Giri, S. J. | Search bioRxiv

bioRxiv2023

GO2Sum: Generating Human Readable Functional Summary of Proteins from GO Terms

Understanding the biological functions of proteins is of fundamental importance in modern biology. To represent function of proteins, Gene Ontology (GO), a controlled vocabulary, is frequently used, because it is easy to handle by computer programs avoiding open-ended text interpretation. Particularly, the majority of current protein function prediction methods rely on GO terms. However, the extensive list of GO terms that describe a protein function can pose challenges for biologists when it comes to interpretation. In response to this issue, we developed GO2Sum (Gene Ontology terms Summarizer), a model that takes a set of GO terms as input and generates a human-readable summary using the T5 large language model. GO2Sum was developed by fine-tuning T5 on GO term assignments and free-text function descriptions for UniProt entries, enabling it to recreate function descriptions by concatenating GO term descriptions. Our results demonstrated that GO2Sum significantly outperforms the original T5 model that was trained on the entire web corpus in generating Function, Subunit Structure, and Pathway paragraphs for UniProt entries.

bioinformatics↗

bioRxiv2022

Micro-colony observation: A rapid and simple approach to count bacterial colony forming units

For enumerating viable bacteria, traditional dilution plating to count colony forming units (CFU) has always been the preferred method in microbiology owing to its simplicity, albeit laborious and time-consuming. Similar CFU counts can be obtained by quantifying growing micro-colonies in conjunction with the perks of a microscope. Here, we employed a simple method of five microliter spotting of differently diluted bacterial culture multiple times on a single Petri dish followed by finding out CFU by counting micro-colonies using a phase-contrast microscope. In this method, the CFU of an Escherichia coli culture can be estimated within a four-hour period. Further, within a ten-hour period, CFU in a culture of Ralstonia solanacearum, a bacterium with a generation time of around 2 h, can be estimated. The CFU number determined by micro-colonies observed is comparable with that obtained by the dilution plating method. Micro-colonies number observed in the early hours of growth (2 h in case of E. coli and 8 h in case of R. solanacearum) were found to remain consistent at later hours, though there was a noticeable increase in the size of the colonies. It suggested that micro-colonies observed in the early hours indeed represent the bacterial number in the culture. Practical applications to this counting method were employed in studying the rifampicin-resistant mutation rate as well as performing the fluctuation test in E. coli. The method described here results in a 90% reduction of labour, time and resources. Thus, the method is likely to be adopted by many microbiologists in their routine laboratory research.

microbiology↗