SlideShare una empresa de Scribd logo
1 de 18
Descargar para leer sin conexión
Machine Learning for Chemical Sciences
Ichigaku Takigawa
HU-SNU Joint Symposium
2018 International Workshop on

New Frontiers in Convergence Science and Technology
Graduate School of Information Science and Technology, HU
Institute for Chemical Reaction Design and Discovery (WPI-ICRD), HU
Brief Bio: Ichigaku Takigawa
Modulatory proteolysis

(MCP 2016)
Transcription elongation
regulation (Nat Comm 2015)
Neurodegenerative disease and
genomes (Mol Brain 2017)
Catalytic conversion of
methane (JPCC 2017)
10 years Hokkaido University
(1995-2005)
7 years at Kyoto University
(2005-2011)
7 years at Hokkaido University
(2012-2018)
PhD in Computer Science/Statistical Science
(Multivariate Analysis, Statistical Signal Processing)
• Bioinformatics Center, Institute for Chemical Research
• Graduate School of Pharmaceutical Sciences
(X-omics, Molecular Biology, Medicinal Chemistry, Biochemistry)
Research in Machine Learning & Data Mining
(ML with discrete structures, ML for sciences)
Two Approaches to Sciences
Our main interest in science: 'unknown mechanism/principle'
mechanism/principle
(unknown)
observations/data
Theory/Hypothesis-driven modeling (as in natural sciences)
explicit model observations/data
e.g. Newtonian mechanics, quantum mechanics, theory of relativity, etc.
we can run a simulation!
Data-driven modeling (as in statistics, machine learning, AI, etc)
model w/ unfixed observations/data
best tuned to fit the given data
✓
Deduction vs Induction/Abduction
The grand aim of science is to cover the greatest number
of experimental facts by logical deduction from the
smallest number of hypotheses or axioms.
Albert Einstein
Hypothesis Experimental facts (data)
Deduction
Induction
Abduction
“Experience/Observation”
“Intuition/Serendipity”
Not logical at all
Logical
Can we somehow “rationalize” this part by using the data?
Machine Learning for Sciences
REVIEW
Inverse molecular design using
machine learning: Generative models
for matter engineering
Benjamin Sanchez-Lengeling1
and Alán Aspuru-Guzik2,3,4
*
The discovery of new materials can bring enormous societal and technological progress. In this
context, exploring completely the large space of potential materials is computationally
intractable. Here, we review methods for achieving inverse design, which aims to discover
tailored materials from the starting point of a particular desired functionality. Recent advances
from the rapidly growing field of artificial intelligence, mostly from the subfield of machine
learning, have resulted in a fertile exchange of ideas, where approaches to inverse molecular
design are being proposed and employed at a rapid pace. Among these, deep generative models
have been applied to numerous classes of materials: rational design of prospective drugs,
synthetic routes to organic compounds, and optimization of photovoltaics and redox flow
batteries, as well as a variety of other solid-state materials.
M
any of the challenges of the 21st century
(1), from personalized health care to
energy production and storage, share a
common theme: materials are part of
the solution (2). In some cases, the solu-
tions to these challenges are fundamentally
limited by the physics and chemistry of a ma-
terial, such as the relationship of a materials
bandgap to the thermodynamic limits for the
generation of solar energy (3).
Several important materials discoveries arose
by chance or through a process of trial and error.
For example, vulcanized rubber was prepared in
the 19th century from random mixtures of com-
pounds, based on the observation that heating
with additives such as sulfur improved the
rubber’s durability. At the molecular level, in-
dividual polymer chains cross-linked, forming
bridges that enhanced the macroscopic mechan-
ical properties (4). Other notable examples in
this vein include Teflon, anesthesia, Vaseline,
Perkin’s mauve, and penicillin. Furthermore,
these materials come from common chemical
compounds found in nature. Potential drugs
either were prepared by synthesis in a chem-
ical laboratory or were isolated from plants,
soil bacteria, or fungus. For example, up until
2014, 49% of small-molecule cancer drugs were
natural products or their derivatives (5).
In the future, disruptive advances in the dis-
covery of matter could instead come from unex-
plored regions of the set of all possible molecular
and solid-state compounds, known as chemical
space (6, 7). One of the largest collections of
molecules, the chemical space project (8), has
mapped 166.4 billion molecules that contain at
most 17 heavy atoms. For pharmacologically rele-
vant small molecules, the number of structures is
estimated to be on the order of 1060
(9). Adding
consideration of the hierarchy of scale from sub-
nanometer to microscopic and mesoscopic fur-
ther complicates exploration of chemical space
in its entirety (10). Therefore, any global strategy
for covering this space might seem impossible.
Simulation offers one way of probing this
space without experimentation. The physics
and chemistry of these molecules are governed
by quantum mechanics, which can be solved via
the Schrödinger equation to arrive at their ex-
act properties. In practice, approximations are
used to lower computational time at the cost of
accuracy.
Although theory enjoys enormous progress,
now routinely modeling molecules, clusters, and
perfect as well as defect-laden periodic solids, the
size of chemical space is still overwhelming, and
smart navigation is required. For this purpose,
machine learning (ML), deep learning (DL), and
artificial intelligence (AI) have a potential role
to play because their computational strategies
automatically improve through experience (11).
In the context of materials, ML techniques are
often used for property prediction, seeking to
learn a function that maps a molecular material
to the property of choice. Deep generative models
are a special class of DL methods that seek to
model the underlying probability distribution of
both structure and property and relate them in a
nonlinear way. By exploiting patterns in massive
datasets, these models can distill average and
salient features that characterize molecules (12, 13).
Inverse design is a component of a more
complex materials discovery process. The time
scale for deployment of new technologies, from
discovery in a laboratory to a commercial pro-
duct, historically, is 15 to 20 years (14). The pro-
cess (Fig. 1) conventionally involves the following
steps: (i) generate a new or improved material
concept and simulate its potential suitability; (ii)
synthesize the material; (iii) incorporate the ma-
terial into a device or system; and (iv) characterize
and measure the desired properties. This cycle
generates feedback to repeat, improve, and re-
fine future cycles of discovery. Each step can take
up to several years.
In the era of matter engineering, scientists
seek to accelerate these cycles, reducing the
FRONTIERS IN COMPUTATION
KI
onJuly26,2018http://science.sciencemag.org/Downloadedfrom
REVIEW https://doi.org/10.1038/s41586-018-0337-2
Machine learning for molecular and
materials science
Keith T. Butler1
, Daniel W. Davies2
, Hugh Cartwright3
, Olexandr Isayev4
* & Aron Walsh5,6
*
Here we summarize recent progress in machine learning for the chemical sciences. We outline machine-learning
techniques that are suitable for addressing research questions in this domain, as well as future directions for the field.
We envisage a future in which the design, synthesis, characterization and application of molecules and materials is
accelerated by artificial intelligence.
T
he Schrödinger equation provides a powerful structure–
property relationship for molecules and materials. For a given
spatial arrangement of chemical elements, the distribution of
electrons and a wide range of physical responses can be described. The
development of quantum mechanics provided a rigorous theoretical
foundationforthechemicalbond.In1929,PaulDiracfamouslyproclaimed
that the underlying physical laws for the whole of chemistry are “completely
known”1
. John Pople, realizing the importance of rapidly developing
computer technologies, created a program—Gaussian 70—that could
perform ab initio calculations: predicting the behaviour, for molecules
of modest size, purely from the fundamental laws of physics2
. In the 1960s,
the Quantum Chemistry Program Exchange brought quantum chemistry
to the masses in the form of useful practical tools3
. Suddenly, experi-
mentalists with little or no theoretical training could perform quantum
calculations too. Using modern algorithms and supercomputers,
systems containing thousands of interacting ions and electrons can now
be described using approximations to the physical laws that govern the
world on the atomic scale4–6
.
The field of computational chemistry has become increasingly pre-
dictive in the twenty-first century, with activity in applications as wide
ranging as catalyst development for greenhouse gas conversion, materials
discovery for energy harvesting and storage, and computer-assisted drug
design7
. The modern chemical-simulation toolkit allows the properties
of a compound to be anticipated (with reasonable accuracy) before it has
been made in the laboratory. High-throughput computational screening
has become routine, giving scientists the ability to calculate the properties
of thousands of compounds as part of a single study. In particular, den-
sity functional theory (DFT)8,9
, now a mature technique for calculating
the structure and behaviour of solids10
, has enabled the development of
extensive databases that cover the calculated properties of known and
hypothetical systems, including organic and inorganic crystals, single
molecules and metal alloys11–13
.
The emergence of contemporary artificial-intelligence methods has
the potential to substantially alter and enhance the role of computers in
science and engineering. The combination of big data and artificial intel-
ligence has been referred to as both the “fourth paradigm of science”14
and the “fourth industrial revolution”15
, and the number of applications
in the chemical domain is growing at an astounding rate. A subfield of
generating, testing and refining scientific models. Such techniques are
suitable for addressing complex problems that involve massive combi-
natorial spaces or nonlinear processes, which conventional procedures
either cannot solve or can tackle only at great computational cost.
As the machinery for artificial intelligence and machine learning
matures, important advances are being made not only by those in main-
stream artificial-intelligence research, but also by experts in other fields
(domain experts) who adopt these approaches for their own purposes. As
we detail in Box 1, the resources and tools that facilitate the application
of machine-learning techniques mean that the barrier to entry is lower
than ever.
In the rest of this Review, we discuss progress in the application of
machine learning to address challenges in molecular and materials
research. We review the basics of machine-learning approaches, iden-
tify areas in which existing methods have the potential to accelerate
research and consider the developments that are required to enable more
wide-ranging impacts.
Nuts and bolts of machine learning
With machine learning, given enough data and a rule-discovery algo-
rithm, a computer has the ability to determine all known physical laws
(and potentially those that are currently unknown) without human
input. In traditional computational approaches, the computer is little
more than a calculator, employing a hard-coded algorithm provided
by a human expert. By contrast, machine-learning approaches learn
the rules that underlie a dataset by assessing a portion of that data
and building a model to make predictions. We consider the basic steps
involved in the construction of a model, as illustrated in Fig. 1; this
constitutes a blueprint of the generic workflow that is required for the
successful application of machine learning in a materials-discovery
process.
Data collection
Machine learning comprises models that learn from existing (train-
ing) data. Data may require initial preprocessing, during which miss-
ing or spurious elements are identified and handled. For example, the
Inorganic Crystal Structure Database (ICSD) currently contains more
than 190,000 entries, which have been checked for technical mistakes
DNA to be sequences into distinct pieces,
parcel out the detailed work of sequencing,
and then reassemble these independent ef-
forts at the end. It is not quite so simple in the
world of genome semantics.
Despite the differences between genome se-
quencing and genetic network discovery, there
are clear parallels that are illustrated in Table 1.
In genome sequencing, a physical map is useful
to provide scaffolding for assembling the fin-
ished sequence. In the case of a genetic regula-
tory network, a graphical model can play the
same role. A graphical model can represent a
high-level view of interconnectivity and help
isolate modules that can be studied indepen-
dently. Like contigs in a genomic sequencing
project, low-level functional models can ex-
plore the detailed behavior of a module of genes
in a manner that is consistent with the higher
level graphical model of the system. With stan-
dardized nomenclature and compatible model-
ing techniques, independent functional models
can be assembled into a complete model of the
cell under study.
To enable this process, there will need to
be standardized forms for model representa-
tion. At present, there are many different
modeling technologies in use, and although
models can be easily placed into a database,
they are not useful out of the context of their
specific modeling package. The need for a
standardized way of communicating compu-
tational descriptions of biological systems ex-
tends to the literature. Entire conferences
have been established to explore ways of
mining the biology literature to extract se-
mantic information in computational form.
Going forward, as a community we need
to come to consensus on how to represent
what we know about biology in computa-
tional form as well as in words. The key to
postgenomic biology will be the computa-
tional assembly of our collective knowl-
edge into a cohesive picture of cellular and
organism function. With such a comprehen-
sive model, we will be able to explore new
types of conservation between organisms
and make great strides toward new thera-
peutics that function on well-characterized
pathways.
References
1. S. K. Kim et al., Science 293 , 2087 (2001).
2. A. Hartemink et al., paper presented at the Pacific
Symposium on Biocomputing 2000, Oahu, Hawaii, 4
to 9 January 2000.
3. D. Pe’er et al., paper presented at the 9th Conference
on Intelligent Systems in Molecular Biology (ISMB),
Copenhagen, Denmark, 21 to 25 July 2001.
4. H. McAdams, A. Arkin, Proc. Natl. Acad. Sci. U.S.A.
94 , 814 ( 1997 ).
5. A. J. Hartemink, thesis, Massachusetts Institute of
Technology, Cambridge (2001).
V I E W P O I N T
Machine Learning for Science: State of the
Art and Future Prospects
Eric Mjolsness* and Dennis DeCoste
Recent advances in machine learning methods, along with successful
applications across a wide variety of fields such as planetary science and
bioinformatics, promise powerful new tools for practicing scientists. This
viewpoint highlights some useful characteristics of modern machine learn-
ing methods and their relevance to scientific applications. We conclude
with some speculations on near-term progress and promising directions.
Machine learning (ML) (1) is the study of
computer algorithms capable of learning to im-
prove their performance of a task on the basis of
their own previous experience. The field is
closely related to pattern recognition and statis-
tical inference. As an engineering field, ML has
become steadily more mathematical and more
successful in applications over the past 20
years. Learning approaches such as data clus-
tering, neural network classifiers, and nonlinear
regression have found surprisingly wide appli-
cation in the practice of engineering, business,
and science. A generalized version of the stan-
dard Hidden Markov Models of ML practice
have been used for ab initio prediction of gene
structures in genomic DNA (2). The predictions
correlate surprisingly well with subsequent
gene expression analysis (3). Postgenomic bi-
ology prominently features large-scale gene ex-
pression data analyzed by clustering methods
(4), a standard topic in unsupervised learning.
Many other examples can be given of learning
and pattern recognition applications in science.
Where will this trend lead? We believe it will
lead to appropriate, partial automation of every
element of scientific method, from hypothesis
generation to model construction to decisive
experimentation. Thus, ML has the potential to
amplify every aspect of a working scientist’s
progress to understanding. It will also, for better
or worse, endow intelligent computer systems
with some of the general analytic power of
creating hypotheses, testing by decisive exper-
iment or observation, and iteratively building
up comprehensive testable models or theories is
shared across disciplines. For each stage of this
abstracted scientific process, there are relevant
developments in ML, statistical inference, and
pattern recognition that will lead to semiauto-
matic support tools of unknown but potentially
broad applicability.
Increasingly, the early elements of scientific
method—observation and hypothesis genera-
tion—face high data volumes, high data acqui-
sition rates, or requirements for objective anal-
ysis that cannot be handled by human percep-
tion alone. This has been the situation in exper-
imental particle physics for decades. There
automatic pattern recognition for significant
events is well developed, including Hough
transforms, which are foundational in pattern
recognition. A recent example is event analysis
for Cherenkov detectors (8) used in neutrino
oscillation experiments. Microscope imagery in
cell biology, pathology, petrology, and other
Table 1. Parallels between genome sequencing
and genetic network discovery.
Genome
sequencing
Genome semantics
Physical maps Graphical model
Contigs Low-level functional
models
Contig
reassembly
Module assembly
Finished genome
sequence
Comprehensive model
C O M P U T E R S A N D S C I E N C E
onAugust29,2018http://science.sciencemag.org/Downloadedfrom
Nature, 559

