Search for Novel Lead Inhibitors of Yeast Cytochrome bc1, from Drugbank and COCONUT

In this work we introduce a novel filtering and molecular modeling pipeline based on a fingerprint and descriptor similarity procedure, coupled with molecular docking and molecular dynamics (MD), to select potential novel quoinone outside inhibitors (QoI) of cytochrome bc1 with the aim of determining the same or different chromophores to usual. The study was carried out using the yeast cytochrome bc1 complex with its docked ligand (stigmatellin), using all the fungicides from FRAC code C3 mode of action, 8617 Drugbank compounds and 401624 COCONUT compounds. The introduced drug repurposing pipeline consists of compound similarity with C3 fungicides and molecular docking (MD) simulations with final QM/MM binding energy determination, while aiming for potential novel chromophores and perserving at least an amide (R1HN(C=O)R2) or ester functional group of almost all up to date C3 fungicides. 3D descriptors used for a similarity test were based on the 280 most stable Padel descriptors. Hit compounds that passed fingerprint and 3D descriptor similarity condition and had either an amide or an ester group were submitted to docking where they further had to satisfy both Chemscore fitness and specific conformation constraints. This rigorous selection resulted in a very limited number of candidates that were forwarded to MD simulations and QM/MM binding affinity estimations by the ORCA DFT program. In this final step, stringent criteria based on (a) sufficiently high frequency of H-bonds; (b) high interaction energy between protein and ligand through the whole MD trajectory; and (c) high enough QM/MM binding energy scores were applied to further filter candidate inhibitors. This elaborate search pipeline led finaly to four Drugbank synthetic lead compounds (DrugBank) and seven natural (COCONUT database) lead compounds—tentative new inhibitors of cytochrome bc1. These eleven lead compounds were additionally validated through a comparison of MM/PBSA free binding energy for new leads against those obtatined for 19 QoIs.

ChAlPred: A Web Server for Prediction of Allergenicity of Chemical Compounds

Allergy is the abrupt reaction of the immune system that may occur after the exposure with allergens like protein/peptide or chemical allergens. In past number of methods of have been developed for classifying the protein/peptide based allergen. To the best of our knowledge, there is no method to classify the allergenicity of chemical compound. Here, we have proposed a method named ChAlPred, which can be used to fill the gap for predicting the chemical compound that might cause allergy. In this study, we have obtained the dataset of 403 allergen and 1074 non-allergen chemical compounds and used 2D, 3D and FP descriptors to train, test and validate our prediction models. The fingerprint analysis of the dataset indicates that PubChemFP129 and GraphFP1014 are more frequent in the allergenic chemical compounds, whereas KRFP890 is highly present in non-allergenic chemical compounds. Our XGB based model achieved the AUC of 0.89 on validation dataset using 2D descriptors. RF based model has outperformed other classifiers using 3D descriptors (AUC = 0.85), FP descriptors (AUC = 0.92), combined descriptors (AUC = 0.93), and hybrid model (AUC = 0.92) on validation dataset. In addition, we have also reported some FDA-approved drugs like Cefuroxime, Spironolactone, and Tioconazole which can cause the allergic symptoms. A user user-friendly web server named ChAlPred has been developed to predict the chemical allergens. It can be easily accessed at https://webs.iiitd.edu.in/raghava/chalpred/.

Performance Evaluation of 3D Descriptors Paired with Learned Keypoint Detectors

Matching surfaces is a challenging 3D Computer Vision problem typically addressed by local features. Although a plethora of 3D feature detectors and descriptors have been proposed in literature, it is quite difficult to identify the most effective detector-descriptor pair in a certain application. Yet, it has been shown in recent works that machine learning algorithms can be used to learn an effective 3D detector for any given 3D descriptor. In this paper, we present a performance evaluation of the detector-descriptor pairs obtained by learning a 3D detector for the most popular 3D descriptors. Purposely, we address experimental settings dealing with object recognition and surface registration. Our results show how pairing a learned detector to a learned descriptors like CGF leads to effective local features when pursuing object recognition (e.g., 0.45 recall at 0.8 precision on the UWA dataset), while there is not a clear performance gap between CGF and effective hand-crafted features like SHOT for surface registration (0.18 average precision for the former versus 0.16 for the latter).

QSAR Modeling Based on Conformation Ensembles Using a Multi-Instance Learning Approach

Modern QSAR approaches have wide practical applications in drug discovery for screening potentially bioactive molecules before their experimental testing. Most models predicting the bioactivity of compounds are based on molecular descriptors derived from 2D structure losing explicit information about the spatial structure of molecules which is important for protein-ligand recognition. The major problem in constructing models using 3D descriptors is the choice of a probable bioactive conformation that affects the predictive performance. Multi-instance (MI) learning approach considering multiple conformations upon the model training can be a reasonable solution to the above problem. Here, we compared MI-QSAR with the classical single-instance QSAR (SI-QSAR) approach, where each molecule was encoded by either 2D descriptors or 3D descriptors issued from the single lowest-energy conformation. The calculations were carried out on a sample of 175 datasets extracted from the ChEMBL23 database. It was demonstrated that (<i>i</i>) MI-QSAR outperforms SI-QSAR in numerous cases and (<i>ii</i>) MI algorithms can automatically identify plausible bioactive conformations. Instance-attention based network can be applied for most important conformer selection which was shown to correspond PDB conformer in 50-84% of molecules.

