Viola Fanfani

@yarathedon @SuicideWatchWF @samaritans

Single-sample network inference remains an area of ongoing development. A new method, BONOBO, uses empirical Bayes to estimate single-sample correlation matrices drawing evidence from a population of samples. @DrEnakshiSaha @violafanfani @HarvardBiostats genome.cshlp.org/content/early/…

Live-post of Maggie Beheler-Amass: Dynamic gene regulatory network inference with interpretable, biophysically-motivated neural ODEs #ISMB2024 bsky.app/profile/michae…

Huge milestone for @SynGenome with 10 new papers on 9 new chromosomes and a #yeast cell with > half #synthetic #genome! Proud to have contributed to 8 of them with @violafanfani and @biomed_ai_geno in my lab, who analysed tons of data! @SBSatEd @EdEngBio @BioMedAI_CDT

My dear colleague and friend, Claudia Cea @claudiacea8, has just left Columbia to advance her research career as a post-doc at MIT. I was lucky to to work with her over years, and I'm gladly announce that our paper came out today in Nature Materials: nature.com/articles/s4156…

@BioDecoded @SaveToNotion #thread

Elucidating tumor heterogeneity from spatially resolved transcriptomics data by multi-view graph collaborative learning | Nature Communications nature.com/articles/s4146… #Bioinformatics

@AnnaSECuomo @MolSystBiol @tobi_heinen @OliverStegle @SaveToNotion #thread

CellRegMap is finally out in @MolSystBiol! 🎉 Introducing a statistical framework to map context-specific eQTL using single-cell data, without the need to discretise single cells into distinct groups. Dream work with @tobi_heinen, @OliverStegle et al! Tweetorial 👇 (1/n)

@BenSiranosian @SaveToNotion #thread

Why are bioinformatics pipelines different than workflows in data engineering? My thoughts on the ecosystem of workflow managers, and where the field might be headed: bsiranosian.com/bioinformatics…

@XiuweiZhang @SaveToNotion #thread

Excited to share scMoMaT, a mosaic integration method for single cell multi-omics data. scMoMaT jointly learns bio-markers (marker genes, TF motifs and proteins) to interpret each cell cluster in addition to the integrated cell embedding. biorxiv.org/content/10.110…

@AI4Pathology @Cancer_Cell @harvardmed @BWHPath @broadinstitute @SaveToNotion #thread

Excited to share our @Cancer_Cell article presenting a pan-cancer integrative histology-genomic analysis, multimodal integration improves prognostic models, discovers molecular & morphologic correlates of prognosis. bit.ly/3PbnUVM @harvardmed @BWHPath @broadinstitute 1/2

@i_amanchadha @SaveToNotion #thread

📚 Natural Language Processing from Stanford University: Distilled Notes 👉🏼 nlp.aman.ai - NLP is one of the most popular #AI domains, widely used from language translation to auto-complete to voice assistants. - Presenting notes from Stanf…lnkd.in/gBBWfvUi

@KirkDBorne @SaveToNotion #thread

Harvard CS109A #DataScience course materials — huge collection free & open! 1. Lecture notes 2. R code, #Python notebooks 3. Lab material 4. Advanced sections Find it all here: harvard-iacs.github.io/2019-CS109A/pa… — #BigData #DataScientists #MachineLearning #AI #DeepLearning #NeuralNetworks

@svpino @SaveToNotion #thread

The best linear algebra course out there. PERIOD. For Free! MIT's Professor Gilbert Strang. Go through these videos, and you'll never ever have a problem with linear algebra again! ocw.mit.edu/courses/18-06-…

@diunguyen_vn_uk @SaveToNotion #thread

Wow! Huge valuable database for cancer research! sciencedirect.com/science/articl…

@tangming2005 @SaveToNotion #thread

Two of the best statistics books using biological data as examples: 1. Modern Statistics for Modern Biology lnkd.in/e9jSU6xq 2. Data Analysis for the Life Sciences Series lnkd.in/ejWp5egX I am grateful to have those open materials available online. #genomics #rstats

@razoralign @SaveToNotion #thread

PyGenePlexus: A Python package for gene discovery using network-based machine learning biorxiv.org/content/10.110…

@jw9730 @SaveToNotion #thread

New preprint on Graph Transformers! We show that a vanilla Transformer on nodes and edges becomes a powerful graph learner (in both theory and practice) if simple auxiliary input embeddings are provided. We call this Tokenized Graph Transformer (TokenGT). arxiv.org/abs/2207.02505

@YuriEngelhardt @nlenvironagency @filipdeblois @AlbertoCairo @allardwarrink @SaveToNotion #thread

@m_a_sherman @NatureBiotech @SaveToNotion #thread

So excited to share our paper "Genome-wide mapping of somatic mutation rates uncovers drivers of cancer" is out on @NatureBiotech (and open access)! nature.com/articles/s4158…. Here's a🧵on what we did and what we found!

@Aiims1742 @SaveToNotion #thread

Pan-cancer whole genome comparison of primary and metastatic solid tumors biorxiv.org/content/10.110… “5 cancer types - breast, prostate, thyroid, kidney clear carcinoma & pancreatic neuroendocrine - display an extensive transformation of their genomic landscape in advanced stages”.