Using in-silico mutagenesis, we discovered that exogenous genomes utilize known yeast transcription-factor binding sites, but some can be discovered only by ExoShorkie, which we fine-tuned for this task.
Preprint: biorxiv.org/content/10.6...
GitHub: github.com/OrensteinLab...
New preprint alert! we developed ExoShorkie to predict RNA-seq coverage of exogenous genomes in yeast. We fine-tuned the recently developed Shorkie on RNA-seq data of exogenous genomes, and show that ExoShorkie performs best on held-out genomes.
Key results:
Learns repair mechanisms without manual features
Generalizes across cell types & experiments
Quantifies frameshift probability for any gRNA
Preprint: biorxiv.org/content/10.6...
Design better knockouts! Code: github.com/OrensteinLab...
Our solution:
✅ First feature-independent deep learning model
✅ End-to-end - learns microhomology rules directly from raw sequences
✅ Multi-dataset training overcomes class imbalance
✅ 18-dataset benchmark - beats all SOTA methods
🚀 New preprint: CROP - Revolutionizing #CRISPR repair outcome prediction! ✂️🧬
Problem: How to predict frameshift rates (key for gene knockout design) across diverse experiments?
#CRISPR #GeneEditing #MachineLearning #Bioinformatics
Happy to share our new method F-MoDA to find motifs in genomic attribution maps just published in MLCB 2025 proceedings! F-MoDA has improved specificity, sensitivity, accuracy, conciseness, and runtime compared to TF-MoDISco. Led by Ofir Yaish: proceedings.mlr.press/v311/yaish25...
Excited to share this preprint which describe the IBIS challenge to predict TF binding sites across experimental assays. My students achieved best performance in the in vitro -> in vivo task! Thanks so much for the organizers for their herculean efforts!
Interested in a post-doc in Israel? The deadline for the Azrieli International Postdoctoral Fellowship is November 19. The fellowship offers generous funding for postdocs to conduct research in any academic discipline at eligible Israeli institutions: azrielifoundation.org/fellows/inte...
The start of a new academic year at the Orenstein lab - we are excited to welcome three new MSc students: Yehuda, Evyatar, and Sapir, and continue with three PhD students: Ido, Jonathan, and Noam. Good luck in your studies and research!
The GreedyMini paper is finally out as part of #ISMBECCB2025 proceedings: academic.oup.com/bioinformati.... Arseny will present it on the last day (July 24th) and last session (14:20) of the HiTSeq meeting.
🚨 Attention US PhDs in Bioinformatics:
Interested in a postdoc in my group at Bar-Ilan University 🇮🇱 through the Fulbright Israel fellowship (2026–2027)?
🧬 2 years of research
💰 $95,000 stipend + relocation + benefits
📅 Apply by 15/9
🔗 www.fulbright.org.il/program/2/842
✉️ Email me!
It was a delight to host my former PhD advisor Prof. Ron Shamir and hear about his current research on clustering cancer patients and standardising Parkinson's disease progression scores (in addition to the usual chit-chatting and updates...)
🚨 Deadline Extended: Call for Papers - RECOMB-seq 2025 🚨
Great news! You now have an extra week to submit your work. 🎉
Updated Deadlines:
🔹 Abstract Registration: Jan 31, 2025
🔹 Submission: Feb 7, 2025
recomb-seq.github.io/papers/
🚨 Call for Papers: RECOMB-seq 2025 🚨
🗓️ Dates: April 24-25, 2025
📍 Location: Seoul, South Korea
Key deadlines:
🔹 Abstract registration: Jan 24, 2025
🔹 Submission: Jan 31, 2025
More details: recomb-seq.github.io/papers/
Excited to share FiSSC, a new method to find a smallest sequence cover of sets of degenerate reads. We prove that the problem is NP-hard, and suggest filtering steps and an ILP solution. We apply it to RNA A-to-I editing data to gauge biological complexity
dl.acm.org/doi/10.1145/...
