JUCHMME: a Java Utility for Class Hidden Markov Models and Extensions for biological sequence analysis

CW-PRED: Prediction of C-terminal surface anchoring sorting signals in bacteria and Archaea

Sorting signals are crucial for the anchoring of proteins to the cell surface in archaea and bacteria. These proteins often feature distinct motifs at their C-terminus, cleaved by sortase or sortase-like enzymes. Gram-positive bacteria exhibit the LPXTGX consensus motif, cleaved by sortases, while Gram-negative bacteria employ exosortases recognizing motifs like PEP. Archaea utilize exosortase homologs known as archaeosortases for signal anchoring. Traditionally identification of such C-terminal sorting signals was performed with profile Hidden Markov Models (pHMMs). The Cell- Wall PREDiction (CW-PRED) method introduced for the first time a custom-made class HMM for proteins in Gram-positive bacteria that contain a cell wall sorting signal which begins with an LPXTG motif, followed by a hydrophobic domain and a tail of positively charged residues. Here we present a new and updated version of CW-PRED for predicting C-terminal sorting signals in Archaea, Gram-positive, and Gram-negative bacteria. We used a large training set and several model enhancements that improve motif identification in order to achieve better discrimination between C-terminal signals and other proteins. Cross-validation demonstrates CW-PRED's superiority in sensitivity and specificity compared to other methods. Application of the method in reference proteomes reveals a large number of potential surface proteins not previously identified. The method is available for academic use at http://195.251.108.230/apps.compgen.org/CW-PRED/ and as standalone software.

Revolutionizing Medicinal Chemistry: The Application of Artificial Intelligence (AI) in Early Drug Discovery

Artificial intelligence (AI) has permeated various sectors, including the pharmaceutical industry and research, where it has been utilized to efficiently identify new chemical entities with desirable properties. The application of AI algorithms to drug discovery presents both remarkable opportunities and challenges. This review article focuses on the transformative role of AI in medicinal chemistry. We delve into the applications of machine learning and deep learning techniques in drug screening and design, discussing their potential to expedite the early drug discovery process. In particular, we provide a comprehensive overview of the use of AI algorithms in predicting protein structures, drug-target interactions, and molecular properties such as drug toxicity. While AI has accelerated the drug discovery process, data quality issues and technological constraints remain challenges. Nonetheless, new relationships and methods have been unveiled, demonstrating AI's expanding potential in predicting and understanding drug interactions and properties. For its full potential to be realized, interdisciplinary collaboration is essential. This review underscores AI's growing influence on the future trajectory of medicinal chemistry and stresses the importance of ongoing synergies between computational and domain experts.

Hidden neural networks for transmembrane protein topology prediction

Hidden Markov Models (HMMs) are amongst the most successful methods for predicting protein features in biological sequence analysis. However, there are biological problems where the Markovian assumption is not sufficient since the sequence context can provide useful information for prediction purposes. Several extensions of HMMs have appeared in the literature in order to overcome their limitations. We apply here a hybrid method that combines HMMs and Neural Networks (NNs), termed Hidden Neural Networks (HNNs), for biological sequence analysis in a straightforward manner. In this framework, the traditional HMM probability parameters are replaced by NN outputs. As a case study, we focus on the topology prediction of for alpha-helical and beta-barrel membrane proteins. The HNNs show performance gains compared to standard HMMs and the respective predictors outperform the top-scoring methods in the field. The implementation of HNNs can be found in the package JUCHMME, downloadable from http://www.compgen.org/tools/juchmme, https://github.com/pbagos/juchmme. The updated PRED-TMBB2 and HMM-TM prediction servers can be accessed at www.compgen.org.

Significant non-existence of sequences in genomes and proteomes

Minimal absent words (MAWs) are minimal-length oligomers absent from a genome or proteome. Although some artificially synthesized MAWs have deleterious effects, there is still a lack of a strategy for the classification of non-occurring sequences as potentially malicious or benign. In this work, by using Markovian models with multiple-testing correction, we reveal significant absent oligomers, which are statistically expected to exist. This suggests that their absence is due to negative selection. We survey genomes and proteomes covering the diversity of life and find thousands of significant absent sequences. Common significant MAWs are often mono- or dinucleotide tracts, or palindromic. Significant viral MAWs are often restriction sites and may indicate unknown restriction motifs. Surprisingly, significant mammal genome MAWs are often present, but rare, in other mammals, suggesting that they are suppressed but not completely forbidden. Significant human MAWs are frequently present in prokaryotes, suggesting immune function, but rarely present in human viruses, indicating viral mimicry of the host. More than one-fourth of human proteins are one substitution away from containing a significant MAW, with the majority of replacements being predicted harmful. We provide a web-based, interactive database of significant MAWs across genomes and proteomes.