The paper Randomized SMILES Strings Improve the Quality of Molecular Generative Models has been published by the Journal of Cheminformatics. Recurrent Neural Networks (RNNs) trained with a set of molecules represented as unique (canonical) SMILES strings, have shown the capacity to create large chemical spaces of valid and meaningful structures.

The paper Datasets and their influence on the development of computer assisted synthesis planning tools in the pharmaceutical domain has just been accepted by Chemical Science. Computer Assisted Synthesis Planning (CASP) has gained considerable interest as of late. Herein we investigate a template-based retrosynthetic planning tool, trained on a variety

The paper Fluorescence Imaging of Bacterial Killing by Antimicrobial Peptide Dendrimer G3KL has just been accepted by ACS Infectious Diseases. We recently discovered that peptide dendrimers such as G3KL ((KL)8(KKL)4(KKL)2KKL, K = branching L-lysine) exert strong activity against Gram-negative bacteria including Pseudomonas aeruginosa, Acinetobacter baumannii and

The preprint Visualization of Very Large High-Dimensional Data Sets as Minimum Spanning Trees has been posted to ChemRxiv. Here, we introduce a new data visualization and exploration method, TMAP (tree-map), which exploits locality sensitive hashing, Kruskal’s minimum-spanning-tree algorithm, and a multilevel multipole-based graph layout algorithm to represent large and

The paper X‐Ray Crystal Structure of a Second Generation Peptide Dendrimer in Complex with Pseudomonas aeruginosa Lectin LecB has been published by Helvetica Chimica Acta. Dendrimers are regularly branched molecular trees which are notoriously difficult to crystallize. Herein we report the crystal structure of a C‐fucosylated second generation

The paper Stereoselective pH Responsive Peptide Dendrimers for siRNA Transfection has been published by Bioconjugate Chemistry. Transfecting nucleic acids into cells is an essential procedure in biological research usually performed using nonviral transfection reagents. Unfortunately, most transfection reagents have polymeric or undisclosed structures and require nonstandard synthetic procedures. Herein we

The paper Photoswitchable Inhibitor of the Calcium Channel TRPV6 has been published by ACS Medicinal Chemistry Letters. Herein we report the first photoswitchable inhibitor of Transient Receptor Potential Vanilloid 6 (TRPV6), a selective calcium channel involved in a number of diseases and in cancer progression. By surveying analogs of a

The paper Randomized SMILES Strings Improve the Quality of Molecular Generative Models has been published as a preprint on ChemRxiv. Recurrent Neural Networks (RNNs) trained with a set of molecules represented as unique (canonical) SMILES strings, have shown the capacity to create large chemical spaces of valid and meaningful structures.

The paper Medicinal Chemistry Aware Database GDBMedChem has been published by Molecular Informatics. The generated database GDB17 enumerates 166.4 billion possible molecules up to 17 atoms of C, N, O, S and halogens following simple chemical stability and synthetic feasibility rules, however medicinal chemistry criteria are not taken into

The paper Drug Analogs from Fragment-Based Long Short-Term Memory Generative Neural Networks has been published by the Journal of Chemical Information and Modeling. Several recent reports have shown that long short-term memory generative neural networks (LSTM) of the type used for grammar learning efficiently learn to write Simplified Molecular Input

The paper Mapping the Azolog Space Enables the Optical Control of New Biological Targets has been published by ACS Central Science. Photopharmacology relies on molecules that change their biological activity upon irradiation. Many of these are derived from known drugs by replacing their core with an isosteric azobenzene photoswitch (azologization)

The paper Exploring the GDB-13 chemical space using deep generative models has been published by the Journal of Cheminformatics. Recent applications of recurrent neural networks (RNN) enable training models that sample the chemical space. In this study we train RNN with molecular string representations (SMILES) with a subset of the

The paper PubChem and ChEMBL beyond Lipinski has been published by Molecular Informatics. Seven million of the currently 94 million entries in the PubChem database break at least one of the four Lipinski constraints for oral bioavailability, 183,185 of which are also found in the ChEMBL database. These non‐