paper-with-me

Papers

A General-Purpose Molecular Foundation Model Transfers Across Diverse Olfactory Tasks

2026-08-26 · Yikun Han, Yi Wang, Neil Mankodi, Stephen Yang, Ambuj Tewari arxiv

Foundation models have transformed molecular property prediction, yet it remains unclear whether a molecular foundation model, fine-tuned on a single canonical olfactory prediction task, can learn representations that transfer across diverse machine olfaction problems. We investigate this question by fine-tuning Uni-Mol2 on the GS-LF benchmark for multi-label odor descriptor prediction and evaluating the resulting model, without additional deep-learning training, on four complementary downstream settings: cross-dataset odor descriptor prediction, odorous-versus-odorless classification, enantiomer evaluation, and odor mixture discriminability. The fine-tuned model matches or exceeds the performance of the state-of-the-art olfaction-specific baseline on the primary GS-LF benchmark and consistently transfers across these downstream evaluations. The enantiomer analysis further shows that three-dimensional molecular representations distinguish mirror-image molecules in a way that two-dimensional graph models fundamentally cannot, although accurately predicting the perceptual consequences of stereochemistry remains an open challenge. Together, these results support a train-once, transfer-across-tasks paradigm for machine olfaction and suggest that chemically pretrained molecular representations provide a strong foundation for transferable olfactory prediction.

📄 PDF Abstract BibTeX arXiv:2608.25893

Code (0)

등록된 구현이 없습니다.

Tasks

Molecular Property PredictionOdor Descriptor Prediction

Similar Papers 제목 키워드 기반

MMAI Gym for Science: Training Liquid Foundation Models for Drug Discovery

2026-03-03 · Maksim Kuznetsov, Zulfat Miftahutdinov, Rim Shayakhmetov, Mikolaj Mizera 외 arxiv

General-purpose large language models (LLMs) that rely on in-context learning do not reliably deliver the scientific understanding and performance required for drug discovery tasks. Simply increasing model size or introd…

Activity PredictionDrug Discovery

Controllable Molecular Generative Foundation Models

2026-05-14 · Yihan Zhu, Yuhan Liu, Weijiang Li, Tengfei Luo 외 arxiv

Despite the success of foundation models in language and vision, molecular graph generation still lacks a unified framework for heterogeneous design tasks with reliable controllability. While reinforcement learning (RL) …

Reinforcement LearningGraph GenerationDrug Discovery

SpecMol: A Spectroscopy-Grounded Foundation Model for Multi-Task Molecular Learning

2025-09-26 · Shuaike Shen, Jiaqing Xie, Zhuo Yang, Antong Zhang 외 arxiv

Large language models have emerged as transformative tools in molecular science, demonstrating remarkable potential in molecular property prediction and de novo molecular design. However, their application to spectroscop…

Molecular Property PredictionRepresentation Learning

UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning

2024-05-15 · Shikun Feng, Yuyan Ni, Minghao Li, Yanwen Huang 외

Recently, a noticeable trend has emerged in developing pre-trained foundation models in the domains of CV and NLP. However, for molecular pre-training, there lacks a universal model capable of effectively applying to var…

Contrastive LearningDenoisingmolecular representationRepresentation Learning

Fine-grained Multi-class Nuclei Segmentation with Molecular-empowered All-in-SAM Model

2025-08-21 · Xueyuan Li, Can Cui, Ruining Deng, Yucheng Tang 외 arxiv

Purpose: Recent developments in computational pathology have been driven by advances in Vision Foundation Models, particularly the Segment Anything Model (SAM). This model facilitates nuclei segmentation through two prim…

Semantic Segmentation