Tianfan Fu

Deep learning holds immense promise for spectroscopy, yet research and evaluation in this emerging field often lack standardized formulations. To address this issue, we introduce SpectrumWorld, a unified infrastructure for AI-driven spectroscopy. SpectrumWorld consists of SpectrumLab, a pioneering unified platform designed to systematize and accelerate deep learning research in spectroscopy; SpectrumAnnotator, an annotation and curation module that generates high-quality benchmarks from limited seed data; and SpectrumVQA, a multi-layered benchmark suite covering 14 spectroscopic tasks and over 10 spectrum types, featuring spectra curated from over 1.2 million distinct chemical substances. Thorough empirical studies on SpectrumVQA with 23 cutting-edge multimodal LLMs reveal critical limitations of current approaches. We hope SpectrumWorld will serve as a crucial foundation for future advancements in deep learning-driven spectroscopy. Code is released at https://github.com/InternScience/SpectrumLab.

Machine learning (ML) has seen promising developments in materials science, yet its efficacy largely depends on detailed crystal structural data, which are often complex and hard to obtain, limiting their applicability in real-world material synthesis processes. An alternative, using compositional descriptors, offers a simpler approach by indicating the elemental ratios of compounds without detailed structural insights. However, accurately representing materials solely with compositional descriptors presents challenges due to polymorphism, where a single composition can correspond to various structural arrangements, creating ambiguities in its representation. To this end, we introduce PCRL, a novel approach that employs probabilistic modeling of composition to capture the diverse polymorphs from available structural information. Extensive evaluations on sixteen datasets demonstrate the effectiveness of PCRL in learning compositional representation, and analysis on model uncertainty highlights its potential applicability of PCRL in material discovery.

Reinforcement learning (RL) is increasingly applied to Protein Language Models (PLMs), yet its effectiveness varies across tasks, and standard metrics such as pass@k can rise even when the model's solvable problem set is shrinking. We introduce two capability-level diagnostics. The Expansion-Shrinkage Ratio (ESR) measures how RL shifts the set of problems a PLM can solve, separating genuine gain from probability redistribution. Dual-Reward ESR reports ESR under both the training reward and an orthogonal evaluator; the gap ΔESR quantifies reward hacking as a single observable number. Applied across four protein design tasks, three RL algorithms (DPO, PPO, GRPO), and two PLM architectures, the diagnostics reveal that RL on PLMs is governed by two reward properties: verifiability, whether the reward is a fixed environment or a learned surrogate vulnerable to distribution shift, and coverage, the fraction of sequence space giving an informative gradient. The two axes produce three regimes with distinct ΔESR signatures: well-covered verifiable rewards yield genuine expansion; sparse verifiable rewards induce a coverage bottleneck; predicted rewards induce reward hacking. Controlled analyses isolate these two factors as operative, letting practitioners predict an RL run's outcome before committing to costly fine-tuning.

Drug discovery remains costly and time-consuming, requiring substantial effort across target identification, lead optimization, and clinical validation. The rapid growth of artificial intelligence (AI) and machine learning (ML), particularly deep learning (DL), has created new opportunities to accelerate these processes by extracting complex patterns from large-scale biological and chemical data. As diverse datasets and modeling approaches continue to expand, there is a growing need for a structured understanding of how AI/ML methods contribute across the drug discovery pipeline.In this review, we provide a stage-wise synthesis of AI/ML applications in drug discovery, spanning target identification, target development, lead identification, lead optimization, and clinical trials. We highlight key methodological paradigms, including representation learning, graph-based modeling, and generative approaches, and discuss how different data modalities (e.g., omics, chemical structures, and pharmacogenomics) can shape computational model design and performance. We further examine critical challenges such as data bias, distributional shifts, quality, as well as the trade-off between predictive performance and mechanistic interpretability. Overall, while AI/ML methods have demonstrated substantial promise in accelerating drug discovery, their effectiveness remains constrained by data limitations and generalization challenges. Future progress will depend on improved data integration, robust evaluation across datasets, and the development of models that balance predictive accuracy with biological interpretability.

Drug discovery is lengthy and expensive, with traditional computer-aided design facing limits. This paper examines integrating quantum computing across the drug development cycle to accelerate and enhance workflows and rigorous decision-making. It highlights quantum approaches for molecular simulation, drug-target interaction prediction, and optimizing clinical trials. Leveraging quantum capabilities could accelerate timelines and costs for bringing therapies to market, improving efficiency and ultimately benefiting public health.

