Author name cluster

Tianfan Fu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

TMLR Journal 2026 Journal Article

Beyond Affinity: A Benchmark of 1D, 2D, and 3D Methods Reveals Critical Trade-offs in Structure-Based Drug Design

Kangyu Zheng
Kai Zhang
Jiale Tan
Xuehan Chen
Yingzhou Lu
Zaixi Zhang
Lichao Sun
Marinka Zitnik

Currently, the field of structure-based drug design is dominated by three main types of algorithms: search-based algorithms, deep generative models, and reinforcement learning. While existing works have typically focused on comparing models within a single algorithmic category, cross-algorithm comparisons remain scarce. In this paper, to fill the gap, we establish a benchmark to evaluate the performance of fifteen models across these different algorithmic foundations by assessing the pharmaceutical properties of the generated molecules and their docking affinities and poses with specified target proteins. We highlight the unique advantages of each algorithmic approach and offer recommendations for the design of future SBDD models. We emphasize that 1D/2D ligand-centric drug design methods can be used in SBDD by treating the docking function as a black-box oracle, which is typically neglected. Our evaluation reveals distinct patterns across model categories. 3D structure-based models excel in binding affinities but show inconsistencies in chemical validity and pose quality. 1D models demonstrate reliable performance in standard molecular metrics but rarely achieve optimal binding affinities. 2D models offer balanced performance, maintaining high chemical validity while achieving moderate binding scores. Through detailed analysis across multiple protein targets, we identify key improvement areas for each model category, providing insights for researchers to combine strengths of different approaches while addressing their limitations. All the code that are used for benchmarking is available in https://github.com/zkysfls/2025-sbdd-benchmark

PDF Details

NeurIPS Conference 2025 Conference Paper

3D Interaction Geometric Pre-training for Molecular Relational Learning

Namkyeong Lee
Yunhak Oh
Heewoong Noh
Gyoung S. Na
Minkai Xu
Hanchen Wang
Tianfan Fu
Chanyoung Park

Molecular Relational Learning (MRL) is a rapidly growing field that focuses on understanding the interaction dynamics between molecules, which is crucial for applications ranging from catalyst engineering to drug discovery. Despite recent progress, earlier MRL approaches are limited to using only the 2D topological structure of molecules, as obtaining the 3D interaction geometry remains prohibitively expensive. This paper introduces a novel 3D geometric pre-training strategy for MRL (3DMRL) that incorporates a 3D virtual interaction environment, overcoming the limitations of costly traditional quantum mechanical calculation methods. With the constructed 3D virtual interaction environment, 3DMRL trains 2D MRL model to learn the global and local 3D geometric information of molecular interaction. Extensive experiments on various tasks using real-world datasets, including out-of-distribution and extrapolation scenarios, demonstrate the effectiveness of 3DMRL, showing up to a 24. 93% improvement in performance across 40 tasks. Our code is publicly available at https: //github. com/Namkyeong/3DMRL.

PDF Details

AAAI Conference 2025 Conference Paper

Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations

Pengcheng Jiang
Cao Xiao
Tianfan Fu
Parminder Bhatia
Taha Kass-Hout
Jimeng Sun
Jiawei Han

Molecular representation learning is vital for various downstream applications, including the analysis and prediction of molecular properties and side effects. While Graph Neural Networks (GNNs) have been a popular framework for modeling molecular data, they often struggle to capture the full complexity of molecular representations. In this paper, we introduce a novel method called Gode, which accounts for the dual-level structure inherent in molecules. Molecules possess an intrinsic graph structure and simultaneously function as nodes within a broader molecular knowledge graph. Gode integrates individual molecular graph representations with multi-domain biochemical data from knowledge graphs. By pre-training two GNNs on different graph structures and employing contrastive learning, Gode effectively fuses molecular structures with their corresponding knowledge graph substructures. This fusion yields a more robust and informative representation, enhancing molecular property predictions by leveraging both chemical and biological information. When fine-tuned across 11 chemical property tasks, our model significantly outperforms existing benchmarks, achieving an average ROC-AUC improvement of 12.7% for classification tasks and an average RMSE/MAE improvement of 34.4% for regression tasks. Notably, Gode surpasses the current leading model in property prediction, with advancements of 2.2% in classification and 7.2% in regression tasks.

