DataScribe: An AI-Native, Policy-Aligned Web Platform for Multi-Objective Materials Design and Discovery

TL;DR

DataScribe addresses the fragmentation of data and workflows that slow materials discovery by delivering an AI-native, ontology-driven platform that unifies heterogeneous experimental and computational data into machine-actionable knowledge graphs. It embeds multi-objective, multi-fidelity Bayesian optimization directly into the application layer to support closed-loop propose–measure–learn cycles across lab and HPC environments. The system is demonstrated through encoder–decoder regression for high-entropy alloys, redox prediction from cyclic voltammetry, and MOBO workflows, with production pipelines and external data-tool integrations validating end-to-end data fusion and real-time optimization. By combining governance, provenance, and policy-aware optimization within a scalable, cloud-native backbone, DataScribe enables faster, more reproducible materials discovery and paves the way for self-driving laboratories and distributed acceleration platforms.

Abstract

The acceleration of materials discovery requires digital platforms that go beyond data repositories to embed learning, optimization, and decision-making directly into research workflows. We introduce DataScribe, an AI-native, cloud-based materials discovery platform that unifies heterogeneous experimental and computational data through ontology-backed ingestion and machine-actionable knowledge graphs. The platform integrates FAIR-compliant metadata capture, schema and unit harmonization, uncertainty-aware surrogate modeling, and native multi-objective multi-fidelity Bayesian optimization, enabling closed-loop propose-measure-learn workflows across experimental and computational pipelines. DataScribe functions as an application-layer intelligence stack, coupling data governance, optimization, and explainability rather than treating them as downstream add-ons. We validate the platform through case studies in electrochemical materials and high-entropy alloys, demonstrating end-to-end data fusion, real-time optimization, and reproducible exploration of multi-objective trade spaces. By embedding optimization engines, machine learning, and unified access to public and private scientific data directly within the data infrastructure, and by supporting open, free use for academic and non-profit researchers, DataScribe functions as a general-purpose application-layer backbone for laboratories of any scale, including self-driving laboratories and geographically distributed materials acceleration platforms, with built-in support for performance, sustainability, and supply-chain-aware objectives.

Figures (10)

• Figure 1: Ontology-Driven Interfaces as a Self-Evolving Layer for Materials Data Platforms. Four-tier architecture showing how materials ontology (top) automatically generates data capture interfaces (second layer) that enforce FAIR compliance and semantic consistency, populate user-facing forms for sample intake and property measurements (third layer), and produce standardized, ML-ready data tables (bottom). Orange arrows indicate automated propagation of domain knowledge through system layers, enabling seamless integration of Bayesian optimization (BO), Gaussian processes (GP), variational autoencoders (VAE), and generative models (CHGNet) without manual schema engineering.
• Figure 2: (a) Overview of the DataScribe user workflow spanning six stages: organization and access management, project and folder architecture, schema and traveler form design, data ingestion and population, data analysis and workflow execution, and iteration and collaboration. These stages are realized through five platform interfaces, with the outer iteration loop representing continuous refinement as research programs evolve. (b) Example interface panels illustrating key functionalities: user onboarding, hierarchical experiment and characterization folders (shown here for the BIRDSHOT vacuum arc-melting campaign), schema fields for solidification-relevant parameters, traveler forms for structured data and metadata capture, and a workflow canvas integrating public and private datasets with modular AI tools (e.g., thresholding, scaling, encoder–decoder models, and visualizers).
• Figure 3: (a) Result of Variational Encoder-Decoder Regressor trained on Refractory High Entropy Alloy Dataset showing Log-Log parity plot of predicted vs actual yield strength at 1000$^\circ$C, (b) Result obtained from training Vanilla Encoder-Decoder Regressor on Cylic Voltammetry Data showing the predicted CV forward and inverse loops (markers) overlaying the experimental values (solid line) The plot on top corner highlights the parity plot. (c) Result showing the obtained Bayesian Query after 35 iterations based on 5 initial random samples over Goldstein-Price function, a smooth multimodal function with three global minima, (d) Result obtained by invoking DataScribe API and integration of XGBoost and ScikitLearn showing Log–log parity plot of predicted vsȧctual Creep Merit for a held‑out test set from an XGBoost regressor trained on Nb, Cr, V, W, and Zr
• Figure 4: DataScribe Bayesian Multi-Objective Multi-Fidelity Optimization workflow. Step 1: Function and mode selection (benchmark functions or DataScribe API). Step 2: Hyperparameter configuration including iteration count, initial samples, batch size ($q$), exploration parameter ($\beta$), and fidelity mode. Step 3: Data table selection from cloud platform with automatic metadata retrieval and NaN handling. Step 4: Input feature ($X$) and objective ($Y$) column specification with fidelity configuration. Step 5: Sequential Bayesian optimization execution generating newly selected points with acquisition values, hypervolume metrics, and function space visualization showing observed points, Pareto front, and optimization trajectory. Additional diagnostic outputs include fidelity usage distribution, fidelity selection over iterations, hypervolume evolution, hypervolume improvement ($\Delta$HV), distance-to-Pareto-front convergence, and acquisition value progression across iterations. All results exportable as CSV files for downstream analysis.
• Figure 5: DataScribe Microservices Architecture. The system employs a distributed architecture with NGINX reverse proxy handling external requests, Kubernetes Ingress Controller managing internal routing, and seven core microservices: Backend API Service, Frontend Service, Data Table Service, Workflow GUI Service, Authentication Service, Data Analysis Service, and LLM Assistant Service. External integrations include OAuth providers (currently Google OAuth), Google Drive API, LLM inference APIs (Hugging Face), external materials databases (OQMD, Materials Project, AFLOW), and a production database for persistent storage. All services are containerized and orchestrated within a Kubernetes cluster for scalability and resilience.