ResearchPublished All news from that day
Paper describes PrePssmCas, a classifier that fuses language-model and PSSM features for Cas proteins
Published as an accepted early version in BMC Bioinformatics, the method improves on the prior best tool by 3.91 percent in accuracy on an independent validation set.
Check our sources · 3 facts from 1 sourceResearchers described PrePssmCas, a machine-learning classifier for CRISPR-Cas protein systems that fuses two feature families: embeddings from pre-trained protein language models and position-specific scoring matrix (PSSM) features.
The final classifier uses a 143-dimensional feature vector, 87 features from language-model embeddings and 56 from the PSSM representation.
On an independent validation set the method reached 97.98 percent accuracy and a Matthews correlation coefficient of 0.962, improving on the previous best method, CRISPRCasStack, by 3.91 percent in accuracy and 9.60 percent in MCC. The paper appears as an accepted early version in BMC Bioinformatics.
Your reaction
We count reactions per story and day, never who reacted. The counts help us choose what goes in the monthly issue. If you are signed in, your own page shows yours too.
We count reactions per story and day, never who reacted. They help choose what goes in the monthly issue.
Check our sources
Every sentence above is checked against this source.
1 PrePssmCas: fusing pre-trained features and PSSM features for Cas protein classification
Open the source archived copy-
On an independent validation set, PrePssmCas reached 97.98 percent accuracy and a Matthews correlation coefficient of 0.962.
citeThe selected features achieved an accuracy of 97.98% and an MCC of 0.962 on an independent validation set
-
The authors report improvements of 3.91% in accuracy and 9.60% in MCC over CRISPRCasStack.
citerepresenting improvements of 3.91% in accuracy and 9.60% in MCC over the previous best method, CRISPRCasStack.
-
The final classifier uses a 143-dimensional feature vector: 87 features from pre-trained language-model embeddings and 56 from the RPM-PSSM representation.
citeBy employing random forest-based feature selection, a 143-dimensional feature vector was obtained, comprising 87 pre-trained features and 56 RPM-PSSM features.
Every sentence above is checked against this source. Each fact has its own address you can cite.
Source 1 · BMC Bioinformatics · 26 Sep 2026
PrePssmCas: fusing pre-trained features and PSSM features for Cas protein classification
On an independent validation set, PrePssmCas reached 97.98 percent accuracy and a Matthews correlation coefficient of 0.962.
The selected features achieved an accuracy of 97.98% and an MCC of 0.962 on an independent validation set
The authors report improvements of 3.91% in accuracy and 9.60% in MCC over CRISPRCasStack.
representing improvements of 3.91% in accuracy and 9.60% in MCC over the previous best method, CRISPRCasStack.
The final classifier uses a 143-dimensional feature vector: 87 features from pre-trained language-model embeddings and 56 from the RPM-PSSM representation.
By employing random forest-based feature selection, a 143-dimensional feature vector was obtained, comprising 87 pre-trained features and 56 RPM-PSSM features.
The morning email
On the mornings we publish: the three top stories and up to four short ones. Free.
We email you a link to confirm. An issue may include one sponsor, always labelled Sponsored · Advertisement. Our emails count opens and clicks, not who made them. Unsubscribe in one click. What we keep