Youjun Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Youjun Xu has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Jianfeng Pei
Center for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing 100871, China
5 shared publications - Luhua Lai
Center for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing 100871, China
5 shared publications - Shiwei Wang
BNLMS, College of Chemistry and Molecular Engineering, Peking University, Beijing 100871, China
2 shared publications - Chenjing Cai
Center for Quantitative Biology, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing 100871, PR China
1 shared publication - Chia-Han Chou
Infinite Intelligence Pharma
1 shared publication - Fei Xiao
MOE Key Laboratory of Geriatric Diseases and Immunology Suzhou Key Laboratory of Pathogen Bioscience and Anti-infective Medicine Department of Bioinformatics Center for Systems Biology School of Life Sciences Suzhou Medical College of Soochow University Suzhou China
1 shared publication
Latest Publications
- 8 February 2023
- Published by Springer Nature
- p. 159-182
Graph Kernel Learning for Predictive Toxicity Models
- 8 February 2023
- Published by Springer Nature
- p. 159-182
Graph Kernel Learning for Predictive Toxicity Models
- Open Access
A Transferable Deep Learning Approach to Fast Screen Potent Antiviral Drugs against SARS-CoV-2
The COVID-19 pandemic calls for rapid development of effective treatments. Although various drug repurpose approaches have been used to screen the FDA-approved drugs and drug candidates in clinical phases against SARS-CoV-2, the coronavirus that causes this disease, no magic bullets have been found until now. We used directed message passing neural network to first build a broad-spectrum anti-beta-coronavirus compound prediction model, which gave satisfactory predictions on newly reported active compounds against SARS-CoV-2. Then we applied transfer learning to fine-tune the model with the recently reported anti-SARS-CoV-2 compounds. The fine-tuned model was applied to screen a large compound library with 4.9 million drug-like molecules from ZINC15 database and recommended a list of potential anti-SARS-CoV-2 compounds for further experimental testing. As a proof-of-concept, we experimentally tested 7 high-scored compounds that also demonstrated good binding strength in docking study against the 3C-like protease of SARS-CoV-2 and found one novel compound that inhibited the enzyme with an IC 50 of 37.0 μM. Our model is highly efficient and can be used to screen large compound databases with billions or more compounds to accelerate the drug discovery process for the treatment of COVID-19.
Open AccessA Transferable Deep Learning Approach to Fast Screen Potent Antiviral Drugs against SARS-CoV-2
The COVID-19 pandemic calls for rapid development of effective treatments. Although various drug repurpose approaches have been used to screen the FDA-approved drugs and drug candidates in clinical phases against SARS-CoV-2, the coronavirus that causes this disease, no magic bullets have been found until now. We used directed message passing neural network to first build a broad-spectrum anti-beta-coronavirus compound prediction model, which gave satisfactory predictions on newly reported active compounds against SARS-CoV-2. Then we applied transfer learning to fine-tune the model with the recently reported anti-SARS-CoV-2 compounds. The fine-tuned model was applied to screen a large compound library with 4.9 million drug-like molecules from ZINC15 database and recommended a list of potential anti-SARS-CoV-2 compounds for further experimental testing. As a proof-of-concept, we experimentally tested 7 high-scored compounds that also demonstrated good binding strength in docking study against the 3C-like protease of SARS-CoV-2 and found one novel compound that inhibited the enzyme with an IC 50 of 37.0 μM. Our model is highly efficient and can be used to screen large compound databases with billions or more compounds to accelerate the drug discovery process for the treatment of COVID-19.
- Top Cited PapersOpen Access
- 3 March 2020
- Published by Royal Society of Chemistry (RSC) in Chemical Science
- Vol. 11 (12) , 3355-3364
Automatic retrosynthetic route planning using template-free models
Retrosynthetic pathway planning using a template-free model coupled with heuristic Monte Carlo tree search.
- 3 March 2020
- Published by Royal Society of Chemistry (RSC) in Chemical Science
- Vol. 11 (12) , 3355-3364
Top Cited PapersOpen AccessAutomatic retrosynthetic route planning using template-free models
Retrosynthetic pathway planning using a template-free model coupled with heuristic Monte Carlo tree search.
- 1 December 2019
- Published by Elsevier in Drug Discovery Today: Technologies
- Vol. 32-33, 19-27
Efficient molecular encoders for virtual screening
- 1 December 2019
- Published by Elsevier in Drug Discovery Today: Technologies
- Vol. 32-33, 19-27
Efficient molecular encoders for virtual screening
- Open Access
- 23 May 2019
- Published by American Chemical Society (ACS) in ChemRxiv
Automatic Retrosynthetic Pathway Planning Using Template-free Models
We present an attention-based Transformer model for automatic retrosynthesis route planning. Our approach starts from reactants prediction of single-step organic reactions for given products, followed by Monte Carlo tree search-based automatic retrosynthetic pathway prediction. Trained on two datasets from the United States patent literature, our models achieved a top-1 prediction accuracy of over 54.6% and 63.0% with more than 95% and 99.6% validity rate of SMILES, respectively, which is the best up to now to our knowledge. We also demonstrate the application potential of our model by successfully performing multi-step retrosynthetic route planning for four case products, i.e., antiseizure drug Rufinamide, a novel allosteric activator, an inhibitor of human acute-myeloid-leukemia cells and a complex intermediate of drug candidate. Further, by using heuristics Monte Carlo tree search, we achieved automatic retrosynthetic pathway searching and successfully reproduced published synthesis pathways. In summary, our model has achieved the state-of-the-art performance on single-step retrosynthetic prediction and provides a novel strategy for automatic retrosynthetic pathway planning.
