Muhammed Yıldız

Bir gülüşe kancaz

[Muhammed Yıldız @realmyzz]

@MatthiasCaro Which world model?

[Muhammed Yıldız @realmyzz]

@AraPkkdusmani @scihan Öğrenci paketini kullandin mi

[Muhammed Yıldız @realmyzz]

@DeepTechTR Aynen kanka, ucretsiz yap da görelim

[Muhammed Yıldız @realmyzz]

@emirbalbay Ne yazık ki bir sorun oluştu. Lisans almak için lütfen BT departmanınıza başvurun

[Muhammed Yıldız @realmyzz]

@mertcobanov issue açabiliriz

[Muhammed Yıldız @realmyzz]

@AnantAg16023915 @Tim_Damasc @swpnldubey shipper

[Muhammed Yıldız @realmyzz]

@safaorhanTR Sondaki de olmadi mi :/

[Muhammed Yıldız @realmyzz]

@safaorhanTR @happyhackings dikkatli bakınca happy olduklarını anlıyorsunuz

[Muhammed Yıldız @realmyzz]

@e_kelesss Kimse lisanstayken ne yaptın diye de sormuyor, Top üni mi, tamam çok iyisin nolur bize gel

[Muhammed Yıldız @realmyzz]

@DeepTechTR Kuramadım google colab'de, kullanan oldu mu? Yardımcı olabilir mi?

[Muhammed Yıldız @realmyzz]

@D4Vinci1 @DeepTechTR I couldnt install it on collab

[Muhammed Yıldız @realmyzz]

@ibragim_bad I also dropped out from dentistry haha

[Muhammed Yıldız @realmyzz]

@ibragim_bad I cant send you dm

[Tunca Doğan @tuncadogan]

🚀 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: https://t.co/gzHU9nBsiT

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: https://t.co/Wh5LSS4Qam
📡 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: https://t.co/zA2VHmdhS9
⚙️Try the tool: https://t.co/oNjMTl89Vk

***Please repost!***
#AI #LLM #ML #Bioinformatics #KnowledgeGraph #DrugDiscovery #Biomedicine #OpenScience

[Muhammed Yıldız @realmyzz]

@Scholarshiplug Applications closed

[Muhammed Yıldız @realmyzz]

@hazhubble And how can I join? I couldnt DM you.

[Muhammed Yıldız @realmyzz]

@hazhubble Got a summer research offer from Purdue (Daisuke Lab) on Protein LMs & built nanoGPT. Want to stay in SF for the AI scene while visiting Purdue perodically for my research. Can I join?

[Muhammed Yıldız @realmyzz]

@tamerthedark Research ilanları için de olan versiyonu var mı

[Muhammed Yıldız @realmyzz]

@BoWang87 My prof wants us to focus on Mamba-3's architecture and logic for protein representation learning instead of just metrics. We need to understand the 'why' behind the changes and see if it actually fits our data and goals. Is it worth the switch for us?

[Muhammed Yıldız @realmyzz]

@asishcodes Hi! I'm planning a GSoC project on synthetic data generation for CV models using Nano-Banana. It’s a pure Python pipeline, so it's not a PR to an existing lib but a standalone tool. How would you suggest proving its FLOSS impact for a strong application?