The Standard Error (SE) of Prediction: a Measure of Individual Uncertainties
Applications of Multi-Class Machine Learning Models to Drug Design
Until recently, machine learning classification models in Cheminformatics literature have generally modeled binary endpoints (active/inactive, substrate/non-substrate, toxic/non-toxic, etc.)
Using DILIsym, A Quantitative Systems Toxicology (QST) Software Tool of Drug-Induced Liver Injury (DILI), To Assess DILI Risk in Drug Development
A combination of multiple mechanistic, in silico modeling approaches can facilitate drug discovery (QSAR, PBPK, QSP and QST).
Mechanistic Modeling of in vitro Assays to Improve in vitro/in vivo Extrapolation
Mechanistic Modeling of in vitro assays to Improve in vitro/in vivo Extrapolation using Membrane Plus
Incorporating Mechanistic Modeling & Simulation to Assist with Formulation Development and Regulatory Evaluations
A mechanistic, physiologically-based absorption/PK model was constructed in GastroPlus and validated across three dose levels (50, 100, and 300 mg) using in vivo data collected from tablets manufactured…
High-Throughput Pharmacokinetics for Drug Discovery
The high-throughput implementation of PBPK simulation in ADMET Predictor yields results in good agreement with analogous analyses in GastroPlus. HTPK simulations run using purely in silico property…
Discovery PBPK: How to Estimate the Expected Accuracy of ISIVB and IVIVB for New Chemical Entities
PBPK modeling and simulation can be successfully used in the lead optimization phase of drug discovery. Using CLloc, accurate bioavailability can be predicted for new compounds in a chemical series.
Applying the QSP Model NAFLDsym® to Predict and Understand NASH Treatments
NAFLDsym is a mechanistic, mathematical, QSP model 1. Can predict efficacy for compounds that modulate lipids and/or lipotoxicity with v1A 2. NAFLDsym v2A will also include inflammation and fibrosis submodels…
Exploring Pharmacokinetic SARs Early in Drug Discovery
Late-stage attrition due to obviously bad physicochemical properties has been reduced by application of rules-ofthumb like Lipinski’s Rule of Five. Failure due to lack of efficacy remains a major issue.
Predicting Five Rat Acute Toxicity Endpoints with ANNE Models
Used ANNE technology to develop regression and classification models. Curation identified activity cliffs and questionable LD50 values. Model applicability domain is defined by the minimum and…
Mechanistic Absorption/PBPK Modeling to Predict Positive/Negative Food Effects: Approaches and Special Considerations
1) Early examples and proposed approach 2) Fasted vs. fed state model descriptions – where are we today? 3) Case study: positive food effect predictions – input review 4) Case study: negative food effect…
Leveraging PopPK and PBPK Modeling Approaches to Understand Food/PPI Effects
Applying both top-down (PopPK and PBPK) and bottom-up (PBPK) modeling approaches can leverage existing data sets and help prospectively answer questions. Predictions of absorption-related DDIs…
How to Understand Aqueous Ionization and Its Influence on Key Physical Properties of Drugs
Clearing Up Myths About Aqueous Ionization of Drugs, Understanding the pH Dependence of Aqueous Solubility, & Understanding the pH Dependence of Partitioning
Case Study in Placebo Modeling and Its Effect on Drug Development
ADHD (attention-deficit/hyperactivity disorder) is a neurodevelopmental disorder characterized by symptoms of inattention, hyperactivity, and impulsivity associated with clinically significant impairment in functioning.
High-throughput prediction of fraction absorbed and bioavailability in silico
HTPK simulations run using purely in silico property estimates are in reasonable but imperfect agreement with experimental results in humans and rats.
In Silico-In Vitro Extrapolation for Dermal Exposure
Prediction of in vitro dermal delivery and drug in receptor fluid should be done using Nielsen model for vehicle evaporation...
Applying in silico-in vitro-in vivo extrapolation (IS-IVIVE) techniques to predict exposure and guide risk assessment
Combining QSAR, PBPK, and QST models is a powerful approach to getting more information out of your data investments early in product development.
Using Quantitative Systems Toxicology (QST) to Assess Drug Safety: The Experience of the DILIsimInitiative. ®
Drug-Induced Liver Injury (DILI) remains a major problem in drug development.