scholarly journals Distribution-free, Risk-controlling Prediction Sets

2021 ◽  
Vol 68 (6) ◽  
pp. 1-34
Author(s):  
Stephen Bates ◽  
Anastasios Angelopoulos ◽  
Lihua Lei ◽  
Jitendra Malik ◽  
Michael Jordan
Keyword(s):  
Machine Learning ◽  
Structure Prediction ◽  
Error Control ◽  
Large Scale ◽  
Metric Learning ◽  
Finite Sample ◽  
Classification Problems ◽  
Distribution Free ◽  
Distributionally Robust ◽  
Rigorous Error

While improving prediction accuracy has been the focus of machine learning in recent years, this alone does not suffice for reliable decision-making. Deploying learning systems in consequential settings also requires calibrating and communicating the uncertainty of predictions. To convey instance-wise uncertainty for prediction tasks, we show how to generate set-valued predictions from a black-box predictor that controls the expected loss on future test points at a user-specified level. Our approach provides explicit finite-sample guarantees for any dataset by using a holdout set to calibrate the size of the prediction sets. This framework enables simple, distribution-free, rigorous error control for many tasks, and we demonstrate it in five large-scale machine learning problems: (1) classification problems where some mistakes are more costly than others; (2) multi-label classification, where each observation has multiple associated labels; (3) classification problems where the labels have a hierarchical structure; (4) image segmentation, where we wish to predict a set of pixels containing an object of interest; and (5) protein structure prediction. Last, we discuss extensions to uncertainty quantification for ranking, metric learning, and distributionally robust learning.

scholarly journals Accelerated crystal structure prediction of multi-elements random alloy using expandable features

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Taewon Jin ◽  
Ina Park ◽  
Taesu Park ◽  
Jaesik Park ◽  
Ji Hoon Shim
Keyword(s):  
Crystal Structure ◽  
Machine Learning ◽  
Structure Prediction ◽  
Large Scale ◽  
Computational Cost ◽  
Functional Materials ◽  
Training Dataset ◽  
High Entropy Alloy ◽  
Crystal Structure Prediction ◽  
Data Set

AbstractProperties of solid-state materials depend on their crystal structures. In solid solution high entropy alloy (HEA), its mechanical properties such as strength and ductility depend on its phase. Therefore, the crystal structure prediction should be preceded to find new functional materials. Recently, the machine learning-based approach has been successfully applied to the prediction of structural phases. However, since about 80% of the data set is used as a training set in machine learning, it is well known that it requires vast cost for preparing a dataset of multi-element alloy as training. In this work, we develop an efficient approach to predicting the multi-element alloys' structural phases without preparing a large scale of the training dataset. We demonstrate that our method trained from binary alloy dataset can be applied to the multi-element alloys' crystal structure prediction by designing a transformation module from raw features to expandable form. Surprisingly, without involving the multi-element alloys in the training process, we obtain an accuracy, 80.56% for the phase of the multi-element alloy and 84.20% accuracy for the phase of HEA. It is comparable with the previous machine learning results. Besides, our approach saves at least three orders of magnitude computational cost for HEA by employing expandable features. We suggest that this accelerated approach can be applied to predicting various structural properties of multi-elements alloys that do not exist in the current structural database.

scholarly journals Machine learning prediction of Antibody-Antigen binding: dataset, method and testing

2021 ◽  
Author(s):  
Chao Ye ◽  
Wenxing Hu ◽  
Bruno Gaeta
Keyword(s):  
Machine Learning ◽  
Structure Prediction ◽  
Large Scale ◽  
Nearest Neighbor ◽  
Sequence Data ◽  
Antigen Binding ◽  
Immunoglobulin Gene ◽  
Learning Program ◽  
Prediction Program ◽  
Sequencing Technologies

