Browse
Artificial Intelligence
-
Virtual Screening: Filtering Compound Libraries With Software
How virtual screening uses docking, ligand similarity and machine learning to prioritise compounds, and where its predictions fall short.
-
AI in Drug Discovery: An Independent Guide to Methods and Limits
An independent overview of how AI is used in drug discovery, what the methods can and cannot do, and what…
-
Predicting Protein Structures: Methods, Accuracy and Gaps
A plain-language look at how protein structure prediction is used in early drug research, the accuracy reported in peer-reviewed papers,…
-
Validating Drug Discovery Models: Benchmarks, Splits and Pitfalls
Why benchmark scores can mislead, how data splits differ, and which checks make drug discovery model validation more trustworthy.
-
Bias in Drug Discovery Datasets and Why It Matters for Models
Missing negatives, benchmark shortcuts and unrepresentative clinical data can all distort drug discovery models. Here is how the bias arises…
-
How AlphaFold-Style Systems Work: A Plain-Language Explainer
A plain-language explanation of how AlphaFold-style systems predict protein structures, what they can do, and where they fall short.
-
Generative Models for Molecule Design: What They Can and Cannot Do
Generative models propose candidate molecules quickly, but evaluation, synthesizability and biology remain open problems. Here is how to read the…
-
ADMET Prediction With Machine Learning: Approaches and Uncertainty
How machine learning estimates absorption, distribution, metabolism, excretion and toxicity, and where those estimates are uncertain.
-
How Machine Learning Is Used to Propose Drug Targets
A plain-language look at how machine learning ranks candidate drug targets, what data it uses, and why laboratory and clinical…