pp. 547–555 (2018)
Science, 293
pp. 2051-2055 (2001)
Science, 361
pp. 360-365 (2018)
Science is changing, the tools of science are changing. And that
requires different approaches. Erich Bloch, 1925-2016
Machine Learning
Machine learning is a way to construct a computer program
directly by a given (large) collection of input-output examples
without being explicitly programmed.
Generic Object Recognition
Speech Recognition
Machine Translation
Super-Resolution Imaging
AI Game Players
“감사”
J’aime la
musique I love music
My Research Interest: ML with Discrete Structures
Tree/DAG Ensemble Neural Nets/Deep Learning Probabilistic Programming
• Target data themselves have discrete structures
• ML models have discrete structures or constraints
• Variables have structural dependencies or constraints
H
H
H
H
H
H
H
H
O
N
O
O
H
H
H
O
O
H
H
N
O
O
Cl
ClCl
Sets, Sequences, Combinations, Permutations, Branching Chains (Trees), Networks (Graphs), …
Molecular Machine Learning
MoleculeNet: A Benchmark for Molecular Machine Learning

https://arxiv.org/abs/1703.00564

https://github.com/deepchem/deepchem (https://deepchem.io/)
CH3
N
H3C
H
NS
N
O
CH3
N
OH
x
molecule property value
ˆy
ˆy = f✓(x)
Quantitative structure–activity/property relationship (QSAR/QSPR)
Many levels of interest
• Mutagenic potency
• Carcinogenic potency
• Endocrine disruption
• Growth inhibition
• Aqueous solubility
N
NH
OO
HH
H
H H
H
H
H
H
H
H
H
H
H
H
H
H
H
H
H
H
H
H
H
H
O
O
O
O
O
O
Cl
H
H
H
H
H
HH
H
H
H
H
H
H
H
H
H
H
Br
Br O P
O
O Br
Br
O
Br
Br
H
H
H
H
H
H
H
H
H
H
HH
H
HH
N
S
N
N
H
H
H
H
H
H
H
H
H
H
H
H
H
H
H
O
N
O
O
H
H
H
O
O
H
H
N
O
O
Cl
ClCl
H
H
H
H
H
H H
N
O
O
H
H
H
H
H
H
H H
H
N
O
O
H
H
H
H
H
H
H
N
H
N
O
O
N
O
O
H
H
H
H
H
H
H
H
N
CH3
O
O
H
N Cl
Cl
Cl
Cl
Cl
H3C
O O
O
O
O
O
H3C
CH3
CH2
O
HN
O
O
NH
CH3
HO
OH
CH3
N
O
O
CH3
N
N
H
N
H
H3C
N
H3C
H3C
NH
O
N
O
NO
CH3
O N
NH2
O
CH3
Br
CH3
N
H3C
H
NS
N
O
CH3
N
OH
CH3
CH3N
N
N
CH3H3C
H2N NH2
H
OH
O
HO
CH3
H
H
O
CH3
H
O
OH3C HH
H
O
H3C
S
CH3
O
H
H
O
CH3
CH3
OO
HO
H3CH
HO
F
H
O
H3C
NH2
O
N
HO
HO
O
H
H
O
O
OH3C
O
O
O
CH3
O
CH3
HO
CH3
H
O
O
CH3
H
H
N
H
N O
H3C
O
O
O
ML Surrogates for Quantum Chemistry
http://quantum-machine.org/datasets/
Quantum chemistry structures and properties of 134 kilo molecules, Scientific Data 1, 140022 (2014)
Dataset: structure-properties pairs in the ground state 

for all 133,885 compounds with up to 9 heavy atoms of C, O, N, or F
DFT
B3LYP/6-31G(2df,p)
Structure in
the ground state
15 properties in
the ground state
http://www.nature.com/articles/sdata201422
Inverse Design (Machine Teaching)
“machine teaching”
“machine learning”
Bayesian optimization / Black-box optimization / Sequential
design of experiments / Surrogate-based optimization
“television”
Beware: Inverse is not unique??
CH3
N
H3C
H
NS
N
O
CH3
N
OH
x
molecule property value
ˆy
ˆy = f✓(x)
A lot of technical challenges, pitfalls, and potentials
Towards (Semi-)Automated Sciences?
✗
ML for Heterogeneous Catalysis
Chemical Reaction
Catalysts
Heterogeneous catalysts / Surface reactions
Haber–Bosch Process
Ferrous metal Catalysis Noble Metal Catalysis (Pt, Pd, Rh…) Various Metallic Catalysts

(Li, rare earthes, alkaline earths)
(industrial synthesis of ammonia)
Exhaust Gas Purification Conversion of Methane
“Fertilizer from Air”
artificial nitrogen fixation
ML for Heterogeneous Catalysis
Catalyst Informatics
Large Literature Data
(in prep)
Quantum Calculated Data
(RCS Adv 2016; JPCC 2018)
Data from Controlled
Experiments (plan)
ACS 2018 [CATL] 

