Fenglei Cao
Research Subjects
Fenglei Cao has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
Alan Qi
Fudan University
2 shared publicationsJunyi An
Shanghai Academy of Artificial Intelligence for Science, Shanghai, China
2 shared publications- Li-Cheng Xu
Shanghai Academy of Artificial Intelligence for Science, Shanghai, China
2 shared publications - Miao-Jiong Tang
Center of Chemistry for Frontier Technologies Department of Chemistry Zhejiang University Hangzhou 310027 P.R. China
2 shared publications - Yuan Qi
Shanghai Academy of Artificial Intelligence for Science, Shanghai, China
2 shared publications Alan M. Mathiowetz
Medicine Design, Pfizer Inc., 1 Portland Street, Cambridge, Massachusetts 02139, United States
1 shared publication
Latest Publications
- Open Access
- 5 September 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Exploring the Potential of an End-to-End AI Design Framework for Photoresponsive Drug Delivery.
In our effort to more reliably leverage large language models for designing effective photoresponsive molecular materials for drug delivery, we developed the Explanation CPO (XCPO), an end-to-end reinforcement learning fine-tuning workflow. The maturity of RLHF techniques has greatly stimulated the flourishing application of general-purpose LLMs across various scientific domains. Compared with representative RLHF approaches like CPO, our XCPO emphasizes the potential and effectiveness of a fully AI-driven, end-to-end fine-tuning process. In this workflow, the preference dataset for RLFT is derived from the combined output of AI models and XAI tools, whereas traditional RLHF pipelines require domain researchers to identify key features based on their expertise. This streamlined improvement via integration with XAI tools has not been previously reported. Based on our machine learning evaluation and computational chemistry validation, our end-to-end XCPO approach outperformed CPO by over 27\% on the MoE-based Qwen3Moe architecture, while the designed photoresponsive molecular materials aligned well with chemical intuition. Our end-to-end workflow compensates for the subjective influence of chemists' intuitive experience, enabling the model to iterate within a fully AI-driven process.
- 5 September 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessExploring the Potential of an End-to-End AI Design Framework for Photoresponsive Drug Delivery.
In our effort to more reliably leverage large language models for designing effective photoresponsive molecular materials for drug delivery, we developed the Explanation CPO (XCPO), an end-to-end reinforcement learning fine-tuning workflow. The maturity of RLHF techniques has greatly stimulated the flourishing application of general-purpose LLMs across various scientific domains. Compared with representative RLHF approaches like CPO, our XCPO emphasizes the potential and effectiveness of a fully AI-driven, end-to-end fine-tuning process. In this workflow, the preference dataset for RLFT is derived from the combined output of AI models and XAI tools, whereas traditional RLHF pipelines require domain researchers to identify key features based on their expertise. This streamlined improvement via integration with XAI tools has not been previously reported. Based on our machine learning evaluation and computational chemistry validation, our end-to-end XCPO approach outperformed CPO by over 27\% on the MoE-based Qwen3Moe architecture, while the designed photoresponsive molecular materials aligned well with chemical intuition. Our end-to-end workflow compensates for the subjective influence of chemists' intuitive experience, enabling the model to iterate within a fully AI-driven process.
- 19 August 2025
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 7 (9) , 1561-1571
A unified pre-trained deep learning framework for cross-task reaction performance prediction and synthesis planning
- 19 August 2025
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 7 (9) , 1561-1571
A unified pre-trained deep learning framework for cross-task reaction performance prediction and synthesis planning
- Open Access
- 2 July 2025
- Published by Springer Nature in Research Square
A unified pre-trained deep learning framework for cross-task reaction performance prediction and synthesis planning
Artificial intelligence has transformed the field of precise organic synthesis. Data-driven methods, including machine learning and deep learning, have shown great promise in predicting reaction performance and synthesis planning. However, the inherent methodological divergence between numerical regression-driven reaction performance prediction and sequence generation-based synthesis planning creates formidable challenges in constructing a unified deep learning architecture. Here we present RXNGraphormer, a framework to jointly address these tasks through a unified pre-training approach. By synergizing graph neural networks for intramolecular pattern recognition with Transformer-based models for intermolecular interaction modeling, and training on 13 million reactions via a carefully designed strategy, RXNGraphormer achieves state-of-the-art performance across eight benchmark datasets for reactivity/selectivity prediction and forward-/retro-synthesis planning, as well as three external realistic datasets for reactivity and selectivity prediction. Notably, the model generates chemically meaningful embeddings that: (1) spontaneously cluster reactions by type without explicit supervision, and (2) reveal structure-performance relationships through post-hoc interpretation. This work bridges the critical gap between performance prediction and synthesis planning tasks in chemical AI, offering a versatile tool for accurate reaction prediction and synthesis design.
- 2 July 2025
- Published by Springer Nature in Research Square
Open AccessA unified pre-trained deep learning framework for cross-task reaction performance prediction and synthesis planning
Artificial intelligence has transformed the field of precise organic synthesis. Data-driven methods, including machine learning and deep learning, have shown great promise in predicting reaction performance and synthesis planning. However, the inherent methodological divergence between numerical regression-driven reaction performance prediction and sequence generation-based synthesis planning creates formidable challenges in constructing a unified deep learning architecture. Here we present RXNGraphormer, a framework to jointly address these tasks through a unified pre-training approach. By synergizing graph neural networks for intramolecular pattern recognition with Transformer-based models for intermolecular interaction modeling, and training on 13 million reactions via a carefully designed strategy, RXNGraphormer achieves state-of-the-art performance across eight benchmark datasets for reactivity/selectivity prediction and forward-/retro-synthesis planning, as well as three external realistic datasets for reactivity and selectivity prediction. Notably, the model generates chemically meaningful embeddings that: (1) spontaneously cluster reactions by type without explicit supervision, and (2) reveal structure-performance relationships through post-hoc interpretation. This work bridges the critical gap between performance prediction and synthesis planning tasks in chemical AI, offering a versatile tool for accurate reaction prediction and synthesis design.