DNA sequencing technologies are providing new insights into the immune response by allowing the large scale sequencing of rearranged immunoglobulin gene present in an individual, however the applications of this approach are limited by the lack of methods for determining the antigen(s) that an immunoglobulin encoded by a given sequence binds to. Computational methods for predicting antibody-antigen interactions that leverage structure prediction and docking have been proposed, however these methods require knowledge of the 3D structures. As a step towards the development of a machine learning method suitable for predicting antibody-antigen binding affinities from sequence data, a weighted nearest neighbor machine learning approach was applied to the problem. A prediction program was coded in Python and evaluated using cross-validation on a dataset of 600 antibodies interacting with 50 antigens. The classification predicting accuracy was around 76% for this dataset. These results provide a useful frame of reference as well as protocols and considerations for machine learning and dataset creation in this area. Both the dataset (in csv format) and the machine learning program (coded in python) are freely available for download.

A Comparative Study of Different Machine Learning Algorithms for Disease Prediction

2017 ◽  
Vol 7 (7) ◽  
pp. 172
Author(s):  
Anantvir Singh Romana
Keyword(s):  
Machine Learning ◽  
Subsequent Treatment ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Disease Prediction ◽  
Classification Problems ◽  
Learning Techniques ◽  
Neural Network Classifiers ◽  
Diagnostic Detection

Accurate diagnostic detection of the disease in a patient is critical and may alter the subsequent treatment and increase the chances of survival rate. Machine learning techniques have been instrumental in disease detection and are currently being used in various classification problems due to their accurate prediction performance. Various techniques may provide different desired accuracies and it is therefore imperative to use the most suitable method which provides the best desired results. This research seeks to provide comparative analysis of Support Vector Machine, Naïve bayes, J48 Decision Tree and neural network classifiers breast cancer and diabetes datsets.

Evolution of Metastable Structures in Bimetallic Catalysts from Microscopy and Machine-Learning Molecular Dynamics

2020 ◽  
Author(s):  
Jin Soo Lim ◽  
Jonathan Vandermause ◽  
Matthijs A. van Spronsen ◽  
Albert Musaelian ◽  
Christopher R. O’Connor ◽  
...  
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
Large Scale ◽  
Materials Science ◽  
Complete Characterization ◽  
Layer By Layer ◽  
Surface Restructuring ◽  
Metastable Structures ◽  
Mechanistic Investigation ◽  
Underlying Mechanisms

Restructuring of interface plays a crucial role in materials science and heterogeneous catalysis. Bimetallic systems, in particular, often adopt very different composition and morphology at surfaces compared to the bulk. For the first time, we reveal a detailed atomistic picture of the long-timescale restructuring of Pd deposited on Ag, using microscopy, spectroscopy, and novel simulation methods. Encapsulation of Pd by Ag always precedes layer-by-layer dissolution of Pd, resulting in significant Ag migration out of the surface and extensive vacancy pits. These metastable structures are of vital catalytic importance, as Ag-encapsulated Pd remains much more accessible to reactants than bulk-dissolved Pd. The underlying mechanisms are uncovered by performing fast and large-scale machine-learning molecular dynamics, followed by our newly developed method for complete characterization of atomic surface restructuring events. Our approach is broadly applicable to other multimetallic systems of interest and enables the previously impractical mechanistic investigation of restructuring dynamics.

Epigenetic Target Prediction with Accurate Machine Learning Models

2021 ◽  
Author(s):  
Norberto Sánchez-Cruz ◽  
Jose L. Medina-Franco
Keyword(s):  
Machine Learning ◽  
Small Molecules ◽  
Predictive Models ◽  
Large Scale ◽  
Target Prediction ◽  
Quantitative Measure ◽  
Learning Models ◽  
Discovery Research ◽  
Drug Discovery Research ◽  
Machine Learning Models

