Your English writing platform
Discover LudwigExact(2)
We compared both methods in a leave-one-out experiment against FLORA's published dataset and 3 EC digit prediction results (Figure 2).
Network diffusion, however, enables more distant annotations to inform the annotation of this node, leading to a correct fourth EC digit prediction.
Similar(57)
Without the negative labels, accuracy falls: at 50% coverage it drops by 16% and 10.7% for 3 and 4 EC digit predictions, respectively.
According to David Byrne, who was the European Commissioner for Health and Consumer Protection of the European Parliament, "When the current labeling regime... was introduced in 1997, it did not result in increased costs, despite the horrifying (double-digit) prediction of some interests".
The two-digit prediction by PHLAT is also the highest (99.6%) among the tested programs.
In addition, PHLAT continues to lead the two-digit prediction with an accuracy of 98.9%, followed by HLAforest and seq2HLA then HLAminer at 97.7%, 97.7% and 93.1%, respectively.
Currently PHLAT uses a CDS-based reference for HLA inference steps and thereby typically delivering a four- to six-digit prediction that corresponds to the non-synonymous and synonymous coding variants, respectively.
For example, with 5 million × 100-nucleotide simulated RNA-Seq read pairs, four-digit predictions show a 8.9% decrease in sensitivity, 8.2% decrease in specificity, and a 31.9% increase in ambiguity, compared to two-digit predictions.
Four-digit predictions by previous algorithms using the HapMap RNAseq data are not very accurate (Table 1 and Additional file 1: Table S1).
Both the sensitivity and specificity of four-digit allele predictions are reduced relative to their two-digit counterparts, but changes to the ambiguity of predictions are more pronounced.
The seq2HLA achieved 100% specificity and 93.5% sensitivity for two-digit class I prediction on the control samples (Montgomery test samples) and took 10 minutes per sample to run.
Write better and faster with AI suggestions while staying true to your unique style.
Since I tried Ludwig back in 2017, I have been constantly using it in both editing and translation. Ever since, I suggest it to my translators at ProSciEditing.

Justyna Jupowicz-Kozak
CEO of Professional Science Editing for Scientists @ prosciediting.com