Sophia Mosalla

Ms. Sophia Mosalla

Sun Moon University, Asan, Chungnam, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 October 2024 in Journal of Cheminformatics
Verified
Journal Article
Open access
PDF file
ZCZonyfar Candra
Zonyfar Candra
SNSoualihou Ngnamsie Njimbouom
Soualihou Ngnamsie Njimbouom
Sophia MosallaSophia Mosalla
Sophia Mosalla
Jeong Dong KimJeong Dong Kim
Jeong Dong Kim
State‑of‑the‑art medical studies proved that predicting CYP450 enzyme inhibitors is beneficial in the early stage of drug discovery. However, accurate machine learning-based (ML) in silico methods for predicting CYP450 inhibitors remains challenging. Here, we introduce GTransCYPs, an improved graph neural network (GNN) with a transformer mechanism for predicting CYP450 inhibitors. This model significantly enhances the discrimination between inhibitors and non-inhibitors for five major CYP450 isozymes: 1A2, 2C9, 2C19, 2D6, and 3A4. GTransCYPs learns information patterns from molecular graphs by aggregating node and edge representations using a transformer. The GTransCYPs model utilizes transformer convolution layers to process features, followed by a global attention-pooling technique to synthesize the graph-level information. This information is then fed through successive linear layers for final output generation. Experimental results demonstrate that the GTransCYPs model achieved high performance, outperforming other state-of-the-art methods in CYP450 prediction. Scientific contribution The prediction of CYP450 inhibition via computational techniques utilizing biological information has emerged as a cost-effective and highly efficient approach. Here, we presented a deep learning (DL) architecture based on GNN with transformer mechanism and attention pooling (GTransCYPs) to predict CYP450 inhibitors. Four GTransCYPs of different pooling technique were tested on an experimental tasks on the CYP450 prediction problem for the first time. Graph transformer with attention pooling algorithm achieved the best performances. Comparative and ablation experiments provide evidence of the efficacy of our proposed method in predicting CYP450 inhibitors. The source code is publicly available at https://github.com/zonwoo/GTransCYPs .

12 September 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
PGPrince Delator Gidiglo
Prince Delator Gidiglo
Soualihou Ngnamsie NjimbouomSoualihou Ngnamsie Njimbouom
Soualihou Ngnamsie Njimbouom
GAGelany Aly Abdelkader
Gelany Aly Abdelkader
Sophia MosallaSophia Mosalla
Sophia Mosalla
Jeong Dong KimJeong Dong Kim
Jeong Dong Kim
Antimicrobial resistance (AMR) represents a pressing global health challenge with implications for developmental progress, as it increasingly manifests within pathogenic bacterial populations. This phenomenon leads to a substantial public health hazard, given its capacity to undermine the efficacy of medical interventions, thereby jeopardizing patient welfare. In recent years, an increasing number of machine learning methods have been employed to predict antimicrobial resistance. However, these methods still pose challenges in single-drug resistance prediction. This study proposed an effective model for predicting antimicrobial resistance to E. Coli by utilizing the eXtreme Gradient Boosting model (XGBoost), among ten other machine learning methods. The experimental results demonstrate that XGBoost outperforms other machine learning classification methods, particularly in terms of precision and hamming loss, with scores of 0.891 and 0.110, respectively. Our study explores the existing machine learning models for predicting antimicrobial resistance (AMR), thereby improving the diagnosis as well as treatment of infections in clinical settings.

1 April 2024
Verified
Book Chapter
Closed access
Sophia MosallaSophia Mosalla
Sophia Mosalla
RRRahul Ranjan
Rahul Ranjan
SSSaurabh Singh
Saurabh Singh
The 'Umber' mobile app stands as a pioneering technological advancement, reshaping the traditional usage of umbrellas. This abstract encapsulates the app's diverse objectives, focusing on elevated user convenience, technological innovation, environmental sustainability, and increased accessibility. Through seamless integration of technology, 'Umber' revolutionizes the umbrella experience, introducing on-demand services, reducing forgetfulness, and promoting sustainability. Drawing inspiration from successful applications like GCOO, Kakao T, and Panda Korea, 'Umber' adopts a proven model to address umbrella-related challenges. This chapter delves into the innovative development of the 'Umber' mobile app, a paradigm-shifting solution at the intersection of global mobility, Internet of Things (IoT) integration, and cutting-edge technologies. The core of the technological architecture involves the incorporation of Firebase for real-time data management, ESP32 microcontrollers, and Reed switches for seamless interaction, GPS tracking for precise location awareness, and map integration to enhance user experience. The 'Umber' app not only redefines traditional umbrella usage but also serves as a testament to the transformative potential of thoughtful, purpose-driven technology development on a global scale. Future research endeavors may entail augmenting the technological capabilities of the 'Umber' app through the exploration of advanced sensor technologies and machine learning algorithms. This could lead to an enhanced user experience and increased adaptability to diverse weather conditions, potentially manifested in a compact screen on the umbrella box. Users could conveniently access real-time weather updates, monitor the condition of the box, and receive information about the umbrella housed inside. Additionally, there is potential for further innovation by upgrading each umbrella to include features such as a built-in flashlight, providing users with added convenience and safety for nighttime walks.