Machine Learning for Catalysis Research
ML for Chemical Reaction Design & Discovery
Institute for Chemical Reaction Design and Discovery (WPI-ICReDD), HU
We’ll start international hiring!!
Computational Science
Explores Quantum Chemically
Possible Reaction Paths
Information Science
Uses Various Data and Known
Information to Prioritize Paths
Experimental Science
Realizes & Validates Reactions in
Various Application Domains
The AFIR
method
2018 Oct 23-
HU 10 year project got funded
Machine Learning for Chemical Sciences
• Some words by David Hand at KDD2018@London:
• Theory-driven models can be wrong
• But data-driven models cannot be wrong or even right. 😩
• Data-driven are not trying to describe an underlying reality.
• But are merely intended to be useful. 😆
• So they could be poor or useless, but not wrong
• We need to understand the data, the models, the algorithms.
• We need to collaborate with domain experts because many
different conclusions are always possible from finite data.
Thanks for many nice people around me

Más contenido relacionado

La actualidad más candente

AdS Biology and Quantum Information Science
AdS Biology and Quantum Information ScienceAdS Biology and Quantum Information Science
AdS Biology and Quantum Information ScienceMelanie Swan
 
Graphs, Environments, and Machine Learning for Materials Science
Graphs, Environments, and Machine Learning for Materials ScienceGraphs, Environments, and Machine Learning for Materials Science
Graphs, Environments, and Machine Learning for Materials Scienceaimsnist
 
Continual Learning with Deep Architectures - Tutorial ICML 2021
Continual Learning with Deep Architectures - Tutorial ICML 2021Continual Learning with Deep Architectures - Tutorial ICML 2021
Continual Learning with Deep Architectures - Tutorial ICML 2021Vincenzo Lomonaco
 
Overview of Machine Learning for Molecules and Materials Workshop @ NIPS2017
Overview of Machine Learning for Molecules and Materials Workshop @ NIPS2017Overview of Machine Learning for Molecules and Materials Workshop @ NIPS2017
Overview of Machine Learning for Molecules and Materials Workshop @ NIPS2017Kenta Oono
 
“Materials Informatics and Big Data: Realization of 4th Paradigm of Science i...
“Materials Informatics and Big Data: Realization of 4th Paradigm of Science i...“Materials Informatics and Big Data: Realization of 4th Paradigm of Science i...
“Materials Informatics and Big Data: Realization of 4th Paradigm of Science i...aimsnist
 
Machine Learning and Reasoning for Drug Discovery
Machine Learning and Reasoning for Drug DiscoveryMachine Learning and Reasoning for Drug Discovery
Machine Learning and Reasoning for Drug DiscoveryDeakin University
 
Privacy preserving machine learning
Privacy preserving machine learningPrivacy preserving machine learning
Privacy preserving machine learningMichał Kuźba
 
Machine Learning
Machine LearningMachine Learning
Machine LearningVivek Garg
 
Squeezing Deep Learning Into Mobile Phones
Squeezing Deep Learning Into Mobile PhonesSqueezing Deep Learning Into Mobile Phones
Squeezing Deep Learning Into Mobile PhonesAnirudh Koul
 
Machine Learning and Applications
Machine Learning and ApplicationsMachine Learning and Applications
Machine Learning and ApplicationsGeeta Arora
 
COMSOL Multiphysics: Simulation and Development Toolbox for Clusters
COMSOL Multiphysics: Simulation and Development Toolbox for ClustersCOMSOL Multiphysics: Simulation and Development Toolbox for Clusters
COMSOL Multiphysics: Simulation and Development Toolbox for ClustersIntel IT Center
 
Surface modification techniques in biomedical sector
Surface modification techniques in biomedical sector Surface modification techniques in biomedical sector
Surface modification techniques in biomedical sector Sum K
 
Lecture: Interatomic Potentials Enabled by Machine Learning
Lecture: Interatomic Potentials Enabled by Machine LearningLecture: Interatomic Potentials Enabled by Machine Learning
Lecture: Interatomic Potentials Enabled by Machine LearningDanielSchwalbeKoda
 
ETE444-lec5-micro-fabrication.pptx
ETE444-lec5-micro-fabrication.pptxETE444-lec5-micro-fabrication.pptx
ETE444-lec5-micro-fabrication.pptxmashiur
 
Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Present...
Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Present...Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Present...
Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Present...SlideTeam
 
AI for Manufacturing (Machine Vision, Edge AI, Federated Learning)
AI for Manufacturing (Machine Vision, Edge AI, Federated Learning)AI for Manufacturing (Machine Vision, Edge AI, Federated Learning)
AI for Manufacturing (Machine Vision, Edge AI, Federated Learning)byteLAKE
 
The Role of Artificial Intelligence in Manufacturing : 15 High Impacted AI Us...
The Role of Artificial Intelligence in Manufacturing : 15 High Impacted AI Us...The Role of Artificial Intelligence in Manufacturing : 15 High Impacted AI Us...
The Role of Artificial Intelligence in Manufacturing : 15 High Impacted AI Us...CANOPY ONE SOLUTIONS
 
Deep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & FutureDeep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & FutureRouyun Pan
 
Quantum Computing and AI
Quantum Computing and AIQuantum Computing and AI
Quantum Computing and AIAhmed Banafa
 
Artificial intelligence and its application
Artificial intelligence and its applicationArtificial intelligence and its application
Artificial intelligence and its applicationMohammed Abdel Razek
 

La actualidad más candente (20)

AdS Biology and Quantum Information Science
AdS Biology and Quantum Information ScienceAdS Biology and Quantum Information Science
AdS Biology and Quantum Information Science
 
Graphs, Environments, and Machine Learning for Materials Science
Graphs, Environments, and Machine Learning for Materials ScienceGraphs, Environments, and Machine Learning for Materials Science
Graphs, Environments, and Machine Learning for Materials Science
 
Continual Learning with Deep Architectures - Tutorial ICML 2021
Continual Learning with Deep Architectures - Tutorial ICML 2021Continual Learning with Deep Architectures - Tutorial ICML 2021
Continual Learning with Deep Architectures - Tutorial ICML 2021
 
Overview of Machine Learning for Molecules and Materials Workshop @ NIPS2017
Overview of Machine Learning for Molecules and Materials Workshop @ NIPS2017Overview of Machine Learning for Molecules and Materials Workshop @ NIPS2017
Overview of Machine Learning for Molecules and Materials Workshop @ NIPS2017
 
“Materials Informatics and Big Data: Realization of 4th Paradigm of Science i...
“Materials Informatics and Big Data: Realization of 4th Paradigm of Science i...“Materials Informatics and Big Data: Realization of 4th Paradigm of Science i...
“Materials Informatics and Big Data: Realization of 4th Paradigm of Science i...
 
Machine Learning and Reasoning for Drug Discovery
Machine Learning and Reasoning for Drug DiscoveryMachine Learning and Reasoning for Drug Discovery
Machine Learning and Reasoning for Drug Discovery
 
Privacy preserving machine learning
Privacy preserving machine learningPrivacy preserving machine learning
Privacy preserving machine learning
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 
Squeezing Deep Learning Into Mobile Phones
Squeezing Deep Learning Into Mobile PhonesSqueezing Deep Learning Into Mobile Phones
Squeezing Deep Learning Into Mobile Phones
 
Machine Learning and Applications
Machine Learning and ApplicationsMachine Learning and Applications
Machine Learning and Applications
 
COMSOL Multiphysics: Simulation and Development Toolbox for Clusters
COMSOL Multiphysics: Simulation and Development Toolbox for ClustersCOMSOL Multiphysics: Simulation and Development Toolbox for Clusters
COMSOL Multiphysics: Simulation and Development Toolbox for Clusters
 
Surface modification techniques in biomedical sector
Surface modification techniques in biomedical sector Surface modification techniques in biomedical sector
Surface modification techniques in biomedical sector
 
Lecture: Interatomic Potentials Enabled by Machine Learning
Lecture: Interatomic Potentials Enabled by Machine LearningLecture: Interatomic Potentials Enabled by Machine Learning
Lecture: Interatomic Potentials Enabled by Machine Learning
 
ETE444-lec5-micro-fabrication.pptx
ETE444-lec5-micro-fabrication.pptxETE444-lec5-micro-fabrication.pptx
ETE444-lec5-micro-fabrication.pptx
 
Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Present...
Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Present...Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Present...
Artificial Intelligence Machine Learning Deep Learning PPT PowerPoint Present...
 
AI for Manufacturing (Machine Vision, Edge AI, Federated Learning)
AI for Manufacturing (Machine Vision, Edge AI, Federated Learning)AI for Manufacturing (Machine Vision, Edge AI, Federated Learning)
AI for Manufacturing (Machine Vision, Edge AI, Federated Learning)
 
The Role of Artificial Intelligence in Manufacturing : 15 High Impacted AI Us...
The Role of Artificial Intelligence in Manufacturing : 15 High Impacted AI Us...The Role of Artificial Intelligence in Manufacturing : 15 High Impacted AI Us...
The Role of Artificial Intelligence in Manufacturing : 15 High Impacted AI Us...
 
