coolneng
/
master-thesis
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update bibliography

This commit is contained in:
coolneng 2022-10-20 14:23:02 +02:00
parent c1fe9158ce
commit 59529f5142
Signed by: coolneng
GPG Key ID: 9893DA236405AF57
2 changed files with 371 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

203
docs/Bibliography.org
View File

@ -5,8 +5,7 @@
#+OPTIONS: <:nil c:nil todo:nil H:5
#+auto_tangle: t
* Deep Learning
** Transformers
*** Attention is All You Need
** Attention is All You Need
#+begin_src bibtex
@article{https://doi.org/10.48550/arxiv.1706.03762,
doi = {10.48550/ARXIV.1706.03762},
@ -25,7 +24,7 @@
#+end_src
#+LaTeX: \printbibliography[heading=none]
*** Axial Attention in Multidimensional Transformers
** Axial Attention in Multidimensional Transformers
#+begin_src bibtex
@article{https://doi.org/10.48550/arxiv.1912.12180,
doi = {10.48550/ARXIV.1912.12180},
@ -41,7 +40,7 @@
copyright = {arXiv.org perpetual, non-exclusive license}
}
#+end_src
*** Longformer: The Long-Document Transformer
** Longformer: The Long-Document Transformer
#+begin_src bibtex
@article{https://doi.org/10.48550/arxiv.2004.05150,
doi = {10.48550/ARXIV.2004.05150},
@ -55,7 +54,7 @@
copyright = {arXiv.org perpetual, non-exclusive license}
}
#+end_src
*** Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
** Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
#+begin_src bibtex
@article{https://doi.org/10.48550/arxiv.1901.02860,
doi = {10.48550/ARXIV.1901.02860},
@ -73,7 +72,7 @@
International}
}
#+end_src
*** BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
** BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
#+begin_src bibtex
@inproceedings{devlin-etal-2019-bert,
title = "{BERT}: Pre-training of Deep Bidirectional Transformers for
@ -112,7 +111,7 @@
#+end_src
A masked language model (MLM) randomly masks some of the tokens from the input, and the objective is to predict the original input based only on its context.
*** Fast Transformers with Clustered Attention
** Fast Transformers with Clustered Attention
#+begin_src bibtex
@article{https://doi.org/10.48550/arxiv.2007.04825,
doi = {10.48550/ARXIV.2007.04825},
@ -128,7 +127,7 @@ A masked language model (MLM) randomly masks some of the tokens from the input,
copyright = {arXiv.org perpetual, non-exclusive license}
}
#+end_src
*** The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?
** The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?
#+begin_src bibtex
@inproceedings{bastings-filippova-2020-elephant,
title = "The elephant in the interpretability room: Why use
@ -160,7 +159,59 @@ A masked language model (MLM) randomly masks some of the tokens from the input,
state the goal and user for their explanations.",
}
#+end_src
** MultiMAE: Multi-modal Multi-task Masked Autoencoders
#+begin_src bibtex
@article{https://doi.org/10.48550/arxiv.2204.01678,
doi = {10.48550/ARXIV.2204.01678},
url = {https://arxiv.org/abs/2204.01678},
author = {Bachmann, Roman and Mizrahi, David and Atanov, Andrei and
Zamir, Amir},
keywords = {Computer Vision and Pattern Recognition (cs.CV), Machine
Learning (cs.LG), FOS: Computer and information sciences, FOS:
Computer and information sciences},
title = {MultiMAE: Multi-modal Multi-task Masked Autoencoders},
publisher = {arXiv},
year = 2022,
copyright = {arXiv.org perpetual, non-exclusive license}
}
#+end_src
* Deep Learning + Biology
** CpG Transformer for imputation of single-cell methylomes
#+begin_src bibtex
@article{10.1093/bioinformatics/btab746,
