Results & Downloads
Paper Published in Digital Discovery
Paper entitled: “Chemical representation learning for toxicity prediction”
Paper published in Frontiers in Oncology
Paper entitled: “Quantitative proteomic studies addressing unmet clinical needs in sarcoma”
Paper Published in Bioinformatics Advances
Paper entitled: “MonoNet: enhancing interpretability in neural networks via monotonic features”
Paper Published in Cell Reports
Paper entitled: “Systematic multi-omics cell line profiling uncovers principles of Ewing sarcoma fusion oncogene-mediated gene regulation”
Factsheet 4 – Main Achievements & ongoing work
The fourth iPC factsheet about the main achievements and ongoing work is now available. Much has already been done in the first two project periods to achieve the goal to improve the care of children with cancer and our partners are continuously working in the third project period to solve the mathematical and computational bottlenecks of data- and model-based medicine. Therefore, the fourth iPC factsheet describes the most important achievements so far and the ongoing work in the current project period.
D7.3 Identification of cell subpopulations in each tumour type, their association with response to therapy, and prediction of effective alternative therapies
Tumour decomposition into cells and subtypes and inference about the effects of treatments and perturbations on each tumour component (cell or tumor subclone).
Paper Published in Proteomics
Paper entitled: “Opportunities for pharmacoproteomics in biomarker discovery”
Factsheet 3 – iPC Open Source Software
The third iPC factsheet about the iPC Open source software is now available.
It describes 3 of the 25 open source softwares that were developed during the project framework.
The focus will be on INtERAcT, CONSIFER and DECODE, which were developed by our partner IBM.
Paper Published in Cancers
Paper entitled: “Targeting the Unwindosome by Mebendazole Is a Vulnerability of Chemoresistant Hepatoblastoma”
Paper published in Proteomics
Paper entitled: “Clinical applications of mass spectrometry-based proteomics in cancer: Where are we?”
Paper published
Paper entitled: “Computational challenges of cell cycle analysis using single cell transcriptomics”
Factsheet 2 – iPC Platforms
The second iPC factsheet about the iPC Platforms is now available. It describes the 5 cloud-based platforms that were developed during the project framework from our partners BSC, XLAB, CHOP, AMC, PMC, DKFZ, UGent and BCM.
D1.4 Model development data including genetic perturbation screens and gene-drug synergies
This deliverable reports on the generation of CROPseq and drug screening data for two Ewing Sarcoma cell lines, one Hepatoblastoma cell line and one B-cell Acute Lymphoblastic Leukemia cell line.
Paper published in Cancer Cell
Paper entitled: “Pan-cancer proteomic map of 949 human cell lines”
Factsheet 1 – Tumour Type Working Groups
The first iPC factsheet on Tumour Type Working Groups is now available. It describes the 5 different types of childhood cancer and the work our partners are doing.
The working groups are led by our partners IGTP, DKFZ, PMC, CURIE, UZH and MPG.
Paper published in Nature Communication
Paper entitled: “MYCN-driven fatty acid uptake is a metabolic vulnerability in neuroblastoma”
Paper published in Bioinformatics
Paper entitled: “DECODE: a computational pipeline to discover T cell receptor binding rules”
Paper published in Cell Reports
Paper entitled: “MacroH2As regulate enhancer-promoter contacts affecting enhancer activity and sensitivity to inflammatory cytokines”
D7.2 Software to define tumour subclones and association with therapy response
Flow cytometry is an important diagnostic tool in childhood acute lymphoblastic leukaemia (ALL), flow cytometry data analysis is limited by multiple sources of bias and variation. We present a unified machine learning framework for automated analysis of a standardized diagnostic paediatric leukaemia staining that can overcome these challenges. We applied our framework in a large cohort of ALL flow cytometry samples and demonstrated how it can robustly extract the frequencies of cell lineage populations with minimal expert intervention. This work provides a proof of concept that our method meets the needs of an automated analysis tool for diagnostic flow cytometry data.