Deep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & FutureDeep Learning Hardware: Past, Present, & Future
Deep Learning Hardware: Past, Present, & Future
 
Quantum Computing and AI
Quantum Computing and AIQuantum Computing and AI
Quantum Computing and AI
 
Artificial intelligence and its application
Artificial intelligence and its applicationArtificial intelligence and its application
Artificial intelligence and its application
 

Similar a Machine Learning for Chemical Sciences

(2019.9) 不均一系触媒研究のための機械学習と最適実験計画
(2019.9) 不均一系触媒研究のための機械学習と最適実験計画(2019.9) 不均一系触媒研究のための機械学習と最適実験計画
(2019.9) 不均一系触媒研究のための機械学習と最適実験計画Ichigaku Takigawa
 
(2018.9) 分子のグラフ表現と機械学習
(2018.9) 分子のグラフ表現と機械学習(2018.9) 分子のグラフ表現と機械学習
(2018.9) 分子のグラフ表現と機械学習Ichigaku Takigawa
 
The interplay between data-driven and theory-driven methods for chemical scie...
The interplay between data-driven and theory-driven methods for chemical scie...The interplay between data-driven and theory-driven methods for chemical scie...
The interplay between data-driven and theory-driven methods for chemical scie...Ichigaku Takigawa
 
Future Directions in Chemical Engineering and Bioengineering
Future Directions in Chemical Engineering and BioengineeringFuture Directions in Chemical Engineering and Bioengineering
Future Directions in Chemical Engineering and BioengineeringIlya Klabukov
 
Nazeeruddin-2016-ChemSusChem
Nazeeruddin-2016-ChemSusChemNazeeruddin-2016-ChemSusChem
Nazeeruddin-2016-ChemSusChemMd. Nazeeruddin
 
Bio-cryptoeconomy: Smart Contract Blockchain-based Bio-Nano Repair DACs
Bio-cryptoeconomy: Smart Contract Blockchain-based Bio-Nano Repair DACsBio-cryptoeconomy: Smart Contract Blockchain-based Bio-Nano Repair DACs
Bio-cryptoeconomy: Smart Contract Blockchain-based Bio-Nano Repair DACsMelanie Swan
 
Nature-inspired Solutions for Engineering: A Transformative Methodology for I...
Nature-inspired Solutions for Engineering: A Transformative Methodology for I...Nature-inspired Solutions for Engineering: A Transformative Methodology for I...
Nature-inspired Solutions for Engineering: A Transformative Methodology for I...KTN
 
Saint Louis University Research Cluster Grant Competition Whitepaper by Silic...
Saint Louis University Research Cluster Grant Competition Whitepaper by Silic...Saint Louis University Research Cluster Grant Competition Whitepaper by Silic...
Saint Louis University Research Cluster Grant Competition Whitepaper by Silic...waltermoss123
 
Chemistry Reserach as a Social Machine
 Chemistry Reserach as a Social Machine Chemistry Reserach as a Social Machine
Chemistry Reserach as a Social MachineJeremy Frey
 
AI at Scale for Materials and Chemistry
AI at Scale for Materials and ChemistryAI at Scale for Materials and Chemistry
AI at Scale for Materials and ChemistryIan Foster
 
Grandchallengesinchemicalengineering
GrandchallengesinchemicalengineeringGrandchallengesinchemicalengineering
GrandchallengesinchemicalengineeringKiros Hagos
 
kakkar2021.pdf
kakkar2021.pdfkakkar2021.pdf
kakkar2021.pdfkaritoIsa2
 
The physics behind systems biology
The physics behind systems biologyThe physics behind systems biology
The physics behind systems biologyImam Rosadi
 
Applications of Computer Science in Environmental Models
Applications of Computer Science in Environmental ModelsApplications of Computer Science in Environmental Models
Applications of Computer Science in Environmental ModelsIJLT EMAS
 
諾貝爾化學獎揭曉 3學者共享榮耀
諾貝爾化學獎揭曉 3學者共享榮耀諾貝爾化學獎揭曉 3學者共享榮耀
諾貝爾化學獎揭曉 3學者共享榮耀中 央社
 
(Fuel Cells and Hydrogen Energy) Roberto Bove, S. Ubertini-Modeling solid oxi...
(Fuel Cells and Hydrogen Energy) Roberto Bove, S. Ubertini-Modeling solid oxi...(Fuel Cells and Hydrogen Energy) Roberto Bove, S. Ubertini-Modeling solid oxi...
(Fuel Cells and Hydrogen Energy) Roberto Bove, S. Ubertini-Modeling solid oxi...ZeenathulFaridaAbdul1
 

Similar a Machine Learning for Chemical Sciences (20)

(2019.9) 不均一系触媒研究のための機械学習と最適実験計画
(2019.9) 不均一系触媒研究のための機械学習と最適実験計画(2019.9) 不均一系触媒研究のための機械学習と最適実験計画
(2019.9) 不均一系触媒研究のための機械学習と最適実験計画
 
(2018.9) 分子のグラフ表現と機械学習
(2018.9) 分子のグラフ表現と機械学習(2018.9) 分子のグラフ表現と機械学習
(2018.9) 分子のグラフ表現と機械学習
 
The interplay between data-driven and theory-driven methods for chemical scie...
The interplay between data-driven and theory-driven methods for chemical scie...The interplay between data-driven and theory-driven methods for chemical scie...
The interplay between data-driven and theory-driven methods for chemical scie...
 
Future Directions in Chemical Engineering and Bioengineering
Future Directions in Chemical Engineering and BioengineeringFuture Directions in Chemical Engineering and Bioengineering
Future Directions in Chemical Engineering and Bioengineering
 
Nazeeruddin-2016-ChemSusChem
Nazeeruddin-2016-ChemSusChemNazeeruddin-2016-ChemSusChem
Nazeeruddin-2016-ChemSusChem
 
Bio-cryptoeconomy: Smart Contract Blockchain-based Bio-Nano Repair DACs
Bio-cryptoeconomy: Smart Contract Blockchain-based Bio-Nano Repair DACsBio-cryptoeconomy: Smart Contract Blockchain-based Bio-Nano Repair DACs
Bio-cryptoeconomy: Smart Contract Blockchain-based Bio-Nano Repair DACs
 
Nature-inspired Solutions for Engineering: A Transformative Methodology for I...
Nature-inspired Solutions for Engineering: A Transformative Methodology for I...Nature-inspired Solutions for Engineering: A Transformative Methodology for I...
Nature-inspired Solutions for Engineering: A Transformative Methodology for I...
 
Saint Louis University Research Cluster Grant Competition Whitepaper by Silic...
Saint Louis University Research Cluster Grant Competition Whitepaper by Silic...Saint Louis University Research Cluster Grant Competition Whitepaper by Silic...
Saint Louis University Research Cluster Grant Competition Whitepaper by Silic...
 
Chemistry Reserach as a Social Machine
 Chemistry Reserach as a Social Machine Chemistry Reserach as a Social Machine
Chemistry Reserach as a Social Machine
 
AI at Scale for Materials and Chemistry
AI at Scale for Materials and ChemistryAI at Scale for Materials and Chemistry
AI at Scale for Materials and Chemistry
 
Retrosynth
RetrosynthRetrosynth
Retrosynth
 
STUDY OF NANO-SYSTEMS FOR COMPUTER SIMULATIONS
STUDY OF NANO-SYSTEMS FOR COMPUTER SIMULATIONSSTUDY OF NANO-SYSTEMS FOR COMPUTER SIMULATIONS
STUDY OF NANO-SYSTEMS FOR COMPUTER SIMULATIONS
 
Grandchallengesinchemicalengineering
GrandchallengesinchemicalengineeringGrandchallengesinchemicalengineering
Grandchallengesinchemicalengineering
 
kakkar2021.pdf
kakkar2021.pdfkakkar2021.pdf
kakkar2021.pdf
 
The physics behind systems biology
The physics behind systems biologyThe physics behind systems biology
The physics behind systems biology
 
nanotechnology
nanotechnologynanotechnology
nanotechnology
 
Applications of Computer Science in Environmental Models
Applications of Computer Science in Environmental ModelsApplications of Computer Science in Environmental Models
Applications of Computer Science in Environmental Models
 
諾貝爾化學獎揭曉 3學者共享榮耀
諾貝爾化學獎揭曉 3學者共享榮耀諾貝爾化學獎揭曉 3學者共享榮耀
諾貝爾化學獎揭曉 3學者共享榮耀
 
(Fuel Cells and Hydrogen Energy) Roberto Bove, S. Ubertini-Modeling solid oxi...
(Fuel Cells and Hydrogen Energy) Roberto Bove, S. Ubertini-Modeling solid oxi...(Fuel Cells and Hydrogen Energy) Roberto Bove, S. Ubertini-Modeling solid oxi...
(Fuel Cells and Hydrogen Energy) Roberto Bove, S. Ubertini-Modeling solid oxi...
 
Structural revisions of natural products by computer assisted structure eluci...
Structural revisions of natural products by computer assisted structure eluci...Structural revisions of natural products by computer assisted structure eluci...
Structural revisions of natural products by computer assisted structure eluci...
 

Más de Ichigaku Takigawa

データ社会を生きる技術
〜機械学習の夢と現実〜
データ社会を生きる技術
〜機械学習の夢と現実〜データ社会を生きる技術
〜機械学習の夢と現実〜
データ社会を生きる技術
〜機械学習の夢と現実〜Ichigaku Takigawa
 
機械学習を科学研究で使うとは?
機械学習を科学研究で使うとは?機械学習を科学研究で使うとは?
機械学習を科学研究で使うとは?Ichigaku Takigawa
 
A Modern Introduction to Decision Tree Ensembles
A Modern Introduction to Decision Tree EnsemblesA Modern Introduction to Decision Tree Ensembles
A Modern Introduction to Decision Tree EnsemblesIchigaku Takigawa
 
Exploring Practices in Machine Learning and Machine Discovery for Heterogeneo...
Exploring Practices in Machine Learning and Machine Discovery for Heterogeneo...Exploring Practices in Machine Learning and Machine Discovery for Heterogeneo...
Exploring Practices in Machine Learning and Machine Discovery for Heterogeneo...Ichigaku Takigawa
 
機械学習と機械発見:自然科学融合が誘起するデータ科学の新展開
機械学習と機械発見:自然科学融合が誘起するデータ科学の新展開機械学習と機械発見:自然科学融合が誘起するデータ科学の新展開
機械学習と機械発見:自然科学融合が誘起するデータ科学の新展開Ichigaku Takigawa
 
機械学習と機械発見:自然科学研究におけるデータ利活用の再考
機械学習と機械発見:自然科学研究におけるデータ利活用の再考機械学習と機械発見:自然科学研究におけるデータ利活用の再考
機械学習と機械発見:自然科学研究におけるデータ利活用の再考Ichigaku Takigawa
 
小1にルービックキューブを教えてみた 〜群論スポーツの教育とパターン認知〜
小1にルービックキューブを教えてみた 〜群論スポーツの教育とパターン認知〜小1にルービックキューブを教えてみた 〜群論スポーツの教育とパターン認知〜
小1にルービックキューブを教えてみた 〜群論スポーツの教育とパターン認知〜Ichigaku Takigawa
 