author = {De Waele, Gaetan and Clauwaert, Jim and Menschaert, Gerben
and Waegeman, Willem},
title = "{CpG Transformer for imputation of single-cell methylomes}",
journal = {Bioinformatics},
volume = 38,
number = 3,
pages = {597-603},
year = 2021,
month = 10,
abstract = "{The adoption of current single-cell DNA methylation
sequencing protocols is hindered by incomplete coverage,
outlining the need for effective imputation techniques. The
task of imputing single-cell (methylation) data requires
models to build an understanding of underlying biological
processes.We adapt the transformer neural network architecture
to operate on methylation matrices through combining axial
attention with sliding window self-attention. The obtained CpG
Transformer displays state-of-the-art performances on a wide
range of scBS-seq and scRRBS-seq datasets. Furthermore, we
demonstrate the interpretability of CpG Transformer and
illustrate its rapid transfer learning properties, allowing
practitioners to train models on new datasets with a limited
computational and time budget.CpG Transformer is freely
available at
https://github.com/gdewael/cpg-transformer.Supplementary data
are available at Bioinformatics online.}",
issn = {1367-4803},
doi = {10.1093/bioinformatics/btab746},
url = {https://doi.org/10.1093/bioinformatics/btab746},
eprint =
{https://academic.oup.com/bioinformatics/article-pdf/38/3/597/42167564/btab746.pdf},
}
#+end_src
** MSA Transformer
#+begin_src bibtex
@article {Rao2021.02.12.430858,
@ -255,4 +306,140 @@ A masked language model (MLM) randomly masks some of the tokens from the input,
url = {https://doi.org/10.1038/s41586-021-03819-2}
}
#+end_src
** MultiVI: deep generative model for the integration of multi-modal data
#+begin_src bibtex
@article {Ashuach2021.08.20.457057,
author = {Ashuach, Tal and Gabitto, Mariano I. and Jordan, Michael I.
and Yosef, Nir},
title = {MultiVI: deep generative model for the integration of
multi-modal data},
elocation-id = {2021.08.20.457057},
year = 2021,
doi = {10.1101/2021.08.20.457057},
publisher = {Cold Spring Harbor Laboratory},
abstract = {Jointly profiling the transcriptional and chromatin
accessibility landscapes of single-cells is a powerful
technique to characterize cellular populations. Here we
present MultiVI, a probabilistic model to analyze such
multiomic data and integrate it with single modality datasets.
MultiVI creates a joint representation that accurately
reflects both chromatin and transcriptional properties of the
cells even when one modality is missing. It also imputes
missing data, corrects for batch effects and is available in
the scvi-tools framework:
https://docs.scvi-tools.org/.Competing Interest StatementThe
authors have declared no competing interest.},
URL =
{https://www.biorxiv.org/content/early/2021/09/07/2021.08.20.457057},
eprint =
{https://www.biorxiv.org/content/early/2021/09/07/2021.08.20.457057.full.pdf},
journal = {bioRxiv}
}
#+end_src
* Biology
** Cobolt: integrative analysis of multimodal single-cell sequencing data
#+begin_src bibtex
@article{Gong2021,
author = {Gong, Boying and Zhou, Yun and Purdom, Elizabeth},
title = {Cobolt: integrative analysis of multimodal single-cell
sequencing data},
journal = {Genome Biology},
year = 2021,
month = {Dec},
day = 28,
volume = 22,
number = 1,
pages = 351,
abstract = {A growing number of single-cell sequencing platforms enable
joint profiling of multiple omics from the same cells. We
present Cobolt, a novel method that not only allows for
analyzing the data from joint-modality platforms, but provides
