Hands-on, version-pinned tutorials and free browser tools for molecular docking, GROMACS molecular dynamics, MM-PBSA binding free energies, QSAR and cheminformatics.https://insilicobench.com/enhttps://insilicobench.com/notes/honest-qsar-models-start-with-the-assay-not-the-algorithm/https://insilicobench.com/notes/honest-qsar-models-start-with-the-assay-not-the-algorithm/Notes on an Optibrium webinar: curate the assay, match the method to the noise, score the test set once, plot instead of R², and respect the applicability domain.Sun, 25 Oct 2026 00:00:00 GMTQSARADMETmodel-validationcytochrome-P450contact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/tutorials/autodock-vina-meeko-docking/https://insilicobench.com/tutorials/autodock-vina-meeko-docking/Prepare receptor and ligand with Meeko, define the box, dock with Vina 1.2.7, and validate by redocking indinavir into HIV-1 protease (PDB 1HSG).Fri, 23 Oct 2026 00:00:00 GMTdockingautodock-vinameekordkitvalidationcontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/tutorials/choosing-gromacs-mdp-parameters/https://insilicobench.com/tutorials/choosing-gromacs-mdp-parameters/What every line of an EM, NVT, NPT and production .mdp file does, which defaults to trust, and the force-field-specific settings that matter.Fri, 23 Oct 2026 00:00:00 GMTgromacsmolecular-dynamicsmdpthermostatbarostatcontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/tutorials/common-gromacs-errors/https://insilicobench.com/tutorials/common-gromacs-errors/Real grompp, pdb2gmx and mdrun error messages from GROMACS 2026.3, what causes each one, and the fix. No -maxwarn shortcuts.Fri, 23 Oct 2026 00:00:00 GMTgromacstroubleshootingmolecular-dynamicsgromppmdruncontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/tutorials/gromacs-protein-ligand-md/https://insilicobench.com/tutorials/gromacs-protein-ligand-md/A tested protein–ligand MD setup in GROMACS 2026.3: GAFF2/AM1-BCC ligand via ACPYPE, topology merging, solvation, ions, EM, NVT, NPT, production and analysis.Fri, 23 Oct 2026 00:00:00 GMTgromacsmolecular-dynamicsprotein-ligandacpypegaff2ambercontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/tutorials/mm-pbsa-gmx-mmpbsa/https://insilicobench.com/tutorials/mm-pbsa-gmx-mmpbsa/End-state binding energies from a GROMACS trajectory with gmx_MMPBSA 1.7.0: inputs, GB vs PB, dielectric, decomposition, entropy, and how to read the numbers.Fri, 23 Oct 2026 00:00:00 GMTmm-pbsamm-gbsagmx_mmpbsabinding-free-energygromacscontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/notes/bindingdb-pubchem-patent-mining/https://insilicobench.com/notes/bindingdb-pubchem-patent-mining/BindingDB holds the measurement; PubChem holds the crosswalk. Christopher Southan's webinar follows a patent series from one to the other without counting deposits twice.Mon, 19 Oct 2026 00:00:00 GMTBindingDBPubChempatentsprovenancecontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/notes/ai-in-discovery-chemistry-panel/https://insilicobench.com/notes/ai-in-discovery-chemistry-panel/Notes from an Optibrium panel on AI in discovery chemistry: value over marginal accuracy, leakage and open benchmarks, plausible errors, and what LLMs change.Fri, 28 Aug 2026 00:00:00 GMTmachine-learninggenerative-chemistrybenchmarkswebinarcontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/notes/bindingdb-guide/https://insilicobench.com/notes/bindingdb-guide/BindingDB stores measured affinities. Michael Gilson's BindingDB webinar is a guide to which rows can supervise a docking or ML job, and which lookalikes cannot.Sun, 02 Aug 2026 00:00:00 GMTBindingDBbinding-affinitydockingmachine-learningcontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/notes/comfa-vs-comsia-3d-qsar/https://insilicobench.com/notes/comfa-vs-comsia-3d-qsar/What CoMFA and CoMSIA actually compute, how their fields differ, and what that means for alignment, PLS models and contour maps.Mon, 02 Feb 2026 00:00:00 GMT3D-QSARCoMFACoMSIAcontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/notes/bioisosteric-replacement-in-silico/https://insilicobench.com/notes/bioisosteric-replacement-in-silico/A replacement is bioisosteric for one target and one liability, not in general. Property-space neighbours, matched pairs and SwissBioisostere give the idea list.Wed, 07 Jan 2026 00:00:00 GMTbioisosteresmatched-molecular-pairsmedicinal-chemistrylead-optimizationcontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/notes/pca-tsne-umap-chemical-space/https://insilicobench.com/notes/pca-tsne-umap-chemical-space/A chemical-space plot is a chain of choices: representation, distance, projection. PCA, t-SNE and UMAP keep different structure, and a 2D map is not a similarity measure.Fri, 12 Dec 2025 00:00:00 GMTchemical-spaceUMAPPCAt-SNEfingerprintscontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/notes/qsar-model-validation/https://insilicobench.com/notes/qsar-model-validation/A three-tier QSAR validation framework: internal statistics, cross-validation and external checks, with the cuts papers report and where each one comes from.Mon, 18 Nov 2024 00:00:00 GMTQSARmodel-validationcheminformaticscontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/notes/datawarrior-drug-discovery/https://insilicobench.com/notes/datawarrior-drug-discovery/DataWarrior is the triage step, not the model. A guide to the import-and-filter path in Bruno Villoutreix’s tutorial series, and where it sits in a project.Wed, 07 Feb 2024 00:00:00 GMTDataWarriorcheminformaticsvisualizationsubstructure-searchcontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/notes/3d-qsar-workflow-validation-metrics/https://insilicobench.com/notes/3d-qsar-workflow-validation-metrics/A 3D-QSAR model maps aligned fields onto potency. Statistics say whether it predicts; contours say where to change the molecule. Both rest on the alignment.Sun, 02 Apr 2023 00:00:00 GMT3D-QSARCoMFACoMSIAmodel-validationcontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/tutorials/padelpy-fingerprints-qsar/https://insilicobench.com/tutorials/padelpy-fingerprints-qsar/Turn a SMILES table into PaDEL fingerprints and a random forest, then score a held-out split with Matthews correlation. The CV number is computed, not assumed.Sun, 15 Jan 2023 00:00:00 GMTPaDELfingerprintsQSARrandom-forestpythoncontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/notes/chemical-databases-for-ml/https://insilicobench.com/notes/chemical-databases-for-ml/ChEMBL, BindingDB, PubChem, PDBbind and BRENDA answer different questions. The useful choice is the table that holds the measurement you mean to model.Mon, 03 Oct 2022 00:00:00 GMTdatabasesChEMBLBindingDBPubChemmachine-learningcontact@insilicobench.com (Yassir Boulaamane)https://insilicobench.com/tutorials/chembl-bioactivity-data-curation/https://insilicobench.com/tutorials/chembl-bioactivity-data-curation/How a ChEMBL IC50 table for one target becomes a labelled set: one row per molecule, a mean potency, and a class that leaves the uncertain middle out.Wed, 07 Sep 2022 00:00:00 GMTChEMBLdata-curationclassificationpythoncontact@insilicobench.com (Yassir Boulaamane)