TemStaPro: protein thermostability prediction using sequence representations from protein language models.

MOTIVATION: Reliable prediction of protein thermostability from its sequence is valuable for both academic and industrial research. This prediction problem can be tackled using machine learning and by taking advantage of the recent blossoming of deep learning methods for sequence analysis. These methods can facilitate training on more data and, possibly, enable the development of more versatile thermostability predictors for multiple ranges of temperatures. RESULTS: We applied the principle of transfer learning to predict protein thermostability using embeddings generated by protein language models (pLMs) from an input protein sequence. We used large pLMs that were pre-trained on hundreds of millions of known sequences. The embeddings from such models allowed us to efficiently train and validate a high-performing prediction method using over one million sequences that we collected from organisms with annotated growth temperatures. Our method, TemStaPro (Temperatures of Stability for Proteins), was used to predict thermostability of CRISPR-Cas Class II effector proteins (C2EPs). Predictions indicated sharp differences among groups of C2EPs in terms of thermostability and were largely in tune with previously published and our newly obtained experimental data. AVAILABILITY AND IMPLEMENTATION: TemStaPro software and the related data are freely available from https://github.com/ievapudz/TemStaPro and https://doi.org/10.5281/zenodo.7743637.

A new family of CRISPR-type V nucleases with C-rich PAM recognition.

Most CRISPR-type V nucleases are stimulated to cleave double-stranded (ds) DNA targets by a T-rich PAM, which restricts their targeting range. Here, we identify and characterize a new family of type V RNA-guided nuclease, Cas12l, that exclusively recognizes a C-rich (5'-CCY-3') PAM. The organization of genes within its CRISPR locus is similar to type II-B CRISPR-Cas9 systems, but both sequence analysis and functional studies establish it as a new family of type V effector. Biochemical experiments show that Cas12l nucleases function optimally between 37 and 52°C, depending on the ortholog, and preferentially cut supercoiled DNA. Like other type V nucleases, it exhibits collateral nonspecific ssDNA and ssRNA cleavage activity that is triggered by ssDNA or dsDNA target recognition. Finally, we show that one family member, Asp2Cas12l, functions in a heterologous cellular environment, altogether, suggesting that this new group of CRISPR-associated nucleases may be harnessed as genome editing reagents.

Distribution and regulatory roles of oxidized 5-methylcytosines in DNA and RNA of the basidiomycete fungi Laccaria bicolor and Coprinopsis cinerea.

The formation of three oxidative DNA 5-methylcytosine (5mC) modifications (oxi-mCs)-5-hydroxymethylcytosine (5hmC), 5-formylcytosine (5fC) and 5-carboxylcytosine (5caC)-by the TET/JBP family of dioxygenases prompted intensive studies of their functional roles in mammalian cells. However, the functional interplay of these less abundant modified nucleotides in other eukaryotic lineages remains poorly understood. We carried out a systematic study of the content and distribution of oxi-mCs in the DNA and RNA of the basidiomycetes Laccaria bicolor and Coprinopsis cinerea, which are established models to study DNA methylation and developmental and symbiotic processes. Quantitative liquid chromatography-tandem mass spectrometry revealed persistent but uneven occurrences of 5hmC, 5fC and 5caC in the DNA and RNA of the two organisms, which could be upregulated by vitamin C. 5caC in RNA (5carC) was predominantly found in non-ribosomal RNA, which potentially includes non-coding, messenger and small RNA species. Genome-wide mapping of 5hmC and 5fC using the single CG analysis techniques hmTOP-seq and foTOP-seq pointed at involvement of oxi-mCs in the regulation of gene expression and silencing of transposable elements. The implicated diverse roles of 5mC and oxi-mCs in the two fungi highlight the epigenetic importance of the latter modifications, which are often neglected in standard whole-genome bisulfite analyses.