a coherent framework for the integration of multiple datasets
measured on different modalities. We demonstrate its
performance on multi-modality data of gene expression and
chromatin accessibility and illustrate the integration
abilities of Cobolt by jointly analyzing this multi-modality
data with single-cell RNA-seq and ATAC-seq datasets.},
issn = {1474-760X},
doi = {10.1186/s13059-021-02556-z},
url = {https://doi.org/10.1186/s13059-021-02556-z}
}
#+end_src
** MUON: multimodal omics analysis framework
#+begin_src bibtex
@article{Bredikhin2022,
author = {Bredikhin, Danila and Kats, Ilia and Stegle, Oliver},
title = {MUON: multimodal omics analysis framework},
journal = {Genome Biology},
year = 2022,
month = {Feb},
day = 01,
volume = 23,
number = 1,
pages = 42,
abstract = {Advances in multi-omics have led to an explosion of
multimodal datasets to address questions from basic biology to
translation. While these data provide novel opportunities for
discovery, they also pose management and analysis challenges,
thus motivating the development of tailored computational
solutions. Here, we present a data standard and an analysis
framework for multi-omics, MUON, designed to organise,
analyse, visualise, and exchange multimodal data. MUON stores
multimodal data in an efficient yet flexible and interoperable
data structure. MUON enables a versatile range of analyses,
from data preprocessing to flexible multi-omics alignment.},
issn = {1474-760X},
doi = {10.1186/s13059-021-02577-8},
url = {https://doi.org/10.1186/s13059-021-02577-8}
}
#+end_src
** Multimodal single cell data integration challenge: Results and lessons learned
#+begin_src bibtex
@inproceedings{pmlr-v176-lance22a,
title = {Multimodal single cell data integration challenge: Results
and lessons learned},
author = {Lance, Christopher and Luecken, Malte D. and Burkhardt,
Daniel B. and Cannoodt, Robrecht and Rautenstrauch, Pia and
Laddach, Anna and Ubingazhibov, Aidyn and Cao, Zhi-Jie and
Deng, Kaiwen and Khan, Sumeer and Liu, Qiao and Russkikh,
Nikolay and Ryazantsev, Gleb and Ohler, Uwe and data
integration competition participants, NeurIPS 2021 Multimodal
and Pisco, Angela Oliveira and Bloom, Jonathan and
Krishnaswamy, Smita and Theis, Fabian J.},
booktitle = {Proceedings of the NeurIPS 2021 Competitions and
Demonstrations Track},
pages = {162--176},
year = 2022,
editor = {Kiela, Douwe and Ciccone, Marco and Caputo, Barbara},
volume = 176,
series = {Proceedings of Machine Learning Research},
month = {06--14 Dec},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v176/lance22a/lance22a.pdf},
url = {https://proceedings.mlr.press/v176/lance22a.html},
abstract = {Biology has become a data-intensive science. Recent
technological advances in single-cell genomics have enabled
the measurement of multiple facets of cellular state,
producing datasets with millions of single-cell observations.
While these data hold great promise for understanding
molecular mechanisms in health and disease, analysis
challenges arising from sparsity, technical and biological
variability, and high dimensionality of the data hinder the
derivation of such mechanistic insights. To promote the
innovation of algorithms for analysis of multimodal
single-cell data, we organized a competition at NeurIPS 2021
applying the Common Task Framework to multimodal single-cell
data integration. For this competition we generated the first
multimodal benchmarking dataset for single-cell biology and
defined three tasks in this domain: prediction of missing
