Journal: Results in chemistry

Article Title: Assessing the impact of data harmonization on human liver microsomal stability prediction model performance

doi: 10.1016/j.rechem.2026.103305

Figure Lengend Snippet: Visualization of chemical space diversity using a t-SNE plot of RDKit molecular descriptors for Biogen (green), ChEMBL (teal), NCATS (purple), AstraZeneca (orange), Polaris (magenta). (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)

Article Snippet: The single-dataset ChEMBL and single-dataset NCATS models showed comparable performance to each other across all metrics and both the single-dataset ChEMBL and single-dataset NCATS models generally improved with the addition of Biogen data.

Techniques:

Journal: Data in Brief

Article Title: A new ChEMBL dataset for the similarity-based target fishing engine FastTargetPred: Annotation of an exhaustive list of linear tetrapeptides

doi: 10.1016/j.dib.2022.108159

Figure Lengend Snippet: Chemical space . Comparison of the chemical space covered by the extracted ChEMBL bioactive compounds (orange), tetrapeptides (blue) and approved drugs (magenta) obtained after filtering DrugBank 5.0 (downloaded in December 2021). 2509 approved drugs were initially collected but 287 very small compounds (molecules with less than 10 heavy atoms) were removed (e.g., several compounds have only 1 atom). In addition, 124 other molecules (unusual chemistry and some mixtures) were deleted. Six physicochemical properties were computed with DataWarrior and a PCA plot was generated. The explained variance percentage of the first 3 principal components are PCA1: 81.79%, PCA2: 13.27%, PCA3: 2.52%.

Article Snippet: A new ChEMBL dataset for FastTargetPred (Original data) (Mendeley Data).

Techniques: Comparison, Generated

Journal: Data in Brief

Article Title: A new ChEMBL dataset for the similarity-based target fishing engine FastTargetPred: Annotation of an exhaustive list of linear tetrapeptides

doi: 10.1016/j.dib.2022.108159

Figure Lengend Snippet:

Article Snippet: A new ChEMBL dataset for FastTargetPred (Original data) (Mendeley Data).

Techniques: Drug discovery, Generated, Software, Sequencing, Binding Assay