erva retweeted
🚀 Exciting news! Our project, CROssBARv2, is now live as an online tool and its article (preprint)!
We've built a unified AI-powered platform that brings together the fragmented world of biomedical data — and lets you talk to it in plain English.
Here's the story 👇
The problem, in plain terms: Imagine being a detective, but your clues are scattered across 34 different filing cabinets, written in different languages, with no index. That's what biomedical researchers face every day — genes in one database, drugs in another, diseases somewhere else. Connecting the dots is slow & painful without serious programming skills.
CROssBARv2 is our answer to this. 🧬💊🔬
What did we build?
CROssBARv2 is a biomedical Knowledge Graph (KG) — think of it as a giant, intelligent map of biology. We integrated data from 34 well-established databases into a single, structured, and searchable system:
🔵 ~2.7 million nodes (proteins, genes, drugs, diseases, pathways, side effects, & more)
🔗 ~12.6 million edges (biomedical relationships)
🧠 14 node & 51 edge types
🏷️ Rich metadata
Now the exciting part 🤖 — meet CROssBAR-LLM
Large Language Models (LLMs) like ChatGPT or Gemini are brilliant at conversation — but they hallucinate. They confidently tell you things that sound right but aren't. In biomedicine, that's dangerous.
Our solution: ground the LLM in the knowledge graph.
CROssBAR-LLM lets you ask complex biomedical questions in plain English, like:
"What proteins are encoded by genes regulated by NFKB1, participate in the Endocytosis pathway, and are targeted by drugs used to treat diseases comorbid with osteoporosis?"
CROssBAR-LLM tutorial: youtu.be/FjuoKAmzjNM
What happens under the hood:
🗣️ Your natural language question is translated into a formal DB query
⚡ The query runs on the CROssBARv2 KG in real time
📊 Structured, verified results are retrieved
💬 The LLM turns results into a clear, readable answer
No hallucinations. Every answer is traceable back to real data
How does it compare to just directly asking LLMs on a biomedical Q&A benchmark?
GPT/Claude/Gemini: ~50-65%
CROssBAR-LLM (w/ Gemini 1.5 Pro): 98% accuracy 🎯
CROssBAR-LLM (w/ GPT-4o): 97% accuracy 🎯
Everything is open and accessible 🔓
🌐 Web platform: crossbarv2.hubiodatalab.com/
📡 GraphQL API
🖥️ Neo4j Browser for visualisation
📂 Full data on Hugging Face & Google Drive
💻 All code on GitHub
No paywall. No programming required. Just ask your question!
Huge thanks to the team!
Bünyamin Şen, Erva Ulusoy @ervaulusy , Melih Darcan, Mert Ergun, Sebastian Lobentanzer, Ahmet S. Rifaioğlu @ahmet_rifaioglu , Dénes Türei, Julio Saez Rodriguez @JulioSaezRod , and me, in collaboration with Saez Lab @saezlab
spanning Hacettepe University @Hacettepe1967 , Heidelberg University @HeidelbergU , Helmholtz Munich @HelmholtzMunich , and European Bioinformatics Institute | EMBL-EBI @emblebi
📄 Read the preprint: biorxiv.org/content/10.64898…
⚙️Try the tool: crossbarv2.hubiodatalab.com/…
***Please repost!***
#AI #LLM #ML #Bioinformatics #KnowledgeGraph #DrugDiscovery #Biomedicine #OpenScience
erva retweeted
🚀 Our new book chapter is out in Protein Function Prediction: Methods and Protocols:
“A Benchmarking Platform for Assessing Protein Language Models on Function-Related Prediction Tasks”
link.springer.com/protocol/1…
w/ @elif_cevrim @mgyigit @ervaulusy & Ardan Yılmaz
++
erva retweeted
Hacettepe Biological Data Science Lab is on site at #ISMBECCB2025 (20–24 July, ACC Liverpool)—the flagship bioinformatics forum uniting ISMB & ECCB. The atmosphere is truly inspiring and dynamic. 🔬✨ #bioinformatics
