01
Far more efficient experiments
Simulation reduces the number of trials and the risk of failure, so bench time goes to the checks that matter. Automating data analysis also makes the work more efficient.
3 of 4 seats filled · 1 seat left
From a bench-only researcherto a Wet × Dry researcher.
In silico drug discovery education program
From setting up a research environment and Python to screening, MD simulation, research design and publication strategy. You do the hands-on work; we mentor you as you work toward a paper.
CHALLENGES
Does this sound familiar?
- I want to make experiments more efficient.
- I want to take on time-consuming, challenging topics — and still build a stronger publication record.
- I want to keep doing research, even while other work keeps me busy.
ANOTHER PATH
Wet × Dry as a choice
Adding dry research and analysis to your own work can take the project up a stage.
02
Better use of time
Dry research runs on a PC, so you can do other work while calculations finish. AI helps with planning and coding, so you can set up conditions and run the most useful jobs.
03
A growing publication record
Because the computer does the work, dry research tends to deliver results faster than bench experiments. You can build output with dry research alone, or secure a publication record with it while settling into a challenging wet-lab topic.
WORKFLOW
The in silico drug discovery program, step by step
From building a compound library through in silico screening and MD simulation to proposing final compounds. You go through the whole workflow, one that can lead to a publication with nothing but a PC, on your own research topic.
- 1
Compound library construction
Design and filter a library of small molecules and/or peptides from public databases to fit your target.
- 2
In silico screening
Use screening to evaluate binding to the target protein computationally and narrow down hit compounds.
- 3
MD simulation
Verify complex stability with molecular dynamics and estimate binding energies with MM/PBSA and related methods.
- 4
Final compounds & publication
Organize screening and MD results, propose compounds for further validation, and prepare the research for publication.
Typical timeline
No programming experience
- Learning
- about 3 months
- Publication
- about 6 months
Programming experience
- Learning
- about 1.5 months
- Publication
- about 3 months
AFTERWARDS
After the program
Before
- Candidates can only be found at the bench.
- Unsure how dry results become a paper.
- AI is something you have only heard about.
- A bench-only researcher.
After
- You run library construction, screening, MD and interaction analysis on your own topic.
- You have a template for publication: figures, narrative and journal choice.
- You can use the latest AI methods and know how to run research with AI.
- A Wet × Dry researcher who narrows hypotheses computationally, tests them experimentally and sets the next question.
COMPARISON
Comparison with other services
| BaraPhaSilico | Graduate school | Coding bootcamp | |
|---|---|---|---|
| Fees | Academia / individuals: JPY 30,000 per month or JPY 300,000 lump sum. Companies: JPY 400,000 lump sum. | Hundreds of thousands to over JPY 1,000,000 per year. | Hundreds of thousands of yen. |
| Duration | From a few months; designed around your topic through to publication. | Two years for a master’s, three or more for a PhD. | A few months; ends when the curriculum ends. |
| Publication | Mentoring through to publication on your own research topic. | Publication on the lab’s topic; progress depends on your supervisor. | Not covered. Research and publication are out of scope. |
| Instructor | Direct mentoring by the founder, who came from the wet lab, taught himself in silico drug discovery, and published. | Your supervisor; the field depends on the lab. | Software engineers; limited experience in drug discovery or research. |
Descriptions of graduate school and bootcamps are typical examples.
Textbook
The Complete Guide to In Silico Drug Discovery: Write a Paper from Home
This is the textbook we teach from. It is updated regularly.
Read on Zenn (Japanese)Founder's paper
Identification of KKL-35 as a Novel Carnosine Dipeptidase 2 (CNDP2) Inhibitor by In Silico Screening
Shinbara K. et al., Molecules 2025, 30(22), 4370.
What participants say
Our company’s strength has been drug discovery research based on wet-lab experiments, but we wanted to introduce in silico drug discovery to adapt to the increasingly challenging drug discovery landscape. Discovering this program on X came at just the right time. Although I was a complete beginner with no programming experience, I received careful guidance from the basics and was able to run MD simulations within three months. I am also very grateful for the flexibility of the support, which went beyond the textbook to include installing software and checking programs to suit our company’s environment and needs.
Through this program, I no longer feel intimidated by in silico drug discovery or programming, both of which I had previously avoided because they seemed difficult. I now actively consider ways to improve programs and introduce new software. As we continue to build our company’s in-house environment for in silico drug discovery, I hope to receive your support again.
Pharmaceutical industry researcher, U
I had no background in bioinformatics, yet the basics of in silico screening of a small-molecule library against a target protein were explained in a way I could follow. I did not even know how to use a command line, and I hit error after error, but I still made it from setting up a virtual environment all the way to running an MD simulation. I owe that to my mentor and I am truly grateful.
