Benno Schwikowski

Researcher in #SystemsBiology at @InstitutPasteur

[Biology+AI Daily @BiologyAIDaily]

Comparative evaluation of feature reduction methods for drug response prediction @SciReports

1. This study is the first to compare nine feature reduction (FR) methods for drug response prediction (DRP) on cell line and tumor transcriptomes, using over 6,000 machine learning (ML) model runs for robust analysis.

2. A key finding is that Transcription Factor (TF) activities outperform other FR methods on tumor data, distinguishing sensitive from resistant tumors for seven out of 20 drugs tested.

3. The researchers analyzed both knowledge-based methods (e.g., pathway and TF activities) and data-driven approaches (e.g., principal components), providing a broad perspective on FR for DRP.

4. Ridge regression emerged as the most effective ML model across all FR methods, highlighting its ability to handle correlated gene expression data.

5. Cross-validation on cell lines showed that sparse principal components and drug pathway genes performed best, while tumor validation emphasized the robustness of TF activities.

6. The study revealed that effective FR methods often depend on the drug and dataset type, underlining the need for tailored approaches in DRP.

7. TF activities proved to be a compact and interpretable representation of functional cellular states, bridging biological relevance and predictive accuracy in tumor DRP.

8. The findings emphasize the importance of robust FR methods to address the dimensionality challenges in molecular profiling, paving the way for precision medicine.

@bennos @janbaumbach @behnam_bme @Faren_FIR
💻Code: https://t.co/3JpXcLIZug
📜Paper: https://t.co/kO7BDrIEjc

#DrugResponsePrediction #MachineLearning #FeatureReduction #CancerResearch #PrecisionMedicine

[Line Bjørge @DrLB]

Winter-meeting for the PARIS-project Copenhagen. #ovariancancer @bennos, @AnnaVaharautio, @WennerbergLab, @Gynkreft, @reachoutinova, @PrecosL, @haukeland_no, @K_Kleinmanns @forskningsradet, @medofak_uib, @eraper (PARIS = Precision drugs Against Resistance In Subpopulations)

[CarolaDoerr @CarolaDoerr19]

Together with @bennos team @institutpasteur we study ensembles of bivariate monotone classifiers for biomedical applications.
In this @biorxivpreprint we present a preprocessing step that speeds up their construction by factor 10-20: https://t.co/Chhuocp2Vg

[Kaiyang Zhang @KaiyangZhang]

Our paper on #scRNAseq analysis of #chemoresistance in #ovariancancer is out today in @ScienceAdvances! Many thanks to @Sampsa_H @AnnaVaharautio AnttiHakkinen @e_p_erkan @SanazJamalzadeh and all co-authors for your great contribution! https://t.co/x2MsN2SSpa (1/3)

[Tirosh Lab @TiroshLab]

Excited to share our preprint on pan-cancer analysis of intra-tumor heterogeneity (ITH), led by Avishai Gavish and Mike Tyler. After exploring ITH in small patient cohorts, we now curated scRNA-seq data from >1,000 tumors to broadly define ITH patterns. https://t.co/9tld8RHOFO

[Line Bjørge @DrLB]

Preclinical models are important tools in #ovariancancer research. We here describe how to generate xenograft models. @medofak_uib @haukeland_no @reachoutinova @Gynkreft @Kreftforeningen @georgewbasj #CCBIO
https://t.co/jD3q4nGvHo

[Institut Pasteur, since 1887 @institutpasteur]

#Cancer : comment l’IA peut améliorer la prise en charge du cancer de l’ovaire ?
Pour en savoir plus ➡️ https://t.co/cCUj7T45zS

[H2020 TranSYS @H2020TranSYS]

Register now for this free online training school by TranSYS @institutpasteur https://t.co/CiTuVeaNyo #dataanalysis #precisionmedicine #itn #school #training

[Olli Carpen @OlliCarpen]

Pleased to inform that our 1st @deciderproject article is published. Fascinating what AI can achieve @precisionpathology. Artificial intelligence-based image analysis can predict outcome in high-grade serous carcinoma via histology alone https://t.co/7cvGUkUBje

[Sampsa Hautaniemi @Sampsa_H]

Excellent review on platinum resistance by Huang et al. in @oncogenejournal. Systematic literature search resulted in >900 #PlatinumResistance related genes conveniently stored in a database. #SBLread, @HautaniemiLab, @deciderproject, @HerculesOvCa. https://t.co/4ppbhdgVQF

[Benno Schwikowski @bennos]

@DrLB @WennerbergLab @reachoutinova @AnnaVaharautio @forskningsradet @medofak_uib @haukeland_no @georgewbasj @Gynkreft Proud to be part of an awesome team!

[Sampsa Hautaniemi @Sampsa_H]

I am grateful to EU #H2020 for supporting our #ovariancancer research. The main goals of @deciderproject are 1) understand mechanisms causing chemoresistance in #ovariancancer patients and 2) deliver tools for personalized diagnosis and treatment options.

[Saez-Rodriguez Group @saezlab]

Did you ever wonder how well pathway and transcription factor analysis work for scRNA-seq data? Christian Holland (@mr_netherlands) et al. shed light on this question in our latest preprint [https://t.co/JC8Tz59TKz]. 1/6

[Benno Schwikowski @bennos]

@RCFbio @IdoAmitLab Thanks Robin!

[Benno Schwikowski @bennos]

Our lab's debut paper in single cell transcriptomics, co-led by our shared PhD student @bost_pierre. Congratulations, Pierre!

[IdoAmitLab @IdoAmitLab]

We are excited to share a new study by @Ronnie_Blecher @bost_pierre and @kerryhilligan on molecular roadmaps for antigen-specific immunity @CellSystemsCP https://t.co/F5lQd1ZeYo. A fantastic collaboration with @francaronchese lab at the @Malaghan_Inst (1/14)

[Benno Schwikowski @bennos]

Our lab at @institutpasteur in Paris has open #postdoc positions at the interface of statistical data analysis and cancer/autoimmune disease. https://t.co/xG0BLk1LC2 #bioinformatics #jobs

[Benno Schwikowski @bennos]

Finding high-scoring subnetworks is (still) a hard problem! Why? See our new paper at https://t.co/HlUX856fC0

[Benno Schwikowski @bennos]

https://t.co/pkrVMvAGpJ

[Benno Schwikowski @bennos]

Different levels of #omics data visualized in @HerculesOvCa project

[Chris Evelo @Chris_Evelo]

Interesting new Sage-DREAM challenge to find the (best method to find) the networks (not just the genes) involved in BREAST cancer #sagecon