++
erva retweeted
Erva Ulusoy @ervaulusy is on stage presenting ProtHGT—heterogeneous graph transformers + protein LMs for protein‑function prediction with biological knowledge graphs— on the #Function stage at #ISMBECCB2025
erva retweeted
Excited to share our new article 🚨
“Protein Language Models for Predicting Drug–Target Interactions: Novel Approaches, Emerging Methods & Future Directions”
with @atabeyunlu @ervaulusy @mgyigit & Melih Darcan is published in COSTBI
Free access link: authors.elsevier.com/a/1keXR…
erva retweeted
New article 📢
Our study entitled: "Mutual annotation-based prediction of protein domain functions with Domain2GO"
with @ervaulusy is now published in the Protein Science journal
onlinelibrary.wiley.com/doi/…
🧬🤟🎊
#ProteinScience @ProteinSociety
onlinelibrary.wiley.com/jour…
++
Great new work by @ervaulusy @atabeyunlu @tuncadogan et al @hubmb @ai_hacettepe @hubioinf @HUbilisim -'SELFormer: molecular representation learning via #SELFIES language models'- bit.ly/3Ny2aod #machinelearning #compchem #drugdiscovery #AI #materials #bioinformatics #NLP
erva retweeted
New paper alert 🚨
I'm happy to announce that our collaborative project led by @slobentanzer & @JulioSaezRod @saezlab on developing an #opensource framework called "BioCypher" for easy creation & manipulation of biological knowledge graphs has been published @NatureBiotech 🥳
📄 Knowledge graphs (KGs) are a key technology in biomedicine, but can be hard to create/share/reuse. To make KGs as accessible as possible we developed the #opensource framework BioCypher: nature.com/articles/s41587-0…, now peer-reviewed @NatureBiotech. 🧵👇 1/
erva retweeted
Aynı haftada grubumuzdan bir güzel haber daha 🚨
Erva "Heterojen Biyomedikal Verinin Bilgi Çizgeleri ve Derin Öğrenme Tabanlı Analizi ile Protein Fonksiyonlarının Otomatik Tahmini" başlıklı yüksek lisans (YL) tezini başarı ile savundu
Tebrikler @ervaulusy 👏🥳🤟
Beklenen ++
erva retweeted
Good news from our lab 🚨
All of our submissions got accepted (4 oral, 3 posters) at the flagship bioinformatics conference, ISMB/ECCB2023 iscb.org/ismbeccb2023
Congrats to all, starting from presenters: @ervaulusy @atabeyunlu @serbulentunsal Burakcan, Elif & @heval_atas
1/6
erva retweeted
New paper 🚨🤟🥳🎸
"SELFormer: Molecular Representation Learning via SELFIES Language Models" is out as a pre-print
arxiv.org/abs/2304.04662
Started as an undergraduate course project and evolved into a new chemical language model!
#DeepLearning #DrugDiscovery #ML #AI
1/8
erva retweeted
Teyzem göçük altında... Lütfen yardım edin!
Nihal Rifaioğlu
HATAY ANTAKYA akevler mah 432. Sok torunlar apt bedi sabuncu ortaokul yanı
0 (555) 156 31 10 (kardeşi)
@AFADHatay
@AFAD_Ankara
@ahbap
@haluklevent
@OguzhanUgur
This Post is from an account that no longer exists. Learn more
erva retweeted
Building a knowledge graph for biomedical tasks usually takes months or years. 😰 What if you could do it in weeks or days? 🏃 We created BioCypher (biocypher.org) to make it easier than ever, but still flexible and transparent. 🧵⬇️
erva retweeted
Two days full of exciting science #HIBIT2022 Turkish bioinformatics community rocks 🤟🏼
Thanks to organizers @yaydinson Dr Arzu Karahan @BurcakOtlu also @RSGTurkey & all students who worked tirelessly
Love from Hacettepe Biological Data Science Lab, hope to see you all next year – at Erdemli, Mersin
erva retweeted
AI tool to generate colour palettes from any text prompt —
#stablediffusion #ArtificialIntelligence






