PDF Details DOI

TMLR Journal 2025 Journal Article

Gradient GA: Gradient Genetic Algorithm For Drug Molecular Design

Debadyuti Mukherjee
Chris Zhuang
Yingzhou Lu
Tianfan Fu
Ruqi Zhang

Molecular discovery has brought great benefit to the chemical industry. Various molecu- lar design techniques have been developed to identify molecules with desirable properties. Traditional optimization methods, such as genetic algorithms, continue to achieve state-of- the-art results across various molecular design benchmarks. However, these techniques rely solely on undirected random exploration, which hinders both the quality of the final solution and the convergence speed. To address this limitation, we propose a novel approach called Gradient Genetic Algorithm (Gradient GA), which incorporates gradient information from the objective function into genetic algorithms. Instead of random exploration, each proposed sample iteratively progresses toward an optimal solution by following the gradient direction. We achieve this by designing a differentiable objective function parameterized by a neural network and utilizing the Discrete Langevin Proposal to enable gradient guidance in discrete molecular spaces. Experimental results demonstrate that our method significantly improves both convergence speed and solution quality, outperforming cutting-edge techniques. The proposed method has shown up to a 25% improvement in the Top 10 score over the vanilla ge- netic algorithm. The code is available at https://github.com/debadyuti23/GradientGA.

PDF Details

NeurIPS Conference 2025 Conference Paper

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning

Yuhao Zhou
Yiheng Wang
Xuming He
Ruoyao Xiao
Zhiwei Li
Qiantai Feng
Zijie Guo
Yuejin Yang

Scientific discoveries increasingly rely on complex multimodal reasoning based on information-intensive scientific data and domain-specific expertise. Empowered by expert-level scientific benchmarks, scientific Multimodal Large Language Models (MLLMs) hold the potential to significantly enhance this discovery process in realistic workflows. However, current scientific benchmarks mostly focus on evaluating the knowledge understanding capabilities of MLLMs, leading to an inadequate assessment of their perception and reasoning abilities. To address this gap, we present the Scientists’ First Exam (SFE) benchmark, designed to evaluate the scientific cognitive capacities of MLLMs through three interconnected levels: scientific signal perception, scientific attribute understanding, scientific comparative reasoning. Specifically, SFE comprises 830 expert-verified VQA pairs across three question types, spanning 66 multimodal tasks across five high-value disciplines. Extensive experiments reveal that current state-of-the-art GPT-o3 and InternVL-3 achieve only 34. 08% and 26. 52% on SFE, highlighting significant room for MLLMs to improve in scientific realms. We hope the insights obtained in SFE will facilitate further developments in AI-enhanced scientific discoveries.

PDF Details

ICML Conference 2024 Conference Paper

Graph Adversarial Diffusion Convolution

Songtao Liu
Jinghui Chen
Tianfan Fu
Lu Lin 0001
Marinka Zitnik
Dinghao Wu

This paper introduces a min-max optimization formulation for the Graph Signal Denoising (GSD) problem. In this formulation, we first maximize the second term of GSD by introducing perturbations to the graph structure based on Laplacian distance and then minimize the overall loss of the GSD. By solving the min-max optimization problem, we derive a new variant of the Graph Diffusion Convolution (GDC) architecture, called Graph Adversarial Diffusion Convolution (GADC). GADC differs from GDC by incorporating an additional term that enhances robustness against adversarial attacks on the graph structure and noise in node features. Moreover, GADC improves the performance of GDC on heterophilic graphs. Extensive experiments demonstrate the effectiveness of GADC across various datasets. Code is available at https: //github. com/SongtaoLiu0823/GADC.

Details

ICLR Conference 2022 Conference Paper

Differentiable Scaffolding Tree for Molecule Optimization

Tianfan Fu
Wenhao Gao 0001
Cao Xiao
Jacob Yasonik
Connor W. Coley
Jimeng Sun 0001

The structural design of functional molecules, also called molecular optimization, is an essential chemical science and engineering task with important applications, such as drug discovery. Deep generative models and combinatorial optimization methods achieve initial success but still struggle with directly modeling discrete chemical structures and often heavily rely on brute-force enumeration. The challenge comes from the discrete and non-differentiable nature of molecule structures. To address this, we propose differentiable scaffolding tree (DST) that utilizes a learned knowledge network to convert discrete chemical structures to locally differentiable ones. DST enables a gradient-based optimization on a chemical graph structure by back-propagating the derivatives from the target properties through a graph neural network (GNN). Our empirical studies show the gradient-based molecular optimizations are both effective and sample efficient (in terms of oracle calling number). Furthermore, the learned graph parameters can also provide an explanation that helps domain experts understand the model output. The code repository (including processed data, trained model, demonstration, molecules with the highest property) is available at https://github.com/futianfan/DST.

