Explore the vast range of titles available.

In recent years, the development of high-throughput screening (HTS) technologies and their establishment in an industrialized environment have given scientists the possibility to test millions of molecules and profile them against a multitude of biological targets in a short period of time, generating data in a much faster pace and with a higher quality than before. Besides the structure activity data from traditional bioassays, more complex assays such as transcriptomics profiling or imaging have also been established as routine profiling experiments thanks to the advancement of Next Generation Sequencing or automated microscopy technologies. In industrial pharmaceutical research, these technologies are typically established in conjunction with automated platforms in order to enable efficient handling of screening collections of thousands to millions of compounds. To exploit the ever-growing amount of data that are generated by these approaches, computational techniques are constantly evolving. In this regard, artificial intelligence technologies such as deep learning and machine learning methods play a key role in cheminformatics and bio-image analytics fields to address activity prediction, scaffold hopping, molecule design, reaction/retrosynthesis predictions, or high content screening analysis. Herein we summarize the current state of analyzing large-scale compound data in industrial pharmaceutical research and describe the impact it has had on the drug discovery process over the last two decades, with a specific focus on deep-learning technologies.

Computer-Aided Drug Design (CADD) is an integral part of the drug discovery endeavor at Boehringer Ingelheim (BI). CADD contributes to the evaluation of new therapeutic concepts, identifies small molecule starting points for drug discovery, and develops strategies for optimizing hit and lead compounds. The CADD scientists at BI benefit from the global use and development of both software platforms and computational services. A number of computational techniques developed in-house have significantly changed the way early drug discovery is carried out at BI. In particular, virtual screening in vast chemical spaces, which can be accessed by combinatorial chemistry, has added a new option for the identification of hits in many projects. Recently, a new framework has been implemented allowing fast, interactive predictions of relevant on and off target endpoints and other optimization parameters. In addition to the introduction of this new framework at BI, CADD has been focusing on the enablement of medicinal chemists to independently perform an increasing amount of molecular modeling and design work. This is made possible through the deployment of MOE as a global modeling platform, allowing computational and medicinal chemists to freely share ideas and modeling results. Furthermore, a central communication layer called the computational chemistry framework provides broad access to predictive models and other computational services.

Neuroglobin (Ngb) is a recently discovered protein in vertebrate brain tissue that belongs to the globin family of proteins. It has been implicated in the neuronal response to hypoxia or ischemia, although its physiological role has been hitherto unknown. Ngb is hexacoordinate in the ferrous deoxy form under physiological conditions. To bind exogenous ligands like O2and CO, the His E7 endogenous ligand is displaced from the sixth coordination. By using infrared spectroscopy and nanosecond time-resolved visible spectroscopy, we have investigated the ligand-binding reaction over a wide temperature range (3-353 K). Multiple, intrinsically heterogeneous distal heme pocket conformations exist in NgbCO. Photolysis at cryogenic temperatures creates a five-coordinate deoxy species with very low geminate-rebinding barriers. The photodissociated CO is observed to migrate within the distal heme pocket even at 20 K. Flash photolysis near physiological temperature (275-353 K) exhibits four sequential kinetic features: (i) geminate rebinding (t < 1 µs); (ii) extremely fast bimolecular exogenous ligand binding (10 µs < t < 1 ms) with a nontrivial temperature dependence; (iii) endogenous ligand binding (100 µs < t < 10 ms), which can be studied by using flash photolysis on deoxy Ngb; and (iv) displacement of the endogenous by the exogenous ligand (10 ms < t < 10 ks). All four processes are markedly nonexponential, suggesting that Ngb fluctuates among different conformations on surprisingly long time scales.

We have studied the temperature dependence of the IR stretch bands of carbon monoxide (CO) in the Xe 4 internal cavity of myoglobin mutant L29W-S108L at cryogenic temperatures. Pronounced changes of band areas and positions were analyzed quantitatively by using a simple dynamic model in which CO rotation in the cavity is constrained by a static potential. The librational dynamics of the CO causes a decrease of the total spectral area. A strong local electric field splits the CO stretch absorption into a doublet, indicating that CO can assume opposite orientations in the cavity. With increasing temperature, the two peaks approach each other, because the average angle of the CO with respect to the electric field increases. A combined classical and quantum-mechanical analysis precisely reproduces the observed temperature dependencies of both spectral area and peak shifts. It yields the height of the energy barrier between the two wells associated with opposite CO orientations, V0≈ 2 kJ/mol, and the frequency of oscillation within a well, $\\omega\\approx 25\\>cm^{-1}$. The electric field in the protein cavity was estimated as 10 MV/cm.

