Page 370 - Special Topic Session (STS) - Volume 4

STS1080 Mahmoud Rafea et al.
dataset shows the human hormones (ER, PR, and HER-2), the metastases of
cancer (liver, brain, bone, and ovary), and treatment to the patient
(chemotherapy and radiotherapy). They categorized NED and ED to detect the
relationship between the different factors mentioned above. This paper is
useful for knowing the main important factor which influences the patient.
In [9], it was provided a computational study, based on the Apriori
algorithm to discover the associations among clinical traits and risk factors of
asthma disease. The experiment was done on the original dataset collected
from the asthma patients. They identified association among four attributes a
cough, wheezing, running nose and stuffy nose. The Apriori algorithm was
used to find the frequent symptoms and related causes of asthma disease
from the dataset that was collected from the self-reported asthma patients.
The remaining attributes like breathing shortness, dust allergy, skin allergy,
fruit allergy and allergy to air conditioner may be considered for further
analysis. Additional features such as the nature of foods, living environment,
working environment, stress, and other related diseases may be considered.

3. Biomarkers Discovery
a. Proteomics
Proteomics-science identifies and characterizes protein expression in
biological systems. Due to the limitations of studying DNA and RNA alone,
Proteomics has been gaining full energy and trust. Gene sequences also can
give little information about how much of its transcribed protein will be
expressed and in what cellular states. By the usage of proteomics, studying
gene expression at the protein level can achieve complementary knowledge
at the nucleic acid level. Proteins are more diverse than DNA or RNA and
therefore carry more information than nucleic acids, since alternative splicing
and more than 100 unique post-translational modifications result in tens (and
possibly hundreds) of species of protein from each gene [10].
Clinical proteomics is the application of proteomic techniques to the field
of medicine with the aim of solving a specific clinical problem. The study of
clinical proteomic may provide us with opportunities in more effective
strategies for early disease detection and monitoring, more effective therapies,
and developing a better understanding of disease pathogenesis [11]. Such
studies may aim at earlier or more accurate diagnosis, improvement of
therapeutic strategies, and better evaluation of prognosis and/or prevention
of the disease. Although clinical proteomics currently mainly focuses on
diagnostics and biomarker discovery, it includes the identification of new
therapeutic targets, drugs, and vaccines for better therapeutic outcomes and
successful disease prevention. [12].
The application of clinical proteomic research is growing rapidly in the field
of biomarker discovery, especially in the area of cancer diagnostics. Clinical
proteomics holds the potential of taking a snapshot of the total protein

359 | I S I W S C 2 0 1 9