"データ化"する化学と情報技術・人工知能・データサイエンス
"データ化"する化学と情報技術・人工知能・データサイエンス"データ化"する化学と情報技術・人工知能・データサイエンス
"データ化"する化学と情報技術・人工知能・データサイエンスIchigaku Takigawa
 
自然科学における機械学習と機械発見
自然科学における機械学習と機械発見自然科学における機械学習と機械発見
自然科学における機械学習と機械発見Ichigaku Takigawa
 
幾何と機械学習: A Short Intro
幾何と機械学習: A Short Intro幾何と機械学習: A Short Intro
幾何と機械学習: A Short IntroIchigaku Takigawa
 
決定森回帰の信頼区間推定, Benign Overfitting, 多変量木とReLUネットの入力空間分割
決定森回帰の信頼区間推定, Benign Overfitting, 多変量木とReLUネットの入力空間分割決定森回帰の信頼区間推定, Benign Overfitting, 多変量木とReLUネットの入力空間分割
決定森回帰の信頼区間推定, Benign Overfitting, 多変量木とReLUネットの入力空間分割Ichigaku Takigawa
 
機械学習を自然現象の理解・発見に使いたい人に知っておいてほしいこと
機械学習を自然現象の理解・発見に使いたい人に知っておいてほしいこと機械学習を自然現象の理解・発見に使いたい人に知っておいてほしいこと
機械学習を自然現象の理解・発見に使いたい人に知っておいてほしいことIchigaku Takigawa
 
自己紹介:機械学習・機械発見とデータ中心的自然科学
自己紹介:機械学習・機械発見とデータ中心的自然科学自己紹介:機械学習・機械発見とデータ中心的自然科学
自己紹介:機械学習・機械発見とデータ中心的自然科学Ichigaku Takigawa
 
機械学習・機械発見から見るデータ中心型化学の野望と憂鬱
機械学習・機械発見から見るデータ中心型化学の野望と憂鬱機械学習・機械発見から見るデータ中心型化学の野望と憂鬱
機械学習・機械発見から見るデータ中心型化学の野望と憂鬱Ichigaku Takigawa
 
Machine Learning for Molecular Graph Representations and Geometries
Machine Learning for Molecular Graph Representations and GeometriesMachine Learning for Molecular Graph Representations and Geometries
Machine Learning for Molecular Graph Representations and GeometriesIchigaku Takigawa
 
(2021.11) 機械学習と機械発見:データ中心型の化学・材料科学の教訓とこれから
(2021.11) 機械学習と機械発見:データ中心型の化学・材料科学の教訓とこれから(2021.11) 機械学習と機械発見:データ中心型の化学・材料科学の教訓とこれから
(2021.11) 機械学習と機械発見:データ中心型の化学・材料科学の教訓とこれからIchigaku Takigawa
 
機械学習~データを予測に変える技術~で化学に挑む! (サイエンスアゴラ2021)
機械学習~データを予測に変える技術~で化学に挑む! (サイエンスアゴラ2021)機械学習~データを予測に変える技術~で化学に挑む! (サイエンスアゴラ2021)
機械学習~データを予測に変える技術~で化学に挑む! (サイエンスアゴラ2021)Ichigaku Takigawa
 
(2021.10) 機械学習と機械発見 データ中心型の化学・材料科学の教訓とこれから
(2021.10) 機械学習と機械発見 データ中心型の化学・材料科学の教訓とこれから (2021.10) 機械学習と機械発見 データ中心型の化学・材料科学の教訓とこれから
(2021.10) 機械学習と機械発見 データ中心型の化学・材料科学の教訓とこれから Ichigaku Takigawa
 
帰納バイアスと分子の組合せ的表現・幾何的表現 (本発表)
帰納バイアスと分子の組合せ的表現・幾何的表現 (本発表)帰納バイアスと分子の組合せ的表現・幾何的表現 (本発表)
帰納バイアスと分子の組合せ的表現・幾何的表現 (本発表)Ichigaku Takigawa
 

Más de Ichigaku Takigawa (20)

機械学習と自動微分
機械学習と自動微分機械学習と自動微分
機械学習と自動微分
 
データ社会を生きる技術
〜機械学習の夢と現実〜
データ社会を生きる技術
〜機械学習の夢と現実〜データ社会を生きる技術
〜機械学習の夢と現実〜
データ社会を生きる技術
〜機械学習の夢と現実〜
 
機械学習を科学研究で使うとは?
機械学習を科学研究で使うとは?機械学習を科学研究で使うとは?
機械学習を科学研究で使うとは?
 
A Modern Introduction to Decision Tree Ensembles
A Modern Introduction to Decision Tree EnsemblesA Modern Introduction to Decision Tree Ensembles
A Modern Introduction to Decision Tree Ensembles
 
Exploring Practices in Machine Learning and Machine Discovery for Heterogeneo...
Exploring Practices in Machine Learning and Machine Discovery for Heterogeneo...Exploring Practices in Machine Learning and Machine Discovery for Heterogeneo...
Exploring Practices in Machine Learning and Machine Discovery for Heterogeneo...
 
機械学習と機械発見:自然科学融合が誘起するデータ科学の新展開
機械学習と機械発見:自然科学融合が誘起するデータ科学の新展開機械学習と機械発見:自然科学融合が誘起するデータ科学の新展開
機械学習と機械発見:自然科学融合が誘起するデータ科学の新展開
 
機械学習と機械発見:自然科学研究におけるデータ利活用の再考
機械学習と機械発見:自然科学研究におけるデータ利活用の再考機械学習と機械発見:自然科学研究におけるデータ利活用の再考
機械学習と機械発見:自然科学研究におけるデータ利活用の再考
 
小1にルービックキューブを教えてみた 〜群論スポーツの教育とパターン認知〜
小1にルービックキューブを教えてみた 〜群論スポーツの教育とパターン認知〜小1にルービックキューブを教えてみた 〜群論スポーツの教育とパターン認知〜
小1にルービックキューブを教えてみた 〜群論スポーツの教育とパターン認知〜
 
"データ化"する化学と情報技術・人工知能・データサイエンス
"データ化"する化学と情報技術・人工知能・データサイエンス"データ化"する化学と情報技術・人工知能・データサイエンス
"データ化"する化学と情報技術・人工知能・データサイエンス
 
自然科学における機械学習と機械発見
自然科学における機械学習と機械発見自然科学における機械学習と機械発見
自然科学における機械学習と機械発見
 
幾何と機械学習: A Short Intro
幾何と機械学習: A Short Intro幾何と機械学習: A Short Intro
幾何と機械学習: A Short Intro
 
決定森回帰の信頼区間推定, Benign Overfitting, 多変量木とReLUネットの入力空間分割
決定森回帰の信頼区間推定, Benign Overfitting, 多変量木とReLUネットの入力空間分割決定森回帰の信頼区間推定, Benign Overfitting, 多変量木とReLUネットの入力空間分割
決定森回帰の信頼区間推定, Benign Overfitting, 多変量木とReLUネットの入力空間分割
 
機械学習を自然現象の理解・発見に使いたい人に知っておいてほしいこと
機械学習を自然現象の理解・発見に使いたい人に知っておいてほしいこと機械学習を自然現象の理解・発見に使いたい人に知っておいてほしいこと
機械学習を自然現象の理解・発見に使いたい人に知っておいてほしいこと
 
自己紹介:機械学習・機械発見とデータ中心的自然科学
自己紹介:機械学習・機械発見とデータ中心的自然科学自己紹介:機械学習・機械発見とデータ中心的自然科学
自己紹介:機械学習・機械発見とデータ中心的自然科学
 
機械学習・機械発見から見るデータ中心型化学の野望と憂鬱
機械学習・機械発見から見るデータ中心型化学の野望と憂鬱機械学習・機械発見から見るデータ中心型化学の野望と憂鬱
機械学習・機械発見から見るデータ中心型化学の野望と憂鬱
 
Machine Learning for Molecular Graph Representations and Geometries
Machine Learning for Molecular Graph Representations and GeometriesMachine Learning for Molecular Graph Representations and Geometries
Machine Learning for Molecular Graph Representations and Geometries
 
(2021.11) 機械学習と機械発見:データ中心型の化学・材料科学の教訓とこれから
(2021.11) 機械学習と機械発見:データ中心型の化学・材料科学の教訓とこれから(2021.11) 機械学習と機械発見:データ中心型の化学・材料科学の教訓とこれから
(2021.11) 機械学習と機械発見:データ中心型の化学・材料科学の教訓とこれから
 
機械学習~データを予測に変える技術~で化学に挑む! (サイエンスアゴラ2021)
機械学習~データを予測に変える技術~で化学に挑む! (サイエンスアゴラ2021)機械学習~データを予測に変える技術~で化学に挑む! (サイエンスアゴラ2021)
機械学習~データを予測に変える技術~で化学に挑む! (サイエンスアゴラ2021)
 
(2021.10) 機械学習と機械発見 データ中心型の化学・材料科学の教訓とこれから
(2021.10) 機械学習と機械発見 データ中心型の化学・材料科学の教訓とこれから (2021.10) 機械学習と機械発見 データ中心型の化学・材料科学の教訓とこれから
(2021.10) 機械学習と機械発見 データ中心型の化学・材料科学の教訓とこれから
 
帰納バイアスと分子の組合せ的表現・幾何的表現 (本発表)
帰納バイアスと分子の組合せ的表現・幾何的表現 (本発表)帰納バイアスと分子の組合せ的表現・幾何的表現 (本発表)
帰納バイアスと分子の組合せ的表現・幾何的表現 (本発表)
 

Último

Principles & Formulation of Hair Care Products
Principles & Formulation of Hair Care  ProductsPrinciples & Formulation of Hair Care  Products
Principles & Formulation of Hair Care Productspurwaborkar@gmail.com
 
Bureau of Indian Standards Specification of Shampoo.pptx
Bureau of Indian Standards Specification of Shampoo.pptxBureau of Indian Standards Specification of Shampoo.pptx
Bureau of Indian Standards Specification of Shampoo.pptxkastureyashashree
 
biosynthesis of the cell wall and antibiotics
biosynthesis of the cell wall and antibioticsbiosynthesis of the cell wall and antibiotics
biosynthesis of the cell wall and antibioticsSafaFallah
 
