Llamol: a dynamic multi-conditional generative transformer for de novo molecular design.

Generative models have demonstrated substantial promise in Natural Language Processing (NLP) and have found application in designing molecules, as seen in General Pretrained Transformer (GPT) models. In our efforts to develop such a tool for exploring the organic chemical space in search of potentially electro-active compounds, we present Llamol, a single novel generative transformer model based on the Llama 2 architecture, which was trained on a 12.5M superset of organic compounds drawn from diverse public sources. To allow for a maximum flexibility in usage and robustness in view of potentially incomplete data, we introduce Stochastic Context Learning (SCL) as a new training procedure. We demonstrate that the resulting model adeptly handles single- and multi-conditional organic molecule generation with up to four conditions, yet more are possible. The model generates valid molecular structures in SMILES notation while flexibly incorporating three numerical and/or one token sequence into the generative process, just as requested. The generated compounds are very satisfactory in all scenarios tested. In detail, we showcase the model's capability to utilize token sequences for conditioning, either individually or in combination with numerical properties, making Llamol a potent tool for de novo molecule design, easily expandable with new properties. SCIENTIFIC CONTRIBUTION: We developed a novel generative transformer model, Llamol, based on the Llama 2 architecture that was trained on a diverse set of 12.5 M organic compounds. It introduces Stochastic Context Learning (SCL) as a new training procedure, allowing for flexible and robust generation of valid organic molecules with up to multiple conditions that can be combined in various ways, making it a potent tool for de novo molecular design.

Insights into the Folding of Disulfide-Rich µ-Conotoxins.

The study of protein conformations using molecular dynamics (MD) simulations has been in place for decades. A major contribution to the structural stability and native conformation of a protein is made by the primary sequence and disulfide bonds formed during the folding process. Here, we investigated µ-conotoxins GIIIA, KIIIA, PIIIA, SIIIA, and SmIIIA as model peptides possessing three disulfide bonds. Their NMR structures were used for MD simulations in a novel approach studying the conformations between the folded and the unfolded states by systematically breaking the distinct disulfide bonds and monitoring the conformational stability of the peptides. As an outcome, the use of a combination of the existing knowledge and results from the simulations to classify the studied peptides within the extreme models of disulfide folding pathways, namely the bovine pancreatic trypsin inhibitor pathway and the hirudin pathway, is demonstrated. Recommendations for the design and synthesis of cysteine-rich peptides with a reduced number of disulfide bonds conclude the study.

The octet rule in chemical space: generating virtual molecules.

We present a generator of virtual molecules that selects valid chemistry on the basis of the octet rule. Also, we introduce a mesomer group key that allows a fast detection of duplicates in the generated structures. Compared to existing approaches, our model is simpler and faster, generates new chemistry and avoids invalid chemistry. Its versatility is illustrated by the correct generation of molecules containing third-row elements and a surprisingly adept handling of complex boron chemistry. Without any empirical parameters, our model is designed to be valid also in unexplored regions of chemical space. One first unexpected finding is the high prevalence of dipolar structures among generated molecules.