D8.3 Metabolic models
Oncogene-driven metabolic rewiring in cancer is key to allow proliferation of tumour cells in low nutrient and oxygen conditions. To study such phenomena, reconstructing context-specific metabolic models through omics data integration is crucial. Here we report the original pipeline to construct context-specific metabolic models from scRNA-seq data and we applied it to scRNA-seq data from Ewing Sarcoma.
D4.3 Topological analysis of multi-omics and multi-cancer molecular networks resulting in the definition of molecular mechanisms
Three types of network-based analysis of gene-gene interaction networks have been suggested and tested on the multi-omics paediatric cancer datasets. User-friendly computational environment for joint application of matrix factorization and network analysis has been implemented.
D8.2 Network models for molecular target identification
We focused on the development of patient specific signalling networks using prior knowledge about the molecular events and CRISPR perturbation datasets and associated the activity of the nodes of signalling network with drug response data to find molecular targets.
D4.4 Consensus multi-omics subtypes of paediatric cancers
We report on the implementation of a method for multilayer community trajectory analysis and its applications, including a published study on medulloblastoma, a study on congenital myasthenic syndromes, and a study on the functional characterization of commonalities among a selection of paediatric tumours.
Consensus multi-omics subtypes of paediatric cancers
We report on the implementation of a method for multilayer community trajectory analysis and its applications, including a published study on medulloblastoma, a study on congenital myasthenic syndromes, and a study on the functional characterization of commonalities among a selection of paediatric tumours.
D2.4 DAC Portal prototype, validated analytical workflows, analysis prototype, updated metadata standards and portal prototype
We report on the selection of the appropriate data models to handle the available data and metadata to the iPC Central Computational and Data platform. We also report on the current status of the development for the iPC Data portal.
Paper published in Journal of Hepatology
Paper entitled: “Hepatoblastomas with carcinoma features represent a biological spectrum of aggressive hepatocellular neoplasms in children and adolescents”
Paper published in Molecular Cell
Paper entitled: “Oncogenic chimeric transcription factors drive tumor-specific transcription, processing, and translation of silent genomic regions”
Paper published in Bioinformatics
Paper entitled: “BIODICA: a computational environment for Independent Component Analysis of omics data”
Paper published in Cancer Science
Paper entitled: “Mutational spectrum of ATRX aberrations in neuroblastoma and associated patient and tumor characteristics”
Paper published in Nature Communication
Paper entitled: “A single-cell analysis of breast cancer cell lines to study tumour heterogeneity and drug response”
Paper published in frontiers in Molecular Bioscience
Paper entitled: „Modeling Progression of Single Cell Populations Through the Cell Cycle as a Sequence of Switches“
Paper published in iScience
Paper entitled: “Machine learning for multi-omics data integration in cancer“
D3.3 Integration of INtERAcT, MelanomaMine and LimTox and application to biomedical publications on paediatric cancers
This deliverable reports on the integration of INtERAcT and the implemented text mining workflow. The workflow was developed to adapt LimTox and MelanomaMine to pediatric tumor abstracts from PubMed and relies on INtERAcT in its downstream component of inferring molecular associations between entities extracted from unstructured text.
D1.3 Synthetic data for testing and training patient, cancer, and drug models
Synthetic data generation is emerging as an important solution for precision medicine. Therefore, an explainable Variational AutoEncoder (VAE) model is developed for synthetic transcriptomics data generation in medulloblastoma. The model can be used to complement and interpolate available data with synthetic instances. It is also transparent as it is able to match the learned latent variables with unique gene expression patterns. The model can also be adapted to other pediatric cancers and the resulting synthetic datasets used to test and train patient, cancer, and drug models in other work packages of the iPC project.
