Benjamin Haibe‐Kains

Evaluation of ensilication technology for ambient DNA preservation

This paper evaluates ensilication technology for ambient DNA preservation, finding it maintains sequencing fidelity and reduces artifacts compared to frozen storage.

Distributed Biomarker Discovery for Immuno-Oncology

This paper develops a distributed pipeline for immuno-oncology biomarker discovery using federated learning to integrate clinical and molecular data across institutions without sharing sensitive data.

Functional landscape of circular RNAs in human cancer cells

The paper identifies essential circRNAs in human cancer cells and introduces FunCirc, a database of functional circRNAs across cancer cell lines and tissues.

Circular RNA profiling and functional screening in breast cancer identify circNSD1 as a suppressor of tumor autophagy

The paper identifies circNSD1 as a tumor suppressor in breast cancer that inhibits autophagy and oxidative stress tolerance.

MorphoDiff: Cellular Morphology Painting with Diffusion Models

MorphoDiff predicts high-resolution cell morphology changes under different interventions using diffusion models and perturbation embeddings.

A dynamic microRNA profile that tracks a chemotherapy resistance phenotype in osteosarcoma. Implications for novel therapeutics.

The paper identifies a dynamic microRNA profile associated with chemotherapy resistance in osteosarcoma and predicts novel therapeutic targets that could reverse resistance.

Reusability Report: Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients

This paper reproduces and improves the reusability of the TCRP method for predicting drug response across preclinical and clinical datasets.

Similarity metric learning on perturbational datasets improves functional identification of perturbations

This paper introduces PeML, a similarity metric learning method for perturbational datasets, improving the identification of perturbation mechanisms and biological relationships.

GENIUS: GEnome traNsformatIon and spatial representation of mUltiomicS data

GENIUS transforms multi-omics data into images for deep learning analysis to predict metastatic cancer progression from primary tumors.

Detection of circular RNAs and their potential as biomarkers predictive of drug response

The paper assesses the inter-lab consistency of circular RNA expression in cancer cell lines and identifies factors affecting reproducibility.

Genome-wide DNA methylation patterns reveal clinically relevant predictive and prognostic subtypes in osteosarcoma.

This study identifies DNA methylation subtypes in osteosarcoma that predict clinical outcomes and response to chemotherapy.

Similarity bias from consensus perturbational signatures from the L1000 Connectivity Map

The paper shows that consensus signatures from the L1000 Connectivity Map exhibit similarity bias, which can be mitigated by mean normalization.

PharmacoDB 2.0 : Improving scalability and transparency of in vitro pharmacogenomics analysis

PharmacoDB 2.0 enhances pharmacogenomics analysis by integrating new datasets, implementing FAIR pipelines, and improving drug response analysis tools.

Orchestrating and sharing large multimodal data for transparent and reproducible research

The paper introduces a cloud-based platform called ORCESTRA for reproducible processing and sharing of multimodal biomedical data in a FAIR manner.

Drug Sensitivity Prediction From Cell Line-Based Pharmacogenomics Data: Guidelines for Developing Machine Learning Models

This paper provides guidelines for developing machine learning models to predict drug sensitivity using cell line-based pharmacogenomics data, emphasizing proper training and validation practices.

Meta-gene markers predict meningioma recurrence with high accuracy

The paper identifies a gene co-expression module that accurately predicts meningioma recurrence with an AUC of 0.81.

KuLGaP: A Selective Measure for Assessing Therapy Response in Patient-Derived Xenografts

The paper introduces KuLGaP, a selective measure to assess therapy response in patient-derived xenografts by comparing treatment and control arms, improving accuracy over existing methods.

MicroRNA-mRNA networks define translatable molecular outcome phenotypes in osteosarcoma.

The paper identifies microRNA-mRNA networks associated with prognosis in osteosarcoma and validates their predictive value across independent datasets.

Machine learning-based prediction of response to PARP inhibition across cancer types.

The paper develops a multi-gene signature predicting PARP inhibitor response across cancer types using machine learning and validates it in vitro and in clinical datasets.

Modeling cellular response in large-scale radiogenomic databases to advance precision radiotherapy

This study develops RadioGx, a computational platform to analyze radioresponse in radiogenomic databases, identifying molecular pathways and drug correlations with radiation response.

Creating reproducible pharmacogenomic analysis pipelines

The paper develops reproducible pharmacogenomic analysis pipelines using Common Workflow Language to process breast cancer datasets and share them with a Digital Object Identifier.

MetaGxData: Clinically Annotated Breast, Ovarian and Pancreatic Cancer Datasets and their Use in Generating a Multi-Cancer Gene Signature

MetaGxData provides standardized cancer transcriptomic and clinical data for cross-tumour analyses, identifying common prognostic genes and creating a multi-cancer gene signature.

Integrative Pharmacogenomics Analysis of Patient Derived Xenografts

The paper develops Xeva, an open-source tool for analyzing PDX pharmacogenomic data, finding that few genes and pathways show passage-specific changes.

Meta-analysis of 1,200 transcriptomic profiles identifies a prognostic model for pancreatic ductal adenocarcinoma

The paper develops a prognostic model for pancreatic ductal adenocarcinoma using meta-analysis of transcriptomic data, identifying gene pairs associated with early mortality after surgery.

Whole Genomes Define Concordance of Matched Primary, Xenograft, and Organoid Models of Pancreas Cancer

The paper compares whole-genome data from primary pancreatic cancer, xenografts, and organoids to assess genetic concordance across different models.

Metabolic adaptations underlie epigenetic vulnerabilities in chemoresistant breast cancer.

This study identifies metabolic adaptations in taxane-resistant triple-negative breast cancer cells that lead to epigenetic vulnerabilities, specifically through altered methionine metabolism and H3K27me3 redistribution.

CREAM: Clustering of genomic REgions Analysis Method

CREAM identifies COREs from cis-regulatory data, outperforming ROSE, and shows their enrichment near essential genes and TAD boundaries.

Software For The Integration Of Multi-Omics Experiments In Bioconductor

The paper introduces MultiAssayExperiment, a Bioconductor package for integrating multi-omics data, demonstrating its use with TCGA datasets to simplify analysis and visualization.

Gene isoforms as expression-based biomarkers predictive of drug response in vitro

The paper identifies gene isoform-based biomarkers predictive of drug response in breast cancer using pharmacogenomic data from CCLE and GDSC.

PharmacoDB: an integrative database for mining in vitro anticancer drug screening studies

PharmacoDB integrates large pharmacogenomic studies to enable comparison and analysis of drug screening data by curating identifiers and standardizing drug response metrics.