1/ 🎉 Our paper "Protein Language Models Expose Viral Mimicry and Immune Escape" is accepted at #ICML2024. We delve into how machine learning can help us understand tricky viruses better! 🦠
2/ 🧬 Viruses often mimic host proteins to evade the immune system. We used Protein Language Models (PLMs) to identify these mimicries by distinguishing between viral and human proteins.
#ESM #PLM #LLM
3/ 📊 Our models achieved a whopping 99.7% accuracy! But, mistakes were particularly insightful, revealing the characteristics of viruses like HIV and Herpes in escaping immune detection. #DataScience #Virology
1/ Excited to share our work 🧬 "Detecting Anomalous Proteins Using Deep Representations" 🧬published in NAR Genomics and Bioinformatics!
2/ Our research looks at identifying proteins with unique, often unexpected functions. Traditional methods fall short due to the sheer volume and complexity of biological databases. Our solution? Anomaly detection with deep learning.
3/ We adapt anomaly detection techniques from computer vision to the bioinformatics realm, using pretrained deep neural networks. This enables us to generate meaningful protein representations without labeled data, a significant leap forward in protein analysis #LLM #anomaly #CV
1/ 🧪🔬 Ever wondered if scientific research can be predicted? Our latest paper "What's next? Forecasting scientific research trends" tackles this question. Check out the details here 👉 arXiv:2305.04133v1 [thread] 🧵
2/ 🌍 The world of science is constantly evolving. But what if we could predict these trends, especially in life sciences? That's what our work aims to do. Imagine the possibilities!
3/ 📚 We've mined historical publications, research/review articles, and patents. The result? Models that can foresee scientific trends 5 years in advance. Time travel, anyone? #AI#DataScience#timeseries#trends