{"id":223270,"date":"2026-10-11T16:23:13","date_gmt":"2026-10-11T23:23:13","guid":{"rendered":"https:\/\/molecularforecaster.com\/canopy-willow-from-metabolic-prediction-to-clearer-design-decisions\/"},"modified":"2026-10-21T10:36:08","modified_gmt":"2026-10-21T17:36:08","slug":"canopy-willow-from-metabolic-prediction-to-clearer-design-decisions","status":"publish","type":"post","link":"https:\/\/molecularforecaster.com\/fr\/canopy-willow-from-metabolic-prediction-to-clearer-design-decisions\/","title":{"rendered":"CANOPY + WILLOW : De la pr\u00e9diction m\u00e9tabolique \u00e0 des d\u00e9cisions de conception plus \u00e9clair\u00e9es"},"content":{"rendered":"
<\/span>\n
\n
\n

ENGLISH ONLY<\/p>\n<\/div><\/div>\n\n

CANOPY + WILLOW: From metabolic prediction to clearer design decisions<\/p>\n<\/div><\/div>\n\n

A new preprint presents the science behind Willow, the first module released in MFI Canopy, and shows how mechanistically grounded metabolism predictions can help discovery teams identify liabilities earlier, interpret them in context, and decide what to do next.<\/p>\n<\/div><\/div>\n<\/div>\n\n

\n
<\/span><\/div>\n\n
<\/div><\/div>\n\n
<\/span><\/div>\n<\/div>\n<\/div>\n<\/div>\n\n
\n
\n
\n

The science behind Willow<\/p>\n<\/div><\/div>\n\n

Cytochrome P450 (CYP) enzymes metabolize most marketed drugs. Understanding where oxidation is likely to occur can help medicinal chemists anticipate metabolic \u201chot spots,\u201d investigate potential metabolites, and design compounds with improved metabolic profiles. <\/p>\n

Willow brings this capability into Canopy through MFI\u2019s hybrid model combining quantum mechanics with structure-based docking to predict CYP sites of metabolism. Rather than returning a score alone, Willow considers chemical reactivity, three-dimensional accessibility, and how a compound can orient within a CYP active site, giving scientists a basis for interpreting why a site may be metabolized. <\/p>\n<\/div><\/div>\n\n

<\/span><\/div>\n\n

Structure-based and ligand-only ranking across nine CYP isoforms.<\/em><\/p>\n<\/div><\/div>\n<\/div>\n<\/div>\n<\/div>\n\n

\n
\n
\n

What the new study shows<\/p>\n<\/div><\/div>\n<\/div>\n<\/div>\n\n

\n
\n

74.7%<\/p>\n<\/div><\/div>\n\n

Global Top-2 accuracy across nine equally weighted CYP isoforms<\/p>\n<\/div><\/div>\n<\/div>\n\n

\n

9<\/p>\n<\/div><\/div>\n\n

Major human CYP isoforms evaluated<\/p>\n<\/div><\/div>\n<\/div>\n\n

\n

2,425<\/p>\n<\/div><\/div>\n\n

Curated molecule\u2013CYP pairs, representing 890 unique compounds<\/p>\n<\/div><\/div>\n<\/div>\n\n

\n

<1 min\n<\/p>\n<\/div><\/div>\n\n

Effective runtime per metabolite for eight of nine isoforms<\/p>\n<\/div><\/div>\n<\/div>\n<\/div>\n\n

\n
\n

The update introduces a three-dimensional solvent-accessible surface area correction, a more efficient L-BFGS optimizer, and a streamlined docking workflow. In matched testing, the accessibility correction improved L-BFGS Top-1 accuracy by 9.9 percentage points and Top-2 accuracy by 4.4 percentage points. <\/p>\n<\/div><\/div>\n\n

<\/span><\/div>\n\n

Accuracy across nine CYP isoforms and sensitivity to crystal-structure selection.<\/em><\/p>\n<\/div><\/div>\n<\/div>\n<\/div>\n<\/div>\n\n

\n
\n
\n

Docked poses in context<\/p>\n<\/div><\/div>\n\n

The work was also tested on six real-world examples spanning approved drugs and clinical candidates. The method identified experimentally observed metabolic sites for structurally diverse compounds including resmetirom, seladelpar, tranilast, nirmatrelvir, and a challenging macrocyclic voxilaprevir analogue. The case studies show how structure-based results can reveal the interactions behind a prediction and suggest where a design change may alter metabolism. <\/p>\n<\/div><\/div>\n\n

<\/span><\/div>\n\n
<\/span><\/div>\n\n
<\/span><\/div>\n\n

Docked poses for the six case-study compounds. Ligands are shown in magenta, with the heme below and active-site residues labelled. The panels retain the reported ranking results and limitations, including crystal-structure sensitivity for the voxilaprevir analogue and the missed metabolic site in the odanacatib analogue.
<\/em><\/p>\n<\/div><\/div>\n<\/div>\n<\/div>\n<\/div>\n\n

\n
\n
\n

From a prediction to a next step<\/p>\n<\/div><\/div>\n\n

Canopy is MFI\u2019s chemistry-first platform for turning computational insight into clearer small-molecule design decisions. Willow is its first module, bringing metabolism and ADMET insight into the same workflow as chemical structures, molecular properties, and compound comparison. <\/p>\n

With Canopy and Willow, teams can:<\/p>\n