Details

NeurIPS Conference 2022 Conference Paper

Reinforced Genetic Algorithm for Structure-based Drug Design

Tianfan Fu
Wenhao Gao
Connor Coley
Jimeng Sun

Structure-based drug design (SBDD) aims to discover drug candidates by finding molecules (ligands) that bind tightly to a disease-related protein (targets), which is the primary approach to computer-aided drug discovery. Recently, applying deep generative models for three-dimensional (3D) molecular design conditioned on protein pockets to solve SBDD has attracted much attention, but their formulation as probabilistic modeling often leads to unsatisfactory optimization performance. On the other hand, traditional combinatorial optimization methods such as genetic algorithms (GA) have demonstrated state-of-the-art performance in various molecular optimization tasks. However, they do not utilize protein target structure to inform design steps but rely on a random-walk-like exploration, which leads to unstable performance and no knowledge transfer between different tasks despite the similar binding physics. To achieve a more stable and efficient SBDD, we propose Reinforced Genetic Algorithm (RGA) that uses neural models to prioritize the profitable design steps and suppress random-walk behavior. The neural models take the 3D structure of the targets and ligands as inputs and are pre-trained using native complex structures to utilize the knowledge of the shared binding physics from different targets and then fine-tuned during optimization. We conduct thorough empirical studies on optimizing binding affinity to various disease targets and show that RGA outperforms the baselines in terms of docking scores and is more robust to random initializations. The ablation study also indicates that the training on different targets helps improve the performance by leveraging the shared underlying physics of the binding processes. The code is available at https: //github. com/futianfan/reinforced-genetic-algorithm.

PDF Details

NeurIPS Conference 2022 Conference Paper

Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization

Wenhao Gao
Tianfan Fu
Jimeng Sun
Connor Coley

Molecular optimization is a fundamental goal in the chemical sciences and is of central interest to drug and material design. In recent years, significant progress has been made in solving challenging problems across various aspects of computational molecular optimizations, emphasizing high validity, diversity, and, most recently, synthesizability. Despite this progress, many papers report results on trivial or self-designed tasks, bringing additional challenges to directly assessing the performance of new methods. Moreover, the sample efficiency of the optimization---the number of molecules evaluated by the oracle---is rarely discussed, despite being an essential consideration for realistic discovery applications. To fill this gap, we have created an open-source benchmark for practical molecular optimization, PMO, to facilitate the transparent and reproducible evaluation of algorithmic advances in molecular optimization. This paper thoroughly investigates the performance of 25 molecular design algorithms on 23 single-objective (scalar) optimization tasks with a particular focus on sample efficiency. Our results show that most ``state-of-the-art'' methods fail to outperform their predecessors under a limited oracle budget allowing 10K queries and that no existing algorithm can efficiently solve certain molecular optimization problems in this setting. We analyze the influence of the optimization algorithm choices, molecular assembly strategies, and oracle landscapes on the optimization performance to inform future algorithm development and benchmarking. PMO provides a standardized experimental setup to comprehensively evaluate and compare new molecule optimization methods with existing ones. All code can be found at https: //github. com/wenhao-gao/mol_opt.

PDF Details

AAAI Conference 2021 Conference Paper

MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization

Tianfan Fu
Cao Xiao
Xinhao Li
Lucas M. Glass
Jimeng Sun

Molecule optimization is a fundamental task for accelerating drug discovery, with the goal of generating new valid molecules that maximize multiple drug properties while maintaining similarity to the input molecule. Existing generative models and reinforcement learning approaches made initial success, but still face difficulties in simultaneously optimizing multiple drug properties. To address such challenges, we propose the MultI-constraint MOlecule SAmpling (MIMOSA) approach, a sampling framework to use input molecule as an initial guess and sample molecules from the target distribution. MIMOSA first pretrains two propertyagnostic graph neural networks (GNNs) for molecule topology and substructure-type prediction, where a substructure can be either atom or single ring. For each iteration, MIMOSA uses the GNNs’ prediction and employs three basic substructure operations (add, replace, delete) to generate new molecules and associated weights. The weights can encode multiple constraints including similarity and drug property constraints, upon which we select promising molecules for next iteration. MIMOSA enables flexible encoding of multiple property- and similarity-constraints and can efficiently generate new molecules that satisfy various property constraints and achieved up to 49. 1% relative improvement over the best baseline in terms of success rate.

