UH Biocomputation Group - Manal Helalhttp://biocomputation.herts.ac.uk/2023-11-27T13:36:16+00:00Enhancing Deep Learning Models through Tensorization: A Comprehensive Survey and Framework2023-11-27T13:36:16+00:002023-11-27T13:36:16+00:00Manal Helaltag:biocomputation.herts.ac.uk,2023-11-27:/2023/11/27/enhancing-deep-learning-models-through-tensorization-a-comprehensive-survey-and-framework.html<p class="first last">Manal Helal's Journal Club session where she will talk about her under-review draft paper "Enhancing Deep Learning Models through Tensorization: A Comprehensive Survey and Framework".</p>
<p>On this week's Journal Club session, Manal Helal will talk about her under-review draft paper "Enhancing Deep Learning Models through Tensorization: A Comprehensive Survey and Framework".</p>
<hr class="docutils" />
<p>The burgeoning growth of public domain data and the increasing complexity of deep learning
model architectures have underscored the need for more efficient data representation and
analysis techniques. This paper is motivated by the work of (Helal, 2023) and aims to
present a comprehensive overview of tensorization. This transformative approach bridges
the gap between the inherently multidimensional nature of data and the simplified
2-dimensional matrices commonly used in linear algebra-based machine learning algorithms.
This paper explores the steps involved in tensorization, multidimensional data sources,
various multiway analysis methods employed, and the benefits of these approaches. A small
example of Blind Source Separation (BSS) is presented comparing 2-dimensional algorithms
and a multiway algorithm in Python. Results indicate that multiway analysis is more
expressive. Contrary to the intuition of the dimensionality curse, utilising
multidimensional datasets in their native form and applying multiway analysis methods
grounded in multilinear algebra reveal a profound capacity to capture intricate
interrelationships among various dimensions while, surprisingly, reducing the number of
model parameters and accelerating processing. A survey of the multi-away analysis methods
and integration with various Deep Neural Networks models is presented using case studies
in different application domains.</p>
<div class="line-block">
<div class="line"><br /></div>
</div>
<p>References:</p>
<ul class="simple">
<li>M. Helal, <a class="reference external" href="https://doi.org/10.48550/arXiv.2309.02428">"Enhancing Deep Learning Models through Tensorization: A Comprehensive Survey and Framework"</a>, 2023, arXiv,</li>
<li>M. Helal, "Introduction to Tensor Computing in Python: From First Principles to Deep Learning"
Book published by Amazon Publishing PROS, 2023. IBSN:978-1-916626-33-1</li>
</ul>
<p><strong>Date:</strong> 2023/12/01 <br />
<strong>Time:</strong> 14:00 <br />
<strong>Location</strong>: 2J124 & online</p>
miRe2e: A Full End-to-End Deep Model Based on Transformers for Prediction of Pre-miRNAs2023-02-08T13:28:44+00:002023-02-08T13:28:44+00:00Manal Helaltag:biocomputation.herts.ac.uk,2023-02-08:/2023/02/08/mire2e-a-full-end-to-end-deep-model-based-on-transformers-for-prediction-of-pre-mirnas.html<p class="first last">Manal Helal's Journal Club session where she will talk about a paper "miRe2e: A Full End-to-End Deep Model Based on Transformers for Prediction of Pre-miRNAs"</p>
<p>This week on Journal Club session Manal Helal will talk about a paper "miRe2e: A Full End-to-End Deep Model Based on Transformers for Prediction of Pre-miRNAs".</p>
<hr class="docutils" />
<p><strong>Motivation</strong></p>
<p>MicroRNAs (miRNAs) are small RNA sequences with key roles in the regulation of
gene expression at post-transcriptional level in different species. Accurate
prediction of novel miRNAs is needed due to their importance in many biological
processes and their associations with complicated diseases in humans. Many
machine learning approaches were proposed in the last decade for this purpose,
but requiring handcrafted features extraction to identify possible de novo
miRNAs. More recently, the emergence of deep learning (DL) has allowed the
automatic feature extraction, learning relevant representations by themselves.
