CONTENT

1
Introduction to genetic
disorder
2
Gene therapy
3
Viruses and modified
virus
4examples
genetic diseases and
5
AI functionality
in Genetic Engineering
treatment
 GENETIC DISORDER
• A genetic disorder is a disease caused in whole or in part by a change in the DNA sequence away from the
normal sequence.

• Genetic disorders can be caused by a mutation in one gene (monogenic disorder), by mutations in multiple
genes (multifactorial inheritance disorder),
by a combination of gene mutations and environmental factors, or by damage to
chromosomes (changes in the number or structure)

• Some diseases are caused by mutations that are inherited from the parents and are present in an individual
at birth
 GENETIC DISORDER
DNA: is a biological macromolecule that carries hereditary information
in many organisms
for the development and functioning of an organism.

Gene: is considered the basic unit of inheritance. Genes are passed

from parents to offspring and contain the information needed to
specify physical and biological traits.
Most genes code for specific proteins, or segments of proteins,
which have differing functions within the body.
HOW TO HANDLE GENETIC DISORDERS

01 GENE THERAPY

Gene therapy is an experimental technique that uses genes to treat or prevent

disease.

gene therapy try to intraduct a new normal gene into an individual’s genome in
order to repair a mutation that causes a genetic disease. (replacement to
Damaged gene ),Inactivating the affected gene or editing Damaged gene
HOW GENE THERAPY
WORK
Genetically modified virus
In 2001, it was reported that genetically
modified viruses can possibly be used to
modify human genes by using a proven safe
vaccine virus, such as adenovirus, and modify
its genome to include desired gene to handle
genes disorder
HOW VIRUSES INVADE CELLS ?

1. A virus particle attaches to cell.

2. The particle releases its genetic instructions into the cell.
3. The injected genetic material recruits the cell's enzymes.
4. The enzymes make parts for more new virus particles.
5. The new particles assemble the parts into new viruses cells.
CHALLENGES THAT FACING SCIENTISTS

• In some cases, the immune system attacks

modified viruses

• The appearance of disturbances in the

behavior of modified cells
SICKLE CELL DISEASE

Sickle cell disease is the most common inherited blood disorder. Sickle
cell disease is caused by a mutation in the hemoglobin-Beta gene found
on chromosome 11. Hemoglobin transports oxygen from the lungs to
other parts of the body.
 SICKLE CELL DISEASE
• Red blood cells with normal hemoglobin (hemoglobin-A) are smooth and
round and glide through blood vessels.

• In people with sickle cell disease, abnormal hemoglobin molecules -

hemoglobin S - stick to one another and form long, rod-like structures.

• These structures cause red blood cells to become stiff, assuming a sickle
shape. Their shape causes these red blood cells to pile up , block the flow of
blood through vessels, causing blockages and damaging vital organs and
tissue
INHERITANCE OF SICKLE CELL DISEASE
• A baby born with sickle cell disease inherits a gene for the
disorder from both parents. When both parents have the
genetic defect (Hbs)

• if a child inherits only one copy of the defective gene (from

either parent), there is a 50 percent chance that the child will
carry the sickle cell trait.

• People who only carry the sickle cell trait typically don't get
the disease
HEMOGLOBIN SEQUENCE
 HEMOGLOBIN MUTATIONS

• The disease. Develop When Both Copies are mutated Producing abnormal beta globin

• The two Copy maybe mutated different, Producing 2 different form of abnormal Beta subunits in the same person

• various combination of these mutation produce different forms of sickle cell diseases

• the most common and also most sever called sickle cell anemia is caused by 2 copies of the same mutation
preducing the mutated hemoglobin S each copy come from parent
Hemoglobin-S VS Hemoglobin-A
SYMPTOMS OF SICKLE CELL DISEASE
1. Anemia
2. Pain attacks
3. Swelling of the hand and foot
4. Damage to the liver, heart, kidneys, vision and eyes
5. Bone damage as a result of the bone marrow's attempts to produce
large amounts of blood cells
6. Problems with the spleen due to the presence of large amounts of
dead cells
7. Easily exposed to infections due to weak immune system functions
8. Stroke due to lack of oxygen
 TREATMENT APPROACHES

• Gene therapy approach

• Bone Marrow Transplantation approach

 GENE THERAPY APPROACH

Gene therapies use your own stem cells , in gene therapy your stem cells are changed by
altering part of your genes.