Paper published in BMC Bioinformatics
Paper entitled: “Emulating complex simulations by machine learning methods (SP)”
Paper will be presented at SPIE Medical Imaging
Paper entitled: “Segmentation of Multiple Myeloma Plasma Cells in Microscopy Images with Noisy Labels” (Presentation)
Paper published in bioRxiv
Paper entitled: “Loss of p16INK4a in neuroblastoma cells induces shift to an immature state with mesenchymal characteristics and increases sensitivity to EGFR inhibitors”
Paper published in BMC Bioinformatics
Paper entitled “DECONbench: a benchmarking platform dedicated to deconvolution methods for tumor heterogeneity quantification”
Paper published in Bioinformatics
Paper entitled: “FUNKI: Interactive functional footprint-based analysis of omics data”
Paper published in the Frontiers in Immunology
Paper entitled: “From Infection to Immunity: Understanding the Response to SARS-CoV2 Through In-Silico Modeling (SP)“
Paper published in Symmetry 2021
Paper entitled: “The Multiple Dimensions of Networks in Cancer: A Perspective”
Paper published in the Elsevier Journal
Paper entitled “Applications of single-cell and bulk RNA sequencing in onco-immunology”.
Paper published in Advanced Science
Paper entitled: “CHAF1A Blocks Neuronal Differentiation and Promotes Neuroblastoma Oncogenesis via Metabolic Reprogramming”
Paper published in the Special Issue Hepatoblastoma and Other Pediatric Liver Tumors
Paper entitled “Bridging molecular basis, prognosis, and treatment of pediatric liver tumors”.
Paper published in the Current Protocols in Bioinformatics.
Paper entitled “PIONEER: Pipeline for Generating High‐Quality Spectral Libraries for DIA‐MS Data”.
Paper published in the Journal for ImmunoTherapy of Cancer
Paper entitled “Identification and validation of viral antigens sharing sequence and structural homology with tumor-associated antigens (TAAs).”
Paper presented in the “Computer Vision for Microscopy Image Analysis (CVMI)” workshop
Paper entitled “Unsupervised Detection of Cancerous Regions in Histology Imagery using Image-to-Image Translation”
Paper published in Bioinformatics
Paper entitled: “Improved identification and quantification of peptides in mass spectrometry data via chemical and random additive noise elimination (CRANE)”
Paper published in Physics of Life Reviews: pp. 132-134
Paper entiteld: „Adaptation through the lense of single-cell multi-omics data Comment on “Dynamic and thermodynamic models of adaptation” by A.N. Gorban et al.”
Paper published in the BIORXIV
Paper entitled “Hepatoblastomas with carcinoma features represent a biological spectrum of aggressive neoplasms in children and young adults”.
Paper published in Bioinformatics
Paper entitled: “On the feasibility of deep learning applications using raw mass spectrometry data”
Paper published in Bioinformatics
Paper entitled: “TITAN: T-cell receptor specificity prediction with bimodal attention networks“
Paper published in NATURE COMMUNICATIONS
Paper entitled: “Restoration of the molecular clock is tumor suppressive in neuroblastoma”
Paper published in Bioinformatics
Paper entitled: “SysMod: the ISCB community for data-driven computational modelling and multi-scale analysis of biological systems”
Paper published in the Proceedings of International Conference on Machine Learning (ICML) 2021
A new network inference algorithm from TUDA with iPC acknowledge was published in the ICML 2021. Paper entitled “Active Learning of Continuous-Time Bayesian Networks Through Interventions”.
Paper published in Nature Biotechnology
Paper entitled: “The RNA Atlas expands the catalog of human non-coding RNAs”
D4.2 An interactive online atlas of interconnected network maps based on the NaviCell platform
With the development of the NaviCell 3.0 web server, there is a complete and automated web-based infrastructure for hosting molecular maps, patient similarity network maps, and multi-omics datasets for the project. The NaviCell platform supports molecular map navigation and exploration using the Google maps™ engine. The logic of navigation is taken from Google maps. This NaviCell 3.0 web-server is freely available and several step-by-step tutorials are accessible.