QSAR Modeling Based on Conformation Ensembles Using a Multi-Instance Learning Approach

Modern QSAR approaches have wide practical applications in drug discovery for screening potentially bioactive molecules before their experimental testing. Most models predicting the bioactivity of compounds are based on molecular descriptors derived from 2D structure losing explicit information about the spatial structure of molecules which is important for protein-ligand recognition. The major problem in constructing models using 3D descriptors is the choice of a probable bioactive conformation that affects the predictive performance. Multi-instance (MI) learning approach considering multiple conformations upon the model training can be a reasonable solution to the above problem. Here, we compared MI-QSAR with the classical single-instance QSAR (SI-QSAR) approach, where each molecule was encoded by either 2D descriptors or 3D descriptors issued from the single lowest-energy conformation. The calculations were carried out on a sample of 175 datasets extracted from the ChEMBL23 database. It was demonstrated that (<i>i</i>) MI-QSAR outperforms SI-QSAR in numerous cases and (<i>ii</i>) MI algorithms can automatically identify plausible bioactive conformations. Instance-attention based network can be applied for most important conformer selection which was shown to correspond PDB conformer in 50-84% of molecules.

QSAR-Based Design of The More Potent Betulinic Acid Derivatives as HIV Maturation Inhibitor

In this study, we make QSAR models from 29 of BA derivatives’ HIV maturation inhibition activities against their 3D descriptors. The best model involve 5 descriptors as follows: 1/log EC50 = -462.275 + (69.213 × TDB6u) + (723.745 × TDB6e) + (-0.576 × FPSA-3) + (0.849 × RDF140u) + (0.302 × RDF80e) r2 training = 0.7918; Q2 test = 0.9644; r2test = 0.9798; and r2m-test = 0.9445 TDB6u and TDB6e are the 3d topological distance-based autocorrelation-lag 6 /unweighted and weighted by Sanderson electronegati-vities, respectively. FPSA-3 is the value of charge weighted partial positive surface area / total molecular surface area. RDF140u is radial distribution function-140 / unweighted. RDF80e is radial distribution function-080/weighted by relative Sanderson electronegativities. The QSAR model was then used to design and predict some of the new BA derivatives’ HIV maturation activities. The best predicted compound had pEC50 value of -0.838 and EC50 value of 0.064 nM with the chemical IUPAC name of 4‐[(1R, 3aR, 5aR, 5bR, 7aS, 11aR, 11bS, 13aS,13bS)‐5a, 5b, 8, 8, 11b pentamethyl‐1‐(prop‐1‐en‐2‐yl)‐3a[({2‐[4‐(pyrimidin2yl)piperazin-1-yl]ethyl}amino) methyl]‐icosahydro‐1H-cyclopenta[a]chrysen‐9‐yl]benzoic acid. We also suggest the synthetic route to the proposed compound.

CNN-BASED PLACE RECOGNITION TECHNIQUE FOR LIDAR SLAM

Place recognition or loop closure is a technique to recognize landmarks and/or scenes visited by a mobile sensing platform previously in an area. The technique is a key function for robustly practicing Simultaneous Localization and Mapping (SLAM) in any environment, including the global positioning system (GPS) denied environment by enabling to perform the global optimization to compensate the drift of dead-reckoning navigation systems. Place recognition in 3D point clouds is a challenging task which is traditionally handled with the aid of other sensors, such as camera and GPS. Unfortunately, visual place recognition techniques may be impacted by changes in illumination and texture, and GPS may perform poorly in urban areas. To mitigate this problem, state-of-art Convolutional Neural Networks (CNNs)-based 3D descriptors may be directly applied to 3D point clouds. In this work, we investigated the performance of different classification strategies utilizing a cutting-edge CNN-based 3D global descriptor (PointNetVLAD) for place recognition task on the Oxford RobotCar dataset.

3D Object Recognition and Relative Localization using a 3D sensor Embedded on a Mobile Robot

The technology in current research scenario is marching towards automation forhigher productivity with accurate and precise product development. Vision andRobotics are domains which work to create autonomous systems and are the keytechnology in quest for mass productivity. The automation in an industry canbe achieved by detecting interactive objects and estimating the pose to manipulatethem. Therefore the object localization ( i.e., pose) includes position andorientation of object, has profound ?significance. The application of object poseestimation varies from industry automation to entertainment industry and fromhealth care to surveillance. The objective of pose estimation of objects is verysigni?cant in many cases, like in order for the robots to manipulate the objects,for accurate rendering of Augmented Reality (AR) among others.This thesis tries to solve the issue of object pose estimation using 3D dataof scene acquired from 3D sensors (e.g. Kinect, Orbec Astra Pro among others).The 3D data has an advantage of independence from object texture and invarianceto illumination. The proposal is divided into two phases : An o?ine phasewhere the 3D model template of the object ( for estimation of pose) is built usingIterative Closest Point (ICP) algorithm. And an online phase where the pose ofthe object is estimated by aligning the scene to the model using ICP, providedwith an initial alignment using 3D descriptors (like Fast Point Feature Transform(FPFH)).The approach we develop is to be integrated on two di?erent platforms :1)Humanoid robot `Pyrene' which has Orbec Astra Pro 3D sensor for data acquisition,and 2)Unmanned Aerial Vehicle (UAV) which has Intel Realsense Euclidon it. The datasets of objects (like electric drill, brick, a small cylinder, cake box)are acquired using Microsoft Kinect, Orbec Astra Pro and Intel RealSense Euclidsensors to test the performance of this technique. The objects which are used totest this approach are the ones which are used by robot. This technique is testedin two scenarios, fi?rstly, when the object is on the table and secondly when theobject is held in hand by a person. The range of objects from the sensor is 0.6to 1.6m. This technique could handle occlusions of the object by hand (when wehold the object), as ICP can work even if partial object is visible in the scene.