Types of gene therapy include

gene addition and gene editing.
There are two types of gene editing: gene silencing and gene correction.
 GENE ADDITION

Patient stem cells are collected and taken to a lab for modification. An
extra copy of a hemoglobin A gene (without the variant) is added to the
stem cell, which allows your cells to produce hemoglobin A (non-
sickling hemoglobin).
 GENE EDITING

Gene silencing
Patient stem cells are collected and taken to a lab for modification. The
gene that produces the BCL11A-blocking protein, which inactivates
hemoglobin F, is silenced. By silencing this gene, the gene that makes
hemoglobin F can be activated, which allows your cells to produce
hemoglobin F (non- sickling).
 GENE EDITING

gene correction
Patient stem cells are collected and taken to a lab for modification. The
variant in the gene that causes sickle cell disease is corrected so that it
codes for a non- sickling hemoglobin.
 BONE MARROW TRANSPLANTATION

In a bone marrow transplant, also called a stem cell transplant, your stem cells are replaced with
new stem cells that have genes that do not code for sickle cell disease. In this procedure a sick
patient is transplanted with bone marrow from healthy, genetically compatible sibling donors.
 RETINITIS PIGMENTOSA
Retinitis pigmentosa (RP) is the name given to a group of inherited eye diseases that affect the retina (the light-sensitive
part of the eye).
RP causes the breakdown of photoreceptor cells (the light –sensitive rods and cones in the retina)
• rods (retinal cells that detect dim light)
• cones (retinal cells that detect light and color)

Most forms of RP first cause the breakdown of rod cells ,These forms of RP usually begin with
night blindness.

RP patients mainly suffers from night blindness ( nyctalopia)and peripheral vision loss that can
lead to central vision loss .
 WHAT CAUSES RETINITIS PIGMENTOSA?

• RP is most frequently the result of genetic mutations in rod photoreceptors.

• More than 70 genes with more than 3000 mutations pheno typically present as RP.
• (RHO) was the first gene mutation identified as a cause of RP .
• More than 150 different RHO mutations are associated with 25% of autosomal dominant (RP) cases.
• RHO mutation is the most common cause of RP
 THE RHO GENE

• The RHO gene transcribes the RHO protein, which is the major visual pigment in the outer segment of rod
photoreceptors.
• It absorbs light photons at 495 nm and helps with vision in dim light.
• RHO protein, help a cascade of chemical reactions that create electrical signals. These signals are
transmitted to the brain where they are interpreted as vision.
 SIGNS AND SYMPTOMS

• Since RP begins as rod degeneration, the patient notices first increasing difficulty in night vision followed
by difficulty central vision and Distinguishing between colours
• A small area of central vision on both eyes usually persists of years .
• Total blindness eventually ensues in most cases, the age of appearance of legal blindness range from as
early as childhood to as late as the 40s.
 HOW IS RP DIAGNOSED?

1. ACUITY tests :measure the accuracy of central vision

2. COLOR testing : help determine the status of your cone cells the retinal cells that
interpret color.
3. DARK ADAPTION test : measure how well the eyes adjust to changes in lights .
 GENE THERAPY METHODS
• Viral Vectors: There are mainly three types of vector strategies based on viruses:
1.adenoviruses (Ad)
2. adeno -associated viruses (AAV)
3. lentiviruses (LV)
AAV are favoured in gene therapy methods for the treatment of inherited retinopathies (IR); their small size
enables the efficient target of retinal layers.

• Gene Editing System :The success of gene editing is highly dependent on the guide RNA (RNA) design,
the cell target

• RNA Replacement
 Predicting genetic disorders through DNA sequencing using AI

This study delves into the realm of genetic disorder prediction and species classification through DNA
sequencing and Machine Learning Algorithms. It explores the utilization of advanced technology to
revolutionize early diagnosis and treatment in the field of genetics. The study involves the analysis of DNA
sequences from various species, including humans, chimps, and dogs, to predict genetic abnormalities.
 DATASET

This study used two datasets from Kaggle were :

one for DNA sequencing and the other for the genetic disorder.

