Publications

1449 Publications visible to you, out of a total of 1449

Abstract (Expand)

Chemical (molecular, quantum) machine learning relies on representing molecules in unique and informative ways. Here, we present the matrix of orthogonalized atomic orbital coefficients (MAOC) as a quantum-inspired molecular and atomic representation containing both structural (composition and geometry) and electronic (charge and spin multiplicity) information. MAOC is based on a cost-effective localization scheme that represents localized orbitals via a predefined set of atomic orbitals. The latter can be constructed from such small atom-centered basis sets as pcseg-0 and STO-3G in conjunction with guess (non-optimized) electronic configuration of the molecule. Importantly, MAOC is suitable for representing monatomic, molecular, and periodic systems and can distinguish compounds with identical compositions and geometries but distinct charges and spin multiplicities. Using principal component analysis, we constructed a more compact but equally powerful version of MAOC—PCX-MAOC. To test the performance of full and reduced MAOC and several other representations (CM, SOAP, SLATM, and SPAHM), we used a kernel ridge regression machine learning model to predict frontier molecular orbital energy levels and ground state single-point energies for chemically diverse neutral and charged, closed- and open-shell molecules from an extended QM7b dataset, as well as two new datasets, N-HPC-1 (N-heteropolycycles) and REDOX (nitroxyl and phenoxyl radicals, carbonyl, and cyano compounds). MAOC affords accuracy that is either similar or superior to other representations for a range of chemical properties and systems.

Authors: Stiv Llenga, Ganna Gryn’ova

Date Published: 7th Jun 2023

Publication Type: Journal

Abstract (Expand)

The chloroquine resistance transporter (PfCRT) confers resistance to a wide range of quinoline and quinoline-like antimalarial drugs in Plasmodium falciparum , with local drug histories driving itsrum , with local drug histories driving its evolution and, hence, the drug transport specificities. For example, the change in prescription practice from chloroquine (CQ) to piperaquine (PPQ) in Southeast Asia has resulted in PfCRT variants that carry an additional mutation, leading to PPQ resistance and, concomitantly, to CQ re-sensitization. How this additional amino acid substitution guides such opposing changes in drug susceptibility is largely unclear. Here, we show by detailed kinetic analyses that both the CQ- and the PPQ-resistance conferring PfCRT variants can bind and transport both drugs. Surprisingly, the kinetic profiles revealed subtle yet significant differences, defining a threshold for in vivo CQ and PPQ resistance. Competition kinetics, together with docking and molecular dynamics simulations, show that the PfCRT variant from the Southeast Asian P . falciparum strain Dd2 can accept simultaneously both CQ and PPQ at distinct but allosterically interacting sites. Furthermore, combining existing mutations associated with PPQ resistance created a PfCRT isoform with unprecedented non-Michaelis-Menten kinetics and superior transport efficiency for both CQ and PPQ. Our study provides additional insights into the organization of the substrate binding cavity of PfCRT and, in addition, reveals perspectives for PfCRT variants with equal transport efficiencies for both PPQ and CQ.

Authors: Guillermo M. Gomez, Giulia D’Arrigo, Cecilia P. Sanchez, Fiona Berger, Rebecca C. Wade, Michael Lanzer

Date Published: 7th Jun 2023

Publication Type: Journal

Abstract

Not specified

Authors: Natalia Lahén, Thorsten Naab, Guinevere Kauffmann, Dorottya Szécsi, Jessica May Hislop, Antti Rantala, Alexandra Kozyreva, Stefanie Walch, Chia-Yu Hu

Date Published: 1st Jun 2023

Publication Type: Journal

Abstract

Not specified

Author: Johannes Resin

Date Published: 31st May 2023

Publication Type: Journal

Abstract (Expand)

Metal-organic frameworks (MOF) and covalent organic frameworks (COFs) are promising nanocarriers for targeted drug delivery. Noncovalent interactions between frameworks and drugs play a fundamental role in the therapeutic uptake and release of the latter. However, the scope of framework functionalizations and deliverable drugs remains underexplored. Using a multilevel approach combining molecular docking and density functional theory, we show for a range of drugs and frameworks that experimentally reported release metrics are in good agreement with the in silico computed host–guest interaction energies. Functional groups within the framework significantly impact the strength of these host–guest interactions, while a given framework can serve as an efficient delivery agent for drugs beyond the prototypical few. Our findings identify the interaction energy as a reliable and relatively easy to compute descriptor of organic framework materials for drug delivery, able to facilitate their high-throughput screening and targeted design towards extended-release times.

Authors: Michelle Ernst, Ganna Gryn'ova

Date Published: 26th May 2023

Publication Type: Journal

Abstract (Expand)

Abstract Machine learning (ML) models are widely used in life sciences and medicine; however, they are scattered across various platforms and there are several challenges that hinder their accessibility,r their accessibility, reproducibility and reuse. In this manuscript, we present the formalisation and pilot implementation of community protocol to enable FAIReR (Findable, Accessible, Interoperable, Reusable, and Reproducible) sharing of ML models. The protocol consists of eight steps, including sharing model training code, dataset information, reproduced figures, model evaluation metrics, trained models, Dockerfiles, model metadata, and FAIR dissemination. Applying these measures we aim to build and share a comprehensive public collection of FAIR ML models in the BioModels repository through incentivized community curation. In a pilot implementation, we curated diverse ML models to demonstrate the feasibility of our approach and we discussed the current challenges. Building a FAIReR collection of ML models will directly enhance the reproducibility and reusability of ML models, minimising the effort needed to reimplement models, maximising the impact on the application and significantly accelerating the advancement in the field of life science and medicine.

Authors: Divyang Deep Tiwari, Nils Hoffmann, Kieran Didi, Sumukh Deshpande, Sucheta Ghosh, Tung V. N. Nguyen, Karthik Raman, Henning Hermjakob, Rahuman Sheriff

Date Published: 23rd May 2023

Publication Type: Misc

Abstract (Expand)

Recently, there has been a growing interest in designing text generation systems from a discourse coherence perspective, e.g., modeling the interdependence between sentences. Still, recent BERT-based evaluation metrics are weak in recognizing coherence, and thus are not reliable in a way to spot the discourse-level improvements of those text generation systems. In this work, we introduce DiscoScore, a parametrized discourse metric, which uses BERT to model discourse coherence from different perspectives, driven by Centering theory. Our experiments encompass 16 non-discourse and discourse metrics, including DiscoScore and popular coherence models, evaluated on summarization and document-level machine translation (MT). We find that (i) the majority of BERT-based metrics correlate much worse with human rated coherence than early discourse metrics, invented a decade ago; (ii) the recent state-of-the-art BARTScore is weak when operated at system level—which is particularly problematic as systems are typically compared in this manner. DiscoScore, in contrast, achieves strong system-level correlation with human ratings, not only in coherence but also in factual consistency and other aspects, and surpasses BARTScore by over 10 correlation points on average. Further, aiming to understand DiscoScore, we provide justifications to the importance of discourse coherence for evaluation metrics, and explain the superiority of one variant over another. Our code is available at https://github.com/AIPHES/DiscoScore.

Authors: Wei Zhao, Michael Strube, Steffen Eger

Date Published: 2nd May 2023

Publication Type: InProceedings

Powered by
(v.1.12.2)
Copyright © 2008 - 2022 The University of Manchester and HITS gGmbH