Skip to content

Commit

Permalink
update thesis proposals
Browse files Browse the repository at this point in the history
  • Loading branch information
@viettr
viettr committed Jun 17, 2024
1 parent d20906d commit d1d471b
Show file tree
Hide file tree
Showing 2 changed files with 14 additions and 14 deletions.
Empty file removed .Rhistory
View file
Empty file.
28 changes: 14 additions & 14 deletions proposals.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -76,14 +76,14 @@ <h2></h2>
</section>
<div class="row">
<div class="span3">
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_CovidTensor.pdf">Analyzing covid-19 data as three-dimensional tensor</a></strong></p></span>
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://bio-datascience.github.io/msc_proposals//MScProposal_CovidTensor.pdf">Analyzing covid-19 data as three-dimensional tensor</a></strong></p></span>
<h6 align="justify">
The purpose of this M.Sc. thesis proposal is to retrospectively analyze the covid-19
incidence data from the German Robert-Koch-Intitut (RKI) in three dimensions: age, region and time.
This makes it possible to show which age groups were infected at which point in time in which parts of Germany.
To uncover age specific spatio-temporal patterns from the data, we consider the incidence data as a three-dimensional
tensor and apply non-negative tensor factorization.
You can read the full proposal <strong><a href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_CovidTensor.pdf" target="_blank">here</a></strong>
You can read the full proposal <strong><a href="https://bio-datascience.github.io/msc_proposals/MScProposal_CovidTensor.pdf" target="_blank">here</a></strong>
</h6>.
</div>
</div>
Expand All @@ -94,7 +94,7 @@ <h6 align="justify">

<div class="row">
<div class="span3">
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_microbiome_cardiovascular.pdf">Learning graphical models to explore the relationship between human gut microbiota and cardiovascular diseases</a></strong></p></span>
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://bio-datascience.github.io/msc_proposals/MScProposal_microbiome_cardiovascular.pdf">Learning graphical models to explore the relationship between human gut microbiota and cardiovascular diseases</a></strong></p></span>
<h6 align="justify">
Many diseases are multifactorial in origin, meaning that they are caused by
a combination of genetic and environmental components. These independent genetic
Expand All @@ -103,7 +103,7 @@ <h6 align="justify">
microbiome plays in these diseases remains unexplored. <br>
The purpose of this M.Sc. thesis is to explore the relationship between microbiome
composition and cardiovascular disease using state-of-art machine learning and
statistical methods. You can read the full proposal <strong><a href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_microbiome_cardiovascular.pdf" target="_blank">here</a></strong>
statistical methods. You can read the full proposal <strong><a href="https://bio-datascience.github.io/msc_proposals/MScProposal_microbiome_cardiovascular.pdf" target="_blank">here</a></strong>

</h6>.
</div>
Expand All @@ -115,7 +115,7 @@ <h6 align="justify">

<div class="row">
<div class="span3">
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposalGeneExpression.pdf">Prediction of gene expression in response to chemical stress</a></strong></p></span>
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://bio-datascience.github.io/msc_proposals/MScProposalGeneExpression.pdf">Prediction of gene expression in response to chemical stress</a></strong></p></span>
<h6 align="justify">
The purpose of this M.Sc. thesis proposal is to evaluate the effectiveness of different representations
of molecular structures at predicting the transcriptional response of human gut pathogens to different
Expand All @@ -124,7 +124,7 @@ <h6 align="justify">
<i>Campylobacter jejuni</i> have been measured in response to various chemical compounds.
<br>
The student will compare commonly used chemical representations such as the extended connectivity fingerprint (ECFP4), and chemical descriptors, to our previously described pre-trained chemical representation MolE.
You can read the full proposal <strong><a href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposalGeneExpression.pdf" target="_blank">here</a></strong>
You can read the full proposal <strong><a href="https://bio-datascience.github.io/msc_proposals/MScProposalGeneExpression.pdf" target="_blank">here</a></strong>