A group of gene sequences from three DNA sequence text files (one each for humans), chimps, and dogs (each
having 4380 human DNA sequences), 1682 chimpanzee DNA sequences, and 820 dog DNA sequences

the genetic disorder dataset included three genetic disorders and nine disorder subclasses. Thirty five (35) features
were utilized to predict genetic abnormalities across 22083 patient data.
PREPROCESSING
• Data Encoding: Categorical data in the datasets were encoded using techniques like Label Encoding to convert
them into numerical representations suitable for Machine Learning algorithms.
label encoder that used the letters “a,” “c,” “g,” and “t” from the DNA alphabet in addition to the character “n” for everything else.
It returned a NumPy array with A = 0.25, C = 0.50, G = 0.75, T = 1.00, and n = 0.
• Exploratory Data Analysis (EDA):was conducted on the DNA sequencing dataset to understand genetic
sequences. Techniques like SeqIO were used to extract sequence IDs and lengths.
• Normalization: Numerical data in the datasets were normalized to bring them to a comparable scale without
distorting the differences in value variations. This step was crucial for avoiding bias in the models during training
and prediction.
• Feature Engineering: Feature engineering techniques have been applied to extract relevant features from the DNA
sequences and genetic disorder data.
• Data Splitting: The datasets were split into training and testing sets to train the models on a subset of the data and
evaluate their performance on unseen data.
(Train Size 80% Test Size 20%)
 MODELS USED IN THIS STUDY
• The research employed various machine learning algorithms, including Logistic Regression, Gaussian Naive
Bayes, K Neighbors, Decision Tree, Random Forest, Gradient Boosting, and CatBoost, for predictive modeling on
the genetic disorder

MODEL TRAINING
• the model training process involved feeding the prepared data into the selected Machine Learning
Algorithms to teach them how to make predictions based on the input features. This training phase is
crucial for the models to learn patterns and relationships within the data and improve their predictive
capabilities.
MODEL TESTING

• During testing, the model is presented with a separate dataset (referred to as the test set) that it has not
seen during training. The model then makes predictions on this test set, and its performance is evaluated
using various metrics depending on the type of problem being addressed (classification, regression, etc.).
MODELS CHART
 RESULTS
The study identified the best-performing models For DNA sequencing, the Multinomial Naive BayesClassifier
achieved the highest accuracy rate
 DETECTION OF RETINITIS PIGMENTOSA USING AI

The purpose of this study was to detect the presence of (RP) based on color fundus photographs using a deep
learning model. 1153 fundus images were downloaded from the picture archiving and communication system.

Three transfer learning models based on pre-trained Inception V3, Inception Resnet V2, and Xception deep
learning architectures, respectively, were developed to classify the presence of RP on fundus images.
 (RETINITIS PIGMENTOSA) DATASET

• The model sensitivity, specificity, and area under the receiver operating characteristic (AUROC) curve were
compared.
• The results from the best transfer learning model
(X-ception) were compared with the reading results of two general ophthalmologists, one
retinal specialist, and one specialist in retina and inherited retinal degenerations
 (RETINITIS PIGMENTOSA) DATASET
• the Xception model had the best performance, achieving an AUROC of 96.74%.

• Gradient-weighted class activation mapping indicated that the contrast between the periphery and the macula on
fundus photographs was an important feature in detecting RP.
METHODOLOGY
1.DATA collection:
Researchers gather retinal images from various sources , such as medical databases ,clinical studies, or research collaborations , these
images may include scans from fundus photography . Diagnosis RP using color fundus images
1670 fundus images were downloaded from the picture archiving and communication system.

2.Preprocessing :
all images were de-identified to mask off the patient’s personal information.
As the images were captured by different machines with different resolutions, each image was cropped automatically to have the same
height–widthin the same ratio.
Deep learning models were used to learn RP features and the corresponding classification from the entire input image.
Unimportant regions, such as regions outside of the round boundary of the main object, were cropped out automatically.
These unimportant regions could result from artifacts generated during image acquisition. After removing the irrelevant areas, the
images were resized to 300 × 375 pixels, with pixel values from 0 to 1.
Reasonable augmentations, such as image rotation and horizontal and vertical flips, were applied to increase the number of training
images. The augmented dataset was used only for training the AI models.
METHODOLOGY
3.Extraction and classification:
three different models, Inception V3, Inception Resnet V2, and Xception.
The last output layer within the models was replaced with two dense layers for classification. The first dense layer has 1024 units, and the
second has one (for binary classification), all with the sigmoid activation.