D7.1 Application of software enabling computational deconvolution of bulk RNA-sequencing data to immune cell profiles of patient samples
Computational deconvolution of bulk RNA-sequencing data to infer cell type composition of a sample is challenging. Benchmarking of various computational deconvolution tools revealed various data processing parameters that impact deconvolution accuracy and revealed the importance of a complete reference matrix. As a complete reference matrix is often not available, an algorithm was designed that can handle missing cell types. This algorithm can be applied to establish the immune cell repertoire of primary tumor biopsies without prior knowledge of the full spectrum of cell types in the biopsy.
D3.1 Identification of important regulatory elements using multi-level matrix factorization approaches
D3.1 describes the techniques for dimensionality reduction used in iPC and their application to a selection of cohorts (at different omics levels) as well as a meta-analysis of the four solid tumor types of interest. The goal of the deliverable is to provide a list of pathways and biological functions having a key role in multiple paediatric cancers.
D3.2 Adaptation of MelanomaMine and LiMTox to the analysis of paediatric cancers and application to biomedical publications on paediatric cancers
The paper reports on the implementation of the iPC text mining workflow and three use cases for extracting biomedical information from large volumes. The workflow builds on the general framework of two text mining tools, LimTox and MelanomaMine. These tools will be used in the framework of the iPC project but also beyond, having a clear impact in the research community.
D8.1 Data-driven model for molecular targets and drug repositioning
This deliverable provides a detailed overview of the proposed computational tool for predicting patient-specific drugs with potential therapeutic benefit for paediatric cancer treatment and provides, for example, evidence for the goodness of the model in predicting such patient-specific drugs.
D2.3 Recommended metadata standards and portal prototype
The iPC project aims to ensure interoperability of data between different resources, so the platform must enforce principles and well-defined standards for data accessibility, usability, and registration. This deliverable provides an overview of the different approaches to representing metadata within the iPC Platform, and the efforts to integrate and leverage them within the iPC Catalog and the overall iPC Central Computational and Data Platform to enable meaningful management of research data.
D1.2 Collection of high-quality clinical and molecular paediatric cancer datasets as well as other tumour types
In this deliverable, demographic, clinical, and molecular profiles were collected for several pediatric and adult tumors. In addition, the focus here is on collections of single cell profiles of high risk cancers. The datasets will be used to evaluate the effects of treatments and perturbations on cancer cells, build models, and provide information on deciphering regulatory interactions. These data will allow characterization of cancer cell types that predict treatment outcome, as well as cell types that are resistant to therapies.
“Estimage: a webserver hub for the computation of methylation age (SP)”
Article published in the Nucleic Acids Research Journal.
“Artificial Intelligence in Cancer Research: learning at different levels of data granularity”
Article published in the Molecular Oncology Journal, Volume 15, Issue 4 Pages 817-829.
Article published in the Cancer Cell Journal, Volume 39, Issue 6, P 810-826
Article entitled “STAG2 mutations alter CTCF-anchored loop extrusion, reduce cis-regulatory interactions and EWSR1-FLI1 activity in Ewing sarcoma”.
“The multilayer community structure of medulloblastoma”
Article published in the iScience Journal, Volume 24, ISSUE 4 by partner Barcelona Supercomputing Center (BSC).
Paper published in Machine Learning: Science and Technology
Paper entitled: “Data-driven molecular design for discovery and synthesis of novel ligands: a case study on SARS-CoV-2”
Publication in the Journal of Medical Internet Research (JMIR).
Article entitled “Artificial Intelligence–Aided Precision Medicine for COVID-19: Strategic Areas of Research and Development”.
Published in the JMIR, Volume 23 Issue 3 by partner Barcelona Supercomputing Center (BSC).
“Tumor to normal single-cell mRNA comparisons reveal a pan-neuroblastoma cancer cell”
Article published in the Science Advances Journal, Vol. 7, no. 6.
