DNAcycP2

This is a probabilistic modelling pipeline for computing per- nucleotide posterior probabilities of modification from the data collected in structure probing experiments. The model supports multiple experimental replicates and empirically corrects coverage- and sequence-dependent biases. The model utilises the measure of a "drop-off rate" for each nucleotide, which is compared between replicates through a log-ratio (LDR). The LDRs between control replicates define a null distribution of variability in drop-off rate observed by chance and LDRs between treatment and control replicates gets compared to this distribution. Resulting empirical p-values (probability of being "drawn" from the null distribution) are used as observations in a Hidden Markov Model with a Beta-Uniform Mixture model used as an emission model. The resulting posterior probabilities indicate the probability of a nucleotide of having being modified in a structure probing experiment.

R-based computational framework for a comprehensive in silico analysis of circRNAs. This computational framework allows to combine and analyze circRNAs previously detected by multiple publicly available annotation-based circRNA detection tools. It covers different aspects of circRNAs analysis from differential expression analysis, evolutionary conservation, biogenesis to functional analysis.

Package that implements the COSNet classification algorithm. The algorithm predicts node labels in partially labeled graphs where few positives are available for the class being predicted.

The identification of novel compound-protein interaction (CPI) is important in drug discovery. Revealing unknown compound-protein interactions is useful to design a new drug for a target protein by screening candidate compounds. The accurate CPI prediction assists in effective drug discovery process. To identify potential CPI effectively, prediction methods based on machine learning and deep learning have been developed. Data for sequences are provided as discrete symbolic data. In the data, compounds are represented as SMILES (simplified molecular-input line-entry system) strings and proteins are sequences in which the characters are amino acids. The outcome is defined as a variable that indicates how strong two molecules interact with each other or whether there is an interaction between them. In this package, a deep-learning based model that takes only sequence information of both compounds and proteins as input and the outcome as output is used to predict CPI. The model is implemented by using compound and protein encoders with useful features. The CPI model also supports other modeling tasks, including protein-protein interaction (PPI), chemical-chemical interaction (CCI), or single compounds and proteins. Although the model is designed for proteins, DNA and RNA can be used if they are represented as sequences.

DNAhapeR is an R/BioConductor package for ultra-fast, high-throughput predictions of DNA shape features. The package allows to predict, visualize and encode DNA shape features for statistical learning.

The AlphaMissense publication <https://www.science.org/doi/epdf/10.1126/science.adg7492> outlines how a variant of AlphaFold / DeepMind was used to predict missense variant pathogenicity. Supporting data on Zenodo <https://zenodo.org/record/10813168> include, for instance, 71M variants across hg19 and hg38 genome builds. The 'AlphaMissenseR' package allows ready access to the data, downloading individual files to DuckDB databases for exploration and integration into *R* and *Bioconductor* workflows.