Biology subjects

Gendelev, L.

Publications and source records attributed to Gendelev, L..

4 recordsLinked to original sources

bioRxiv2024

A high-throughput phenotypic screen combined with an ultra-large-scale deep learning-based virtual screening reveals novel scaffolds of antibacterial compounds

The proliferation of multi-drug-resistant bacteria underscores an urgent need for novel antibiotics. Traditional discovery methods face challenges due to limited chemical diversity, high costs, and difficulties in identifying structurally novel compounds. Here, we explore the integration of small molecule high-throughput screening with a deep learning-based virtual screening approach to uncover new antibacterial compounds. Leveraging a diverse library of nearly 2 million small molecules, we conducted comprehensive phenotypic screening against a sensitized Escherichia coli strain that, at a low hit rate, yielded thousands of hits. We trained a deep learning model, GNEprop, to predict antibacterial activity, ensuring robustness through out-of-distribution generalization techniques. Virtual screening of over 1.4 billion compounds identified potential candidates, of which 82 exhibited antibacterial activity, illustrating a 90X improved hit rate over the high-throughput screening experiment GNEprop was trained on. Importantly, a significant portion of these newly identified compounds exhibited high dissimilarity to known antibiotics, indicating promising avenues for further exploration in antibiotic discovery.

bioinformatics↗

bioRxiv2024

Deep phenotypic profiling of neuroactive drugs in larval zebrafish

Behavioral larval zebrafish screens leverage a high-throughput small molecule discovery format to find neuroactive molecules relevant to mammalian physiology. We screened a library of 650 central nervous system active compounds in high replicate to train a deep metric learning model on zebrafish behavioral profiles. The machine learning initially exploited subtle artifacts in the phenotypic screen, necessitating a complete experimental re-run with rigorous well-wise randomization. These large matched phenotypic screening datasets (initial and well-randomized) provided a unique opportunity to quantify and understand shortcut learning in a full-scale, real-world drug discovery dataset. The final deep metric learning model substantially outperforms correlation distance-the canonical way of computing distances between profiles-and generalizes to an orthogonal dataset of novel druglike compounds. We validated predictions by prospective in vitro radio-ligand binding assays against human protein targets, achieving a hit rate of 58% despite crossing species and chemical scaffold boundaries. These newly discovered neuroactive compounds exhibited diverse chemical scaffolds, demonstrating that zebrafish phenotypic screens combined with metric learning achieve robust scaffold hopping capabilities.

bioinformatics↗

bioRxiv2020

Simultaneous classification of neuroactive compounds in zebrafish

Neuroactive compounds are crucial tools in drug discovery and neuroscience, but it remains difficult to discover neuroactive compounds with new mechanisms of action. To address this need, researchers have developed mid-throughput phenotype-first approaches using zebrafish. This study introduces an open, non-commercial, and extensible hardware/software platform that captures and analyzes drugmodulated phenotypic responses larval zebrafish. We provide full specifications, computer-aided design (CAD) documents, and source code. Accompanying this study, we are also publicly depositing phenotypic data on 3.9 million animals and 34,000 compounds. The data include a high-replicate benchmark set on 14 compounds, a wellcontrolled reference set of 648 known neuroactive compounds, 20 specialized reference sets, a library of 1,520 FDA-approved drugs, 3 screening libraries. This open data resource is curated, structured, tied to extensive metadata, and available under a Creative Commons CC-BY license.

systems biology↗

bioRxiv2017

A Simple Representation Of Three-Dimensional Molecular Structure

Statistical and machine learning approaches predict drug-to-target relationships from 2D small-molecule topology patterns. One might expect 3D information to improve these calculations. Here we apply the logic of the Extended Connectivity FingerPrint (ECFP) to develop a rapid, alignment-invariant 3D representation of molecular conformers, the Extended Three-Dimensional FingerPrint (E3FP). By integrating E3FP with the Similarity Ensemble Approach (SEA), we achieve higher precision-recall performance relative to SEA with ECFP on ChEMBL20, and equivalent receiver operating characteristic performance. We identify classes of molecules for which E3FP is a better predictor of similarity in bioactivity than is ECFP. Finally, we report novel drug-to-target binding predictions inaccessible by 2D fingerprints and confirm three of them experimentally with ligand efficiencies from 0.442 - 0.637 kcal/mol/heavy atom.

bioinformatics↗