Paper published in Scientifc Reports
Paper entitled: “MDM4 inhibition: a novel therapeutic strategy to reactivate p53 in hepatoblastoma”
Paper published in the International Joint Conference on Neural Networks-2021 (IJCNN2021)
Paper entitled: “Clinical trajectories estimated from bulk tumoral molecular proles using elastic principal trees”
D4.1 Building of cancer type-specific multi-layered molecular and patient similarity networks
iPC uses network inference techniques and applies a selection of pediatric patient cohorts at different omic levels. Networks will be generated, for example, for the generation of molecular patient networks to be used in downstream project activities involving the use of networks.
“Benchmarking of cell type deconvolution pipelines for transcriptomics data”
Article published in “Nature Communications” (2020, 11:5650) by partner UGENT
“FPGA Accelerated Analysis of Boolean Gene Regulatory Networks”
Article published in the IEEE/ACM Transactions on Computational Biology and Bioinformatics ( Volume: 17, Issue: 6)
“COSIFER: a Python package for the consensus inference of molecular interaction networks”
Article published in the Bioinformatics Journal.
Paper published in Briefings in Bioinformatics
Paper entitled: “Deep learning in systems medicine”
D2.2 “Initial infrastructure framework”
An initial demonstrator of the iPC infrastructure is reviewed. The platform’s architecture is based on modules, which allow parallel developments and integration of different open source-based software components. This allows us to leverage other efforts and contribute towards its sustainability and maintainability. The release of a minimum viable platform is allowing us to capture early feedback from researchers at iPC.
“Designing a Network Proximity-Based Drug Repurposing Strategy for COVID-19”
The ongoing COVID-19 pandemic still requires fast and effective efforts from all fronts, including epidemiology, clinical practice, molecular medicine, and pharmacology.
Paper published in Frontiers in Cell and Developmental Biology.
Paper entitled: “Designing a Network Proximity-Based Drug Repurposing Strategy for COVID-19”
Journal article in MICCAI 2020
XLAB contributed to 23rd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2020) with an article about anomaly detection in visual data.
“Inferring clonal composition from multiple tumor biopsies”
Knowledge about the clonal evolution of a tumor can help to interpret the function of its genetic alterations by identifying initiating events and events that contribute to the selective advantage of proliferative, metastatic, and drug-resistant subclones.
ICML 2020 paper
TUDA submitted a manuscript about continous-time Bayesian networks to the 37th International Conference on Machine Learning.
Paper presented at International Conference of Machine Learning 2020 (ICML 2020)
Paper entitled: “Continuous-Time Bayesian Networks with Clocks (Conference Proceedings/Presentation)”
D1.1 “Collection of public molecular and clinical data”
The development of iPC predictive models for paediatric cancer genesis, progression, and response to therapies, as well as patient response to therapy, requires a vast quantity of molecular and clinical training data. In this deliverable, we have assembled a collection of these data to enable model construction and testing.
Paper published in BMC Bioinformatics
Paper entitled: “Methylation data imputation performances under different representations and missingness patterns”
Publication in Nucleic Acids Research
IBM published a new paper about their web service “PaccMann”.
Publication in Cancers 2020
“Comprehensive Map of the Regulated Cell Death Signaling Network” in Issue 990 of the “Cancers” Journal by CURIE.
AAAI 2020 paper
TUDA contributed to the 34th Conference on Artificial Intelligence with the paper “A Variational Perturbative Approach to Planning in Graph-Based Markov Decision Processes”.
Ewing sarcoma book
CURIE contributed to the Springer book “Ewing Sarcoma – Methods and Protocols, Springer”.
Publication in Journal of Hepatology
IGTP contributed with a paper entitled “Epigenetic footprint enables molecular risk stratification of hepatoblastoma with clinical implications”.
ROSUS 2020 paper
XLAB published a paper about “Visual Anomaly Detection in Domains with Limited Amount of Labeled Data”.
Publication in Entropy
CURIE published a paper on “Robust and Scalable Learning of Complex Intrinsic Dataset Geometry via ElPiGraph”
Press Release
CURIE elaborates on a better understanding of the intratumoral heterogeneity of Ewing sarcoma.
