MEN: leveraging explainable multimodal encoding network for precision prediction of CYP450 inhibitors

Abstract

Drug-drug interactions (DDIs) present serious risks in clinical settings, especially for patients who are prescribed multiple medications. A major factor contributing to these interactions is the inhibition of cytochrome P450 (CYP450) enzymes, which are vital for drug metabolism. As a result, reliably identifying compounds that may inhibit CYP450 enzymes is a key step in drug development. However, existing machine learning (ML) methods often fall short in terms of prediction accuracy and biological interpretability. To address this challenge, we introduce a Multimodal Encoder Network (MEN) aimed at improving the prediction of CYP450 inhibitors. This model combines three types of molecular data (chemical fingerprints, molecular graphs, and protein sequences) by applying specialized encoders tailored to each format. Specifically, the Fingerprint Encoder Network (FEN) processes molecular fingerprints, the Graph Encoder Network (GEN) extracts structural features from graph-based representations, and the Protein Encoder Network (PEN) captures sequential patterns from protein sequences. By integrating these diverse data types, MEN can extract complementary information that enhances predictive performance. The encoded outputs from FEN, GEN, and PEN are fused to build a comprehensive feature representation. An explainable AI (XAI) module is incorporated into the model to support biological interpretation, using visualization techniques such as heatmaps. The model was trained and validated using two datasets: chemical structures in SMILES format from PubChem and protein sequences of five CYP450 isoforms (1A2, 2C9, 2C19, 2D6, and 3A4) obtained from the Protein Data Bank (PDB). MEN achieved an average accuracy of 93.7% across all isoforms. The individual encoders performed with accuracies of 80.8% (FEN), 82.3% (GEN), and 81.5% (PEN). Additional performance results include an AUC of 98.5%, sensitivity of 95.9%, specificity of 97.2%, precision of 80.6%, F1-score of 83.4%, and a Matthews correlation coefficient (MCC) of 88.2%. All data and code are available at https://github.com/GracedAbena/MEN-Leveraging-Explainable-Multimodal-Encoding-Network .

Keywords: Attentive hierarchical graph isomorphism network (AHGIN); Cytochrome P450; Inhibitor; Interpretable artificial intelligence (IAI); Residual multi local attention (ReMLA); Self-attention.

Fig. 1

The procedure of Drug-Drug Interaction (DDI). The CYP450 enzymes play a key role in how these drugs are metabolized in the body.

Fig. 2

A recent survey analyzed AI-based research on CYP450 inhibitor predictions from 2020 to 2024. Part (a) shows a yearly summary of publications, while part (b) categorizes these studies into Machine Learning, Deep Learning, and Hybrid AI models, highlighting trends in methodology preferences. This data was sourced from Google Scholar.

Fig. 3

The Proposed end-to-end AI framework for predicting CYP450 inhibitors.

Fig. 4

Examples of the chemical compounds. This dataset was sourced from the PubChem database.

Fig. 5

Examples from the CYP Target Protein Sequence dataset (Section  “Examining ReMLA”) are shown. This dataset, sourced from the Protein Data Bank (PDB), includes the 3D structures of each of the five CYP450 isoforms along with their ligand inhibitors, depicted as balls in the first row. In the second row, each isoform’s key binding residues within a 5-angstrom radius of the ligands are displayed, with ligand inhibitors highlighted in yellow.

Fig. 6

Representation of the detailed FEN module.

Fig. 7

The preprocessing flowchart for converting SMILES strings into a format suitable for further analysis.

Fig. 8

Detailed AI structure of the proposed Graph Encoder Network (GEN).

Algorithm 1

AHGIN

Fig. 9

AI modeling structure of the proposed Protein Encoder Network (PEN).

Algorithm 2

AAC Encoder

Algorithm 3

Local Merger

Algorithm 4

Global Merger Algorithm:

Fig. 10

AI modeling structure of the individual Position Awareness Module (PAM).

Algorithm 5

PAM

Fig. 11

a Vision Transformer with Dynamic Attention (ViTDA) and b shows the Interpreter representations.

Algorithm 6

ViTDA

Fig. 12

Training convergency curves for the proposed FEN and its sub models.

Fig. 13

Training convergency curves for the proposed GEN and its sub-models.

Fig. 14

Training convergency curves for the proposed PEN against its sub-models.

Fig. 15

Training convergency curves for the proposed MEN against is sub models.

Fig. 16

Confusion matrices for a FEN, b GEN, c PEN, and d MEN.

Fig. 17

Comparison evaluation performance of the proposed MEN against its sub models of FEN, GEN, and PEN in terms of overall accuracy (Acc) and F1-score.

Fig. 18

Interpreting results for each CYP isoform.