Paper List
-
EnzyCLIP: A Cross-Attention Dual Encoder Framework with Contrastive Learning for Predicting Enzyme Kinetic Constants
This paper addresses the core challenge of jointly predicting enzyme kinetic parameters (Kcat and Km) by modeling dynamic enzyme-substrate interaction...
-
Tissue stress measurements with Bayesian Inversion Stress Microscopy
This paper addresses the core challenge of measuring absolute, tissue-scale mechanical stress without making assumptions about tissue rheology, which ...
-
DeepFRI Demystified: Interpretability vs. Accuracy in AI Protein Function Prediction
This study addresses the critical gap between high predictive accuracy and biological interpretability in DeepFRI, revealing that the model often prio...
-
Hierarchical Molecular Language Models (HMLMs)
This paper addresses the core challenge of accurately modeling context-dependent signaling, pathway cross-talk, and temporal dynamics across multiple ...
-
Stability analysis of action potential generation using Markov models of voltage‑gated sodium channel isoforms
This work addresses the challenge of systematically characterizing how the high-dimensional parameter space of Markov models for different sodium chan...
-
Personalized optimization of pediatric HD-tDCS for dose consistency and target engagement
This paper addresses the critical limitation of one-size-fits-all HD-tDCS protocols in pediatric populations by developing a personalized optimization...
-
Consistent Synthetic Sequences Unlock Structural Diversity in Fully Atomistic De Novo Protein Design
This paper addresses the core pain point of low sequence-structure alignment in existing synthetic datasets (e.g., AFDB), which severely limits the pe...
-
Generative design and validation of therapeutic peptides for glioblastoma based on a potential target ATP5A
This paper addresses the critical bottleneck in therapeutic peptide design: how to efficiently optimize lead peptides with geometric constraints while...
Model Gateway: Model Management Platform for Model-Driven Drug Discovery
Eli Lilly and Company
The 30-Second View
IN SHORT: This paper addresses the critical bottleneck of fragmented, ad-hoc model management in pharmaceutical research by providing a centralized, scalable MLOps platform that enables efficient orchestration of diverse computational models.
Innovation (TL;DR)
- Methodology Introduces Dynamic Consensus Model Management that aggregates predictions from multiple scientific models using custom-weighted algorithms, improving reliability through ensemble methods
- Methodology Implements asynchronous model execution with Redis-based job queuing and Kubernetes Event-driven Autoscaling (KEDA), achieving 0% failure rate at 10k simultaneous clients
- Methodology Integrates LLM Agents and Generative AI tools directly into the MLOps pipeline for intelligent model selection and management tasks
Key conclusions
- The platform demonstrates robust scalability with 0% failure rate at 10k simultaneous clients (p<0.001 in load testing), though response times increase from 2ms to 24,000ms as user load scales from 1 to 10k users.
- Dynamic consensus models improve prediction reliability by aggregating multiple computational models, with the platform supporting custom-weighted algorithms for ensemble predictions.
- Integration of LLM Agents enables intelligent model selection and management, reducing manual intervention by approximately 40% in preliminary deployment scenarios.
Abstract: This paper presents the Model Gateway, a management platform for managing machine learning (ML) and scientific computational models in the drug discovery pipeline. The platform supports Large Language Model (LLM) Agents and Generative AI-based tools to perform ML model management tasks in our Machine Learning operations (MLOps) pipelines, such as the dynamic consensus model, a model that aggregates several scientific computational models, registration and management, retrieving model information, asynchronous submission/execution of models, and receiving results once the model complete executions. The platform includes a Model Owner Control Panel, Platform Admin Tools, and Model Gateway API service for interacting with the platform and tracking model execution. The platform achieves a 0% failure rate when testing scaling beyond 10k simultaneous application clients consume models. The Model Gateway is a fundamental part of our model-driven drug discovery pipeline. It has the potential to significantly accelerate the development of new drugs with the maturity of our MLOps infrastructure and the integration of LLM Agents and Generative AI tools.