AI & experimental-based discovery and preclinical IND-enabling studies of selective BMX inhibitors for development of cancer therapeutics.

The current work aims to design and provide a preliminary IND-enabling study of selective BMX inhibitors for cancer therapeutics development. BMX is an emerging target, more notably in oncological and immunological diseases. In this work, we have employed a predictive AI-based platform to design the selective inhibitors considering the novelty, IP prior protection, and drug-likeness properties. Furthermore, selected top candidates from the initial iteration of the design were synthesized and chemically characterized utilizing 1H NMR and LC-MS. Employing a panel of biochemical (enzymatic) and cancer cell lines, the selected molecules were tested against these assays. In addition, we used artificial intelligence to predict and evaluate several critical IND-focused physicochemical and pharmacokinetics values of the selected molecules. A secondary objective of the current work was also to validate the sole role of BMX in animal models known to be mediated by BMX. More than 50 molecules were designed in the present study employing five novel discovered scaffolds. Two molecules were nominated for further IND-focused studies. Compound II showed promising in-vitro activity against BMX in both enzymatic assays compared to other kinases and in cancer cell lines with known BMX overexpression. Interestingly, compound II showed very favorable physicochemical and pharmacokinetics properties as predicted by the used platforms. The animal study further confirmed the sole role of BMX in the disease model. The current work provides promising data on a selective BMX inhibitor as a potential lead for therapeutics development, and the asset is currently in the optimization stage. Notably, the current study shows a framework for a combined approach employing both AI and experimentation that can be used by academic labs in their research programs to more streamline programs into IND-focused to be bridged easily for further clinical development with industrial partners.

Insight into the molecular mechanism of the transposon-encoded type I-F CRISPR-Cas system.

CRISPR-Cas9 is a popular gene-editing tool that allows researchers to introduce double-strand breaks to edit parts of the genome. CRISPR-Cas9 system is used more than other gene-editing tools because it is simple and easy to customize. However, Cas9 may produce unintended double-strand breaks in DNA, leading to off-target effects. There have been many improvements in the CRISPR-Cas system to control the off-target effect and improve the efficiency. The presence of a nuclease-deficient CRISPR-Cas system in several bacterial Tn7-like transposons inspires researchers to repurpose to direct the insertion of Tn7-like transposons instead of cleaving the target DNA, which will eventually limit the risk of off-target effects. Two transposon-encoded CRISPR-Cas systems have been experimentally confirmed. The first system, found in Tn7 like-transposon (Tn6677), is associated with the variant type I-F CRISPR-Cas system. The second one, found in Tn7 like-transposon (Tn5053), is related to the variant type V-K CRISPR-Cas system. This review describes the molecular and structural mechanisms of DNA targeting by the transposon-encoded type I-F CRISPR-Cas system, from assembly around the CRISPR-RNA (crRNA) to the initiation of transposition.

Data Mining Meets Machine Learning: A Novel ANN-based Multi-body Interaction Docking Scoring Function (MBI-score) Based on Utilizing Frequent Geometric and Chemical Patterns of Interfacial Atoms in Native Protein-ligand Complexes.

Accurate prediction of binding poses is crucial to structure-based drug design. We employ two powerful artificial intelligence (AI) approaches, data-mining and machine-learning, to design artificial neural network (ANN) based pose-scoring function. It is a simple machine-learning-based statistical function that employs frequent geometric and chemical patterns of interacting atoms at protein-ligand interfaces. The patterns are derived by mining interfaces of "native" protein-ligand complexes. Each interface is represented by a graph where nodes are atoms and edges connect protein-ligand interfacial atoms located within certain cutoff distance of each other. Applying frequent subgraph mining to these interfaces provides "native" frequent patterns of interacting atoms. Subsequently, given a pose for a protein-ligand complex of interest, the pose-scoring function (the information-processing unit or neuron) calculates the degree of matching between the interaction patterns present at the pose's interface and the native frequent patterns. The pose-scoring function takes into account the frequency of occurrence of the matching native patterns, the size of the match, and the degree of geometrical similarity between pose-specific and matching native frequent patterns. This novel "multi-body interaction" pose-scoring function (MBI-Score) was validated using two databases, PDBbind and Astex-85, and it outperformed seven commonly used commercial scoring functions. MBI-Score is available at www.khashanlab.org/mbi-score.

