Kevin Song

Mr. Kevin Song

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
28 May 2025 in bioRxiv
Verified
Preprint
Open access
PDF file
DHDelower Hossain
Delower Hossain
ESEhsan Saghapour
Ehsan Saghapour
KSKevin Song
Kevin Song
JCJake Y. Chen
Jake Y. Chen
Antibody-facilitated immune responses are central to the body’s defense against pathogens, viruses, and other foreign invaders. The ability of antibodies to specifically bind and neutralize antigens is vital for maintaining immunity. Over the past few decades, bioengineering advancements have significantly accelerated therapeutic antibody development. These antibody-derived drugs have shown remarkable efficacy, particularly in treating Cancer, SARS-Cov-2, autoimmune disorders, and infectious diseases. Traditionally, experimental methods for affinity measurement have been time-consuming and expensive. With the realm of Artificial Intelligence, in silico medicine has revolutionized; recent developments in machine learning, particularly the use of large language models (LLMs) for representing antibodies, have opened up new avenues for AI-based designing and improving affinity prediction. Herein, we present an advanced antibody-antigen binding affinity prediction model (LlamaAffinity), leveraging an open-source Llama 3 backbone and antibody sequence data employed from the Observed Antibody Space (OAS) database. The proposed approach significantly improved over existing state-of-the-art (SOTA) approaches (AntiFormer, AntiBERTa, AntiBERTy) across multiple evaluation metrics. Specifically, the model achieved an accuracy of 0.9640, an F1-score of 0.9643, a precision of 0.9702, a recall of 0.9586, and an AUC-ROC of 0.9936. Moreover, this strategy unveiled higher computational efficiency, with a five-fold average cumulative training time of only 0.46 hours, significantly lower than previous studies. LlamaAffinity defines a new benchmark for antibody-antigen binding affinity prediction, achieving advanced performance in the immunotherapies and immunoinformatics field. Furthermore, it can effectively assess binding affinities following novel antibody design, accelerating the discovery and optimization of therapeutic candidates.

16 July 2026 in Journal of Chemical Information and Modeling
Verified
Journal Article
Open access
PPPhuc Pham
Phuc Pham
VNViet Thanh Duy Nguyen
Viet Thanh Duy Nguyen
KSKevin Song
Kevin Song
JCJake Chen
Jake Chen
THTruong-Son Hy
Truong-Son Hy
Accurate identification of interactions between protein residues and ligand functional groups is critical for understanding molecular recognition and guiding rational drug design. Existing deep learning approaches for protein–ligand interpretability typically rely on three-dimensional structural input or distance-based contact labels, which limit both their applicability and biological relevance. Here, we present LINKER, the first sequence-based model to predict residue-functional group interactions according to biologically defined interaction types, using only a protein sequence and the SMILES representation of the ligand. LINKER is trained via structure-supervised interaction learning, in which interaction labels are derived from three-dimensional protein–ligand complexes through functional group-based motif extraction. By representing ligands as ensembles of functional groups, the model emphasizes chemically meaningful substructures rather than mere spatial proximity. Importantly, LINKER requires only sequence-level input at inference, enabling large-scale applications in contexts where structural data are unavailable. Extensive experiments demonstrate that LINKER consistently outperforms established baselines, highlighting the utility of functional group abstractions and structure-based supervision for interpretable protein–ligand interaction prediction. Our source code is publicly available at: https://github.com/HySonLab/LINKER/.

14 March 2026 in SocArXiv
Verified
Preprint
Open access
KSKevin Song
Kevin Song
JZJohn Zhang
John Zhang
YCYunxi Chen
Yunxi Chen
Umbilical cord blood banking has established clinical value in hematopoietic transplantation, but the strongest ethical case for universal neonatal collection is not that every child should receive a form of private biological insurance. The better case is narrower: neonatal cells can be preserved as public biomedical infrastructure, while genomic sequencing, induced pluripotent stem cell (iPSC) derivation, and downstream clinical use are governed as later, distinct, and higher-stakes decisions. This article defends that model. The empirical record supports a disciplined middle position. Professional guidance favors public over routine private banking; long-term cryostorage can preserve clinically usable material across decades, even if cryopreservation is not functionally neutral; cord blood is a plausible source for iPSC derivation; and pluripotent-cell translation has entered early clinical use. Specific use cases make the policy argument concrete, including cardiotoxicity modeling before anthracycline therapy, phenotype testing in inherited arrhythmia syndromes, and selective autologous cell-replacement strategies in ophthalmology. These examples do not justify universal autologous manufacturing, but they do show that preserved neonatal cells may carry meaningful future clinical option value. Review-level evidence also sets important limits: support for public banking exceeds support for private banking and open-ended research use, regenerative signals remain heterogeneous and condition-specific, and support for newborn genomic sequencing is constrained by concerns about privacy, discrimination, and long-term governance. The most defensible policy endpoint is therefore universal public collection and long-term stewardship of neonatal cells, selective sequencing, indication-based or coverage-based iPSC activation, data minimization, adult recontact where feasible, and explicit limits on commercialization. Overall, the more defensible policy goal is universal cell banking capacity, selective genomic use, and governed iPSC activation rather than universal genomic archiving or the creation of a personal iPSC line for every newborn.

28 February 2025 in bioRxiv
Verified
Preprint
Open access
PDF file
KSKevin Song
Kevin Song
JCJake Y. Chen
Jake Y. Chen
Drug repurposing offers a promising strategy to accelerate therapeutic discovery for complex diseases; however, conventional approaches often overlook the multi-scale, dynamic nature of drug-induced perturbations. In this study, we introduce PETS (Predictive Evaluation of Therapeutic Simulations), an innovative in silico framework that synergistically integrates curated pathway models with multi-layer network propagation, adaptive dampening, and memory mechanisms to simulate drug-gene interactions with high fidelity. By propagating perturbations through tissue- and cell-specific protein-protein interaction networks via iterative state updates, PETS robustly captures both proximal and distal regulatory feedback, enabling the identification and ranking of drug candidates capable of reversing disease-specific gene expression signatures. Validation against the SigCom L1000 dataset demonstrates that PETS achieves lower mean squared errors and higher predictive consistency compared to existing methods across models of Alzheimers disease, AD-expressing neuroblastoma, and glioblastoma multiforme. Moreover, PETS concurrently quantifies on-target therapeutic efficacy and potential off-target toxicity, providing mechanistic insights that are critical for candidate prioritization. Looking ahead, the integration of patient-specific multi-omics data and dynamic network topologies is expected to further enhance the translational impact of PETS. Our framework represents a significant advancement in the computational prediction of drug-gene perturbation effects, positioning it as a cornerstone tool for precision medicine and preclinical drug discovery.

3 August 2025 in bioRxiv
Verified
Preprint
Open access
KSKevin Song
Kevin Song
JZJianyi Zhang
Jianyi Zhang
Withdrawal Statement: The authors have withdrawn this manuscript due to an open and unresolved matter regarding authorship attribution and the clarification of intellectual property rights associated with the work. Therefore, the authors do not wish this work to be cited as reference for the project. If you have any questions, please contact the corresponding author.