Infusing theory into deep learning for interpretable reactivity prediction

AbstractDespite recent advances of data acquisition and algorithms development, machine learning (ML) faces tremendous challenges to being adopted in practical catalyst design, largely due to its limited generalizability and poor explainability. Herein, we develop a theory-infused neural network (TinNet) approach that integrates deep learning algorithms with the well-established d-band theory of chemisorption for reactivity prediction of transition-metal surfaces. With simple adsorbates (e.g., *OH, *O, and *N) at active site ensembles as representative descriptor species, we demonstrate that the TinNet is on par with purely data-driven ML methods in prediction performance while being inherently interpretable. Incorporation of scientific knowledge of physical interactions into learning from data sheds further light on the nature of chemical bonding and opens up new avenues for ML discovery of novel motifs with desired catalytic properties.

Download Full-text

Iterative Supervised Principal Component Analysis-Driven Ligand Design for Regioselective Ti-Catalyzed Pyrrole Synthesis

10.26434/chemrxiv.12284378 ◽

2020 ◽

Author(s):

Xin Yi See ◽

Benjamin Reiner ◽

Xuelan Wen ◽

T. Alexander Wheeler ◽

Channing Klein ◽

...

Keyword(s):

Principal Component Analysis ◽

De Novo ◽

Principal Component ◽

Component Analysis ◽

Catalyst Design ◽

Data Driven ◽

Initial Reaction ◽

Training Set ◽

Reaction Conditions ◽

Component Loadings

<div> <div> <div> <p>Herein, we describe the use of iterative supervised principal component analysis (ISPCA) in de novo catalyst design. The regioselective synthesis of 2,5-dimethyl-1,3,4-triphenyl-1H- pyrrole (C) via Ti- catalyzed formal [2+2+1] cycloaddition of phenyl propyne and azobenzene was targeted as a proof of principle. The initial reaction conditions led to an unselective mixture of all possible pyrrole regioisomers. ISPCA was conducted on a training set of catalysts, and their performance was regressed against the scores from the top three principal components. Component loadings from this PCA space along with k-means clustering were used to inform the design of new test catalysts. The selectivity of a prospective test set was predicted in silico using the ISPCA model, and only optimal candidates were synthesized and tested experimentally. This data-driven predictive-modeling workflow was iterated, and after only three generations the catalytic selectivity was improved from 0.5 (statistical mixture of products) to over 11 (> 90% C) by incorporating 2,6-dimethyl- 4-(pyrrolidin-1-yl)pyridine as a ligand. The successful development of a highly selective catalyst without resorting to long, stochastic screening processes demonstrates the inherent power of ISPCA in de novo catalyst design and should motivate the general use of ISPCA in reaction development. </p> </div> </div> </div>

Download Full-text

Computational Complexity Reduction of Neural Networks of Brain Tumor Image Segmentation by Introducing Fermi–Dirac Correction Functions

Entropy ◽

10.3390/e23020223 ◽

2021 ◽

Vol 23 (2) ◽

pp. 223

Author(s):

Yen-Ling Tai ◽

Shin-Jhe Huang ◽

Chien-Chang Chen ◽

Henry Horng-Shing Lu

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Computational Complexity ◽

High Performance ◽

Low Cost ◽

Structural Complexity ◽

Correction Function ◽

Computational Time ◽

Learning Methods ◽

Band Theory

Nowadays, deep learning methods with high structural complexity and flexibility inevitably lean on the computational capability of the hardware. A platform with high-performance GPUs and large amounts of memory could support neural networks having large numbers of layers and kernels. However, naively pursuing high-cost hardware would probably drag the technical development of deep learning methods. In the article, we thus establish a new preprocessing method to reduce the computational complexity of the neural networks. Inspired by the band theory of solids in physics, we map the image space into a noninteraction physical system isomorphically and then treat image voxels as particle-like clusters. Then, we reconstruct the Fermi–Dirac distribution to be a correction function for the normalization of the voxel intensity and as a filter of insignificant cluster components. The filtered clusters at the circumstance can delineate the morphological heterogeneity of the image voxels. We used the BraTS 2019 datasets and the dimensional fusion U-net for the algorithmic validation, and the proposed Fermi–Dirac correction function exhibited comparable performance to other employed preprocessing methods. By comparing to the conventional z-score normalization function and the Gamma correction function, the proposed algorithm can save at least 38% of computational time cost under a low-cost hardware architecture. Even though the correction function of global histogram equalization has the lowest computational time among the employed correction functions, the proposed Fermi–Dirac correction function exhibits better capabilities of image augmentation and segmentation.

