NexLAB: An Integrated Electronic Laboratory Notebook with Embedded Machine Learning and AI Tutoring for Workforce-Aligned Biotechnology Education

Effective biotechnology training requires learners to connect conducting experiments with quantitative analytics, and to document decision-making in ways that support reproducibility and collaboration. In many learning contexts, however, instructional toolchains often separate course materials, laboratory documentation, and data analysis across different systems, making it difficult for both learners and educators to keep analytic decisions and interpretations traceable. This paper presents NexLAB, a web-based platform that integrates instructor-authored course materials, a Design–Build–Test (DBT) structured electronic laboratory notebook (ELN), a course-grounded AI tutor, and embedded machine-learning analyses within a single workflow. We developed cancer-research-focused courses within NexLAB and demonstrated the workflow using the Breast Cancer Wisconsin (Diagnostic) dataset. We report the results as reproducible instructional examples, running the models with fixed split/seed settings to show how feature representation affects classification error patterns and how predictor choice influences regression performance and cross-validation stability. This manuscript’s supporting evidence is reported at the artifact-level, rather than at the level of learner outcome gains, and it synthesizes design requirements for teaching effective quantitative interpretation, experimental revision, and reproducibility.