Generating "fragment-based virtual library" using pocket similarity search of ligand-receptor complexes.

As the number of available ligand-receptor complexes is increasing, researchers are becoming more dedicated to mine these complexes to aid in the drug design and development process. We present free software which is developed as a tool for performing similarity search across ligand-receptor complexes for identifying binding pockets which are similar to that of a target receptor. The search is based on 3D-geometric and chemical similarity of the atoms forming the binding pocket. For each match identified, the ligand's fragment(s) corresponding to that binding pocket are extracted, thus forming a virtual library of fragments (FragVLib) that is useful for structure-based drug design. The program provides a very useful tool to explore available databases.

The Development of Novel Chemical Fragment-Based Descriptors Using Frequent Common Subgraph Mining Approach and Their Application in QSAR Modeling.

We present a novel approach to generating fragment-based molecular descriptors. The molecules are represented by labeled undirected chemical graph. Fast Frequent Subgraph Mining (FFSM) is used to find chemical-fragments (subgraphs) that occur in at least a subset of all molecules in a dataset. The collection of frequent subgraphs (FSG) forms a dataset-specific descriptors whose values for each molecule are defined by the number of times each frequent fragment occurs in this molecule. We have employed the FSG descriptors to develop variable selection k Nearest Neighbor (kNN) QSAR models of several datasets with binary target property including Maximum Recommended Therapeutic Dose (MRTD), Salmonella Mutagenicity (Ames Genotoxicity), and P-Glycoprotein (PGP) data. Each dataset was divided into training, test, and validation sets to establish the statistical figures of merit reflecting the model validated predictive power. The classification accuracies of models for both training and test sets for all datasets exceeded 75 %, and the accuracy for the external validation sets exceeded 72 %. The model accuracies were comparable or better than those reported earlier in the literature for the same datasets. Furthermore, the use of fragment-based descriptors affords mechanistic interpretation of validated QSAR models in terms of essential chemical fragments responsible for the compounds' target property.

FragVLib a free database mining software for generating "Fragment-based Virtual Library" using pocket similarity search of ligand-receptor complexes.

BACKGROUND: With the exponential increase in the number of available ligand-receptor complexes, researchers are becoming more dedicated to mine these complexes to facilitate the drug design and development process. Therefore, we present FragVLib, free software which is developed as a tool for performing similarity search across database(s) of ligand-receptor complexes for identifying binding pockets which are similar to that of a target receptor. RESULTS: The search is based on 3D-geometric and chemical similarity of the atoms forming the binding pocket. For each match identified, the ligand's fragment(s) corresponding to that binding pocket are extracted, thus, forming a virtual library of fragments (FragVLib) that is useful for structure-based drug design. CONCLUSIONS: An efficient algorithm is implemented in FragVLib to facilitate the pocket similarity search. The resulting fragments can be used for structure-based drug design tools such as Fragment-Based Lead Discovery (FBLD). They can also be used for finding bioisosteres and as an idea generator.

Scoring protein interaction decoys using exposed residues (SPIDER): a novel multibody interaction scoring function based on frequent geometric patterns of interfacial residues.

Accurate prediction of the structure of protein-protein complexes in computational docking experiments remains a formidable challenge. It has been recognized that identifying native or native-like poses among multiple decoys is the major bottleneck of the current scoring functions used in docking. We have developed a novel multibody pose-scoring function that has no theoretical limit on the number of residues contributing to the individual interaction terms. We use a coarse-grain representation of a protein-protein complex where each residue is represented by its side chain centroid. We apply a computational geometry approach called Almost-Delaunay tessellation that transforms protein-protein complexes into a residue contact network, or an undirectional graph where vertex-residues are nodes connected by edges. This treatment forms a family of interfacial graphs representing a dataset of protein-protein complexes. We then employ frequent subgraph mining approach to identify common interfacial residue patterns that appear in at least a subset of native protein-protein interfaces. The geometrical parameters and frequency of occurrence of each "native" pattern in the training set are used to develop the new SPIDER scoring function. SPIDER was validated using standard "ZDOCK" benchmark dataset that was not used in the development of SPIDER. We demonstrate that SPIDER scoring function ranks native and native-like poses above geometrical decoys and that it exceeds in performance a popular ZRANK scoring function. SPIDER was ranked among the top scoring functions in a recent round of CAPRI (Critical Assessment of PRedicted Interactions) blind test of protein-protein docking methods.