Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Biopharmaceutical Factors Influencing Drug Product Design: Overview

Biopharmaceutical Factors Influencing Drug Product Design: Overview

Rational drug product design integrates knowledge of the drug’s physicochemical properties, formulation components, manufacturing techniques, and intended route of administration. Each factor influences the drug’s performance, including how it is released, absorbed, and eliminated in the body.The physicochemical properties of a drug—such as solubility, stability, and particle size—affect its compatibility with excipients and the choice of dosage form. Excipients, though...

Factors Influencing Drug Absorption: Pharmaceutical Parameters

Factors Influencing Drug Absorption: Pharmaceutical Parameters

Solid dosage forms such as tablets and capsules undergo rigorous manufacturing processes to ensure stability and effectiveness. Their dissolution and absorption properties are influenced significantly by the choice of excipients (inactive ingredients that serve various roles in the formulation), and the methodology applied during production. The manufacturing parameters, such as compression force and granulation techniques, significantly affect dissolution rates. Elevated compression forces...

Pharmaceutical Alternatives: Polymorphic Form-Related and Particle Size-Related Therapeutic Nonequivalence

Pharmaceutical Alternatives: Polymorphic Form-Related and Particle Size-Related Therapeutic Nonequivalence

Changes in polymorphic forms can significantly influence the bioavailability of poorly soluble drugs. Although the FDA defines pharmaceutical equivalence based on having the same active ingredient, dosage form, and route of administration, it does not automatically disqualify products with different polymorphic forms. This means two products with different polymorphs can still be deemed pharmaceutically equivalent. However, polymorphic differences can affect properties like wettability,...

Biopharmaceutics and Pharmacokinetics: Overview

Biopharmaceutics and Pharmacokinetics: Overview

Understanding drugs, drug products, and their performance in pharmaceutical science is pivotal. Drugs, whether simple molecules or complex compounds, are designed to interact with the body's biological systems to diagnose, treat, or prevent diseases. Drug products include various delivery systems such as tablets, capsules, injections, and inhalers. The performance of these drug products is gauged by their ability to deliver the active ingredient to the desired site of action at the...

Drug Dissolution: Requirements and Profile Comparison

The acceptance criteria for dissolution profile data are anchored in Q values, representing the percentage of drug dissolved within a specified period. This assessment unfolds in three stages:First Stage: The test passes if all six drug dosage units are equal to or greater than Q plus 5%; otherwise, the sample proceeds to the second stage.Second Stage: The average of twelve units must be equal to or greater than Q, with no unit falling below Q - 15% to pass; if not, it progresses to the final...

In Vitro Drug Dissolution: Compendial Testing Models I

In Vitro Drug Dissolution: Compendial Testing Models I

Compendial dissolution methods are standardized procedures defined by pharmacopeias to evaluate the rate at which a drug dissolves in a specific medium. These methods ensure batch-to-batch consistency, enable quality control, and support the prediction of drug bioavailability. They are critical for both immediate and modified-release drug products.The apparatuses used for dissolution testing differ in their design and mechanical function, but all aim to simulate the physiological environment of...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Proteome microarray-guided identification of mycobacterial antigens and ELISA-based peptide mapping for improved serological detection of <i>Mycobacterium bovis</i> infection in European badgers.

Journal of clinical microbiology·2026

Same author

The Impact of Bacillus Calmette-Guérin Vaccination and <i>Mycobacterium bovis</i> Infection on Diagnostic Antibody Tests for Mycobacterial Infections.

Vaccines·2025

Same author

Anti-phenolic glycolipid antibodies in <i>Mycobacterium bovis</i> infected cattle.

One health (Amsterdam, Netherlands)·2025

Same author

An ELISA Using Synthetic Mycolic Acid-Based Antigens with DIVA Potential for Diagnosing Johne's Disease in Cattle.

Animals : an open access journal from MDPI·2024

Same author

Temporal dynamics of the early immune response following Mycobacterium bovis infection of cattle.

Scientific reports·2024

Same author

Vaccination of calves with Bacillus Calmette-Guerin Danish strain 1331 results in a duration of immunity of at least 52 weeks.

Vaccine·2023

Same journal

Functional Genomic Evidence for Candidate Small Viral RNA-Mediated Epigenetic Interference in SARS-CoV-1 and SARS-CoV-2.

Computational and structural biotechnology journal·2026

Same journal

From Pixels to Patterns: A Multidimensional Framework to Decode Cytoskeletal Organization.

