| Configuration: PIDE‡ | Protocol: Genome-wide prophage detection (Genome-wide prophage detection) Dataset: LAMBDA genome-wide prophage test | 0.984 Specificity fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcePIDE‡: Genome-wide prophage detection Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Aggregation: Not reported LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PIDE‡, column Specificity; XML row7 column4 |
|---|
| Configuration: PIDE‡ | Protocol: Genome-wide prophage detection (Genome-wide prophage detection) Dataset: LAMBDA genome-wide prophage test | 0.715 MCC unitless · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcePIDE‡: Genome-wide prophage detection Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Aggregation: Not reported LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PIDE‡, column MCC; XML row7 column7 |
|---|
| Configuration: PIDE‡ | Protocol: Genome-wide prophage detection (Genome-wide prophage detection) Dataset: LAMBDA genome-wide prophage test | 0.707 F1 fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcePIDE‡: Genome-wide prophage detection Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Aggregation: Not reported LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PIDE‡, column F1; XML row7 column6 |
|---|
| Configuration: PIDE‡ | Protocol: Genome-wide prophage detection (Genome-wide prophage detection) Dataset: LAMBDA genome-wide prophage test | 0.647 Precision fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcePIDE‡: Genome-wide prophage detection Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Aggregation: Not reported LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PIDE‡, column Precision; XML row7 column2 |
|---|
| Configuration: PIDE‡ | Protocol: Genome-wide prophage detection (Genome-wide prophage detection) Dataset: LAMBDA genome-wide prophage test | 0.844 Recall fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcePIDE‡: Genome-wide prophage detection Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Aggregation: Not reported LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PIDE‡, column Recall; XML row7 column3 |
|---|
| Configuration: PIDE‡ | Protocol: Genome-wide prophage detection (Genome-wide prophage detection) Dataset: LAMBDA genome-wide prophage test | 0.016 FPR fraction · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcePIDE‡: Genome-wide prophage detection Scan complete genomes with overlapping windows and postprocess predictions into prophage regions. Genome-wide metrics are computed at region level and macro-averaged across genomes. Filtered gLM pipelines include normalization, smoothing, clustering and size filtering; these are not standalone encoder scores. 80 bacterial genomes,47 species,four phyla;386 annotated prophage locations. Aggregation: Not reported LAMBDA: A Prophage Detection Benchmark for Genomic Language Models · Table 5., row PIDE‡, column FPR; XML row7 column5 |
|---|