Here you will find links to Jupyter Notebooks discussed in the second edition of the book Docking Screens for Drug Discovery (DOI: 10.1007/978-1-0716-4949-7). This new edition concentrates on the development of computational models to predict binding affinity based on the atomic coordinates of protein-ligand complexes. All codes are Python snippets based on the program SAnDReS 2.0 (de Azevedo et al., 2024). You will also find data about the statistical analysis of machine learning models developed using SAnDReS 2.0. As in the first edition, this book focuses on recent developments in docking simulations for target proteins with chapters on specific techniques or applications for docking simulations, including the major docking programs. Additionally, the volume explores the scoring functions developed for the analysis of docking results and to predict ligand-binding affinity as well as the importance of docking simulations for the initial stages of drug discovery. Written for the highly successful Methods in Molecular Biology series, this collection presents the kind of detail and key implementation advice to ensure successful results. You find infomation about the second edition in the following link: Docking Screens for Drug Discovery (2nd Edition).
de Azevedo WF Jr, editor. Docking screens for drug discovery. 2nd ed. New York, NY: Springer; 2026. DOI: 10.1007/978-1-0716-4949-7
Available at amazonda Silva AD, Veit-Acosta M, Tarasova O, de Azevedo WF Jr. A Primer on SAnDReS 2.0 for Scoring Function Design. Methods Mol Biol. 2026;2984:1-17. doi: 10.1007/978-1-0716-4949-7_1. PMID: 41075081. PubMed
Jupyter NotebooksLinearRegression4RandomData.ipynb
LinearRegression4CDK2_Ki.ipynb
LinearRegression4CASF-2016_Ki.ipynb (solution of code exercise 1)
LinearRegression4CDK19_IC50.ipynb (solution of code exercise 2)
LinearRegressionMultipleModels4CDK2_Ki.ipynb (solution of code challenge)
da Silva AD, Baud S, de Azevedo WF Jr. Exploring the Scoring Function Space with Lasso Regression. Methods Mol Biol. 2026;2984:19-34. doi: 10.1007/978-1-0716-4949-7_2. PMID: 41075082. PubMed
Jupyter NotebooksLasso4RandomData.ipynb
Lasso4CDK2_Ki.ipynb
Lasso4CASF_2016_Ki.ipynb (solution of code exercises 1 and 2)
LassoRegressionMultipleModels4CASF_2016_Ki.ipynb (solution of code challenge)
Pehlivan SN, da Silva AD, de Azevedo WF Jr. Combining MVD and Ridge Method to Predict CDK2 Inhibition. Methods Mol Biol. 2026;2984:35-49. doi: 10.1007/978-1-0716-4949-7_3. PMID: 41075083. PubMed
Jupyter NotebooksRidge4RandomData.ipynb
Ridge_CDK2_Ki_MVD.ipynb
RidgeRegressionMultipleAlphaModels4CDK2_Ki_MVD.ipynb (solution of code exercise 2)
Ridge_CDK2_Ki_Vina.ipynb (solution of code exercise 3)
RidgeRegressionMultipleModels4CDK2_Ki_MVD.ipynb (solution of code challenge)
da Silva AD, de Azevedo WF Jr. Elastic Net Regression to Predict CDK2 Inhibition. Methods Mol Biol. 2026;2984:51-64. doi: 10.1007/978-1-0716-4949-7_4. PMID: 41075084. PubMed
Jupyter NotebooksElasticNet4RandomData.ipynb
ElasticNet4CDK2_Ki.ipynb
ElasticNet4CASF_2016_Ki.ipynb (solution for code exercises 1 and 2)
ElasticNetRegressionModels4CASF_2016_Ki.ipynb (solution for code challenge)
da Silva AD, de Azevedo WF Jr. Gradient Descent to Predict Enzyme Inhibition. Methods Mol Biol. 2026;2984:65-79. doi: 10.1007/978-1-0716-4949-7_5. PMID: 41075085. PubMed
Jupyter NotebooksBGDRegressor4RandomData.ipynb
SGDRegressor4RandomData.ipynb
SGDRegressor4CDK2_Ki.ipynb
SGDRegressor4CASF_2016_Ki.ipynb (solution for code exercises 1 and 2)
SGDRegressorModels4CASF_2016_Ki.ipynb (solution for code challenge)