- 23 May 2019
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessAutomatic Retrosynthetic Pathway Planning Using Template-free Models
We present an attention-based Transformer model for automatic retrosynthesis route planning. Our approach starts from reactants prediction of single-step organic reactions for given products, followed by Monte Carlo tree search-based automatic retrosynthetic pathway prediction. Trained on two datasets from the United States patent literature, our models achieved a top-1 prediction accuracy of over 54.6% and 63.0% with more than 95% and 99.6% validity rate of SMILES, respectively, which is the best up to now to our knowledge. We also demonstrate the application potential of our model by successfully performing multi-step retrosynthetic route planning for four case products, i.e., antiseizure drug Rufinamide, a novel allosteric activator, an inhibitor of human acute-myeloid-leukemia cells and a complex intermediate of drug candidate. Further, by using heuristics Monte Carlo tree search, we achieved automatic retrosynthetic pathway searching and successfully reproduced published synthesis pathways. In summary, our model has achieved the state-of-the-art performance on single-step retrosynthetic prediction and provides a novel strategy for automatic retrosynthetic pathway planning.
- Open Access
- 1 January 2015
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 13, 520-527
Comparisons of Prostate Cancer Inhibitors Abiraterone and TOK-001 Binding with CYP17A1 through Molecular Dynamics
Cytochrome P450 17A1 (CYP17A1) is associated in the steroid hormone biosynthesis in human. As cell proliferation of prostate cancer in response to androgen steroid, an inhibition of CYP17A1 becomes an alternative approach to inhibit biosynthesis of androgen and support treatment of prostate cancer. However, biology-driven inhibitor development of prostate cancer is poorly elucidated. The aims of this study are to address structural differences at atomic-level between CYP17A1 and inhibitors i.e., abiraterone and TOK-001, and further investigate the effect of point mutation of CYP17A1 on the active site stability and the local interactions that are hydrophobic interaction and hydrogen bonding throughout molecular dynamics (MD) simulation. After performing multiple comparisons among four different complexes across CYP17A1 and inhibitors, interestingly TOK-001 oriented toward the active pocket and formed larger volume with I-helix of CYP17A1 than abiraterone, whereas abiraterone showed tighter binding and more active site stability. Considering on the effect of hydrophobic interaction and hydrogen bonding between abiraterone and CYP17A1, the key residues of Phe114, Ile371, Val482, and Asn202 were identified. This contributes into tight binding interactions; however abiraterone is effectively weakened along with the global conformation mobility increased in A105L mutation. Surprisingly, overall conformation of the CYP17A1 remained stable when bound to TOK-001. This basic knowledge can guide future experiments on design of efficient inhibitors for CYP17A1, which provides theoretical basis of androgen-dependent disease therapy.
- 1 January 2015
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 13, 520-527
Open AccessComparisons of Prostate Cancer Inhibitors Abiraterone and TOK-001 Binding with CYP17A1 through Molecular Dynamics
Cytochrome P450 17A1 (CYP17A1) is associated in the steroid hormone biosynthesis in human. As cell proliferation of prostate cancer in response to androgen steroid, an inhibition of CYP17A1 becomes an alternative approach to inhibit biosynthesis of androgen and support treatment of prostate cancer. However, biology-driven inhibitor development of prostate cancer is poorly elucidated. The aims of this study are to address structural differences at atomic-level between CYP17A1 and inhibitors i.e., abiraterone and TOK-001, and further investigate the effect of point mutation of CYP17A1 on the active site stability and the local interactions that are hydrophobic interaction and hydrogen bonding throughout molecular dynamics (MD) simulation. After performing multiple comparisons among four different complexes across CYP17A1 and inhibitors, interestingly TOK-001 oriented toward the active pocket and formed larger volume with I-helix of CYP17A1 than abiraterone, whereas abiraterone showed tighter binding and more active site stability. Considering on the effect of hydrophobic interaction and hydrogen bonding between abiraterone and CYP17A1, the key residues of Phe114, Ile371, Val482, and Asn202 were identified. This contributes into tight binding interactions; however abiraterone is effectively weakened along with the global conformation mobility increased in A105L mutation. Surprisingly, overall conformation of the CYP17A1 remained stable when bound to TOK-001. This basic knowledge can guide future experiments on design of efficient inhibitors for CYP17A1, which provides theoretical basis of androgen-dependent disease therapy.