2025 Hyper Recent •CC0 1.0 Universal

This work is dedicated to the public domain. No rights reserved.

Access Preprint From Server
April 5th, 2025
Version: 1
University of Alabama at Birmingham
bioinformatics
biorxiv

NeSyDPP4-QSAR: A Neuro-Symbolic AI Approach for Potent DPP-4-Inhibitor Discovery in Diabetes Treatment

Hossain, D.Open in Google Scholar•Chen, J. Y.Open in Google Scholar

Diabetes Mellitus (DM) is a global epidemic and among the top ten leading causes of mortality (WHO, 2019), projected to rank seventh by 2030. The US National Diabetes Statistics Report (2021) states that 38.4 million Americans have diabetes. Dipeptidyl Peptidase-4 (DPP-4) is an FDA-approved target for type 2 diabetes mellitus (T2DM) treatment. However, current DPP-4 inhibitors are associated with adverse effects, including gastrointestinal issues, severe joint pain (FDA safety warning), nasopharyngitis, hypersensitivity, and nausea. Identifying novel inhibitors is crucial. Direct in vivo DPP-4 inhibition assessment is costly and impractical, making in silico IC50 prediction a viable alternative. Quantitative Structure-Activity Relationship (QSAR) modeling is a widely used computational approach for chemical substance assessment. We employ LTN, a neuro-symbolic approach, alongside DNN and transformers as baselines. DPP-4-related data is sourced from PubChem, ChEMBL, BindingDB, and GTP, comprising 6,563 bioactivity records (SMILES-based compounds with IC50 values) after deduplication and thresholding. A diverse set of features including descriptors (CDK Extended-PaDEL), fingerprints (Morgan), chemical language model embeddings (ChemBERTa2), LLaMa 3.2, and physicochemical properties is used to train the NeSyDPP4-QSAR model. The NeSyDPP4-QSAR model yielded the highest accuracy, incorporating CDKextended and Morgan fingerprints, with an accuracy of 0.9725, an F1-score of 0.9723, an ROC AUC of 0.9719, and an MCC of 0.9446. The performance was benchmarked against two standard baseline models: a deep neural network and a transformer. To ensure fair comparisons, DNN models used the equivalent attributes with the same dimension and network configuration as NeSyDPP4-QSAR. Our findings showed that integrating the Neuro-symbolic strategy (neural network-based learning and symbolic reasoning) holds immense potential for discovering drugs that can inhibit diabetes mellitus and classifying biological activities that inhibit it.

