Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

PaccMann: a web service for interpretable anticancer compound sensitivity prediction.

Joris Cadow1, Jannis Born1,2, Matteo Manica1

  • 1Computational Systems Biology Group, IBM Research Europe, Säumerstrasse 4, Rüschlikon, 8803, Switzerland.

Nucleic Acids Research
|May 14, 2020
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Fine-tuning large language models to generate single-atom catalyst synthesis procedures.

Communications chemistry·2026
Same author

From fragments to drugs: How AI and in silico methods accelerate fragment-to-lead optimization.

European journal of medicinal chemistry·2026
Same author

Modeling chimeric antigen receptor response at the single-cell level with conditional optimal transport.

Cell systems·2026
Same author

Unifying non-Markovian dynamics and agent heterogeneity in scalable stochastic networks.

Nature communications·2026
Same author

Pediatric acute myeloid leukemia tumor composition predicts patient outcomes at diagnosis and reveals mechanisms of resistance to chemotherapy.

Research square·2026
Same author

Correction: Proteomic-based stratification of intermediate-risk prostate cancer patients.

Life science alliance·2025
Same journal

Correction to 'scSuperAnnotator: A platform for benchmarking comparison and visualizing automated cellular annotation methods for scRNA-seq data'.

Nucleic acids research·2026
Same journal

Correction to 'Differentiable partition function calculation for RNA'.

Nucleic acids research·2026
Same journal

Deployment of non-canonical splicing in tunicate genomes is mediated by divergent U2AF function and changing m6A modification in U1 and U6 snRNA.

Nucleic acids research·2026
Same journal

Bacillus subtilis DnaB forms multiple protein-protein interactions essential for DNA replication initiation.

Nucleic acids research·2026
Same journal

Multiple forms of protein-protein and DNA binding are exhibited by BrxC from the BREX phage restriction system.

Nucleic acids research·2026
Same journal

Biosynthesis of glycosylated 5-hydroxycytosine in the DNA of diverse viruses.

Nucleic acids research·2026
See all related articles

PaccMann is a new AI tool that predicts anticancer drug efficacy using multimodal data. It outperforms existing methods, aiding in the discovery of new cancer therapies.

Area of Science:

  • Computational biology
  • Bioinformatics
  • Artificial intelligence in drug discovery

Background:

  • Accurate prediction of anticancer compound efficacy is crucial for developing targeted cancer therapies.
  • Integrating diverse data sources, such as transcriptomics and chemical structures, can enhance drug efficacy prediction models.

Purpose of the Study:

  • To introduce PaccMann, a web-based platform utilizing multimodal attention-based neural networks for predicting anticancer compound sensitivity.
  • To provide a user-friendly tool for in-silico drug testing and analysis of compound efficacy on various transcriptomic profiles.

Main Methods:

  • PaccMann is trained on public transcriptomic cell line profiles, compound structure information, and drug sensitivity screening data.
  • The platform employs multimodal attention-based neural networks to integrate these diverse data types.

Related Experiment Videos

  • Model interpretability methods, including confidence scores and attention heatmaps, are utilized.

    • Main Results:

    • PaccMann demonstrates superior performance compared to state-of-the-art methods in anticancer drug sensitivity prediction.
    • The platform successfully integrates transcriptomic data, compound structures, and drug sensitivity information.
    • Attention heatmaps provide insights into key genes and chemical substructures influencing predictions.

    Conclusions:

    • PaccMann offers a powerful and accurate tool for predicting anticancer drug efficacy, supporting drug repositioning and lead compound identification.
    • The platform's interpretability features facilitate a deeper understanding of drug-biomolecular interactions.
    • PaccMann serves as a valuable resource for the cancer research community, accelerating the validation of potential therapeutic compounds.