- Open Access
An Open Quantum Chemistry Property Database of 120 Kilo Molecules with 20 Million Conformers
Artificial intelligence is revolutionizing computational chemistry, bringing unprecedented innovation and efficiency to the field. To further advance research and expedite progress, we introduce the Quantum Open Organic Molecular (QO2Mol) database -- a large-scale quantum chemistry dataset designed for professional and transformative research in organic molecular sciences under an open-source license. The database comprises 120,000 organic molecules and approximately 20 million conformers, encompassing 10 different elements (C, H, O, N, S, P, F, Cl, Br, I), with heavy atom counts exceeding 40. Utilizing the high-precision B3LYP/def2-SVP quantum mechanical level, each conformation was meticulously computed for quantum mechanical properties, including potential energy and forces. These molecules are derived from fragments of compounds in ChEMBL, ensuring their structural relevance to real-world compounds. Its extensive coverage of molecular structures and diverse elemental composition enables comprehensive studies of structure-property relationships, enhancing the accuracy and applicability of machine learning models in predicting molecular behaviors. The QO2Mol database and benchmark codes are available at https://github.com/saiscn/QO2Mol/ .
Open AccessAn Open Quantum Chemistry Property Database of 120 Kilo Molecules with 20 Million Conformers
Artificial intelligence is revolutionizing computational chemistry, bringing unprecedented innovation and efficiency to the field. To further advance research and expedite progress, we introduce the Quantum Open Organic Molecular (QO2Mol) database -- a large-scale quantum chemistry dataset designed for professional and transformative research in organic molecular sciences under an open-source license. The database comprises 120,000 organic molecules and approximately 20 million conformers, encompassing 10 different elements (C, H, O, N, S, P, F, Cl, Br, I), with heavy atom counts exceeding 40. Utilizing the high-precision B3LYP/def2-SVP quantum mechanical level, each conformation was meticulously computed for quantum mechanical properties, including potential energy and forces. These molecules are derived from fragments of compounds in ChEMBL, ensuring their structural relevance to real-world compounds. Its extensive coverage of molecular structures and diverse elemental composition enables comprehensive studies of structure-property relationships, enhancing the accuracy and applicability of machine learning models in predicting molecular behaviors. The QO2Mol database and benchmark codes are available at https://github.com/saiscn/QO2Mol/ .
- 29 December 2023
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 20 (2) , 799-818
Development and Comprehensive Benchmark of a High-Quality AMBER-Consistent Small Molecule Force Field with Broad Chemical Space Coverage for Molecular Modeling and Free Energy Calculation
Biomolecular simulations have become an essential tool in contemporary drug discovery, and molecular mechanics force fields (FFs) constitute its cornerstone. Developing a high quality and broad coverage general FF is a significant undertaking that requires substantial expert knowledge and computing resources, which is beyond the scope of general practitioners. Existing FFs originate from only a limited number of groups and organizations, and they either suffer from limited numbers of training sets, lower than desired quality because of oversimplified representations, or are costly for the molecular modeling community to access. To address these issues, in this work, we developed an AMBER-consistent small molecule FF with extensive chemical space coverage, and we provide Open Access parameters for the entire modeling community. To validate our FF, we carried out benchmarks of quantum mechanics (QM)/molecular mechanics conformer comparison and free energy perturbation calculations on several benchmark data sets. Our FF achieves a higher level of performance at reproducing QM energies and geometries than two popular open-source FFs, OpenFF2 and GAFF2. In relative binding free energy calculations for 31 protein-ligand data sets, comprising 1079 pairs of ligands, the new FF achieves an overall root-mean-square error of 1.19 kcal/mol for ΔΔG and 0.92 kcal/mol for ΔG on a subset of 463 ligands without bespoke fitting to the data sets. The results are on par with those of the leading commercial series of OPLS FFs.
- 29 December 2023
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 20 (2) , 799-818
Development and Comprehensive Benchmark of a High-Quality AMBER-Consistent Small Molecule Force Field with Broad Chemical Space Coverage for Molecular Modeling and Free Energy Calculation
Biomolecular simulations have become an essential tool in contemporary drug discovery, and molecular mechanics force fields (FFs) constitute its cornerstone. Developing a high quality and broad coverage general FF is a significant undertaking that requires substantial expert knowledge and computing resources, which is beyond the scope of general practitioners. Existing FFs originate from only a limited number of groups and organizations, and they either suffer from limited numbers of training sets, lower than desired quality because of oversimplified representations, or are costly for the molecular modeling community to access. To address these issues, in this work, we developed an AMBER-consistent small molecule FF with extensive chemical space coverage, and we provide Open Access parameters for the entire modeling community. To validate our FF, we carried out benchmarks of quantum mechanics (QM)/molecular mechanics conformer comparison and free energy perturbation calculations on several benchmark data sets. Our FF achieves a higher level of performance at reproducing QM energies and geometries than two popular open-source FFs, OpenFF2 and GAFF2. In relative binding free energy calculations for 31 protein-ligand data sets, comprising 1079 pairs of ligands, the new FF achieves an overall root-mean-square error of 1.19 kcal/mol for ΔΔG and 0.92 kcal/mol for ΔG on a subset of 463 ligands without bespoke fitting to the data sets. The results are on par with those of the leading commercial series of OPLS FFs.