modalities, aligning modalities, and learning a joint
representation across modalities. We further specified
evaluation metrics and developed a cloud-based algorithm
evaluation pipeline. Using this setup, 280 competitors
submitted over 2600 proposed solutions within a 3 month
period, showcasing substantial innovation especially in the
modality alignment task. Here, we present the results,
describe trends of well performing approaches, and discuss
challenges associated with running the competition.}
}
#+end_src

176
docs/bibliography.bib
View File

@ -134,6 +134,54 @@
state the goal and user for their explanations.",
}
@article{https://doi.org/10.48550/arxiv.2204.01678,
doi = {10.48550/ARXIV.2204.01678},
url = {https://arxiv.org/abs/2204.01678},
author = {Bachmann, Roman and Mizrahi, David and Atanov, Andrei and
Zamir, Amir},
keywords = {Computer Vision and Pattern Recognition (cs.CV), Machine
Learning (cs.LG), FOS: Computer and information sciences, FOS:
Computer and information sciences},
title = {MultiMAE: Multi-modal Multi-task Masked Autoencoders},
publisher = {arXiv},
year = 2022,
copyright = {arXiv.org perpetual, non-exclusive license}
}
@article{10.1093/bioinformatics/btab746,
author = {De Waele, Gaetan and Clauwaert, Jim and Menschaert, Gerben
and Waegeman, Willem},
title = "{CpG Transformer for imputation of single-cell methylomes}",
journal = {Bioinformatics},
volume = 38,
number = 3,
pages = {597-603},
year = 2021,
month = 10,
abstract = "{The adoption of current single-cell DNA methylation
sequencing protocols is hindered by incomplete coverage,
outlining the need for effective imputation techniques. The
task of imputing single-cell (methylation) data requires
models to build an understanding of underlying biological
processes.We adapt the transformer neural network architecture
to operate on methylation matrices through combining axial
attention with sliding window self-attention. The obtained CpG
Transformer displays state-of-the-art performances on a wide
range of scBS-seq and scRRBS-seq datasets. Furthermore, we
demonstrate the interpretability of CpG Transformer and
illustrate its rapid transfer learning properties, allowing
practitioners to train models on new datasets with a limited
computational and time budget.CpG Transformer is freely
available at
https://github.com/gdewael/cpg-transformer.Supplementary data
are available at Bioinformatics online.}",
issn = {1367-4803},
doi = {10.1093/bioinformatics/btab746},
url = {https://doi.org/10.1093/bioinformatics/btab746},
eprint =
{https://academic.oup.com/bioinformatics/article-pdf/38/3/597/42167564/btab746.pdf},
}
@article {Rao2021.02.12.430858,
author = {Rao, Roshan and Liu, Jason and Verkuil, Robert and Meier,
Joshua and Canny, John F. and Abbeel, Pieter and Sercu, Tom
@ -223,3 +271,131 @@
doi = {10.1038/s41586-021-03819-2},
url = {https://doi.org/10.1038/s41586-021-03819-2}
}
@article {Ashuach2021.08.20.457057,
author = {Ashuach, Tal and Gabitto, Mariano I. and Jordan, Michael I.
and Yosef, Nir},
title = {MultiVI: deep generative model for the integration of
multi-modal data},
elocation-id = {2021.08.20.457057},
year = 2021,
doi = {10.1101/2021.08.20.457057},
publisher = {Cold Spring Harbor Laboratory},
abstract = {Jointly profiling the transcriptional and chromatin
accessibility landscapes of single-cells is a powerful
technique to characterize cellular populations. Here we
present MultiVI, a probabilistic model to analyze such
multiomic data and integrate it with single modality datasets.