Download Full-text

A 2020 perspective on “DeRec: A data-driven approach to accurate recommendation with deep learning and weighted loss function”

Electronic Commerce Research and Applications ◽

10.1016/j.elerap.2021.101064 ◽

2021 ◽

Vol 48 ◽

pp. 101064

Author(s):

Wen Zhang ◽

Qiang Wang ◽

Ye Yang ◽

Taketoshi Yoshida

Keyword(s):

Deep Learning ◽

Loss Function ◽

Data Driven ◽

Data Driven Approach

Download Full-text

A Data-driven Decision-making Approach for Complex Product Design Based on Deep Learning

2021 IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD) ◽

10.1109/cscwd49262.2021.9437761 ◽

2021 ◽

Author(s):

Zou Lai ◽

Siqin Fu ◽

Hang Yu ◽

Shulin Lan ◽

Chen Yang

Keyword(s):

Decision Making ◽

Deep Learning ◽

Product Design ◽

Data Driven ◽

Data Driven Decision Making ◽

Complex Product

Download Full-text

High-Resolution ISAR Imaging and Autofocusing via 2D-ADMM-Net

Remote Sensing ◽

10.3390/rs13122326 ◽

2021 ◽

Vol 13 (12) ◽

pp. 2326

Author(s):

Xiaoyong Li ◽

Xueru Bai ◽

Feng Zhou

Keyword(s):

Deep Learning ◽

High Resolution ◽

Phase Error ◽

Random Phase ◽

Back Propagation ◽

Estimation Method ◽

Data Driven ◽

Reconstruction Performance ◽

Imaging Results ◽

Isar Imaging

A deep-learning architecture, dubbed as the 2D-ADMM-Net (2D-ADN), is proposed in this article. It provides effective high-resolution 2D inverse synthetic aperture radar (ISAR) imaging under scenarios of low SNRs and incomplete data, by combining model-based sparse reconstruction and data-driven deep learning. Firstly, mapping from ISAR images to their corresponding echoes in the wavenumber domain is derived. Then, a 2D alternating direction method of multipliers (ADMM) is unrolled and generalized to a deep network, where all adjustable parameters in the reconstruction layers, nonlinear transform layers, and multiplier update layers are learned by an end-to-end training through back-propagation. Since the optimal parameters of each layer are learned separately, 2D-ADN exhibits more representation flexibility and preferable reconstruction performance than model-driven methods. Simultaneously, it is able to better facilitate ISAR imaging with limited training samples than data-driven methods owing to its simple structure and small number of adjustable parameters. Additionally, benefiting from the good performance of 2D-ADN, a random phase error estimation method is proposed, through which well-focused imaging can be acquired. It is demonstrated by experiments that although trained by only a few simulated images, the 2D-ADN shows good adaptability to measured data and favorable imaging results with a clear background can be obtained in a short time.

Download Full-text

A Data-Driven Approach to Structural Health Monitoring of Bridge Structures Based on the Discrete Model and FFT-Deep Learning

Journal of Vibration Engineering & Technologies ◽

10.1007/s42417-021-00343-5 ◽

2021 ◽

Author(s):

Thanh Q. Nguyen

Keyword(s):

Deep Learning ◽

Structural Health Monitoring ◽

Health Monitoring ◽

Discrete Model ◽

Data Driven ◽

Structural Health ◽

Bridge Structures ◽

Data Driven Approach

Download Full-text

Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review

Sensors ◽

10.3390/s20102778 ◽

2020 ◽

Vol 20 (10) ◽

pp. 2778 ◽

Cited By ~ 12

Author(s):

Mohsen Azimi ◽

Armin Eslamlou ◽

Gokhan Pekcan

Keyword(s):

Deep Learning ◽

Structural Health Monitoring ◽

Health Monitoring ◽

High Speed ◽

Deep Neural Networks ◽

State Of The Art ◽

Data Driven ◽

Structural Health ◽

Promising Tool ◽

Significant Attention

Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep learning (DL) in civil engineering, particularly in SHM, this emerging and promising tool has attracted significant attention among researchers. The main goal of this paper is to review the latest publications in SHM using emerging DL-based methods and provide readers with an overall understanding of various SHM applications. After a brief introduction, an overview of various DL methods (e.g., deep neural networks, transfer learning, etc.) is presented. The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed. The review concludes with prospects and potential limitations of DL-based methods in SHM applications.

Download Full-text

A comparative study of class-D β-lactamases

Biochemical Journal ◽

10.1042/bj2920555 ◽

1993 ◽

Vol 292 (2) ◽

pp. 555-562 ◽

Cited By ~ 56

Author(s):

P Ledent ◽

X Raquet ◽

B Joris ◽

J Van Beeumen ◽

J M Frère

Keyword(s):

Active Site ◽

Gene Sequence ◽

Catalytic Properties ◽

Ion Exchange Chromatography ◽

Exchange Chromatography ◽

Beta Lactamase ◽

Serine Residue ◽

Beta Lactamases ◽

Class D ◽

Burst Kinetics

Three class-D beta-lactamases (OXA2, OXA1 and PSE2) were produced and purified to protein homogeneity. 6 beta-Iodopenicillanate inactivated the OXA2 enzyme without detectable turnover. Labelling of the same beta-lactamase with 6 beta-iodo[3H]penicillanate allowed the identification of Ser-70 as the active-site serine residue. In agreement with previous reports, the apparent M(r) of the OXA2 enzyme as determined by molecular-sieve filtration, was significantly higher than that deduced from the gene sequence, but this was not due to an equilibrium between a monomer and a dimer. The heterogeneity of the OXA2 beta-lactamase on ion-exchange chromatography contrasted with the similarity of the catalytic properties of the various forms. A first overview of the enzymic properties of the three ‘oxacillinases’ is presented. With the OXA2 enzyme, ‘burst’ kinetics, implying branched pathways, seemed to prevail with many substrates.

Download Full-text