Filter
Exclude
Time range
-
Near
An Interactive AI Agent for Adaptive Modeling of RNA Region-Ligand Interactions via LLM-Generated Machine Learning Workflows 1. A novel new framework called RLAgent has been introduced, offering a novel approach to modeling RNA-ligand interactions at the region level rather than focusing solely on binding sites. This method provides higher resolution and more flexible modeling, which is crucial for understanding complex RNA segments that may contain multiple or diffuse binding motifs. 2. RLAgent reframes the RNA-ligand prediction workflow as a dialogue-driven process, allowing users to interactively configure modeling preferences through a natural language interface without writing code. This lowers technical barriers and enhances reproducibility, making RNA-ligand prediction more accessible for both computational and experimental biologists. 3. The framework integrates large language model (LLM) capabilities with optional retrieval-augmented generation (RAG), automated debugging mechanisms, and optional RNA foundation model-based feature encoding. It forms a coherent, end-to-end pipeline that supports various model types, from classical machine learning models like Random Forest and XGBoost to deep learning architectures such as LSTM and Transformer. 4. RLAgent’s robustness was tested with different LLM backends, revealing that larger-scale LLMs like GPT-4o and DeepSeek-R1:70B are significantly more reliable for domain-specific code generation. This finding provides practical guidance for selecting LLM backends in future agent-based systems. 5. An ablation study highlighted the importance of query validation and debugging in RLAgent’s workflow. While single-pass code generation achieved high conformity, it came at the cost of significantly longer runtimes. The standard interactive workflow balanced accuracy and efficiency effectively. 6. In terms of performance, deep architectures like the Transformer and Mamba achieved the highest AUC and F1-scores. However, classical learners such as XGBoost and Random Forest also performed competitively, demonstrating RLAgent’s architecture-agnostic capabilities. 7. A case study demonstrated RLAgent’s interactive modeling capabilities using the Mamba model. The entire process, from feature encoding to model evaluation, was driven by natural language commands, showcasing the framework’s user-friendly experience and potential for real-world biomedical research. 8. Despite its contributions, RLAgent has limitations, including a relatively small training dataset and potential overfitting risks. Future versions may support multi-resolution prediction and could serve as a general-purpose interface for human-AI collaborative hypothesis generation in RNA-targeted therapeutics. 📜Paper: biorxiv.org/content/10.1101/… #RNA #LigandInteractions #AI #MachineLearning #ComputationalBiology #InteractiveModeling #LLM #DeepLearning
1
4
1,189
The SIP Summer Retreat was all about preparing for the new year! These co-created anchor charts are here to support our teachers! #ClearDirection #InteractiveModeling @MECME_School @jpachec1 @AldridgeMECME We are Ready Y’all!
13
468
Love all of the professional learning and laughing that is occurring at White Oaks! @Sansone39 @WhiteOaksDragon @dnwillia2 @PGIVBCPS #teachearlanguage #interactivemodeling #morningmeeting
6
1,287
In Morning Meeting, Ss shared when they may need to press pause & get their mind ready to be their best. We used #interactivemodeling to practice what it looks like, sounds like, and feels like. Thanks for having me @dicksjt @MrsAmieSwitzer #KindnessStartsWithME #CometWellness
2
11
Training our team in positive behavior expectations! It's part of what makes us SCORE (safe, caring, on-task, responsible, everyday!) @ghschools #howwedolife #teampeach #bettertogether #interactivemodeling
4
We LOVE interactive modeling! Check out our "ready to learn" carpet spots - listening ears, eyes on the speaker, brains ready to learn! 👍🏽👀 #ResponsiveClassroom #interactivemodeling #GrahamFam @GrahamRoadES
2
5
This morning I had the opportunity to visit Mr. Anekwe’s class to model a math lesson. This afternoon, he delivered! Way to go Mr. A @SmithES_AISD 👏🏼👏🏼👏🏼 #AldineConnected #AboveAndBeyond #MathCoach @eureka_math
6
Our Math IS @cmmonson1 is in the zone during 5th grade CBPL! #showingnotjusttelling #interactivemodeling #aboveandbeyond
8
Establishing a predictable closing routine helps calm students and prepares them for the next part of their school day. Using the steps of #interactivemodeling to teach lining up engages students in actively practicing what this procedure should look like and sound like. #physed
1
5
These #MasonElementary Comets are ready to beat their previous times on their shuttle runs. Thank you @AndyWilson14PE for using their excitement for the lesson to engage them. #interactivemodeling #KindnessStartsWithME
1
9
Some pictures courtesy of the best supervisor in the world @McMaryJean from the “Enemy Pie” (my new favorite book) lesson on my birthday! #MineolaProud #EnemyPie #InteractiveModeling #Literacy #SEL @mrs_ekloff @valerie_sunjka @Hampton_Street @AdelphiU
13
@misspetela class creating self-portraits. #academicchoice provided through a variety of mediums - oil pastel, crayons, markers and colored pencils. We are learning to care for our materials using #interactivemodeling #responsiveclassroom @WPSSicomac
2
4
Meditation or deep-breathing techniques, stretches, and tactile grounding techniques like standing with their back pressed against a wall are all useful skills that can be taught through #interactivemodeling. #seeingthegoodinstudents #SEL #teachthemtheskills #refocus
10
25
Teach impulse control. Try a freeze dance or Simon says. #SEL #teachimpulse #interactivemodeling
6
26
Thank You to @hjsmithreads for volunteering to do #InteractiveModeling for us in Collaborative Planning Pull-Outs yesterday. @ParkerESAldine @dunnbears @ConleyES_AISD @CalvertCougars @STARS_902 #CampComeback #Allin4Aldine
1
2