MultiVI creates a joint representation that accurately
reflects both chromatin and transcriptional properties of the
cells even when one modality is missing. It also imputes
missing data, corrects for batch effects and is available in
the scvi-tools framework:
https://docs.scvi-tools.org/.Competing Interest StatementThe
authors have declared no competing interest.},
URL =
{https://www.biorxiv.org/content/early/2021/09/07/2021.08.20.457057},
eprint =
{https://www.biorxiv.org/content/early/2021/09/07/2021.08.20.457057.full.pdf},
journal = {bioRxiv}
}
@article{Gong2021,
author = {Gong, Boying and Zhou, Yun and Purdom, Elizabeth},
title = {Cobolt: integrative analysis of multimodal single-cell
sequencing data},
journal = {Genome Biology},
year = 2021,
month = {Dec},
day = 28,
volume = 22,
number = 1,
pages = 351,
abstract = {A growing number of single-cell sequencing platforms enable
joint profiling of multiple omics from the same cells. We
present Cobolt, a novel method that not only allows for
analyzing the data from joint-modality platforms, but provides
a coherent framework for the integration of multiple datasets
measured on different modalities. We demonstrate its
performance on multi-modality data of gene expression and
chromatin accessibility and illustrate the integration
abilities of Cobolt by jointly analyzing this multi-modality
data with single-cell RNA-seq and ATAC-seq datasets.},
issn = {1474-760X},
doi = {10.1186/s13059-021-02556-z},
url = {https://doi.org/10.1186/s13059-021-02556-z}
}
@article{Bredikhin2022,
author = {Bredikhin, Danila and Kats, Ilia and Stegle, Oliver},
title = {MUON: multimodal omics analysis framework},
journal = {Genome Biology},
year = 2022,
month = {Feb},
day = 01,
volume = 23,
number = 1,
pages = 42,
abstract = {Advances in multi-omics have led to an explosion of
multimodal datasets to address questions from basic biology to
translation. While these data provide novel opportunities for
discovery, they also pose management and analysis challenges,
thus motivating the development of tailored computational
solutions. Here, we present a data standard and an analysis
framework for multi-omics, MUON, designed to organise,
analyse, visualise, and exchange multimodal data. MUON stores
multimodal data in an efficient yet flexible and interoperable
data structure. MUON enables a versatile range of analyses,
from data preprocessing to flexible multi-omics alignment.},
issn = {1474-760X},
doi = {10.1186/s13059-021-02577-8},
url = {https://doi.org/10.1186/s13059-021-02577-8}
}
@inproceedings{pmlr-v176-lance22a,
title = {Multimodal single cell data integration challenge: Results
and lessons learned},
author = {Lance, Christopher and Luecken, Malte D. and Burkhardt,
Daniel B. and Cannoodt, Robrecht and Rautenstrauch, Pia and
Laddach, Anna and Ubingazhibov, Aidyn and Cao, Zhi-Jie and
Deng, Kaiwen and Khan, Sumeer and Liu, Qiao and Russkikh,
Nikolay and Ryazantsev, Gleb and Ohler, Uwe and data
integration competition participants, NeurIPS 2021 Multimodal
and Pisco, Angela Oliveira and Bloom, Jonathan and
Krishnaswamy, Smita and Theis, Fabian J.},
booktitle = {Proceedings of the NeurIPS 2021 Competitions and
Demonstrations Track},
pages = {162--176},
year = 2022,
editor = {Kiela, Douwe and Ciccone, Marco and Caputo, Barbara},
volume = 176,
series = {Proceedings of Machine Learning Research},
month = {06--14 Dec},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v176/lance22a/lance22a.pdf},
url = {https://proceedings.mlr.press/v176/lance22a.html},
abstract = {Biology has become a data-intensive science. Recent
technological advances in single-cell genomics have enabled
the measurement of multiple facets of cellular state,
producing datasets with millions of single-cell observations.
While these data hold great promise for understanding
molecular mechanisms in health and disease, analysis
challenges arising from sparsity, technical and biological
variability, and high dimensionality of the data hinder the
derivation of such mechanistic insights. To promote the
innovation of algorithms for analysis of multimodal
single-cell data, we organized a competition at NeurIPS 2021
applying the Common Task Framework to multimodal single-cell
data integration. For this competition we generated the first
multimodal benchmarking dataset for single-cell biology and
defined three tasks in this domain: prediction of missing
modalities, aligning modalities, and learning a joint
representation across modalities. We further specified
evaluation metrics and developed a cloud-based algorithm
evaluation pipeline. Using this setup, 280 competitors
submitted over 2600 proposed solutions within a 3 month
period, showcasing substantial innovation especially in the
modality alignment task. Here, we present the results,
describe trends of well performing approaches, and discuss
challenges associated with running the competition.}
}