29 August 2025 in Bioinformatics and Biology Insights
Verified
Journal Article
Open access
ZCZonyfar Candra
Zonyfar Candra
Soualihou Ngnamsie NjimbouomSoualihou Ngnamsie Njimbouom
Soualihou Ngnamsie Njimbouom
Sophia MosallaSophia Mosalla
Sophia Mosalla
Jeong Dong KimJeong Dong Kim
Jeong Dong Kim
An advanced graph neural network (GNN) is of great promise to facilitate predicting Poly ADPribose polymerase inhibitors (PARPi). Recent studies design models by leveraging graph representations and molecular descriptor representations, unfortunately, still face challenges in comprehensively capturing spatial relationships and contextual information between atoms. Moreover, combining molecular descriptors with graph representations may introduce information redundancy or lead to the loss of intrinsic molecular structures. To this end, we proposed a novel Residual Reconstruction Enhanced Graph Isomorphism Network (R2eGIN) learning model. Specifically, we first designed a residual GIN to learn molecular representations, reduced the impact of vanishing gradients, and enabled the model to capture long-range dependencies. Then, the reconstruction block, by predicting adjacency matrices and node features, was adopted to reconstruct the input graph. To prove the effectiveness of the proposed model, extensive experiments were conducted on 4 data sets of PARPi and compared with 7 existing models. Our evaluation of R2eGIN, conducted using 4 PARPi data sets, shows that the proposed model is comparable to or even outperforms other state-of-the-art models for PARPi prediction. Furthermore, R2eGIN can revolutionize the drug repurposing process through a substantial reduction in the time and costs commonly encountered in traditional drug development methods.

31 May 2025 in The Journal of Korean Institute of Communications and Information Sciences
Verified
Journal Article
Closed access
Sophia MosallaSophia Mosalla
Sophia Mosalla
KAKazunari Akashi
Kazunari Akashi
CAChunghwan Alao
Chunghwan Alao
JKJeong-Dong Kim
Jeong-Dong Kim
TLTaek Lee
Taek Lee
JLJung-Been Lee
Jung-Been Lee
This study presents the development and evaluation of an IoT-based smart umbrella rental service designed to address urban challenges such as the inconvenience of carrying umbrellas and the inefficiencies in existing umbrella rental systems. Inspired by IoT-driven solutions like Ikasa and Retbella, this system enhances user convenience through real-time tracking, efficient management, and user-friendly mobile applications. The system architecture incorporates the NEO-6 GPS module for precise location tracking, ESP32 microcontrollers for seamless integration with reed switches, and Firebase for real-time data updates and secure management. Developed using React Native, the app offers cross-platform compatibility and QR code functionality for streamlined user interactions. Results demonstrate the system's ability to optimize umbrella management and rental processes, contributing to operational efficiency and environmental sustainability. Future directions include integrating advanced sensor technology and AI to elevate user adaptability and real-time monitoring.

28 May 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Sophia MosallaSophia Mosalla
Sophia Mosalla
SJSo Yeon Jeon
So Yeon Jeon
Jeong Dong KimJeong Dong Kim
Jeong Dong Kim
TLTaek Lee
Taek Lee
JLJung-Been Lee
Jung-Been Lee
Caregiver burden is a critical public health issue among individuals providing long-term care for family members with cognitive impairment and is closely associated with physiological stress. However, conventional assessments primarily rely on self-reported measures, which provide limited insight into underlying physiological processes and temporal dynamics. To address this limitation, we investigate the use of wearable-derived physiological and behavioral signals for the objective assessment of caregiver burden. We analyzed multimodal data collected from 78 informal caregivers using Fitbit devices, including heart rate, activity patterns, sleep architecture, and variability-based features aggregated over a 7-day window. Associations with caregiver burden, measured by the Zarit Burden Interview (ZBI), were evaluated using Spearman correlation with false discovery rate correction and multivariable regression models adjusted for demographic and clinical covariates. Variability in REM sleep duration showed an exploratory negative association with caregiver burden (ρ = −0.32, p = 0.004), with similar but weaker nominal patterns observed for light and total sleep variability. In multivariable analysis, maximum daily heart rate was positively associated with caregiver burden (β = 2.59, p = 0.005), although overall model performance was modest (R2 = 0.32, adjusted R2 = 0.08) and the full model did not reach statistical significance. These findings demonstrate that multimodal wearable signals may provide complementary objective insights into caregiver burden and support the evaluation of sleep variability and heart rate measures as candidate indicators.