<p>Epigenetic targets are a significant focus for drug discovery research, as demonstrated by the eight approved epigenetic drugs for treatment of cancer and the increasing availability of chemogenomic data related to epigenetics. This data represents a large amount of structure-activity relationships that has not been exploited thus far for the development of predictive models to support medicinal chemistry efforts. Herein, we report the first large-scale study of 26318 compounds with a quantitative measure of biological activity for 55 protein targets with epigenetic activity. Through a systematic comparison of machine learning models trained on molecular fingerprints of different design, we built predictive models with high accuracy for the epigenetic target profiling of small molecules. The models were thoroughly validated showing mean precisions up to 0.952 for the epigenetic target prediction task. Our results indicate that the herein reported models have considerable potential to identify small molecules with epigenetic activity. Therefore, our results were implemented as freely accessible and easy-to-use web application.</p>

Adsorption Isotherm Predictions for Multiple Molecules in MOFs Using the Same Deep Learning Model

2019 ◽  
Author(s):  
Ryther Anderson ◽  
Achay Biong ◽  
Diego Gómez-Gualdrón
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Molecular Simulation ◽  
Large Scale ◽  
Learning Model ◽  
Operating Conditions ◽  
Small Subset ◽  
Screening Methods ◽  
Large Set ◽  
Metal Organic

<div>Tailoring the structure and chemistry of metal-organic frameworks (MOFs) enables the manipulation of their adsorption properties to suit specific energy and environmental applications. As there are millions of possible MOFs (with tens of thousands already synthesized), molecular simulation, such as grand canonical Monte Carlo (GCMC), has frequently been used to rapidly evaluate the adsorption performance of a large set of MOFs. This allows subsequent experiments to focus only on a small subset of the most promising MOFs. In many instances, however, even molecular simulation becomes prohibitively time consuming, underscoring the need for alternative screening methods, such as machine learning, to precede molecular simulation efforts. In this study, as a proof of concept, we trained a neural network as the first example of a machine learning model capable of predicting full adsorption isotherms of different molecules not included in the training of the model. To achieve this, we trained our neural network only on alchemical species, represented only by their geometry and force field parameters, and used this neural network to predict the loadings of real adsorbates. We focused on predicting room temperature adsorption of small (one- and two-atom) molecules relevant to chemical separations. Namely, argon, krypton, xenon, methane, ethane, and nitrogen. However, we also observed surprisingly promising predictions for more complex molecules, whose properties are outside the range spanned by the alchemical adsorbates. Prediction accuracies suitable for large-scale screening were achieved using simple MOF (e.g. geometric properties and chemical moieties), and adsorbate (e.g. forcefield parameters and geometry) descriptors. Our results illustrate a new philosophy of training that opens the path towards development of machine learning models that can predict the adsorption loading of any new adsorbate at any new operating conditions in any new MOF.</div>

Recent Progress in Machine Learning-based Prediction of Peptide Activity for Drug Discovery

2019 ◽  
Vol 19 (1) ◽  
pp. 4-16 ◽  
Author(s):  
Qihui Wu ◽  
Hanzhong Ke ◽  
Dongli Li ◽  
Qi Wang ◽  
Jiansong Fang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Large Scale ◽  
Recent Progress ◽  
High Specificity ◽  
Learning Approaches ◽  
Anticancer Peptides ◽  
The Past ◽  
Traditional Approaches ◽  
Large Scale Screening

Over the past decades, peptide as a therapeutic candidate has received increasing attention in drug discovery, especially for antimicrobial peptides (AMPs), anticancer peptides (ACPs) and antiinflammatory peptides (AIPs). It is considered that the peptides can regulate various complex diseases which are previously untouchable. In recent years, the critical problem of antimicrobial resistance drives the pharmaceutical industry to look for new therapeutic agents. Compared to organic small drugs, peptide- based therapy exhibits high specificity and minimal toxicity. Thus, peptides are widely recruited in the design and discovery of new potent drugs. Currently, large-scale screening of peptide activity with traditional approaches is costly, time-consuming and labor-intensive. Hence, in silico methods, mainly machine learning approaches, for their accuracy and effectiveness, have been introduced to predict the peptide activity. In this review, we document the recent progress in machine learning-based prediction of peptides which will be of great benefit to the discovery of potential active AMPs, ACPs and AIPs.

Sign in / Sign up

Export Citation Format

Share Document