Next Article in Journal
Development of a Robot for Decontamination of High Places and Decommissioning Work That Can Cope with Slopes and Steps
Next Article in Special Issue
Evaluation and Comparison of Lattice-Based Cryptosystems for a Secure Quantum Computing Era
Previous Article in Journal
Fast Synthesis Method for High-Dimensional Electromagnetic Bandgap Structure Using Deep Neural Network for Power/Ground Noise Suppression
 
 
Review
Peer-Review Record

Unlocking the Potential of Quantum Machine Learning to Advance Drug Discovery

Electronics 2023, 12(11), 2402; https://doi.org/10.3390/electronics12112402
by Maria Avramouli 1,*, Ilias K. Savvas 1, Anna Vasilaki 2 and Georgia Garani 1
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Electronics 2023, 12(11), 2402; https://doi.org/10.3390/electronics12112402
Submission received: 5 May 2023 / Revised: 20 May 2023 / Accepted: 22 May 2023 / Published: 25 May 2023
(This article belongs to the Special Issue Quantum Computation and Its Applications)

Round 1

Reviewer 1 Report

This is a review article summarizing the application of quantum algorithms to machine learning for drug discovery.

Even though this is not an original work, the contents are easy to understand and may be useful for many related researchers.

While the sequences of cited scientific works may be felt somewhat disjointed, this review can provide readers with some guidance for related studies.

If possible, the authors had better show more concrete and comprehensive perspectives how and why the quantum approaches can give overwhelming power over the classical machine-learning approaches.

Concerning the quality of figures, I suggest the improvement of Figure 5 (c).

 

Minor editing of English language required. For example:  

In Line 365 on Page 9: both of whom → both of which 

 

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

The manuscript entitled “Unlocking the Potential of Quantum Machine Learning to Advance Drug Discovery” by Maria Avramouli et al, aimed to present a review of the proposed QML algorithms for application in the drug discovery pipeline, and to compare QML algorithms with their classical and hybrid counterparts in terms of their efficiency.

 

1. Line160 “A qubit can simultaneously be in both states |0> and |1> (superposition) and is denoted as |ψ> = α|0> + β|1>, where α and β are complex probability amplitudes.” What is the meaning of " A qubit can simultaneously be in both states |0> and |1> (superposition)"? Can it be understood that qubits can be in | 0>or | 1>or (| 0>and | 1>)?

“When the qubit α|0⟩ + β|1⟩ is measured, it will no longer be in superposition, and the state collapses to |0⟩ with probability |α|2, or to |1⟩ with probability |β|2. Any valid qubit state has coefficients α and β such that |α|2 + |β|2 = 1.” I want to know what factors determine the collapse of an equivalent subunit to | 0>or | 1>when it is measured? Is it the size of the probability? In other words, can I understand that if| α| 2>| β| 2, will the qubit collapse to | 0>?

2. Some concepts are not clearly distinguished.

For example:

Line185” The most common single-qubit quantum gates are the Hadamard (H), Bit flip (X), and Rotation gates (RX, RY, RZ). The Controlled Not (CNOT) is a two-qubit gate (Figure 2.b).” What is the difference between these single-qubit quantum gates?

Line296” Notably, amplitude embedding [35, 36], angle embedding [31, 36-40], and Hamiltonian [41] are the common encoding methods.” What is the difference between these encoding methods?

3. Figure 2 are generally not clear enough.

“Figure 10. a) Linear and b) no-linear Regression.” There are some formatting issues: a) is bold and b) is not bold.

Most of the Figures are not professional enough. Such as Figure1, Figure5 and Figure10.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Back to TopTop