Predicting the solubility of small molecules is a challenge for drug design scientists due to the lack of consistent experimental data.
Dr Valery Polyakov of Meliora Therapeutics used the Cambridge Structural Database melting point dataset, containing approximately one hundred thousand compounds, to create widely applicable machine learning models of small molecule melting points. Applying the general solubility equation, the aqueous solubilities of the same compounds can be predicted.
Join this webinar to hear from the author, Dr Valery Polyakov, on the details of his work. You will learn:
- the importance of predicting solubility,
- the benefits of using the CSD experimental melting point dataset,
- the pros and cons of different small molecule machine learning models.
The content of this webinar is based on work published in J. Chem. Inf. Model. 2023 (https://doi.org/10.1021/acs.jcim.3c00308).
Dr Valery Polyakov of Meliora Therapeutics used the Cambridge Structural Database melting point dataset, containing approximately one hundred thousand compounds, to create widely applicable machine learning models of small molecule melting points. Applying the general solubility equation, the aqueous solubilities of the same compounds can be predicted.
Join this webinar to hear from the author, Dr Valery Polyakov, on the details of his work. You will learn:
- the importance of predicting solubility,
- the benefits of using the CSD experimental melting point dataset,
- the pros and cons of different small molecule machine learning models.
The content of this webinar is based on work published in J. Chem. Inf. Model. 2023 (https://doi.org/10.1021/acs.jcim.3c00308).