Similar Papers

biorxiv
Sun Apr 06 2025
SnoBIRD: A tool to identify C/D box snoRNAs and refine their annotation across all eukaryotes
Small nucleolar RNAs (snoRNAs), a group of noncoding RNAs present amongst all eukaryotes, are most extensively characterized for their regulation of ribosome biogenesis and splicing. Despite their central roles, current snoRNA annotations remain incomplete. Several eukaryote genome annotations contain few or no snoRNAs, and none distinguish expressed snoRNAs from their pseudogenes, a recently char...
Fafard-Couture, E.
•
Boulanger, C.
•
Faucher-Giguere, L.
•
Sinagoga, V.
...•
Scott, M. S.
biorxiv
Sun Apr 06 2025
Enhancing variant detection in complex genomes: leveraging linked reads for robust SNP, Indel, and structural variant analysis
Accurate detection of genetic variants, including single nucleotide polymorphisms (SNPs), small insertions and deletions (INDELs), and structural variants (SVs), is critical for comprehensive genomic analysis. While traditional short-read sequencing performs well for SNP and INDEL detection, it struggles to resolve SVs, especially in complex genomic regions, due to inherent read length limitations...
Luo, C.
•
Liu, Y. H.
•
Liu, H.
•
Zhang, Z.
...•
Zhou, X. M.
biorxiv
Sun Apr 06 2025
Chemical Genomics Language Model toward Reliable and Explainable Compound-Protein Interaction Exploration
Deep learning-based compound-protein interaction (CPI) prediction models are promising in the field of molecular biology, particularly for facilitating the drug discovery process. In practical applications, CPI models should achieve a high generalization performance, quantify prediction confidence, and ensure explainability. Here, we propose ChemGLaM, a chemical genomics language model for reliabl...
Koyama, T.
•
Tsumura, H.
•
Okita, R.
•
Yamazaki, K.
...•
Okuno, Y.
biorxiv
Sun Apr 06 2025
SpatialAgent: An Autonomous AI Agent for Spatial Biology
Advances in AI are transforming scientific discovery, yet spatial biology, a field that deciphers the molecular organization within tissues, remains constrained by labor-intensive workflows. Here, we present SpatialAgent, a fully autonomous AI agent dedicated for spatial-biology research. SpatialAgent integrates large language models with dynamic tool execution and adaptive reasoning. SpatialAgent...
Wang, H.
•
He, Y.
•
Coelho, P. P.
•
Bucci, M.
...•
Regev, A.
biorxiv
Sun Apr 06 2025
SEHI-PPI: An End-to-End Sampling-Enhanced Human-Influenza Protein-Protein Interaction Prediction Framework with Double-View Learning
Influenza poses a persistent global health challenge, necessitating innovative approaches to predict host-virus interactions and inform antiviral strategies. Despite advancements, machine-learning-based computational methods typically struggle with limited high-quality negative samples and inadequate modeling of complex host-virus interactions, which hinder predictive accuracy and generalization. ...
Yang, Q.
•
Fan, X.
•
Zhao, H.
•
Ma, Z.
...•
Yin, R.
biorxiv
Sun Apr 06 2025
Unsupervised Whole-Genome Representation Learning Captures Bacterial Phenotypes
Shifting from hand-crafted to learned representations of data has revolutionized fields like natural language processing and computer vision. Despite this, current approaches to bacterial phenotype prediction from the genome rely on training machine learning models on hand-crafted features, often binary indicators or counts of the presence of different conserved genomic elements and protein domain...
Dufault, C.
•
Moses, A. M.
biorxiv
Sun Apr 06 2025
Functional prediction of DNA/RNA-binding proteins using deep learning based on gene expression correlations
Deep learning methods have been developed to predict gene expression levels across various cell and tissue types based on DNA-binding sites of protein identified by ChIP-seq. However, the experimental identification of DNA/RNA-binding sites and the functional characterization of certain proteins remain challenging. Here I predicted the regulatory target genes and functional roles of DNA/RNA-bindin...
Osato, N.
biorxiv
Sun Apr 06 2025
Learning interpretable representation for context-specific transcription regulatory networks using a foundation model
Gene expression is shaped by transcription regulatory networks (TRNs), where transcription regulators interact within regulatory elements in a context-specific manner. Despite significant efforts, understanding the intricate interactions of transcription regulators across different genomic regions and cell types remains a major challenge, largely due to data sparsity. Here, we introduce ChromBERT,...
Yu, Z.
•
Yang, D.
•
Chen, Q.
•
Zhang, Y.
...•
Zhang, Y.
biorxiv
Sun Apr 06 2025
Improving hifiasm haplotypes for autopolyploid genome assemblies using constraint programming
Actual versions of hifiasm often produce unbalanced haplotype contigs for autopolyploid genome assemblies. Adding a contraint on the distribution of proteins among haplotypes improves haplotype sizes and busco scores balances. Four species were used to benchmark this approach against hifiasm raw results. The script can be downloaded from https://github.com/chklopp/Separate_haplotypes_with_toulbar2
Schiex, T.
•
Klopp, C.
•
Givry, S. d.
•
Durante, V.
biorxiv
Sat Apr 05 2025
SCORCH2: a generalised heterogeneous consensus model for high-enrichment interaction-based virtual screening
The discovery of effective therapeutics remains a complex, costly, and time-consuming endeavor, characterized by high failure rates and significant resource investments. A central bottleneck in early-stage drug discovery is identifying suitable hit compounds with moderate affinity for known biological targets. Although advancements have been made, current in silico virtual screening methods are su...
Chen, L.
•
Blay, V.
•
Ballester, P. J.
•
Houston, D. R.