ABSTRACT: Predicting quantum chemical properties is a fundamental challenge for computational chemistry. While the development of graph neural networks has advanced molecular representation learning and property prediction, their performance could be further enhanced by incorporating three-dimensional (3D) structural geometry into two-dimensional (2D) molecular graph representation. In this study, we introduce the PointGAT model for quantum molecular property prediction, which integrates 3D molecular coordinates with graph-attention modeling. Comparison with other current models in molecular prediction tasks showed that PointGAT could provide higher predictive accuracy in various benchmark data sets from MoleculeNet, including ESOL, FreeSolv, Lipop, HIV, and 6 out of 12 tasks of the QM9 data set. To further examine PointGAT prediction of quantum mechanical (QM) energies, we constructed a C10 data set comprising 11,841 charged and chiral carbocation intermediates with QM energies calculated at the DM21/6-31G*//B3LYP/6-31G* levels. Notably, PointGAT achieved an R2 value of 0.950 and an MAE of 1.616 kcal/mol, outperforming even the best-performing graph neural network model with a reduction of 0.216 kcal/mol in MAE and an improvement of 0.050 in R2. Additional ablation studies indicated…

ABSTRACT: Glycosylation is a valuable tool for modulating protein solubility; however, the lack of reliable research strategies has impeded efficient progress in understanding and applying this modification. This study aimed to bridge this gap by investigating the solubility of a model glycoprotein molecule, the carbohydrate-binding module (CBM), through a two-stage process. In the first stage, an approach involving chemical synthesis, comparative analysis, and molecular dynamics simulations of a library of glycoforms was employed to elucidate the effect of different glycosylation patterns on solubility and the key factors responsible for the effect. In the second stage, a predictive mathematical formula, innovatively harnessing machine learning algorithms, was derived to relate solubility to the identified key factors and accurately predict the solubility of the newly designed glycoforms. Demonstrating feasibility and effectiveness, this two-stage approach offers a valuable strategy for advancing glycosylation research, especially for the discovery of glycoforms with increased solubility. For detail：https://doi.org/10.1021/acs.biomac.4c00134

ABSTRACT: Cytochrome P450 enzymes (CYPs) play a crucial role in Phase I drug metabolism in the human body, and CYP activity toward compounds can significantly affect druggability, making early prediction of CYP activity and substrate identification essential for therapeutic development. Here, we established a deep learning model for assessing potential CYP substrates, DeepP450, by fine-tuning protein and molecule pretrained models through feature integration with cross-attention and self-attention layers. This model exhibited high prediction accuracy (0.92) on the test set, with area under the receiver operating characteristic curve (AUROC) values ranging from 0.89 to 0.98 in substrate/nonsubstrate predictions across the nine major human CYPs, surpassing current benchmarks for CYP activity prediction. Notably, DeepP450 uses only one model to predict substrates/nonsubstrates for any of the nine CYPs and exhibits certain generalizability on novel compounds and different categories of human CYPs, which could greatly facilitate early stage drug design by avoiding CYP-reactive compounds. For detail：https://pubs.acs.org/doi/10.1021/acs.jcim.4c00115

In the 2024 Tsinghua University Campus Marathon, doctoral student Zhang Rong, from the 2018 cohort, performed remarkably, achieving fourth place in the women's half marathon category with a time of 1 hour, 44 minutes, and 22 seconds. Among current students, she ranked first in the women's category, simultaneously setting a new personal best (previously PB 1:48:22). It's truly exceptional for a non-athlete, burdened with heavy research pressures, to achieve such results. Zhang Rong expressed, "Marathons rely on strong perseverance, unwavering belief, and the relentless pursuit of challenging and surpassing one's own physical limits. During my time at Tsinghua, the university's spirit of sportsmanship flowed through my veins. Competing alongside outstanding individuals brings immense happiness and enjoyment. Continuous self-improvement and moral integrity are essential. I hope every student can develop a passion for sports and experience the allure of competitive athletics. Balancing research and personal development, maintaining such resilience, and embracing more challenges are key to growth."

