Gene annotation

Abstract

This disclosure relates to a method for identifying a gene in an organism. The method comprises receiving an assembled transcript of the organism; determining multiple gene candidates within the transcript; calculating multiple features for each of the multiple gene candidates, wherein the multiple features are indicative of genomic properties of the multiple gene candidates; evaluating a prediction model on the multiple features to calculate a score for each of the multiple gene candidates, the score being indicative of a biological function of that candidate gene; and selecting one of the gene candidates based on the score. 20 25 20 17 97 12 M ar 2 02 5 1 2 M a r 2 0 2 5 A B S T R A C T 2 0 2 5 2 0 1 7 9 7 Models Genomic properties Biological functions combine Gene score Models Genomic properties Biological functions Functions Biological functionsTranscript regions Loss minimise 2 / 9 Figure 3 301 302 303 300 Figure 4 402 400 401 403 402 404 405 406 Figure 5 500 501 502 503 504 505 2 / 9 300 302 301 303 400 Figure 3 402 405 403 401 - Transcript regions Functions Biological functions 406 Loss 402 minimise 404 Genomic Models Biological functions properties 500 Figure 4 502 504 503 501 505 Genomic Models Biological functions combine -Gene score- properties Figure 5 20 25 20 17 97 12 M ar 2 02 5 2 / 9 1 2 M a r 2 0 2 5 3 0 0 2 0 2 5 2 0 1 7 9 7 4 0 0 4 0 3 4 0 1 F u n c t i o n s 4 0 6 L o s s 4 0 2 m i n i m i s e 4 0 4 G e n o m i c M o d e l s 5 0 0 5 0 2 5 0 4 5 0 3 5 0 1 5 0 5 G e n o m i c M o d e l s c o m b i n e G e n e s c o r e

Images