scholarly journals Fine-tuning of a generative neural network for designing multi-target compounds

2021 ◽  
Author(s):  
Thomas Blaschke ◽  
Jürgen Bajorath
Keyword(s):  
Neural Network ◽  
Small Molecules ◽  
De Novo ◽  
Pharmaceutical Research ◽  
Generative Models ◽  
Fine Tuning ◽  
Data Sets ◽  
Single Target ◽  
Fine Tune ◽  
Target Activity

AbstractExploring the origin of multi-target activity of small molecules and designing new multi-target compounds are highly topical issues in pharmaceutical research. We have investigated the ability of a generative neural network to create multi-target compounds. Data sets of experimentally confirmed multi-target, single-target, and consistently inactive compounds were extracted from public screening data considering positive and negative assay results. These data sets were used to fine-tune the REINVENT generative model via transfer learning to systematically recognize multi-target compounds, distinguish them from single-target or inactive compounds, and construct new multi-target compounds. During fine-tuning, the model showed a clear tendency to increasingly generate multi-target compounds and structural analogs. Our findings indicate that generative models can be adopted for de novo multi-target compound design.

scholarly journals Dereplikace látek a de novo charakterizace malých molekul z hmotnostních spekter

2022 ◽  
Vol 116 (1) ◽  
pp. 11-19
Author(s):  
Jiří Novák ◽  
Vladimír Havlíček
Keyword(s):  
Mass Spectrometry ◽  
Small Molecules ◽  
Mass Spectra ◽  
De Novo ◽  
Imaging Mass Spectrometry ◽  
Mass Spectrometry Data ◽  
Data Sets ◽  
Liquid Chromatography Mass Spectrometry ◽  
Imaging Mass Spectrometry Data

We describe the molecular dereplication principles and de novo characterization of small molecules obtained from liquid-chromatography mass spectrometry and imaging mass spectrometry data sets. Our methodology aims at supporting chemists and computer programmers to understand the hidden computing algorithms used for metabolomics mass spectrometry data processing. The approaches have been made available in the open-source tool CycloBranch. The presented tutorial extends the interpretation of mass spectra portfolia described in a series of papers published in Chemicke Listy, issues 2/2020 and 3/2020.

Incremental inputs improve the automated detection of implant loosening using machine-learning algorithms

2020 ◽  
Vol 102-B (6_Supple_A) ◽  
pp. 101-106
Author(s):  
Romil F. Shah ◽  
Stefano A. Bini ◽  
Alejandro M. Martinez ◽  
Valentina Pedoia ◽  
Thomas P. Vail
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Clinical Decision Making ◽  
De Novo ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Fine Tuning ◽  
Final Model ◽  
Prosthetic Loosening

Aims The aim of this study was to evaluate the ability of a machine-learning algorithm to diagnose prosthetic loosening from preoperative radiographs and to investigate the inputs that might improve its performance. Methods A group of 697 patients underwent a first-time revision of a total hip (THA) or total knee arthroplasty (TKA) at our institution between 2012 and 2018. Preoperative anteroposterior (AP) and lateral radiographs, and historical and comorbidity information were collected from their electronic records. Each patient was defined as having loose or fixed components based on the operation notes. We trained a series of convolutional neural network (CNN) models to predict a diagnosis of loosening at the time of surgery from the preoperative radiographs. We then added historical data about the patients to the best performing model to create a final model and tested it on an independent dataset. Results The convolutional neural network we built performed well when detecting loosening from radiographs alone. The first model built de novo with only the radiological image as input had an accuracy of 70%. The final model, which was built by fine-tuning a publicly available model named DenseNet, combining the AP and lateral radiographs, and incorporating information from the patient’s history, had an accuracy, sensitivity, and specificity of 88.3%, 70.2%, and 95.6% on the independent test dataset. It performed better for cases of revision THA with an accuracy of 90.1%, than for cases of revision TKA with an accuracy of 85.8%. Conclusion This study showed that machine learning can detect prosthetic loosening from radiographs. Its accuracy is enhanced when using highly trained public algorithms, and when adding clinical data to the algorithm. While this algorithm may not be sufficient in its present state of development as a standalone metric of loosening, it is currently a useful augment for clinical decision making. Cite this article: Bone Joint J 2020;102-B(6 Supple A):101–106.

scholarly journals Transfer learning using AlexNet Convolutional Neural Network for Face Recognition

2020 ◽  
Vol 9 (11) ◽  
pp. 285-294
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Transfer Learning ◽  
Data Augmentation ◽  
Recognition System ◽  
Training Data ◽  
Fine Tuning ◽  
Data Sets ◽  
Learning Method ◽  
Face Recognition System