AI program loads color fundus images and trains a CNN using the images.
The CNN extracts the image features in the intermediate hidden layers to predict the probability of the two classes of RP and normal. If the
probability of RP is high, we can suggest the patient to consult an IRD specialist for further examination.
This program has the potential to be developed into a decision support system for diagnosing RP in rural areas with limited medical resources,
METHODOLOGY
• There are 3 basics to define CNN:
1.Convolution layer
2.Pooling layer
3.Fully-connected layer (Output layer)

• There are several of CNN architectures:

1.X-ception
2.of Inception V3
3.Inception Resnet V2
METHODOLOGY
• Inception v3 Arcitecture

he inception v3 model was released in the year 2015, it has a total of 42 layers and a lower error rate than its predecessors.
The major modifications done on the Inception V3 model are Factorization into Smaller
Convolutions Spatial Factorization into Asymmetric Convolutions Utilitv of Auxiliarv Classifiers Efficient
 XCEPTION MODEL ARCHITECTURE

Xception is a deep convolutional neural network architecture that involves Depthwise Separable Convolutions. It was
developed by Google researchers.

The data first goes through the entry flow, then through the middle flow which is repeated eight times, and finally
through the exit flow. Note that all Convolution and SeparableConvolution layers are followed by batch normalization

XCeption is an efficient architecture that relies on two main points :

• Depthwise Separable Convolution
• Shortcuts between Convolution blocks as in ResNet
METHODOLOGY

flowchart, which shows the acquisition of color fundus images,

training and testing of the model, and model visualization and evaluation
METHODOLOGY
• Training and performance:
The collected images (1670) consisting of RP and normal images were separated into a training set
(960 RP and 324 normal) and a test set (193 RP and 193 normal). For training, we used X-ception as the
pre-trained model and performed fivefold cross-validation for model evaluation.
• Among the three CNN models we used, Xception demonstrated the best sensitivity and specificity for early detection of RP
with an AUROC of 80%, better than those of Inception V3 and Inception Resnet V2 models.
 COMPARING AND RESULTS
• The Xception model demonstrated the best performance, as compared to Inception V3 and Inception Resnet V2.
• Both Xception and Inception-ResNet V2 are the modifications of the Inception V3 model.
• The Inception-ResNet V2 model combines a residue connection and a revised version of the Inception architecture, which increases the model
depth while retaining its computational efficiency.
• Similarly, the Xception model is the latest modification in the Inception model series; it adds a residue connection into the model and improves the
Inception architectures by replacing Inception modules with depthwise separable convolutions.
• The separable convolution used in Xception has a major impact on its improvement as it can potentially decouple the learning of channel-wise and
space-wise features.
• We assume this to be the case because RP color fundus images show neurodegenerative patterns both space-wise and channel-wise.
• The separate learning of channel-wise and space-wise features might result in better outcome of our model. Therefore, the Xception model
performs better on our dataset
CONCLUSION

• This study validates the value of applying deep learning to the detection of RP from color fundus images. This should be of
importance as RP is a disease that may lead to irreversible blindness, and early detection could help the patients to seek
further consultation and potential treatments.
• a deep learning-based algorithm trained using color fundus images was demonstrated. It achieved high sensitivity and
specificity in identifying eyes with RP.
• To the best of our knowledge, this is the first study to evaluate the utility of deep learning in automating the detection of RP
from fundus photographs.
• Further research is needed to explore the practicality of clinical applications of this algorithm.
• The field of gene therapy has made extensive progress in medicine, including ophthalmology, in recent years. Gene therapy
strategies are searching for the option that is simple, does not need to be repeated frequently, has the best efficacy results,
least safety concerns, and least financial burden on patients and healthcare systems.
• Physicians should remain up to date on underlying disease pathophysiology and current developments in gene therapy, as it
may very well be the answer to a once-incurable, blinding RP.