da Silva AD, de Azevedo WF Jr. Decision Tree for Prediction of Binding Affinity. Methods Mol Biol. 2026;2984:81-95. doi: 10.1007/978-1-0716-4949-7_6. PMID: 41075086. PubMed
Jupyter NotebookSKReg4Model.ipynb
da Silva AD, de Azevedo WF Jr. Calculating Enzyme Inhibition with Random Forests. Methods Mol Biol. 2026;2984:97-110. doi: 10.1007/978-1-0716-4949-7_7. PMID: 41075087. PubMed
Jupyter NotebooksMVD4ML.ipynb
SKReg4Model.ipynb
da Silva AD, de Azevedo WF Jr. Extremely Randomized Trees to Determine Binding Affinity. Methods Mol Biol. 2026;2984:111-123. doi: 10.1007/978-1-0716-4949-7_8. PMID: 41075088. PubMed
Jupyter NotebooksMVD4ML.ipynb
SKReg4Model.ipynb
Dere D, Pehlivan SN, da Silva AD, de Azevedo WF Jr. Hands-On Docking with Molegro Virtual Docker. Methods Mol Biol. 2026;2984:125-138. doi: 10.1007/978-1-0716-4949-7_9. PMID: 41075089. PubMed
Jupyter NotebooksMVD4ML.ipynb
SKReg4Model.ipynb
Oliveira JMV, da Silva AD, Soares AMDS, de Azevedo WF Jr. Molegro Virtual Docker for Docking Screens. Methods Mol Biol. 2026;2984:139-152. doi: 10.1007/978-1-0716-4949-7_10. PMID: 41075090. PubMed
Jupyter Notebooksprepare_BindingDB.ipynb
prepare_MVD.ipynb
csv4metrics.ipynb
da Silva AD, da Silveira NJF, Oliveira PR, de Azevedo WF Jr. Molegro Data Modeller for Machine Learning. Methods Mol Biol. 2026;2984:153-166. doi: 10.1007/978-1-0716-4949-7_11. PMID: 41075091. PubMed
Jupyter Notebooksprepare_BindingDB.ipynb
prepare_MVD.ipynb
csv4metrics.ipynb
da Silva AD, de Azevedo WF Jr. Neural Networks with Molegro Data Modeller. Methods Mol Biol. 2026;2984:167-181. doi: 10.1007/978-1-0716-4949-7_12. PMID: 41075092. PubMed
Jupyter Notebooksprepare_BindingDB.ipynb
prepare_MVD.ipynb
csv4metrics.ipynb
da Silva AD, de Azevedo WF Jr. AlphaFold for Docking Screens. Methods Mol Biol. 2026;2984:183-196. doi: 10.1007/978-1-0716-4949-7_13. PMID: 41075093. PubMed
Jupyter Notebooksprepare_BindingDB.ipynb
prepare_MVD.ipynb
visualize_dataset.ipynb
csv4metrics.ipynb
da Silva AD, Russo S, González-Vergara E, de Azevedo WF Jr. Differential Evolution for Docking Simulations. Methods Mol Biol. 2026;2984:197-210. doi: 10.1007/978-1-0716-4949-7_14. PMID: 41075094. PubMed
Jupyter NotebookDarwin.ipynb
de Azevedo WF Jr. Machine Learning to Predict CDK4 Inhibition. Methods Mol Biol. 2026;2984:211-225. doi: 10.1007/978-1-0716-4949-7_15. PMID: 41075095. PubMed
Jupyter Notebooksprepare_BindingDB.ipynb
prepare_MVD.ipynb
visualize_dataset.ipynb
csv4metrics.ipynb
de Azevedo WF Jr. Targeting CDK9 with Molegro Virtual Docker. Methods Mol Biol. 2026;2984:227-242. doi: 10.1007/978-1-0716-4949-7_16. PMID: 41075096. PubMed
Jupyter Notebooksprepare_BindingDB.ipynb
prepare_MVD.ipynb
visualize_dataset.ipynb
csv4metrics.ipynb
de Azevedo WF Jr. CDK7 as a Target for Docking Screens. Methods Mol Biol. 2026;2984:243-258. doi: 10.1007/978-1-0716-4949-7_17. PMID: 41075097. PubMed
Jupyter Notebooksprepare_BindingDB.ipynb
prepare_MVD.ipynb
visualize_dataset.ipynb
csv4metrics.ipynb
de Azevedo WF Jr. Molegro Data Modeller to Estimate CDK6 Inhibition. Methods Mol Biol. 2026;2984:259-275. doi: 10.1007/978-1-0716-4949-7_18. PMID: 41075098. PubMed
Jupyter Notebooksprepare_BindingDB.ipynb
prepare_MVD.ipynb
visualize_dataset.ipynb
csv4metrics.ipynb
de Azevedo WF Jr. Neural Networks to Calculate CDK2 Inhibition. Methods Mol Biol. 2026;2984:277-293. doi: 10.1007/978-1-0716-4949-7_19. PMID: 41075099. PubMed
Jupyter Notebooksprepare_BindingDB.ipynb
prepare_MVD.ipynb
visualize_dataset.ipynb
csv4metrics.ipynb