This research is aimed to achieve high-precision accuracy and for face recognition system. Convolution Neural Network is one of the Deep Learning approaches and has demonstrated excellent performance in many fields, including image recognition of a large amount of training data (such as ImageNet). In fact, hardware limitations and insufficient training data-sets are the challenges of getting high performance. Therefore, in this work the Deep Transfer Learning method using AlexNet pre-trained CNN is proposed to improve the performance of the face-recognition system even for a smaller number of images. The transfer learning method is used to fine-tuning on the last layer of AlexNet CNN model for new classification tasks. The data augmentation (DA) technique also proposed to minimize the over-fitting problem during Deep transfer learning training and to improve accuracy. The results proved the improvement in over-fitting and in performance after using the data augmentation technique. All the experiments were tested on UTeMFD, GTFD, and CASIA-Face V5 small data-sets. As a result, the proposed system achieved a high accuracy as 100% on UTeMFD, 96.67% on GTFD, and 95.60% on CASIA-Face V5 in less than 0.05 seconds of recognition time.

scholarly journals Integrating Synthetic Accessibility with AI-based Generative Drug Design

2021 ◽  
Author(s):  
Maud Parrot ◽  
Hamza Tajmouati ◽  
Vinicius Barros Ribeiro da Silva ◽  
Brian Ross Atwood ◽  
Robin Fourcade ◽  
...  
Keyword(s):  
Neural Network ◽  
De Novo ◽  
De Novo Design ◽  
Generative Models ◽  
Data Driven ◽  
Planning Software ◽  
Synthetic Accessibility ◽  
Retrosynthetic Analysis ◽  
Practice Methods ◽  
Fundamental Requirement

Generative models are frequently used for de novo design in drug discovery projects to propose new molecules. However, the question of whether or not the generated molecules can be synthesized is not systematically taken into account during generation, even though being able to synthesize the generated molecules is a fundamental requirement for such methods to be useful in practice. Methods have been developed to estimate molecule synthesizability, but, so far, there is no consensus on whether or not a molecule is synthesizable. In this paper we introduce the Retro-Score (RScore), which computes a synthetic feasibility score of molecules by performing a full retrosynthetic analysis through our data-driven synthetic planning software Spaya, and its dedicated API: Spaya-API (https://spaya.ai). After a comparison of RScore with other synthetic scores from the literature, we describe a pipeline to generate molecules that validate a list of targets while still being easy to synthesize. We further this idea by performing experiments comparing molecular generator outputs across a range of constraints and conditions. We show that the RScore can be learned by a Neural Network, which leads to a new score: RSPred. We demonstrate that using the RScore or RSPred as a constraint during molecular generation enables to obtain more synthesizable solutions, with higher diversity. The open-source Python code containing all the scores and the experiments can be found on https://github.com/iktos/generation-under-synthetic- constraint.

scholarly journals MSNovelist: De novo structure generation from mass spectra

2021 ◽  
Author(s):  
Michael A Stravs ◽  
Kai Dührkop ◽  
Sebastian Böcker ◽  
Nicola Zamboni
Keyword(s):  
Neural Network ◽  
Small Molecules ◽  
Natural Product ◽  
Structure Prediction ◽  
Mass Spectra ◽  
Unsolved Problem ◽  
De Novo ◽  
Reference Dataset ◽  
Structure Generation ◽  
Spectral Libraries

Structural elucidation of small molecules de novo from mass spectra is a longstanding, yet unsolved problem. Current methods rely on finding some similarity with spectra of known compounds deposited in spectral libraries, but do not solve the problem of predicting structures for novel or poorly represented compound classes. We present MSNovelist that combines fingerprint prediction with an encoder-decoder neural network to generate structures de novo from fragment spectra. In evaluation, MSNovelist correctly reproduced 61% of database annotations for a GNPS reference dataset. In a bryophyte MS2 dataset, our de novo structure prediction substantially outscored the best database candidate for seven features, and a potential novel natural product with a flavonoid core was identified. MSNovelist allows predicting structures solely from MS2 data, and is therefore ideally suited to complement library-based annotation in the case of poorly represented analyte classes and novel compounds.

scholarly journals Integrating Synthetic Accessibility with AI-based Generative Drug Design

2021 ◽  
Author(s):  
Maud Parrot ◽  
Hamza Tajmouati ◽  
Vinicius Barros Ribeiro da Silva ◽  
Brian Ross Atwood ◽  
Robin Fourcade ◽  
...  
Keyword(s):  
Neural Network ◽  
De Novo ◽  
De Novo Design ◽  
Generative Models ◽  
Data Driven ◽  
Planning Software ◽  
Synthetic Accessibility ◽  
Retrosynthetic Analysis ◽  
Practice Methods ◽  
Fundamental Requirement

Generative models are frequently used for de novo design in drug discovery projects to propose new molecules. However, the question of whether or not the generated molecules can be synthesized is not systematically taken into account during generation, even though being able to synthesize the generated molecules is a fundamental requirement for such methods to be useful in practice. Methods have been developed to estimate molecule synthesizability, but, so far, there is no consensus on whether or not a molecule is synthesizable. In this paper we introduce the Retro-Score (RScore), which computes a synthetic feasibility score of molecules by performing a full retrosynthetic analysis through our data-driven synthetic planning software Spaya, and its dedicated API: Spaya-API (https://spaya.ai). After a comparison of RScore with other synthetic scores from the literature, we describe a pipeline to generate molecules that validate a list of targets while still being easy to synthesize. We further this idea by performing experiments comparing molecular generator outputs across a range of constraints and conditions. We show that the RScore can be learned by a Neural Network, which leads to a new score: RSPred. We demonstrate that using the RScore or RSPred as a constraint during molecular generation enables to obtain more synthesizable solutions, with higher diversity. The open-source Python code containing all the scores and the experiments can be found on https://github.com/iktos/generation-under-synthetic- constraint.