Pests of cumbu_Identification, Binomics, Integrated ManagementDr.UPR.pdf
Pests of cumbu_Identification, Binomics, Integrated ManagementDr.UPR.pdfPests of cumbu_Identification, Binomics, Integrated ManagementDr.UPR.pdf
Pests of cumbu_Identification, Binomics, Integrated ManagementDr.UPR.pdfPirithiRaju
 
Role of herbs in hair care Amla and heena.pptx
Role of herbs in hair care  Amla and  heena.pptxRole of herbs in hair care  Amla and  heena.pptx
Role of herbs in hair care Amla and heena.pptxVaishnaviAware
 
Lehninger_Chapter 17_Fatty acid Oxid.ppt
Lehninger_Chapter 17_Fatty acid Oxid.pptLehninger_Chapter 17_Fatty acid Oxid.ppt
Lehninger_Chapter 17_Fatty acid Oxid.pptSachin Teotia
 
Contracts with Interdependent Preferences (2)
Contracts with Interdependent Preferences (2)Contracts with Interdependent Preferences (2)
Contracts with Interdependent Preferences (2)GRAPE
 
Legacy Analysis of Dark Matter Annihilation from the Milky Way Dwarf Spheroid...
Legacy Analysis of Dark Matter Annihilation from the Milky Way Dwarf Spheroid...Legacy Analysis of Dark Matter Annihilation from the Milky Way Dwarf Spheroid...
Legacy Analysis of Dark Matter Annihilation from the Milky Way Dwarf Spheroid...Sérgio Sacani
 
001 Case Study - Submission Point_c1051231_attempt_2023-11-23-14-08-42_ABS CW...
001 Case Study - Submission Point_c1051231_attempt_2023-11-23-14-08-42_ABS CW...001 Case Study - Submission Point_c1051231_attempt_2023-11-23-14-08-42_ABS CW...
001 Case Study - Submission Point_c1051231_attempt_2023-11-23-14-08-42_ABS CW...marwaahmad357
 
Pests of tenai_Identification,Binomics_Dr.UPR
Pests of tenai_Identification,Binomics_Dr.UPRPests of tenai_Identification,Binomics_Dr.UPR
Pests of tenai_Identification,Binomics_Dr.UPRPirithiRaju
 
Pests of wheat_Identification, Bionomics, Damage symptoms, IPM_Dr.UPR.pdf
Pests of wheat_Identification, Bionomics, Damage symptoms, IPM_Dr.UPR.pdfPests of wheat_Identification, Bionomics, Damage symptoms, IPM_Dr.UPR.pdf
Pests of wheat_Identification, Bionomics, Damage symptoms, IPM_Dr.UPR.pdfPirithiRaju
 
Krishi Vigyan Kendras - कृषि विज्ञान केंद्र
Krishi Vigyan Kendras - कृषि विज्ञान केंद्रKrishi Vigyan Kendras - कृषि विज्ञान केंद्र
Krishi Vigyan Kendras - कृषि विज्ञान केंद्रKrashi Coaching
 
THE HISTOLOGY OF THE CARDIOVASCULAR SYSTEM 2024.pptx
THE HISTOLOGY OF THE CARDIOVASCULAR SYSTEM 2024.pptxTHE HISTOLOGY OF THE CARDIOVASCULAR SYSTEM 2024.pptx
THE HISTOLOGY OF THE CARDIOVASCULAR SYSTEM 2024.pptxAkinrotimiOluwadunsi
 
Role of Herbs in Cosmetics in Cosmetic Science.
Role of Herbs in Cosmetics in Cosmetic Science.Role of Herbs in Cosmetics in Cosmetic Science.
Role of Herbs in Cosmetics in Cosmetic Science.ShwetaHattimare
 
Human brain.. It's parts and function.
Human brain.. It's parts and function. Human brain.. It's parts and function.
Human brain.. It's parts and function. MUKTA MANJARI SAHOO
 
Shiva and Shakti: Presumed Proto-Galactic Fragments in the Inner Milky Way
Shiva and Shakti: Presumed Proto-Galactic Fragments in the Inner Milky WayShiva and Shakti: Presumed Proto-Galactic Fragments in the Inner Milky Way
Shiva and Shakti: Presumed Proto-Galactic Fragments in the Inner Milky WaySérgio Sacani
 
M.Pharm - Question Bank - Drug Delivery Systems
M.Pharm - Question Bank - Drug Delivery SystemsM.Pharm - Question Bank - Drug Delivery Systems
M.Pharm - Question Bank - Drug Delivery SystemsSumathi Arumugam
 
Gene transfer in plants agrobacterium.pdf
Gene transfer in plants agrobacterium.pdfGene transfer in plants agrobacterium.pdf
Gene transfer in plants agrobacterium.pdfNetHelix
 
Basic Concepts in Pharmacology in molecular .pptx
Basic Concepts in Pharmacology in molecular  .pptxBasic Concepts in Pharmacology in molecular  .pptx
Basic Concepts in Pharmacology in molecular .pptxVijayaKumarR28
 
Identification of Superclusters and Their Properties in the Sloan Digital Sky...
Identification of Superclusters and Their Properties in the Sloan Digital Sky...Identification of Superclusters and Their Properties in the Sloan Digital Sky...
Identification of Superclusters and Their Properties in the Sloan Digital Sky...Sérgio Sacani
 

Último (20)

Principles & Formulation of Hair Care Products
Principles & Formulation of Hair Care  ProductsPrinciples & Formulation of Hair Care  Products
Principles & Formulation of Hair Care Products
 
Bureau of Indian Standards Specification of Shampoo.pptx
Bureau of Indian Standards Specification of Shampoo.pptxBureau of Indian Standards Specification of Shampoo.pptx
Bureau of Indian Standards Specification of Shampoo.pptx
 
biosynthesis of the cell wall and antibiotics
biosynthesis of the cell wall and antibioticsbiosynthesis of the cell wall and antibiotics
biosynthesis of the cell wall and antibiotics
 
Pests of cumbu_Identification, Binomics, Integrated ManagementDr.UPR.pdf
Pests of cumbu_Identification, Binomics, Integrated ManagementDr.UPR.pdfPests of cumbu_Identification, Binomics, Integrated ManagementDr.UPR.pdf
Pests of cumbu_Identification, Binomics, Integrated ManagementDr.UPR.pdf
 
Role of herbs in hair care Amla and heena.pptx
Role of herbs in hair care  Amla and  heena.pptxRole of herbs in hair care  Amla and  heena.pptx
Role of herbs in hair care Amla and heena.pptx
 
Lehninger_Chapter 17_Fatty acid Oxid.ppt
Lehninger_Chapter 17_Fatty acid Oxid.pptLehninger_Chapter 17_Fatty acid Oxid.ppt
Lehninger_Chapter 17_Fatty acid Oxid.ppt
 
Contracts with Interdependent Preferences (2)
Contracts with Interdependent Preferences (2)Contracts with Interdependent Preferences (2)
Contracts with Interdependent Preferences (2)
 
Legacy Analysis of Dark Matter Annihilation from the Milky Way Dwarf Spheroid...
Legacy Analysis of Dark Matter Annihilation from the Milky Way Dwarf Spheroid...Legacy Analysis of Dark Matter Annihilation from the Milky Way Dwarf Spheroid...
Legacy Analysis of Dark Matter Annihilation from the Milky Way Dwarf Spheroid...
 
001 Case Study - Submission Point_c1051231_attempt_2023-11-23-14-08-42_ABS CW...
001 Case Study - Submission Point_c1051231_attempt_2023-11-23-14-08-42_ABS CW...001 Case Study - Submission Point_c1051231_attempt_2023-11-23-14-08-42_ABS CW...
001 Case Study - Submission Point_c1051231_attempt_2023-11-23-14-08-42_ABS CW...
 
Pests of tenai_Identification,Binomics_Dr.UPR
Pests of tenai_Identification,Binomics_Dr.UPRPests of tenai_Identification,Binomics_Dr.UPR
Pests of tenai_Identification,Binomics_Dr.UPR
 
Pests of wheat_Identification, Bionomics, Damage symptoms, IPM_Dr.UPR.pdf
Pests of wheat_Identification, Bionomics, Damage symptoms, IPM_Dr.UPR.pdfPests of wheat_Identification, Bionomics, Damage symptoms, IPM_Dr.UPR.pdf
Pests of wheat_Identification, Bionomics, Damage symptoms, IPM_Dr.UPR.pdf
 
Krishi Vigyan Kendras - कृषि विज्ञान केंद्र
Krishi Vigyan Kendras - कृषि विज्ञान केंद्रKrishi Vigyan Kendras - कृषि विज्ञान केंद्र
Krishi Vigyan Kendras - कृषि विज्ञान केंद्र
 
THE HISTOLOGY OF THE CARDIOVASCULAR SYSTEM 2024.pptx
THE HISTOLOGY OF THE CARDIOVASCULAR SYSTEM 2024.pptxTHE HISTOLOGY OF THE CARDIOVASCULAR SYSTEM 2024.pptx
THE HISTOLOGY OF THE CARDIOVASCULAR SYSTEM 2024.pptx
 
Role of Herbs in Cosmetics in Cosmetic Science.
Role of Herbs in Cosmetics in Cosmetic Science.Role of Herbs in Cosmetics in Cosmetic Science.
Role of Herbs in Cosmetics in Cosmetic Science.
 
Human brain.. It's parts and function.
Human brain.. It's parts and function. Human brain.. It's parts and function.
Human brain.. It's parts and function.
 
