Dimethyltensor

Analyze and predict drug-target binding kinetics with advanced modeling techniques.

Facilitate fragment-based drug design with tools for library creation and ligand efficiency analysis.

Last-resort skill for retrieving peer-reviewed literature when solutions are unclear or hallucination risk is high.

Nextflow enables writing, debugging, and optimizing scalable computational pipelines for bioinformatics and HPC workflows.

Run coarse-grained molecular dynamics simulations with MARTINI 3 for efficient modeling of complex systems.

Use when working with TorchDrug for graph-based drug discovery and molecular ML. Covers molecular property prediction, protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, and GNN architectures on chemical data.

Compute free energy differences for drug discovery with high accuracy.

Framework for in silico peptide screening and evolutionary optimization.

Utilize molecular mechanics force fields for MD simulations with OpenMM and OpenFF.

Convert molecular file formats and generate 3D coordinates with OpenBabel's pybel API and obabel CLI.

Master cheminformatics with Daylight theory, covering SMILES, SMARTS, SMIRKS, and molecular fingerprints.

Perform Matched Molecular Pair Analysis (MMPA) for SAR extraction and bioisostere discovery.

Design and evaluate generative models for de novo drug and molecule design.

Graph-based toolkit for reaction informatics, enabling advanced chemical analysis and synthesis planning.

Facilitate quantum chemistry and DFT calculations with a comprehensive Python-based toolkit.

Facilitates pharmacophore modeling for drug discovery, covering various feature types and workflows.

Facilitate active learning and closed-loop molecular optimization for drug discovery.

Create interactive 3D molecular visualizations in Jupyter notebooks using py3Dmol.

Build 3D protein structures from sequences using homology modeling techniques.

Calibrate uncertainty estimates in QSAR/ML models for reliable predictions.

Utilize ASE for atomistic simulations including structure building and molecular dynamics.

A flexible framework for structuring computational chemistry tasks and generating hypotheses.

Perform protein-ligand docking and virtual screening for drug design.

Use when working with DeepChem for molecular machine learning, drug discovery, quantum chemistry, materials science, or bioinformatics. Handles molecular datasets, featurization strategies, model training/evaluation, and predictions on chemical data.

Analyze molecular dynamics trajectories with MDAnalysis for various structural insights.

Use when working with RDKit for cheminformatics in Python. Covers molecular I/O, property calculation, Lipinski filters, fingerprints, similarity, 3D conformer generation, reactions, fragmentation, substructure search, MCS, stereochemistry, and tautomers.

Utilize the EASE framework for analyzing polar organic reaction mechanisms and synthesis problems.