CMU School of Computer Science PhD Student @SCSatCMU @CMUCompBio @CMUPittCompBio
Pittsburgh
Joined January 2020
- Tweets215
- Following333
- Followers73
- Likes17.1K
Excited to see the MHS research preview begin! As part of CMU’s work in the preview, I focused on AI orchestration and software integration, bringing instruments with incompatible interfaces together into a unified, agent-driven lab system. Rewarding to see our work featured!
Today, we're kicking off the first phase of the research preview for Model Hardware Standard (MHS): a new standard for AI agents to safely operate physical equipment in scientific research and advanced manufacturing.
Read more: anthropic.com/news/model-har…
Very excited to finally share this work!
My focus in CMU’s contribution to the MHS research preview was the AI orchestration and software integration, helping bring disconnected instrument interfaces into a unified system that an AI agent could coordinate.
Sina Barazandeh retweeted
SCS researchers used MHS to run experiments about 3x faster than before, with an AI agent orchestrating a liquid handler, a plate reader, a robotic arm and monitoring cameras across three computers with fundamentally incompatible interfaces.
Today, we're kicking off the first phase of the research preview for Model Hardware Standard (MHS): a new standard for AI agents to safely operate physical equipment in scientific research and advanced manufacturing.
Read more: anthropic.com/news/model-har…
Sina Barazandeh retweeted
We're rapidly approaching the fundamental physical limits of transistor scaling
Sina Barazandeh retweeted
Very happy to announce that our study on designing RNA to bind and target proteins is now published @PLOSCompBiol.
RNAtranslator is a generative language model that formulates protein-conditional RNA design as a sequence-to-sequence natural language translation problem for the first time.
Aside from enabling the design of RNAs with natural-like properties and high binding affinity, this approach also allows us to target proteins for which no RNA interaction data are available—something that was not previously possible. As an example, we designed an RNA (red) that binds with PRP4K (blue) with high affinity, and the resulting complex is shown below.
This is the result of the hard work of our grad students at CICEKLAB: Sobhan Shukueian Tabrizi @sobhanshukueian, Sina Barazandeh @sinabr01 & Helyasadat Hashemi Aghdam @HelyaHashemi.
Paper is available here - open access: journals.plos.org/ploscompbi…
The code is available at GitHub: github.com/ciceklab/RNAtrans…
Sina Barazandeh retweeted
📢📢Our study on designing novel 5’ UTRs to that yield higher expression levels and mean ribosome load for the target genes is now published in @BioinfoAdv. This was a study with graduates from my group @sinabr01, @furkozden; and a collaboration with @uosseker and his student Ahmet Hincer.
🧬 Just out in Bioinformatics Advances: “UTRGAN: Learning to generate 5’ UTR sequences for optimized translation efficiency and gene expression”
Explore the full study: doi.org/10.1093/bioadv/vbaf1…
Authors include: @sinabr01, @uosseker, @crashius
Sina Barazandeh retweeted
🧬 Just out in Bioinformatics Advances: “UTRGAN: Learning to generate 5’ UTR sequences for optimized translation efficiency and gene expression”
Explore the full study: doi.org/10.1093/bioadv/vbaf1…
Authors include: @sinabr01, @uosseker, @crashius
Sina Barazandeh retweeted
CICEKLAB’s latest graduate is @sinabr01. He lead multiple projects related to genAI, language models and biological sequences. He is now going to seek a Ph.D. Degree at @CarnegieMellon
PS. @CMUCompBio enrolled 20 Ph.D. students this year and 2 are from our lab. What is the pval?
Sina Barazandeh retweeted
This is RNAGEN, a model to generate RNA sequences that are optimized for tasks such as targeting a protein. In collab. with @SekerLab, we show that the top sequences generated to target SOX2 selectively bind via in-vitro experiments. @furkozden, @sinabr01, Dogus Akboga, @uosseker
RNAGEN: A generative adversarial network-based model to generate synthetic RNA sequences to target proteins biorxiv.org/cgi/content/shor… #biorxiv_bioinfo
Sina Barazandeh retweeted
.@gunkaynar is presenting his poster #17 @RECOMBconf. The paper is here academic.oup.com/bioinformat… w/@cakmakcid @mnmsPlatform
Sina Barazandeh retweeted
.@sinabr01 is presenting our joint work with @uosseker/@sekerlab as a poster #67 @RECOMBconf! with The preprint is here: biorxiv.org/content/10.1101/…