PDF Details

NeurIPS Conference 2021 Conference Paper

Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development

Kexin Huang
Tianfan Fu
Wenhao Gao
Yue Zhao
Yusuf Roohani
Jure Leskovec
Connor Coley
Cao Xiao

Therapeutics machine learning is an emerging field with incredible opportunities for innovation and impact. However, advancement in this field requires the formulation of meaningful tasks and careful curation of datasets. Here, we introduce Therapeutics Data Commons (TDC), the first unifying platform to systematically access and evaluate machine learning across the entire range of therapeutics. To date, TDC includes 66 AI-ready datasets spread across 22 learning tasks and spanning the discovery and development of safe and effective medicines. TDC also provides an ecosystem of tools and community resources, including 33 data functions and diverse types of data splits, 23 strategies for systematic model evaluation, 17 molecule generation oracles, and 29 public leaderboards. All resources are integrated and accessible via an open Python library. We carry out extensive experiments on selected datasets, demonstrating that even the strongest algorithms fall short of solving key therapeutics challenges, including distributional shifts, multi-scale and multi-modal learning, and robust generalization to novel data points. We envision that TDC can facilitate algorithmic advances and considerably accelerate machine-learning model development, validation and transition into biomedical and clinical implementation. TDC is available at https: //tdcommons. ai.

PDF Details

AAAI Conference 2020 Conference Paper

CORE: Automatic Molecule Optimization Using Copy & Refine Strategy

Tianfan Fu
Cao Xiao
Jimeng Sun

Molecule optimization is about generating molecule Y with more desirable properties based on an input molecule X. The state-of-the-art approaches partition the molecules into a large set of substructures S and grow the new molecule structure by iteratively predicting which substructure from S to add. However, since the set of available substructures S is large, such an iterative prediction task is often inaccurate especially for substructures that are infrequent in the training data. To address this challenge, we propose a new generating strategy called “Copy&Reﬁne” (CORE), where at each step the generator ﬁrst decides whether to copy an existing substructure from input X or to generate a new substructure, then the most promising substructure will be added to the new molecule. Combining together with scaffolding tree generation and adversarial training, CORE can signiﬁcantly improve several latest molecule optimization methods in various measures including drug likeness (QED), dopamine receptor (DRD2) and penalized LogP. We tested CORE and baselines using the ZINC database and CORE obtained up to 11% and 21% relatively improvement over the baselines on success rate on the complete test set and the subset with infrequent substructures, respectively.

PDF Details

IJCAI Conference 2019 Conference Paper

DDL: Deep Dictionary Learning for Predictive Phenotyping

Tianfan Fu
Trong Nghia Hoang
Cao Xiao
Jimeng Sun

Predictive phenotyping is about accurately predicting what phenotypes will occur in the next clinical visit based on longitudinal Electronic Health Record (EHR) data. Several deep learning (DL) models have demonstrated great performance in predictive phenotyping. However, these DL-based phenotyping models requires access to a large amount of labeled data, which are often expensive to acquire. To address this label-insufficient challenge, we propose a deep dictionary learning framework (DDL) for phenotyping, which utilizes unlabeled data as a complementary source of information to generate a better, more succinct data representation. With extensive experiments on multiple real-world EHR datasets, we demonstrated DDL can outperform the state of the art predictive phenotyping methods on a wide variety of clinical tasks that require patient phenotyping such as heart failure classification, mortality prediction, and sequential prediction. All empirical results consistently show that unlabeled data can indeed be used to generate better data representation, which helps improve DDL's phenotyping performance over existing baseline methods that only uses labeled data.

PDF Details

UAI Conference 2016 Conference Paper

Quasi-Newton Hamiltonian Monte Carlo

Tianfan Fu
Luo Luo
Zhihua Zhang 0004

The Hamiltonian Monte Carlo (HMC) method has become significantly popular in recent years. It is the state-of-the-art MCMC sampler due to its more efficient exploration to the parameter space than the standard random-walk based proposal. The key idea behind HMC is that it makes use of first-order gradient information about the target distribution. In this paper, we propose a novel dynamics using second-order geometric information about the desired distribution. The second-order information is estimated by using a quasi-Newton method (say, the BFGS method), so it does not bring heavy computational burden. Moreover, our theoretical analysis guarantees that this dynamics remains the target distribution invariant. As a result, the proposed quasiNewton Hamiltonian Monte Carlo (QNHMC) algorithm traverses the parameter space more efficiently than the standard HMC and produces a less correlated series of samples. Finally, empirical evaluation on simulated data verifies the effectiveness and efficiency of our approach. We also conduct applications of QNHMC in Bayesian logistic regression and online Bayesian matrix factorization problems.

Details