scholarly journals Structured data sets of compounds with multi-target and corresponding single-target activity from biological assays

2021 ◽  
pp. FSO685
Author(s):  
Christian Feldmann ◽  
Dimitar Yonchev ◽  
Jürgen Bajorath
Keyword(s):  
Test Data ◽  
Medicinal Chemistry ◽  
Structured Data ◽  
Target Space ◽  
Data Sets ◽  
Biological Assays ◽  
Single Target ◽  
Target Set ◽  
Screening Assays ◽  
Target Activity

Aim: Providing compound data sets for promiscuity analysis with single-target (ST) and multi-target (MT) activity, taking confirmed inactivity against targets into account. Methodology: Compounds and target annotations are extracted from screening assays. For a given combination of targets, MT and ST compounds are identified, ensuring test data completeness. Exemplary results & data: A total of 1242 MT compounds active against five or more targets and 6629 corresponding ST compounds are characterized, organized and made freely available. Limitations & next steps: Screening campaigns typically cover a smaller target space than compounds from the medicinal chemistry literature and their activity annotations might be of lesser quality. Reported compound groups will be subjected to target set-based promiscuity analysis and predictions.

scholarly journals Material Recognition Using Deep Learning Techniques

2019 ◽  
Author(s):  
Nampally Tejasri ◽  
Mongkol Ekapanyapong
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Fine Tuning ◽  
Data Sets ◽  
Network Architectures ◽  
Data Set ◽  
Material Recognition ◽  
Learning Techniques ◽  
Computer Vision Systems ◽  
Fully Connected

The classification and recognition of variety of materials that are present in our surroundings be-come an important visual competition have been focused by computer vision systems in the recentyears. Understanding the recognition of the materials in different images that involve a deep learn-ing process made use of the recent development in the field of Artificial Neural Networks broughtthe ability to train various neural network architectures for the extraction of features for this chal-lenging task. In this work, state-of-the-art Convolutional Neural Network (CNN) techniques areused to classify materials and also compare the results obtained by them.The results are gath-ered over two material data sets applying the two popular approaches of Transfer Learning. Theresults showcase that fine-tuning approach achieves very good results compared to the case of ap-proach when the information derived from the layer which is just before the fully connected layeris limited. The results of the comparison indicates the fact that there is an improvement in theperformance and the accuracy of the system particularly in the data set that contains large numberof images.

The importance of transfer learning in seismic modeling and imaging

Geophysics ◽  
2019 ◽  
Vol 84 (6) ◽  
pp. A47-A52 ◽  
Author(s):  
Ali Siahkoohi ◽  
Mathias Louboutin ◽  
Felix J. Herrmann
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Low Cost ◽  
Fine Tuning ◽  
Numerical Dispersion ◽  
High Fidelity ◽  
Velocity Models ◽  
Current Survey ◽  
Exploration Seismology ◽  
Fine Tune

Accurate forward modeling is essential for solving inverse problems in exploration seismology. Unfortunately, it is often not possible to afford being physically or numerically accurate. To overcome this conundrum, we make use of raw and processed data from nearby surveys. We have used these data, consisting of shot records or velocity models, to pretrain a neural network to correct for the effects of, for instance, the free surface or numerical dispersion, both of which can be considered as proxies for incomplete or inaccurate physics. Given this pretrained neural network, we apply transfer learning to fine-tune this pretrained neural network so it performs well on its task of mapping low-cost, but low-fidelity, solutions to high-fidelity solutions for the current survey. As long as we can limit ourselves during fine-tuning to using only a small fraction of high-fidelity data, we gain processing the current survey while using information from nearby surveys. We examined this principle by removing surface-related multiples and ghosts from shot records and the effects of numerical dispersion from migrated images and wave simulations.

TD-DFT based fine-tuning of molecular excitation energies using evolutionary algorithms

RSC Advances ◽  
2016 ◽  
Vol 6 (5) ◽  
pp. 3661-3670 ◽  
Author(s):  
Sailesh Abburu ◽  
Vishwesh Venkatraman ◽  
Bjørn K. Alsberg
Keyword(s):  
Density Functional ◽  
De Novo ◽  
Design Method ◽  
Fine Tuning ◽  
Time Dependent ◽  
Excitation Energies ◽  
Functional Theory ◽  
Td Dft ◽  
Molecular Excitation ◽  
Fine Tune

An evolutionary de novo design method is presented to fine-tune the excitation energies of molecules calculated using time-dependent density functional theory (TD-DFT).

Sign in / Sign up

Export Citation Format

Share Document