Shiva and Shakti: Presumed Proto-Galactic Fragments in the Inner Milky Way
Shiva and Shakti: Presumed Proto-Galactic Fragments in the Inner Milky WayShiva and Shakti: Presumed Proto-Galactic Fragments in the Inner Milky Way
Shiva and Shakti: Presumed Proto-Galactic Fragments in the Inner Milky Way
 
M.Pharm - Question Bank - Drug Delivery Systems
M.Pharm - Question Bank - Drug Delivery SystemsM.Pharm - Question Bank - Drug Delivery Systems
M.Pharm - Question Bank - Drug Delivery Systems
 
Gene transfer in plants agrobacterium.pdf
Gene transfer in plants agrobacterium.pdfGene transfer in plants agrobacterium.pdf
Gene transfer in plants agrobacterium.pdf
 
Basic Concepts in Pharmacology in molecular .pptx
Basic Concepts in Pharmacology in molecular  .pptxBasic Concepts in Pharmacology in molecular  .pptx
Basic Concepts in Pharmacology in molecular .pptx
 
Identification of Superclusters and Their Properties in the Sloan Digital Sky...
Identification of Superclusters and Their Properties in the Sloan Digital Sky...Identification of Superclusters and Their Properties in the Sloan Digital Sky...
Identification of Superclusters and Their Properties in the Sloan Digital Sky...
 

