Related Experiment Video

Updated: Jan 5, 2026

An Organotypic High Throughput System for Characterization of Drug Sensitivity of Primary Multiple Myeloma Cells
09:41

An Organotypic High Throughput System for Characterization of Drug Sensitivity of Primary Multiple Myeloma Cells

Published on: July 15, 2015

9.0K

Defining subpopulations of differential drug response to reveal novel target populations

Nirmal Keshava1, Tzen S Toh2,3, Haobin Yuan4

  • 1Constellation Analytics, LLC., Needham, MA USA.

NPJ Systems Biology and Applications
|October 12, 2019
PubMed

Insights

Unsupervised machine learning identified novel cancer subpopulations and drug combinations. This approach revealed MEK, BRAF, and PI3K inhibitors are effective for specific BRAF-mutant subpopulations, guiding personalized cancer medicine.

Area of Science:

  • Oncology
  • Computational Biology
  • Pharmacology

Background:

  • Personalized medicine often relies on genetic alterations to predict cancer drug responses.
  • Objective evaluation of differential pharmacology across subpopulations is needed.
  • Understanding resistance mechanisms and pathway crosstalk is crucial for effective combination therapies.

Purpose of the Study:

  • To develop an unsupervised machine learning approach for comparing pharmacological responses between cancer therapy pairs.
  • To identify distinct cancer subpopulations with differential responses to targeted inhibitors.
  • To discover novel biomarkers and effective drug combinations for stratified cancer treatment.

Main Methods:

  • Utilized unsupervised machine learning to analyze 327 pairs of cancer therapies.
  • Integrated multiple response measures to assess drug efficacy.
  • Identified subpopulations reacting differently to inhibitors of the same or different targets.

Main Results:

  • Discovered that MEK, BRAF, and PI3K inhibitors show efficacy as combination therapies in specific BRAF-mutant subpopulations.
  • Analysis of a failed lung cancer trial suggests potential applications in KRAS-mutant pancreatic and colorectal cancers.
  • Demonstrated a method for identifying novel cancer subpopulations and their genetic biomarkers.

Conclusions:

  • The developed machine learning approach enables objective evaluation of differential pharmacology at a subpopulation level.
  • This data-driven strategy facilitates the identification of novel therapeutic strategies for stratified medicine.
  • Highlights the potential of combination therapies for specific genetic profiles in cancer treatment.
Keywords:
BiomarkersCancerMolecular medicineVirtual drug screening

More Related Videos

Drug Repurposing Hypothesis Generation Using the "RE:fine Drugs" System05:10

Drug Repurposing Hypothesis Generation Using the "RE:fine Drugs" System

Published on: December 11, 2016

10.1K
Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization03:08

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Published on: October 3, 2025

856

Related Concept Videos

Analysis of Population Pharmacokinetic Data01:12

Analysis of Population Pharmacokinetic Data

Analysis of population pharmacokinetic data involves studying the behavior of drugs within diverse populations to understand their pharmacokinetic parameters. Traditional pharmacokinetic methods typically involve collecting samples from a few individuals and estimating these parameters. While these methods are commonly used, they have limitations in capturing the variability in drug response among individuals or heterogeneous populations. Population pharmacokinetics is employed to address these...
641
Drug Discovery: Overview01:26

Drug Discovery: Overview

Drug discovery is a multifaceted process involving extensive screening, testing, and optimization of lead compounds to identify potential new drugs for therapeutic use. It combines several approaches, including screening large numbers of natural products, chemical modification of known active molecules, identification of new drug targets, and rational design based on biological mechanisms and drug-receptor structure. These approaches are carried out in both academic research laboratories and...
10.8K
Dosage Regimens: Partial Pharmacokinetic Parameters01:01

Dosage Regimens: Partial Pharmacokinetic Parameters

It is not uncommon for complete drug pharmacokinetic profiles to remain elusive in pharmacokinetics. This necessitates certain educated assumptions by pharmacokineticists to determine appropriate dosage regimens without comprehensive pharmacokinetic data from animal or human studies. One prevalent assumption is setting the bioavailability factor, denoted as F, to 1 or 100%. This assumption caters to the scenario where a drug doesn't achieve full systemic absorption, resulting in the patient...
130
Measurement of Bioavailability: Pharmacodynamic Methods01:20

Measurement of Bioavailability: Pharmacodynamic Methods

Pharmacodynamic methods provide insights into a drug's effects on physiological processes over time and play a crucial role in understanding bioavailability and therapeutic efficacy. These methods can be broadly classified into acute pharmacological and therapeutic response approaches, each with distinct mechanisms and applications.The acute pharmacological response method directly correlates a drug's physiological effects, such as ECG or pupil diameter changes, to its time course in the body.
204
Dose-Response Relationship: Selectivity and Specificity01:25

Dose-Response Relationship: Selectivity and Specificity

Drugs exert their therapeutic effects by interacting with receptors, enzymes, or ion channels that are present throughout the human body. The strength and duration of the interaction between a drug and its target receptor are characterized by the selectivity and specificity of the drug. Selectivity refers to a drug's strong preference for its intended target over other targets. For instance, isoprenaline, a non-selective β-adrenergic agonist, interacts with both β1- and...
9.4K
Dosage Regimen: Individualization01:24

Dosage Regimen: Individualization

Individualization in dosing regimens is the customization of medication doses for individual patients. Its necessity arises from the goal of maximizing therapeutic benefits while minimizing risks. This approach is pivotal because human responses to drugs can vary widely; what is effective for one person may be inadequate or excessive for another. Interpatient (intersubject) variability refers to differences in drug responses between individuals, while intrapatient (intrasubject) variability...
145