On August 26th, the finals of the inaugural AI Drug Development Algorithm Competition were successfully held at Tsinghua University School of Pharmacy. The competition was jointly initiated by Tsinghua University School of Pharmacy, Baidu PaddlePaddle, Baidu AI Cloud, and Lingang Laboratory, with strong support from organizations such as the Chinese Pharmaceutical Association. Several pharmaceutical experts were invited to serve on the expert committee. Following a captivating morning of presentations, the ViSNet-Drug team from Microsoft Research Asia was awarded first prize. The second prize was shared by the Blue Wind team from the Shanghai Institute of Materia Medica, Chinese Academy of Sciences, and the MolAI team from Shanghai Jiao Tong University. The third prize was awarded to the Sword team from the Shanghai Institute of Materia Medica, Chinese Academy of Sciences, the Lightning team from Zhejiang University, the Hulala! team from Nanjing University, and the Paipai team. Additionally, eight other teams received honorable mentions.

ABSTRACT: Accurate prediction of the structurally diverse complementarity determining region heavy chain 3 (CDR-H3) loop structure remains a primary and long-standing challenge for antibody modeling. Here, we present the H3-OPT toolkit for predicting the 3D structures of monoclonal antibodies and nanobodies. H3-OPT combines the strengths of AlphaFold2 with a pre-trained protein language model, and provides a 2.24 Å average RMSDCα between predicted and experimentally determined CDR-H3 loops, thus outperforming other current computational methods in our non-redundant high-quality dataset. The model was validated by experimentally solving three structures of anti-VEGF nanobodies predicted by H3-OPT. We examined the potential applications of H3-OPT through analyzing antibody surface properties and antibody-antigen interactions. This structural prediction tool can be used to optimize antibody-antigen binding, and to engineer therapeutic antibodies with biophysical properties for specialized drug administration route. For detail：https://elifesciences.org/reviewed-preprints/91512

Tian Yang, from the Tian Bo-Xue research group at Tsinghua University, led a team that introduced an opportunity discovery system developed using computational chemistry, machine learning, and expert systems. This system has identified various ultra-fine pharmaceutical building blocks and conducted their synthesis and industrialization. The 9th China International "Internet+" College Student Innovation and Entrepreneurship Competition, Beijing Division, was organized by the Beijing Municipal Education Commission. It is renowned for its extensive participation, with the highest number of universities involved, the highest level of competition, and the most significant impact in the field of innovation and entrepreneurship. It has become an important platform for advancing reforms in innovation and entrepreneurship education at universities and promoting the comprehensive development of university students.

ABSTRACT: Protein-DNA interaction is critical for life activities such as replication, transcription, and splicing. Identifying protein-DNA binding residues is essential for modeling their interaction and downstream studies. However, developing accurate and efficient computational methods for this task remains challenging. Improvements in this area have the potential to drive novel applications in biotechnology and drug design. In this study, we propose a novel approach called CLAPE, which combines a pre-trained protein language model and the contrastive learning method to predict DNA binding residues. We trained the CLAPE-DB model on the protein-DNA binding sites dataset and evaluated the model performance and generalization ability through various experiments. The results showed that the AUC values of the CLAPE-DB model on the two benchmark datasets reached 0.871 and 0.881, respectively, indicating superior performance compared to other existing models. CLAPE-DB showed better generalization ability and was specific to DNA-binding sites. In addition, we trained CLAPE on different protein-ligand binding sites datasets, demonstrating that CLAPE is a general framework for binding sites prediction. To facilitate the scientific community, the benchmark datasets and…

The SRT project "AI Algorithm for Optimizing Small Molecule Drug ADMET Properties" guided by Professor Boxue-Tian, was awarded the Third Prize in the Basic Science category at the 41st "Challenge Cup" Extracurricular Academic Science and Technology Works Competition held at Tsinghua University in April 2023. team: liaoyizheng; xx yizheng liao

On April 30, 2023, the tenth edition of Tsinghua University's "President's Cup" Innovation Challenge concluded successfully in the Jianhua Building of Tsinghua School of Economics and Management. Following intense competition, 15 out of 127 registered teams advanced to the finals, showcasing remarkable innovation and entrepreneurial potential. Led by Ph.D. student Tian Yang from Tsinghua University's Tian Bo Xue research group, the team introduced the development and industrialization of a national first-class new animal medicine, " HEALITY," targeting major economic animal diseases, particularly prevalent diarrhea. Through a captivating presentation and insightful responses during the competition, they demonstrated the project's innovation, feasibility, and significant societal contributions, ultimately earning them the Challenge Award. This competition not only highlighted the innovative spirit and entrepreneurial potential of Tsinghua University students but also emphasized the importance of innovation for societal progress. The successful organization of Tsinghua University's "President's Cup" Innovation Challenge provided a platform for students to showcase their creative and innovative projects. Additionally, it promoted the continuity and development of the culture of innovation and entrepreneurship, infusing fresh vitality into…