Practical strategies and best practices for planning, writing, and publishing high-quality scientific research articles.
Comprehensive, metric-driven workflow for robust 3D-QSAR modeling, based on Xu et al., 2020 and enriched with cheminformatics best practices.
Step-by-step workflow and best practices for building a hybrid genome assembly pipeline using short- and long-read sequencing data.
Exploring how data science techniques—from machine learning to data visualization—are transforming chemistry and accelerating the discovery of new drugs and materials.
A step-by-step tutorial on using PaDELPy to calculate molecular fingerprints and build a Random Forest model for predicting molecular activity in drug discovery.
A beginner-friendly guide to how molecular dynamics (MD) simulations work, their applications in structural bioinformatics and materials science, and the insights they provide into complex molecular systems.
Guidelines for choosing appropriate MD simulation lengths in protein–ligand systems, with key convergence metrics like RMSD, RMSF, and interaction fingerprints.
Overview of supervised and unsupervised learning approaches, highlighting key techniques, applications, and differences in the context of cheminformatics and drug discovery.
Overview of freely available chemical and bioactivity databases—including ChEMBL, BindingDB, PubChem, PDBbind, and BRENDA—that fuel machine learning and cheminformatics research in drug discovery.
Step-by-step tutorial on retrieving, curating, and classifying ChEMBL bioactivity data for machine learning applications in drug discovery.