Machine Learning for Chemical Sciences

  • 1. Machine Learning for Chemical Sciences Ichigaku Takigawa HU-SNU Joint Symposium 2018 International Workshop on
 New Frontiers in Convergence Science and Technology Graduate School of Information Science and Technology, HU Institute for Chemical Reaction Design and Discovery (WPI-ICRD), HU
  • 2. Brief Bio: Ichigaku Takigawa Modulatory proteolysis
 (MCP 2016) Transcription elongation regulation (Nat Comm 2015) Neurodegenerative disease and genomes (Mol Brain 2017) Catalytic conversion of methane (JPCC 2017) 10 years Hokkaido University (1995-2005) 7 years at Kyoto University (2005-2011) 7 years at Hokkaido University (2012-2018) PhD in Computer Science/Statistical Science (Multivariate Analysis, Statistical Signal Processing) • Bioinformatics Center, Institute for Chemical Research • Graduate School of Pharmaceutical Sciences (X-omics, Molecular Biology, Medicinal Chemistry, Biochemistry) Research in Machine Learning & Data Mining (ML with discrete structures, ML for sciences)
  • 3. Two Approaches to Sciences Our main interest in science: 'unknown mechanism/principle' mechanism/principle (unknown) observations/data Theory/Hypothesis-driven modeling (as in natural sciences) explicit model observations/data e.g. Newtonian mechanics, quantum mechanics, theory of relativity, etc. we can run a simulation! Data-driven modeling (as in statistics, machine learning, AI, etc) model w/ unfixed observations/data best tuned to fit the given data ✓
  • 4. Deduction vs Induction/Abduction The grand aim of science is to cover the greatest number of experimental facts by logical deduction from the smallest number of hypotheses or axioms. Albert Einstein Hypothesis Experimental facts (data) Deduction Induction Abduction “Experience/Observation” “Intuition/Serendipity” Not logical at all Logical Can we somehow “rationalize” this part by using the data?
  • 5. Machine Learning for Sciences REVIEW Inverse molecular design using machine learning: Generative models for matter engineering Benjamin Sanchez-Lengeling1 and Alán Aspuru-Guzik2,3,4 * The discovery of new materials can bring enormous societal and technological progress. In this context, exploring completely the large space of potential materials is computationally intractable. Here, we review methods for achieving inverse design, which aims to discover tailored materials from the starting point of a particular desired functionality. Recent advances from the rapidly growing field of artificial intelligence, mostly from the subfield of machine learning, have resulted in a fertile exchange of ideas, where approaches to inverse molecular design are being proposed and employed at a rapid pace. Among these, deep generative models have been applied to numerous classes of materials: rational design of prospective drugs, synthetic routes to organic compounds, and optimization of photovoltaics and redox flow batteries, as well as a variety of other solid-state materials. M any of the challenges of the 21st century (1), from personalized health care to energy production and storage, share a common theme: materials are part of the solution (2). In some cases, the solu- tions to these challenges are fundamentally limited by the physics and chemistry of a ma- terial, such as the relationship of a materials bandgap to the thermodynamic limits for the generation of solar energy (3). Several important materials discoveries arose by chance or through a process of trial and error. For example, vulcanized rubber was prepared in the 19th century from random mixtures of com- pounds, based on the observation that heating with additives such as sulfur improved the rubber’s durability. At the molecular level, in- dividual polymer chains cross-linked, forming bridges that enhanced the macroscopic mechan- ical properties (4). Other notable examples in this vein include Teflon, anesthesia, Vaseline, Perkin’s mauve, and penicillin. Furthermore, these materials come from common chemical compounds found in nature. Potential drugs either were prepared by synthesis in a chem- ical laboratory or were isolated from plants, soil bacteria, or fungus. For example, up until 2014, 49% of small-molecule cancer drugs were natural products or their derivatives (5). In the future, disruptive advances in the dis- covery of matter could instead come from unex- plored regions of the set of all possible molecular and solid-state compounds, known as chemical space (6, 7). One of the largest collections of molecules, the chemical space project (8), has mapped 166.4 billion molecules that contain at most 17 heavy atoms. For pharmacologically rele- vant small molecules, the number of structures is estimated to be on the order of 1060 (9). Adding consideration of the hierarchy of scale from sub- nanometer to microscopic and mesoscopic fur- ther complicates exploration of chemical space in its entirety (10). Therefore, any global strategy for covering this space might seem impossible. Simulation offers one way of probing this space without experimentation. The physics and chemistry of these molecules are governed by quantum mechanics, which can be solved via the Schrödinger equation to arrive at their ex- act properties. In practice, approximations are used to lower computational time at the cost of accuracy. Although theory enjoys enormous progress, now routinely modeling molecules, clusters, and perfect as well as defect-laden periodic solids, the size of chemical space is still overwhelming, and smart navigation is required. For this purpose, machine learning (ML), deep learning (DL), and artificial intelligence (AI) have a potential role to play because their computational strategies automatically improve through experience (11). In the context of materials, ML techniques are often used for property prediction, seeking to learn a function that maps a molecular material to the property of choice. Deep generative models are a special class of DL methods that seek to model the underlying probability distribution of both structure and property and relate them in a nonlinear way. By exploiting patterns in massive datasets, these models can distill average and salient features that characterize molecules (12, 13). Inverse design is a component of a more complex materials discovery process. The time scale for deployment of new technologies, from discovery in a laboratory to a commercial pro- duct, historically, is 15 to 20 years (14). The pro- cess (Fig. 1) conventionally involves the following steps: (i) generate a new or improved material concept and simulate its potential suitability; (ii) synthesize the material; (iii) incorporate the ma- terial into a device or system; and (iv) characterize and measure the desired properties. This cycle generates feedback to repeat, improve, and re- fine future cycles of discovery. Each step can take up to several years. In the era of matter engineering, scientists seek to accelerate these cycles, reducing the FRONTIERS IN COMPUTATION KI onJuly26,2018http://science.sciencemag.org/Downloadedfrom REVIEW https://doi.org/10.1038/s41586-018-0337-2 Machine learning for molecular and materials science Keith T. Butler1 , Daniel W. Davies2 , Hugh Cartwright3 , Olexandr Isayev4 * & Aron Walsh5,6 * Here we summarize recent progress in machine learning for the chemical sciences. We outline machine-learning techniques that are suitable for addressing research questions in this domain, as well as future directions for the field. We envisage a future in which the design, synthesis, characterization and application of molecules and materials is accelerated by artificial intelligence. T he Schrödinger equation provides a powerful structure– property relationship for molecules and materials. For a given spatial arrangement of chemical elements, the distribution of electrons and a wide range of physical responses can be described. The development of quantum mechanics provided a rigorous theoretical foundationforthechemicalbond.In1929,PaulDiracfamouslyproclaimed that the underlying physical laws for the whole of chemistry are “completely known”1 . John Pople, realizing the importance of rapidly developing computer technologies, created a program—Gaussian 70—that could perform ab initio calculations: predicting the behaviour, for molecules of modest size, purely from the fundamental laws of physics2 . In the 1960s, the Quantum Chemistry Program Exchange brought quantum chemistry to the masses in the form of useful practical tools3 . Suddenly, experi- mentalists with little or no theoretical training could perform quantum calculations too. Using modern algorithms and supercomputers, systems containing thousands of interacting ions and electrons can now be described using approximations to the physical laws that govern the world on the atomic scale4–6 . The field of computational chemistry has become increasingly pre- dictive in the twenty-first century, with activity in applications as wide ranging as catalyst development for greenhouse gas conversion, materials discovery for energy harvesting and storage, and computer-assisted drug design7 . The modern chemical-simulation toolkit allows the properties of a compound to be anticipated (with reasonable accuracy) before it has been made in the laboratory. High-throughput computational screening has become routine, giving scientists the ability to calculate the properties of thousands of compounds as part of a single study. In particular, den- sity functional theory (DFT)8,9 , now a mature technique for calculating the structure and behaviour of solids10 , has enabled the development of extensive databases that cover the calculated properties of known and hypothetical systems, including organic and inorganic crystals, single molecules and metal alloys11–13 . The emergence of contemporary artificial-intelligence methods has the potential to substantially alter and enhance the role of computers in science and engineering. The combination of big data and artificial intel- ligence has been referred to as both the “fourth paradigm of science”14 and the “fourth industrial revolution”15 , and the number of applications in the chemical domain is growing at an astounding rate. A subfield of generating, testing and refining scientific models. Such techniques are suitable for addressing complex problems that involve massive combi- natorial spaces or nonlinear processes, which conventional procedures either cannot solve or can tackle only at great computational cost. As the machinery for artificial intelligence and machine learning matures, important advances are being made not only by those in main- stream artificial-intelligence research, but also by experts in other fields (domain experts) who adopt these approaches for their own purposes. As we detail in Box 1, the resources and tools that facilitate the application of machine-learning techniques mean that the barrier to entry is lower than ever. In the rest of this Review, we discuss progress in the application of machine learning to address challenges in molecular and materials research. We review the basics of machine-learning approaches, iden- tify areas in which existing methods have the potential to accelerate research and consider the developments that are required to enable more wide-ranging impacts. Nuts and bolts of machine learning With machine learning, given enough data and a rule-discovery algo- rithm, a computer has the ability to determine all known physical laws (and potentially those that are currently unknown) without human input. In traditional computational approaches, the computer is little more than a calculator, employing a hard-coded algorithm provided by a human expert. By contrast, machine-learning approaches learn the rules that underlie a dataset by assessing a portion of that data and building a model to make predictions. We consider the basic steps involved in the construction of a model, as illustrated in Fig. 1; this constitutes a blueprint of the generic workflow that is required for the successful application of machine learning in a materials-discovery process. Data collection Machine learning comprises models that learn from existing (train- ing) data. Data may require initial preprocessing, during which miss- ing or spurious elements are identified and handled. For example, the Inorganic Crystal Structure Database (ICSD) currently contains more than 190,000 entries, which have been checked for technical mistakes DNA to be sequences into distinct pieces, parcel out the detailed work of sequencing, and then reassemble these independent ef- forts at the end. It is not quite so simple in the world of genome semantics. Despite the differences between genome se- quencing and genetic network discovery, there are clear parallels that are illustrated in Table 1. In genome sequencing, a physical map is useful to provide scaffolding for assembling the fin- ished sequence. In the case of a genetic regula- tory network, a graphical model can play the same role. A graphical model can represent a high-level view of interconnectivity and help isolate modules that can be studied indepen- dently. Like contigs in a genomic sequencing project, low-level functional models can ex- plore the detailed behavior of a module of genes in a manner that is consistent with the higher level graphical model of the system. With stan- dardized nomenclature and compatible model- ing techniques, independent functional models can be assembled into a complete model of the cell under study. To enable this process, there will need to be standardized forms for model representa- tion. At present, there are many different modeling technologies in use, and although models can be easily placed into a database, they are not useful out of the context of their specific modeling package. The need for a standardized way of communicating compu- tational descriptions of biological systems ex- tends to the literature. Entire conferences have been established to explore ways of mining the biology literature to extract se- mantic information in computational form. Going forward, as a community we need to come to consensus on how to represent what we know about biology in computa- tional form as well as in words. The key to postgenomic biology will be the computa- tional assembly of our collective knowl- edge into a cohesive picture of cellular and organism function. With such a comprehen- sive model, we will be able to explore new types of conservation between organisms and make great strides toward new thera- peutics that function on well-characterized pathways. References 1. S. K. Kim et al., Science 293 , 2087 (2001). 2. A. Hartemink et al., paper presented at the Pacific Symposium on Biocomputing 2000, Oahu, Hawaii, 4 to 9 January 2000. 3. D. Pe’er et al., paper presented at the 9th Conference on Intelligent Systems in Molecular Biology (ISMB), Copenhagen, Denmark, 21 to 25 July 2001. 4. H. McAdams, A. Arkin, Proc. Natl. Acad. Sci. U.S.A. 94 , 814 ( 1997 ). 5. A. J. Hartemink, thesis, Massachusetts Institute of Technology, Cambridge (2001). V I E W P O I N T Machine Learning for Science: State of the Art and Future Prospects Eric Mjolsness* and Dennis DeCoste Recent advances in machine learning methods, along with successful applications across a wide variety of fields such as planetary science and bioinformatics, promise powerful new tools for practicing scientists. This viewpoint highlights some useful characteristics of modern machine learn- ing methods and their relevance to scientific applications. We conclude with some speculations on near-term progress and promising directions. Machine learning (ML) (1) is the study of computer algorithms capable of learning to im- prove their performance of a task on the basis of their own previous experience. The field is closely related to pattern recognition and statis- tical inference. As an engineering field, ML has become steadily more mathematical and more successful in applications over the past 20 years. Learning approaches such as data clus- tering, neural network classifiers, and nonlinear regression have found surprisingly wide appli- cation in the practice of engineering, business, and science. A generalized version of the stan- dard Hidden Markov Models of ML practice have been used for ab initio prediction of gene structures in genomic DNA (2). The predictions correlate surprisingly well with subsequent gene expression analysis (3). Postgenomic bi- ology prominently features large-scale gene ex- pression data analyzed by clustering methods (4), a standard topic in unsupervised learning. Many other examples can be given of learning and pattern recognition applications in science. Where will this trend lead? We believe it will lead to appropriate, partial automation of every element of scientific method, from hypothesis generation to model construction to decisive experimentation. Thus, ML has the potential to amplify every aspect of a working scientist’s progress to understanding. It will also, for better or worse, endow intelligent computer systems with some of the general analytic power of creating hypotheses, testing by decisive exper- iment or observation, and iteratively building up comprehensive testable models or theories is shared across disciplines. For each stage of this abstracted scientific process, there are relevant developments in ML, statistical inference, and pattern recognition that will lead to semiauto- matic support tools of unknown but potentially broad applicability. Increasingly, the early elements of scientific method—observation and hypothesis genera- tion—face high data volumes, high data acqui- sition rates, or requirements for objective anal- ysis that cannot be handled by human percep- tion alone. This has been the situation in exper- imental particle physics for decades. There automatic pattern recognition for significant events is well developed, including Hough transforms, which are foundational in pattern recognition. A recent example is event analysis for Cherenkov detectors (8) used in neutrino oscillation experiments. Microscope imagery in cell biology, pathology, petrology, and other Table 1. Parallels between genome sequencing and genetic network discovery. Genome sequencing Genome semantics Physical maps Graphical model Contigs Low-level functional models Contig reassembly Module assembly Finished genome sequence Comprehensive model C O M P U T E R S A N D S C I E N C E onAugust29,2018http://science.sciencemag.org/Downloadedfrom Nature, 559
 pp. 547–555 (2018) Science, 293 pp. 2051-2055 (2001) Science, 361 pp. 360-365 (2018) Science is changing, the tools of science are changing. And that requires different approaches. Erich Bloch, 1925-2016
  • 6. Machine Learning Machine learning is a way to construct a computer program directly by a given (large) collection of input-output examples without being explicitly programmed. Generic Object Recognition Speech Recognition Machine Translation Super-Resolution Imaging AI Game Players “감사” J’aime la musique I love music
  • 7. My Research Interest: ML with Discrete Structures Tree/DAG Ensemble Neural Nets/Deep Learning Probabilistic Programming • Target data themselves have discrete structures • ML models have discrete structures or constraints • Variables have structural dependencies or constraints H H H H H H H H O N O O H H H O O H H N O O Cl ClCl Sets, Sequences, Combinations, Permutations, Branching Chains (Trees), Networks (Graphs), …
  • 8. Molecular Machine Learning MoleculeNet: A Benchmark for Molecular Machine Learning
 https://arxiv.org/abs/1703.00564
 https://github.com/deepchem/deepchem (https://deepchem.io/) CH3 N H3C H NS N O CH3 N OH x molecule property value ˆy ˆy = f✓(x) Quantitative structure–activity/property relationship (QSAR/QSPR)
  • 9. Many levels of interest • Mutagenic potency • Carcinogenic potency • Endocrine disruption • Growth inhibition • Aqueous solubility N NH OO HH H H H H H H H H H H H H H H H H H H H H H H H O O O O O O Cl H H H H H HH H H H H H H H H H H Br Br O P O O Br Br O Br Br H H H H H H H H H H HH H HH N S N N H H H H H H H H H H H H H H H O N O O H H H O O H H N O O Cl ClCl H H H H H H H N O O H H H H H H H H H N O O H H H H H H H N H N O O N O O H H H H H H H H N CH3 O O H N Cl Cl Cl Cl Cl H3C O O O O O O H3C CH3 CH2 O HN O O NH CH3 HO OH CH3 N O O CH3 N N H N H H3C N H3C H3C NH O N O NO CH3 O N NH2 O CH3 Br CH3 N H3C H NS N O CH3 N OH CH3 CH3N N N CH3H3C H2N NH2 H OH O HO CH3 H H O CH3 H O OH3C HH H O H3C S CH3 O H H O CH3 CH3 OO HO H3CH HO F H O H3C NH2 O N HO HO O H H O O OH3C O O O CH3 O CH3 HO CH3 H O O CH3 H H N H N O H3C O O O
  • 10. ML Surrogates for Quantum Chemistry http://quantum-machine.org/datasets/ Quantum chemistry structures and properties of 134 kilo molecules, Scientific Data 1, 140022 (2014) Dataset: structure-properties pairs in the ground state 
 for all 133,885 compounds with up to 9 heavy atoms of C, O, N, or F DFT B3LYP/6-31G(2df,p) Structure in the ground state 15 properties in the ground state http://www.nature.com/articles/sdata201422
  • 11. Inverse Design (Machine Teaching) “machine teaching” “machine learning” Bayesian optimization / Black-box optimization / Sequential design of experiments / Surrogate-based optimization “television” Beware: Inverse is not unique?? CH3 N H3C H NS N O CH3 N OH x molecule property value ˆy ˆy = f✓(x)
  • 12. A lot of technical challenges, pitfalls, and potentials
  • 14. ✗ ML for Heterogeneous Catalysis Chemical Reaction Catalysts Heterogeneous catalysts / Surface reactions Haber–Bosch Process Ferrous metal Catalysis Noble Metal Catalysis (Pt, Pd, Rh…) Various Metallic Catalysts
 (Li, rare earthes, alkaline earths) (industrial synthesis of ammonia) Exhaust Gas Purification Conversion of Methane “Fertilizer from Air” artificial nitrogen fixation
  • 15. ML for Heterogeneous Catalysis Catalyst Informatics Large Literature Data (in prep) Quantum Calculated Data (RCS Adv 2016; JPCC 2018) Data from Controlled Experiments (plan) ACS 2018 [CATL] 
 Machine Learning for Catalysis Research
  • 16. ML for Chemical Reaction Design & Discovery Institute for Chemical Reaction Design and Discovery (WPI-ICReDD), HU We’ll start international hiring!! Computational Science Explores Quantum Chemically Possible Reaction Paths Information Science Uses Various Data and Known Information to Prioritize Paths Experimental Science Realizes & Validates Reactions in Various Application Domains The AFIR method 2018 Oct 23- HU 10 year project got funded
  • 17. Machine Learning for Chemical Sciences • Some words by David Hand at KDD2018@London: • Theory-driven models can be wrong • But data-driven models cannot be wrong or even right. 😩 • Data-driven are not trying to describe an underlying reality. • But are merely intended to be useful. 😆 • So they could be poor or useless, but not wrong • We need to understand the data, the models, the algorithms. • We need to collaborate with domain experts because many different conclusions are always possible from finite data.
  • 18. Thanks for many nice people around me