - 2023 11th …, 2023 - ieeexplore.ieee.org
Recent advent of the second and third generation of sequencing has uncovered many
novel transcripts. These novel transcripts could have crucial functions in different biological …
novel transcripts. These novel transcripts could have crucial functions in different biological …