Clinical trials are pivotal for developing new medical treatments but typically carry risks such as patient mortality and enrollment failure that waste immense efforts spanning over a decade. Applying artificial intelligence (AI) to predict key events in clinical trials holds great potential for providing insights to guide trial designs. However, complex data collection and question definition requiring medical expertise have hindered the involvement of AI thus far. This paper tackles these challenges by presenting a comprehensive suite of 23 meticulously curated AI-ready datasets covering multi-modal input features and 8 crucial prediction challenges in clinical trial design, encompassing prediction of trial duration, patient dropout rate/event, serious adverse event, mortality event, trial approval outcome, trial failure reason, drug dose, and design of eligibility criteria. Furthermore, we provide basic validation methods for each task to ensure the datasets’ usability and reliability. We anticipate that the availability of such open-access datasets will catalyze the development of advanced AI approaches for clinical trial design, ultimately advancing clinical trial research and accelerating medical solution development.

In the real world, a molecule is a 3D geometric structure. Compared to 1D SMILES sequences and 2D molecular graphs, 3D molecules represent the most informative molecular modality. Despite the rapid progress of autoregressive-based language models, they cannot handle the generation of 3D molecular conformation due to several challenges: 1) 3D molecular structures are incompatible with LLMs' discrete token space, 2) integrating heterogeneous inputs like proteins, ligands, and text remains difficult within a unified model, and 3) LLMs lack essential scientific priors, hindering the enforcement of physical and chemical constraints during generation. To tackle these issues, we present Chem3DLLM, a unified protein-conditioned multimodal large language model. Our approach designs a novel reversible text encoding for 3D molecular structures using run-length compression, achieving 3x size reduction while preserving complete structural information. This enables seamless integration of molecular geometry with protein pocket features in a single LLM architecture. We employ reinforcement learning with stability-based rewards to optimize chemical validity and incorporate a lightweight protein embedding projector for end-to-end training. Experimental results on structure-based drug design demonstrate state-of-the-art performance with a Vina score of -7.21, validating our unified multimodal approach for practical drug discovery applications.

The biomedical field is beginning to explore the use of quantum machine learning (QML) for tasks traditionally handled by classical machine learning, especially in predicting ADME (absorption, distribution, metabolism, and excretion) properties, which are essential in drug evaluation. However, ADME tasks pose unique challenges for existing quantum computing systems (QCS) frameworks, as they involve both classification with unbalanced dataset and regression problems. These dual requirements make it necessary to adapt and refine current QCS frameworks to effectively address the complexities of ADME predictions.\\We propose a novel training-free scoring mechanism to evaluate QML circuit performance on imbalanced classification and regression tasks. Our mechanism demonstrates significant correlation between scoring metrics and test performance on imbalanced classification tasks. Additionally, we develop methods to quantify continuous similarity relationships between quantum states, enabling performance prediction for regression tasks. This represents the first comprehensive approach to searching and evaluating QCS circuits specifically for regression applications. \\Validation on representative ADME tasks—eight imbalanced classification and four regression—demonstrates moderate correlation between our scoring metrics and circuit performance, significantly outperforming baseline scoring methods that show negligible correlation.

Motivation: Deep learning has deeply influenced protein science, enabling breakthroughs in predicting protein properties, higher-order structures, and molecular interactions. Results: This article introduces DeepProtein, a comprehensive and user-friendly deep learning library tailored for protein-related tasks. It enables researchers to seamlessly address protein data with cutting-edge deep learning models. To assess model performance, we establish a benchmark that evaluates different deep learning architectures across multiple protein-related tasks, including protein function prediction, subcellular localization prediction, protein–protein interaction prediction, and protein structure prediction. Furthermore, we introduce DeepProt-T5, a series of fine-tuned Prot-T5-based models that achieve state-of-the-art performance on four benchmark tasks, while demonstrating competitive results on six of others. Comprehensive documentation and tutorials are available which could ensure accessibility and support reproducibility. Availability and implementation: Built upon the widely used drug discovery library DeepPurpose, DeepProtein is publicly available at https://github.com/jiaqingxie/DeepProtein.