However, the state-of-art deep models require complex pre-processing of the
input sequences and prediction of their secondary structure to reach an
acceptable performance.</p>
<p><strong>Results</strong></p>
<p>In this work, we present miRe2e, the first full end-to-end DL model for
pre-miRNA prediction. This model is based on Transformers, a neural
architecture that uses attention mechanisms to infer global dependencies
between inputs and outputs. It is capable of receiving the raw genome-wide data
as input, without any pre-processing nor feature engineering. After a training
stage with known pre-miRNAs, hairpin and non-harpin sequences, it can identify
all the pre-miRNA sequences within a genome. The model has been validated
through several experimental setups using the human genome, and it was compared
with state-of-the-art algorithms obtaining 10 times better performance.</p>
<div class="line-block">
<div class="line"><br /></div>
</div>
<p>Papers:</p>
<ul class="simple">
<li>J. Raad, L. Bugnon, D. Milone, G. Stegmayer, <a class="reference external" href="https://doi.org/10.1093/bioinformatics/btab823">"miRe2e: A Full End-to-End Deep
Model Based on Transformers for Prediction of Pre-miRNAs"</a>, 2022, Bioinformatics,
38, 1191--1197</li>
</ul>
<p><strong>Date:</strong> 2023/02/10 <br />
<strong>Time:</strong> 14:00 <br />
<strong>Location</strong>: online</p>
Tensor Decomposition with Relational Constraints for Predicting Multiple Types of microRNA-disease Associations2022-05-11T13:41:48+01:002022-05-11T13:41:48+01:00Manal Helaltag:biocomputation.herts.ac.uk,2022-05-11:/2022/05/11/tensor-decomposition-with-relational-constraints-for-predicting-multiple-types-of-microrna-disease-associations.html<p class="first last">Manal Helal's Journal Club session where he will talk about a paper "Tensor Decomposition with Relational Constraints for Predicting Multiple Types of microRNA-disease Associations"</p>
<p>This week on Journal Club session Manal Helal will talk about a paper "Tensor
Decomposition with Relational Constraints for Predicting Multiple Types of
microRNA-disease Associations".</p>
<hr class="docutils" />
<p>MicroRNAs (miRNAs) play crucial roles in multifarious biological processes
associated with human diseases. Identifying potential miRNA-disease
associations contributes to understanding the molecular mechanisms of
miRNA-related diseases. Most of the existing computational methods mainly focus
on predicting whether a miRNA-disease association exists or not. However, the
roles of miRNAs in diseases are prominently diverged, for instance, Genetic
variants of microRNA (mir-15) may affect expression level of miRNAs leading to
B cell chronic lymphocytic leukemia, while circulating miRNAs (including
mir-1246, mir-1307-3p, etc.) have potentials to detecting breast cancer in the
early stage. In this paper, we aim to predict multi-type miRNA-disease
associations instead of taking them as binary. To this end, we innovatively
represent miRNA-disease-type triplets as a tensor and introduce Tensor
Decomposition methods to solve the prediction task. Experimental results on two
widely-adopted miRNA-disease datasets: HMDD v2.0 and HMDD v3.2 show that tensor
decomposition methods improve a recent baseline in a large scale (up to 38% in
top-1 F1). We further propose a novel method, Tensor Decomposition with
Relational Constraints (TDRC), which incorporates biological features as
relational constraints to further the existing tensor decomposition methods.
Compared with two existing tensor decomposition methods, TDRC can produce
better performance while being more efficient.</p>
<div class="line-block">
<div class="line"><br /></div>
</div>
<p>Papers:</p>
<ul class="simple">
<li>F. Huang, X. Yue, Z. Xiong, Z. Yu, S. Liu, W. Zhang, <a class="reference external" href="https://doi.org/10.1093/bib/bbaa140">"Tensor Decomposition
with Relational Constraints for Predicting Multiple Types of microRNA-disease
Associations"</a>, 2021,
Briefings in Bioinformatics, 22, bbaa140</li>
</ul>
<p><strong>Date:</strong> 2022/05/13 <br />
<strong>Time:</strong> 14:00 <br />
<strong>Location</strong>: online</p>
Spinal Muscle Atrophy Disease Modelling as Bayesian Network2021-10-06T12:07:55+01:002021-10-06T12:07:55+01:00Manal Helaltag:biocomputation.herts.ac.uk,2021-10-06:/2021/10/06/spinal-muscle-atrophy-disease-modelling-as-bayesian-network.html<p class="first last">Manal Helal's Journal Club session where she will talk about her current work on "Spinal Muscle Atrophy Disease Modelling as Bayesian Network"</p>
<p>This week on Journal Club session Manal Helal will talk about her current work on "Spinal Muscle Atrophy Disease Modelling as Bayesian Network".</p>
<hr class="docutils" />
<p>We investigate the molecular gene expressions studies and public databases for
disease modelling using Probabilistic Graphical Models and Bayesian Inference.
A case study on Spinal Muscle Atrophy Genome-Wide Association Study results is
modelled and analyzed. The genes up and down-regulated in 2 stages of the
disease development are linked to prior knowledge published in the public
domain and co-expressions network is created and analyzed. The Molecular
Pathways triggered by these genes are identified. The Bayesian inference
posteriors distributions are estimated using a variational analytical algorithm
and a Markov chain Monte Carlo sampling algorithm. Assumptions, limitations and
possible future work are concluded.</p>
<div class="line-block">
<div class="line"><br /></div>
</div>
<p><strong>Date:</strong> 2021/10/08 <br />
<strong>Time:</strong> 14:00 <br />
<strong>Location</strong>: online</p>