de Azevedo WF Jr. Tree-Based Methods to Predict Enzyme Inhibition. Methods Mol Biol. 2026;2984:295-311. doi: 10.1007/978-1-0716-4949-7_20. PMID: 41075100. PubMed
Jupyter Notebooksprepare_BindingDB.ipynb
prepare_MVD.ipynb
visualize_dataset.ipynb
SKReg4Model.ipynb
Additional Software (Including Third-Party Software)
AutoDock-Vina (1.2.7) (Linux Version)
AutoDock-Vina (1.2.7) (Windows Version)
AutoDock-Vina Split (1.2.7) (Linux Version)
AutoDock-Vina Split (1.2.7) (Windows Version)
My scientific interests are interdisciplinary, with three main emphases: computational structural biology, artificial intelligence, and complex systems. In my studies, I developed several free software programs to explore the concept of Scoring Function Space.
As a result of my research, I published over 200 scientific works about protein structures, computer models of complex systems, and simulations of protein systems. These publications have generated over 12,000 citations on Google Scholar (h-index of 63) and more than 10,000 citations and an h-index of 58 in Scopus.
Due to the impact of my work, I have been ranked among the most influential researchers in the world (Fields: Biophysics, Biochemistry & Molecular Biology, and Biomedical Research) according to a database created by Journal Plos Biology (see news here). The application of the same set of metrics recognized the influence of my work in the following years ( Baas et al., 2021; Ioannidis, 2022; Ioannidis, 2023; Ioannidis, 2024; Ioannidis, 2025). Not bad for a poor guy who was a shoe seller at a store in the city of São Paulo and had the gold opportunity to study at the University of São Paulo with a scholarship for food and housing. I was 23 when I initiated my undergraduate studies and the first in my family to have access to higher education.
Regarding scientific impact (Peterson, 2005), Hirsch says that for a physicist, a value for the h index of 45 or higher could mean membership in the National Academy of Sciences of the USA. So far, there have been no invitations. No hard feelings because I am in good company. Carl Sagan was never allowed into the National Academy of Sciences. According to Google Scholar, his work accumulates more than 1,000 citations per year. Indeed, his current citation rate exceeds that of many members of the National Academy of Sciences.
I will continue working in science with low-budget and interdisciplinary projects, combating denialism and fascism with science and technology. The fight against denialism and fascism is a continuing work, and scientists should not forget their role in a complex society where social media gave the right to speak to legions of imbeciles.
“Social media gives the right to speak to legions of imbeciles who previously only spoke at the bar after a glass of wine, without damaging the community. They were immediately silenced, but now they have the same right to speak as a Nobel Prize winner. It’s the invasion of imbeciles.”
Umberto Eco. Source: Quote Investigator
"Let the light of science end the darkness of denialism." My quote (DOI:10.2174/092986732838211207154549).
de Azevedo WF Jr, Quiroga R, Villarreal MA, da Silveira NJF, Bitencourt-Ferreira G, da Silva AD, Veit-Acosta M, Oliveira PR, Tutone M, Biziukova N, Poroikov V, Tarasova O, Baud S. SAnDReS 2.0: Development of machine-learning models to explore the scoring function space. J Comput Chem. 2024; 45(27): 2333–2346. PubMed
de Azevedo WF Jr. Docking screens for drug discovery. 1st ed. de Azevedo WF Jr, editor. New York, NY: Humana Press; 2020. DOI: 10.1007/978-1-4939-9752-7