Computational and structural biotechnology journal·2026

Same journal

A Large Concept Model for Mechanistic Simulation of Disease Trajectories: A Hypothesis-Generating Exemplar for Pediatric Acute Lymphoblastic Leukemia.

Computational and structural biotechnology journal·2026

Same journal

Adversarial Sequence Mutations in AlphaFold and ESMFold Reveal Nonphysical Structural Invariance, Confidence Failures, and Concerns for Protein Design.

Computational and structural biotechnology journal·2026

Same journal

High-Throughput Prediction of Protein-Protein Interactions Uncovers Hidden Molecular Networks in Biosynthetic Gene Clusters.

Computational and structural biotechnology journal·2026

Same journal

A Region-Aware Structured Framework Improves Prediction of Gene Expression from DNA Methylation.

Computational and structural biotechnology journal·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 11, 2026

A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM

A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM

Published on: August 18, 2023

Machine learning driven acceleration of biopharmaceutical formulation development using Excipient Prediction Software

Estefania Vidal-Henriquez¹, Thomas Holder¹, Nicholas Franciss Lee¹

¹LEUKOCARE AG, Am Klopferspitz 19a, 82152 Martinsried, Munich, Germany.

Computational and Structural Biotechnology Journal

|November 11, 2025

Summary

This summary is machine-generated.

Excipient Prediction Software (ExPreSo) is a new machine learning tool that suggests optimal excipients for protein biopharmaceuticals. This computational approach aids formulation development by predicting excipients based on protein properties, reducing experimental screening.

Keywords:

Biopharmaceuticals Excipients Formulation development Inactive ingredients Machine learning Monoclonal antibodies

More Related Videos

Automated Acoustic Dispensing for the Serial Dilution of Peptide Agonists in Potency Determination Assays

Automated Acoustic Dispensing for the Serial Dilution of Peptide Agonists in Potency Determination Assays

Published on: November 10, 2016

Solubility of Hydrophobic Compounds in Aqueous Solution Using Combinations of Self-assembling Peptide and Amino Acid

Solubility of Hydrophobic Compounds in Aqueous Solution Using Combinations of Self-assembling Peptide and Amino Acid

Published on: September 20, 2017

Related Experiment Videos

Last Updated: Jan 11, 2026

A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM

A Workflow for Lipid Nanoparticle LNP Formulation Optimization using Designed Mixture-Process Experiments and Self-Validated Ensemble Models SVEM

Published on: August 18, 2023

Automated Acoustic Dispensing for the Serial Dilution of Peptide Agonists in Potency Determination Assays

Automated Acoustic Dispensing for the Serial Dilution of Peptide Agonists in Potency Determination Assays

Published on: November 10, 2016

Solubility of Hydrophobic Compounds in Aqueous Solution Using Combinations of Self-assembling Peptide and Amino Acid

Solubility of Hydrophobic Compounds in Aqueous Solution Using Combinations of Self-assembling Peptide and Amino Acid

Published on: September 20, 2017

Area of Science:

Biopharmaceutical Formulation
Computational Chemistry
Machine Learning in Drug Development

Background:

Protein biopharmaceutical formulation is complex, facing challenges from new drug modalities and high concentrations.
Limited drug substance and extensive analytical needs hinder empirical excipient screening.
There is a critical need for in silico tools to guide excipient selection before laboratory work.

Purpose of the Study:

To introduce Excipient Prediction Software (ExPreSo), a machine learning algorithm for predicting excipients in protein biopharmaceuticals.
To leverage protein properties and target product profiles for in silico excipient pre-selection.
To reduce the time, cost, and risk associated with traditional excipient screening methods.

Main Methods:

Developed ExPreSo, a supervised machine learning algorithm trained on 335 regulatory-approved peptide and protein drug products.
Utilized predictive features including protein structural properties, language model embeddings, and drug product characteristics.
Evaluated performance of various ExPreSo variants, including sequence-based and protein-only feature sets.

Main Results:

ExPreSo demonstrated good predictive performance for nine common excipients with minimal overfitting.
A fast, sequence-based ExPreSo variant achieved prediction power comparable to slower, molecular modeling-based versions.
An ExPreSo variant using only protein features showed robust performance, unaffected by platform formulation influences.

Conclusions:

ExPreSo is the first machine learning algorithm to suggest biopharmaceutical excipients using a dataset of approved drug products.
The software shows significant potential to streamline excipient screening in biopharmaceutical formulation development.
ExPreSo can reduce experimental workload, costs, and development timelines for protein-based therapeutics.