Bio statistics and informatics

Used to represent molecular structures in two dimensions, highlighting bonds and connectivity.

Provides spatial representation, essential for understanding molecular interactions and receptor binding.

Calculated properties of molecules that help in predicting drug behavior, such as solubility and bioavailability.

Helps find existing molecular descriptors to compare new drugs against known compounds.

Includes histograms, scatter plots, and pie charts for visualizing trends in medical data.

Helps find existing molecular descriptors to compare new drugs against known compounds.

Determines drug formulation (tablet, injection, capsule) and how it dissolves in the body.

Examines how drugs interact with receptors and produce effects at the cellular level.

Modifies drug structures to improve binding affinity and reduce side effects.

Basic molecular formula representation.

Structural diagram showing connectivity of atoms.

Visualized structure incorporating spatial arrangements.

Includes dynamic changes over time, such as conformational shifts in biological environments.

Represents the volume occupied by the molecule

Shows areas of the molecule exposed to solvent.

Indicate charge distribution influencing interactions with receptors.

Drug fits exactly into receptor binding site

Receptor undergoes conformational change to accommodate the drug.

Defines the essential features for molecular recognition by a biological target.

Quantitative Structure-Activity Relationship

Uses computational models to predict biological activity based on chemical structure.

Determines how well a drug dissolves in fats, impacting cell membrane permeability.

Measures the ratio of drug solubility in octanol (lipid) versus water, predicting bioavailability.

Trains models using known input-output pairs to optimize predictions.

Finds patterns in unlabeled data for classification tasks.

Real-time ECG monitoring, remote consultations, and digital transmission of cardiac data.

Categorical data (e.g., blood type, gender)

Numerical data (e.g., blood pressure, glucose levels).

Labels without inherent order (e.g., blood groups A, B, O): measurement scale

Ranked categories (e.g., pain severity scale: mild, moderate, severe) : measurement scale

Numeric data with equal intervals but no true zero (e.g., temperature in Celsius) : measurement scale

Numeric data with a true zero point (e.g., weight, height) : measurement scale

Statistical Errors

Descriptive Statistics (Central Tendency)

Descriptive Statistics (Dispersion)