BacDoc: A database-driven assisted platform for media prediction and microbial profiling

Limitations in rapid organism identification and access to appropriate cultivation media remain significant bottlenecks in microbiological research, particularly in laboratories without advanced diagnostic infrastructure. Many existing tools address either organism identification or cultivation guidance independently, with limited integration between the two. This study presents BacDoc, a free, web-based platform that integrates bacterial identification with automated cultivation media recommendations using a transparent, rule-based algorithm. BacDoc was developed in two stages, comprising an initial terminal-based prototype with fuzzy string matching and automated media scaling, followed by a full web application implemented using the Flask framework with a responsive HTML5/CSS3/JavaScript interface. For known organisms, the platform returns optimized growth parameters, standardized media formulations scaled to user-defined volumes and associated biochemical and differential characteristics. For unknown isolates, a multifactorial distance-scoring algorithm based on six phenotypic parameters generates hybrid media formulations derived from the five most similar database entries. The curated database currently includes approximately 800 bacterial species with standardized physiological profiles and growth media. Validation demonstrated accurate organism identification, reliable media scaling across 100-2000 mL volumes, and stable system performance with robust error handling. BacDoc provides a practical computational framework for experimental planning, teaching laboratories, and preliminary cultivation support without the need for specialized hardware. Future development will focus on experimental validation of hybrid media, database expansion, and offline mobile implementation.