MOTIVATION: The development of novel compounds targeting proteins of interest is one of the most important tasks in the pharmaceutical industry. Deep generative models have been applied to targeted molecular design and have shown promising results. Recently, target-specific molecule generation has been viewed as a translation between the protein language and the chemical language. However, such a model is limited by the availability of interacting protein-ligand pairs. On the other hand, large amounts of unlabelled protein sequences and chemical compounds are available and have been used to train language models that learn useful representations. In this study, we propose exploiting pretrained biochemical language models to initialize (i.e. warm start) targeted molecule generation models. We investigate two warm start strategies: (i) a one-stage strategy where the initialized model is trained on targeted molecule generation and (ii) a two-stage strategy containing a pre-finetuning on molecular generation followed by target-specific training. We also compare two decoding strategies to generate compounds: beam search and sampling. RESULTS: The results show that the warm-started models perform better than a baseline model trained from scratch. The two proposed warm-start strategies achieve similar results to each other with respect to widely used metrics from benchmarks. However, docking evaluation of the generated compounds for a number of novel proteins suggests that the one-stage strategy generalizes better than the two-stage strategy. Additionally, we observe that beam search outperforms sampling in both docking evaluation and benchmark metrics for assessing compound quality. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/boun-tabi/biochemical-lms-for-drug-design and the materials (i.e., data, models, and outputs) are archived in Zenodo at https://doi.org/10.5281/zenodo.6832145. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Knowledge of pathogen-host protein interactions is required to better understand infection mechanisms. The pathogen-host interaction search tool (PHISTO) is a web-accessible platform that provides relevant information about pathogen-host interactions (PHIs). It enables access to the most up-to-date PHI data for all pathogen types for which experimentally verified protein interactions with human are available. The platform also offers integrated tools for visualization of PHI networks, graph-theoretical analysis of targeted human proteins, BLAST search and text mining for detecting missing experimental methods. PHISTO will facilitate PHI studies that provide potential therapeutic targets for infectious diseases. AVAILABILITY: http://www.phisto.org. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: New analysis methods are being developed to integrate data from transcriptome, proteome, interactome, metabolome, and other investigative approaches. At the same time, existing methods are being modified to serve the objectives of systems biology and permit the interpretation of the huge datasets currently being generated by high-throughput methods. RESULTS: Transcriptomic and metabolic data from chemostat fermentors were collected with the aim of investigating the relationship between these two data sets. The variation in transcriptome data in response to three physiological or genetic perturbations (medium composition, growth rate, and specific gene deletions) was investigated using linear modelling, and open reading-frames (ORFs) whose expression changed significantly in response to these perturbations were identified. Assuming that the metabolic profile is a function of the transcriptome profile, expression levels of the different ORFs were used to model the metabolic variables via Partial Least Squares (Projection to Latent Structures--PLS) using PLS toolbox in Matlab. CONCLUSION: The experimental design allowed the analyses to discriminate between the effects which the growth medium, dilution rate, and the deletion of specific genes had on the transcriptome and metabolite profiles. Metabolite data were modelled as a function of the transcriptome to determine their congruence. The genes that are involved in central carbon metabolism of yeast cells were found to be the ORFs with the most significant contribution to the model.