Publication in Molecular Pharmaceutics
IBM and UKL-HD published a paper on “Toward Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-Based Convolutional Encoders”
Paper published in Scientific Reports (Sci Rep)
Paper entitled: “Stabilized Reconstruction of Signaling Networks from Single-Cell Cue-Response Data”
Publication in Blood Advances
BCM’s paper on “Atovaquone is active against AML by upregulating the integrated stress pathway and suppressing oxidative phosphorylation”
NeurIPS 2019 paper
TUDA’s paper “Scalable Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data” was accepted
NeurIPS 2019 paper
IBM’s paper “PaccMannRL: Designing anticancer drugs from transcriptomic data via reinforcement learning” was accepted
Publication in Bioinformatics Journal
CURIE published a paper on “cd2sbgnml: bidirectional conversion between CellDesigner and SBGN formats”
Paper published in Explainable AI in Healthcare and Medicine
Paper entitled: “DeStress: Deep Learning for Unsupervised Identification of Mental Stress in Firefighters from Heart-rate Variability (HRV) Data”
Publication in Cell Reports
Publication by CURIE on “Transcriptional programs define intratumoral heterogeneity of Ewing sarcoma at single cell resolution”
Publication in International Journal of Molecular Sciences
CURIE published a paper on “Independent Component Analysis for Unraveling the Complexity of Cancer Omics Datasets”
“The RNA Atlas”
UGent and collaborators present a more comprehensive atlas of the human transcriptome that is derived from matching polyA-, total-, and small-RNA profiles of a heterogeneous collection of nearly 300 human tissues and cell lines.
“Using attention-based neural networks to enable explainable drug sensitivity prediction”
Published by Manica Matteo; Oskooei Ali; Born Jannis; Subramanian Vigneshwari; Saez-Rodriguez Julio; Rodriguez Martinez Maria
“Inferring context specific PPI networks”
Published by Manica Matteo; Mathis Roland; Cadow Joris; Rodriguez Martinez Maria
“Interpretability for computational biology”
Published by Nguyen An-phi; Rodriguez-Martinez
“PIMKL: Pathway Induced Multiple Kernel Learning”
Published by Manica Matteo; Cadow Joris; Mathis Roland; Rodriguez Martinez Maria
“Interpretable classification of molecular measurements”
Publication by Cadow Joris
“Interpretability for computational biology”
Publication by Nguyen An-phi; Rodriguez-Martinez Maria
“Using attention-based neural networks”
Publication on enabling explainable drug sensitivity prediction on multimodal data by Manica Matteo; Oskooei Ali; Born Jannis; Subramanian Vigneshwari; Saez-Rodriguez Julio; Rodriguez Martinez Maria
“Computer Modeling of Clonal Dominance”
Publication on Memory-Anti-Naïve and Its Curbing by Attrition by Castiglione, Filippo; Ghersi, Dario; Celada, Franco.
“From causal pathways to drug-response targets”
Presentation from Rosa Hernansaiz Ballesteros on multi-omic analysis to contextualise large signalling networks on 6th June 2019 at EMBL-EBI, Hixton, UK.
Video
Find out more about identifying effective personalized medicine for paediatric cancer in the explanatory video.
iPC Leaflet
The official leaflet of the iPC H2020 project containing Partners, Project Information, Mission, Vision and Goals of the project.
“Assessing reproducibility of matrix factorization methods in independent transcriptomes”
Publication by Laura Cantini, Ulykbek Kairov, Aurélien de Reyniès, Emmanuel Barillot, François Radvanyi, Andrei Zinovyev
D10.1 “Internal and external IT communication infrastructure and project website”
This deliverable constitutes the launch of the internal and external iPC communication infrastructure including the establishment of mailing lists, new IT infrastructure and the iPC website.
D11.1 “Project Quality Plan”
A handbook of the project management process, review process, quality checks, meeting organisation, which is communicated to all partners.
Press Release
New European Project Squares off against Paediatric Cancer
The Austrian-managed iPC project is now underway and bringing hope to the children with cancer
Announcement Letter
The official announcement letter contains all relevant information about the iPC H2020 project.