To determine the magnitude and direction of the internal electric field in the Xe4 cavity of myoglobin mutant L29W-S108L, we have studied the vibrational Stark effect of carbon monoxide (CO) using infrared spectroscopy at cryogenic temperatures. CO was photodissociated from the heme iron and deposited selectively in Xe4. Its infrared spectrum exhibits Stark splitting into two bands associated with CO in opposite orientations. Two different photoproduct states can be distinguished, C′ and C″, with markedly different properties. For C′, characteristic temperature-dependent changes of the area, shift, and width were analyzed, based on a dynamic model in which the CO performs fast librations within a double-well model potential. For the barrier between the wells, a height of ∼1.8 kJ/mol was obtained, in which the CO performs oscillations at an angular frequency of ∼25cm−1. The magnitude of the electric field in the C′ conformation was determined as 11.1 MV/cm; it is tilted by an angle of 29° to the symmetry axis of the potential. Above 140K, a protein relaxation leads to a significantly altered photoproduct, C″, with a smaller Stark splitting and a more confining potential (barrier >4 kJ/mol) governing the CO librations.

The cytochrome P450 (CYP) enzyme superfamily plays a major role in the metabolism of commercially available drugs. Inhibition of these enzymes by a drug may result in a plasma level increase of another drug, thus leading to unwanted drug-drug interactions when two or more drugs are coadministered. Therefore, fast and reliable in silico methods predicting CYP inhibition from calculated molecular properties are an important tool which can be applied to assess both already synthesized as well as virtual compounds. We have studied the performance of support vector machines (SVMs) to classify compounds according to their potency to inhibit CYP3A4. The data set for model generation consists of more than 1300 structural diverse drug-like research molecules which were divided into training and test sets. The predictive power of SVMs crucially depends on a careful selection of parameters specifying the kernel function and the penalty for misclassifications. In this study we have investigated a procedure to identify a valid set of SVM parameters which is based on a sampling of the parameter space on a regular grid. From this set of parameters, either single SVMs or SVM committees were trained to distinguish between strong and weak inhibitors or to achieve a more realistic three-class assignment, with one class representing medium inhibitors. This workflow was studied for several kernel functions and descriptor sets. All SVM models performed significantly better than PLS-DA models which were generated from the corresponding descriptor sets. As a very promising result, simple two-dimensional (2D) descriptors yield a three-class model which correctly classifies more than 70% of the test set. Our work illustrates that SVMs used in combination with simple 2D descriptors provide a very effective and reliable tool which allows a fast assessment of CYP3A4 inhibition potency in an early in silico filtering process.

Data driven decision making is a key element of today’s pharmaceutical research, including early drug discovery. It comprises questions like which target to pursue, which chemical series to pursue, which compound to make next, or which compound to select for advanced profiling and promotion to pre-clinical development. In the following paper we will exemplify how data integrity, i.e. the context data is generated in and auxiliary information that is provided for individual result records, can influence decision making in early lead discovery programs. In addition we will describe some approaches which we pursue at Boehringer Ingelheim to reduce the risk for getting misguided.

Intramolecular electron transfer within proteins plays an essential role in biological energy transduction. Electron donor and acceptor cofactors are bound in the protein matrix at specific locations, and protein-cofactor interactions as well as protein conformational changes can markedly influence the electron transfer rates. To assess these effects, we have investigated charge recombination from the primary quinone acceptor to the special pair bacterio-chlorophyll dimer in wild-type reaction centers of Rhodobacter sphaeroides and four mutants with widely modified free energy gaps. After light-induced charge separation, the recombination kinetics were measured in the light- and dark-adapted forms of the protein from 10 to 300 K. The data were analyzed by using the spin-boson model, which allowed us to self-consistently determine the electronic coupling energy, the distribution of energy gaps, the spectral density of phonons, and the reorganization energy. The analysis revealed slow changes of the energy gap after charge separation. Interesting correlations of the control parameters governing electron transfer were found and related to structural and dynamic properties of the protein.

Many proteins can be immobilized in silica hydrogel matrices without compromising their function, making this a suitable technique for biosensor applications. Immobilization will in general affect protein structure and dynamics. To study these effects, we have measured the P+QA− charge recombination kinetics after laser excitation of QB-depleted wild-type photosynthetic reaction centers from Rhodobacter sphaeroides in a tetramethoxysilane (TMOS) sol-gel matrix and, for comparison, also in cryosolvent. The nonexponential electron transfer kinetics observed between 10 and 300K were analyzed quantitatively using the spin boson model for the intrinsic temperature dependence of the electron transfer and an adiabatic change of the energy gap and electronic coupling caused by protein motions in response to the altered charge distributions. The analysis reveals similarities and differences in the TMOS-matrix and bulk-solvent samples. In both preparations, electron transfer is coupled to the same spectrum of low frequency phonons. As in bulk solvent, charge-solvating protein motions are present in the TMOS matrix. Large-scale conformational changes are arrested in the hydrogel, as evident from the nonexponential kinetics even at room temperature. The altered dynamics is likely responsible for the observed changes in the electronic coupling matrix element.