Skip to content

A Task-Adaptive Multimodal Pretrained Framework for Antibiotic Virtual Screening with Joint Activity and Cytotoxicity Prediction.

Sep 2026 · Journal of Chemical Information and Modeling · Vol 66 18, pp. 11793-11806 · 0 citations · 40 references
Medicine

TL;DR

MAPViS provides a scalable multimodal framework for joint activity–toxicity modeling and offers a practical computational tool for antibiotic virtual screening and candidate prioritization.

Abstract

Antimicrobial resistance (AMR) poses a growing threat to global public health, particularly for priority pathogens such as Staphylococcus aureus (SA) and Neisseria gonorrheae (NG), for which therapeutic options are increasingly limited. Although deep learning has accelerated antibiotic discovery, existing approaches are often constrained by single-modality molecular representations and a lack of joint modeling for antibacterial activity and host cell toxicity. Here, we present MAPViS, a task-adaptive multimodal pretrained framework for jointly predicting antibacterial activity against SA and NG together with cytotoxicity risk in three human cell lines (HepG2, HSkMC, and IMR-90). MAPViS integrates molecular graph representations, molecular fingerprints, and descriptor/3D geometric features through a gated fusion mechanism and combines large-scale self-supervised pretraining with supervised task-specific fine-tuning. The graph encoder is pretrained on approximately 10 million molecules using hierarchical pseudolabel classification and masked graph contrastive learning to improve representation quality and transferability. On benchmark datasets derived from experimentally screened compounds, MAPViS achieves competitive performance across antibacterial activity prediction tasks and shows advantages in early recognition metrics relevant to virtual screening, including AUPRC, Precision@30, and EF@1.0%. External validation further shows strong top-ranked enrichment on the SA task, where all Top-10 candidates are experimentally active, whereas performance on NG is more modest, indicating task-dependent generalization. Overall, MAPViS provides a scalable multimodal framework for joint activity-toxicity modeling and offers a practical computational tool for antibiotic virtual screening and candidate prioritization.

View source

Similar papers

#machine learning Open access Aug 2026

Coarse composition suffices: tabular in-context learning for multi-activity antimicrobial peptide profiling

A simple, sequence-only pipeline can match and surpass leading methods by combining 330 interpretable sequence descriptors with TabPFN, a tabular foundation model that performs in-context prediction in a single forward pass without gradient-based training or hyperparameter search.

Anuj Pal, Raunak Kumar, D. Solanki et al. · 0 citations
Open access Aug 2026

Knowledge-driven multimodal mutual learning for cell line-targeted anticancer peptide prediction.

A hybrid dataset compiled from five well-established peptide databases is integrated and proposed, and the effectiveness of TargetPC is demonstrated, which outperforms the state-of-the-art baselines in terms of prediction accuracy, and maintains strong generalization to unseen ACPs and cell lines.

Xuan Liu, Jian Zhang, Chong-Yang Chen et al. · 2 citations
Aug 2026

HyperMolFusion: A Hypergraph-Enhanced Multi-Modal Fusion Framework for Accurate Molecular Property Prediction.

By holistically integrating atomic, motif, and global fingerprint information via hypergraph modeling, HyperMolFusion offers a more reliable computational tool to enhance the efficiency and accuracy of drug development pipelines.

Yawen Lin, Sheng Lian, Shaoxin Bian et al. · 1 citation
Conference Open access 2026

Atomic Watchtower: A Multi-Modal Machine Learning Framework for Swift Antimicrobial Resistance Prediction Using Whole Genome Sequencing and SMILES-Based Molecular Mapping

The Atomic Watchtower is presented, a multi-modal machine learning framework that incorporates Whole Genome Sequencing k-mer features alongside drug-structure data encoded as SMILES alongside drug-structure data encoded as SMILES that poses the resistance prediction task as a structural-matching problem between pathoge...

Shiva Kashyap Yellavajhala, Police Sandeep Kumar Reddy, Honal Sudhakar John Kamalakar et al. · 0 citations
Sep 2026

MLI-DTA: An interpretable multimodal framework with multi-level interactions for drug-target affinity prediction.

MLI-DTA is proposed, a hierarchical multi-source feature fusion network based on multi-level attention that encodes both sequence and graph modalities of drugs and targets, and performs exceptionally well in the Davis and KIBA benchmarks.

Yu-Ning Liu, Guang-Ze Wang, Dan Liu et al. · 0 citations
Open access Sep 2026

HSSynergy: scale-aware hierarchical attention for interpretable drug synergy prediction

HSSynergy, a hierarchical substructure-aware deep learning framework for predicting anticancer drug synergy, introduces a Scale-Aware Masked Attention mechanism that enforces precise layer-wise alignment, and utilizes hierarchical grouping with mask constraints to achieves same-scale focusing while shielding against cr...

Yue-Hua Feng, Shu-Cong Zhang, Xiao-Ying Yan et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.