new version of the imputation of the single cell RNA

for single cell RNA seq it is necessary to do imputation so this is very useful

1. Paper Methodology Equations Summary
Font-Clos
et al.
(2021)
Boolean network
model
xi∈{0,1} for i=1,2,…,n, where xi is the state of
gene i. The regulatory relationships between
genes are represented by a set of logical rules: xi
=f(xi1,xi2,…,xik), where f is a Boolean function
and xi1,xi2,…,xik are the states of genes i1,i2,
…,ik.
A Boolean network model was
used to classify triple-negative
breast cancers. The model was
trained on gene expression data
from a set of 200 patients. The
model was able to correctly
classify 90% of the patients in
the test set.
Qiu (2020)
Dropout
regularization
p is the dropout rate, which is the probability of a
gene being set to zero during training.
Dropout regularization was
used to improve the
performance of single-cell
RNA-seq analysis. Dropout
regularization randomly sets a
subset of genes to zero during
training, which helps to
prevent the model from
overfitting the data.
Melkman
et al.
(2017)
Probabilistic
Boolean threshold
network
The regulatory relationships between genes are
represented by a set of probabilistic Boolean
rules: $P(x_i = 1 \$
x_{i_1}, x_{i_2}, \ldots,
x_{i_k}) = p, where p is the
probability that gene i is in the
on state if genes i1,i2,…,ik are
in the states xi1,xi2,…,xik,
respectively.
Cheng et
al. (2021)
Discrimination of
attractors with
The Hamming distance between two
attractors A and B is $d(A,B) = \sum_{i=1}^n \$
a_i - b_i\

2. noisy nodes
Anthony
(2001)
Discrete
mathematics of
neural networks
Boolean functions are functions that take on two
values: 0 or 1. They can be used to represent the
connections between neurons in a neural
network.
A discrete mathematics
approach to neural networks
was presented. The approach
was based on the use of
Boolean functions to represent
the connections between
neurons. The approach was
used to analyze the behavior of
a variety of neural networks.
Bornholdt
(2008)
Boolean network
models of cellular
regulation
Boolean network models are a type of
mathematical model that can be used to represent
the regulatory relationships between genes in a
cell. They have been used to study a variety of
biological processes, including cell cycle
regulation, gene expression, and signal
transduction.
Boolean network models of
cellular regulation were
reviewed. The review
discussed the advantages and
disadvantages of Boolean
network models, and it
presented a number of
examples of how Boolean
network models have been
used to study cellular
regulation.
Zañudo et
al. (2011)
Boolean threshold
networks: virtues
and limitations for
biological
modeling
Boolean threshold networks are a type of
Boolean network model in which the regulatory
relationships between genes are represented by a
set of logical rules that take the form of threshold
functions. They have been used to study a variety
of biological processes, including cell cycle
regulation, gene expression, and signal
Boolean threshold networks
were reviewed. The review
discussed the strengths and
weaknesses of Boolean
threshold networks, and it
presented a number of
examples of how Boolean

3. transduction.
threshold networks have been
used to model biological
systems.