</h6>.
</div>
Expand All @@ -136,7 +136,7 @@ <h6 align="justify">

<div class="row">
<div class="span3">
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_hitpipeline.pdf">Statistical methods for the detection of gene expression induction in response to chemical stress</a></strong></p></span>
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://bio-datascience.github.io/msc_proposals/MScProposal_hitpipeline.pdf">Statistical methods for the detection of gene expression induction in response to chemical stress</a></strong></p></span>
<h6 align="justify">
The main objective of this M.Sc. thesis proposal is to develop a statistical pipeline
that detects chemical stress that significantly increases (or decreases)
Expand All @@ -145,7 +145,7 @@ <h6 align="justify">
<br>
Once “hits” are determined, the student will analyze the similarity between compounds based on their measured effects on gene expression via various clustering and network inference algorithms. At the same time,
detection of genetic regulatory circuits will be carried out with similar methods.
You can read the full proposal <strong><a href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_hitpipeline.pdf" target="_blank">here</a></strong>
You can read the full proposal <strong><a href="https://bio-datascience.github.io/msc_proposals/MScProposal_hitpipeline.pdf" target="_blank">here</a></strong>

</h6>.
</div>
Expand All @@ -157,14 +157,14 @@ <h6 align="justify">

<div class="row">
<div class="span3">
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_sparsifiedGAT.pdf">Interpretable chemical representations via sparsified Graph Attention Networks</a></strong></p></span>
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://bio-datascience.github.io/msc_proposals/MScProposal_sparsifiedGAT.pdf">Interpretable chemical representations via sparsified Graph Attention Networks</a></strong></p></span>
<h6 align="justify">
The main objective of this M.Sc. thesis proposal is to explore the use of the SparseMax function in the graph attention network (GAT) framework to generate an interpretable representation
of molecular structures to predict a certain outcome. Benchmarks will include various regression and classification tasks from MoleculeNet. We will also apply the model to the task of predicting
antimicrobial activity in the microbiome.
<br>
The student will determine if the use of SparseMax improves predictive performance over regular GATs.
You can read the full proposal <strong><a href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_sparsifiedGAT.pdf" target="_blank">here</a></strong>
You can read the full proposal <strong><a href="https://bio-datascience.github.io/msc_proposals/MScProposal_sparsifiedGAT.pdf" target="_blank">here</a></strong>

</h6>.
</div>
Expand All @@ -176,7 +176,7 @@ <h6 align="justify">

<div class="row">
<div class="span3">
<span class="byline"><strong><p style="font-size:23px"><a target="_blank" href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_alpha.pdf">Alpha diversity measures for microbiome data</a></strong></p></span>
<span class="byline"><strong><p style="font-size:23px"><a target="_blank" href="https://bio-datascience.github.io/msc_proposals/MScProposal_alpha.pdf">Alpha diversity measures for microbiome data</a></strong></p></span>
<h6 align="justify">
Complex microbiome samples can be summarized into a
single measure by alpha diversity indices, characterizing
Expand All @@ -190,7 +190,7 @@ <h6 align="justify">
measures for microbiome data from a statistical point of
view, and to compare these diversity measures on mock and
clinical microbiome data.
You can read the full proposal <strong><a href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_alpha.pdf" target="_blank">here</a></strong>
You can read the full proposal <strong><a href="https://bio-datascience.github.io/msc_proposals/MScProposal_alpha.pdf" target="_blank">here</a></strong>
</h6>.
</div>
</div>
Expand All @@ -201,10 +201,10 @@ <h6 align="justify">

<div class="row">
<div class="span3">
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_inference_highdimensional_microbiome_regression_analysis.pdf">Inference for high-dimensional microbiome regression analysis</a></strong></p></span>
<span class="byline"><p style="font-size:23px"><strong><a target="_blank" href="https://bio-datascience.github.io/msc_proposals/MScProposal_inference_highdimensional_microbiome_regression_analysis.pdf">Inference for high-dimensional microbiome regression analysis</a></strong></p></span>
<h6 align="justify">
The primary objective of this thesis is to implement and benchmark the FDR-controlled variable selection procedure for sparse log-contrast models, which is a constrained sparse regression model. This procedure is designed to identify microbial predictors while controlling for false discoveries, thereby enhancing the reliability of the results.
You can read the full proposal <strong><a href="https://github.com/bio-datascience/bio-datascience.github.io/blob/master/msc_proposals/MScProposal_inference_highdimensional_microbiome_regression_analysis.pdf" target="_blank">here</a></strong>
You can read the full proposal <strong><a href="https://bio-datascience.github.io/msc_proposals/MScProposal_inference_highdimensional_microbiome_regression_analysis.pdf" target="_blank">here</a></strong>

</h6>.
</div>
Expand Down

0 comments on commit d1d471b

Please sign in to comment.