The technical book was also updated with the points I stumbled on and with tools that were not covered when it was first written, which makes reviewing much easier (I look forward to further additions).
My own PC is probably not powerful enough to run MD simulations at full tilt, but this program has clearly lowered the barrier I felt towards bioinformatics. It has sparked a desire to understand the field more deeply; I intend to keep learning and build more practical skills, and if the chance arises I would very much like to be mentored again.
Postdoctoral researcher, M
My research had been centred on wet-lab experiments, so I was not very familiar with dry analysis or programming and felt some anxiety, but by actually working hands-on I learned a great deal.
Errors were frequent as I got used to Python, but each time I received careful guidance and was able to move forward while properly understanding every step. Gaining knowledge and intuition through practice, something you cannot get just by reading a book, was extremely valuable.
Because of my PC’s specifications I could not run the MD simulation myself and the actual calculation was run on my behalf, but I came to understand the workflow and its significance. The in silico screening also turned up compounds that could become the seed of a research project, a major outcome that I hope to carry through to a journal submission. Thank you for this valuable opportunity.
Assistant professor, H
PROGRAM
Nine pillars of the mentoring program
We mentor you through the textbook, video lectures and weekly meetings, combining the following as needed.
01
Research environment setup
Linux/WSL, conda, GPU: we get the error-prone setup out of the way first.
02
Practical Python for researchers
Learn the Python you need by running analyses on your own data.
03
Literature review & hypothesis design
How to read papers, organise prior work and formulate testable hypotheses.
04
Hands-on in silico drug discovery
Run computational analyses on your own research topic, centered on screening and MD simulation.
05
AI for research productivity
Safely bring generative AI into research, coding and writing.
06
Materials you can revisit anytime
Rewatch the video lessons as often as you need. The textbook code is maintained so it keeps running.
07
Publication strategy & study design
Journal selection, figure planning and reviewer response, planned from the start.
08
Code review & coding support
We review your code and help it grow into a reproducible analysis pipeline.
09
Unlimited questions & online discussion
Ask anytime on Discord, discuss regularly on Zoom. Less time stuck alone.
PRICING
Pricing
Academia / individuals
MonthlyJPY 30,000
Lump sumJPY 300,000
(tax included)
- Mentoring through to publication
Companies
Lump sumJPY 400,000
(tax included)
- Includes one month of technical advising after the program ends.
- GPU rental costs an additional JPY 10,000 per month (tax included), on top of the program fee.
- The standard mentoring scope centers on screening and MD simulation. If three or more tools need to be introduced, the work moves to a collaborative research agreement and additional fees apply based on scope.
- When you publish, please credit us by name (for example as co-first author) according to our contribution to the research.
- Please also provide a testimonial of about 300 Japanese characters at the end of the program.
- The textbook is purchased separately.
FOR WHOM
Who it is for — and who it is not
A good fit
- Master's and PhD students, postdocs, early-career PIs and industry researchers who seriously want to change how they do research
- People who can commit 10+ hours per week and work hands-on
- Wet-lab researchers who want to add computation to their toolkit
- Anyone who wants to publish with in silico drug discovery or bioinformatics
Not a fit
- Those looking to outsource analysis (this is not a contract-analysis service)
- Those who cannot set aside time to do the work themselves
- Those who only want quick results without learning
FAQ
Frequently asked questions
How is this different from technology adoption and consulting?
The mentoring program is built on the premise that you do the hands-on work. We explain concepts, review your code, help you get unstuck and discuss study design, but we do not run the analysis for you. In return, every skill and result you gain is yours. Technology adoption and consulting covers one tool for people who have completed the program or already have an in silico specialist in their company or lab. If three or more tools are needed within the mentoring program, or you want to work on research together, see collaborative research.
Can I join with no programming experience?
Yes. Even if you have never used a command line, we start from environment setup and move one step at a time. Most past participants came from a wet-lab background.
What kind of computer do I need?
Docking and data analysis run on an ordinary laptop (Mac, or Windows with WSL). MD simulation is more comfortable with a GPU. GPU rental costs an additional JPY 10,000 per month (tax included), on top of the program fee.
How much time is required?
The program is for people who can commit at least 10 hours per week. Duration and pace are designed together at the first consultation, based on your topic and goal (conference presentation, journal submission, etc.).
What is the difference between academia/individual and company fees?
Academia and individuals pay JPY 30,000 per month or JPY 300,000 lump sum. Companies pay JPY 400,000 lump sum and receive one month of technical advising after the program. All fees are tax included.
Which tools are in scope?
The standard scope centers on screening and MD simulation. If three or more tools need to be introduced, the work moves to a collaborative research agreement and additional fees apply based on scope.
Do you work in English?
Yes. Our founder has provided technical consulting to overseas researchers and can prepare materials and hold discussions in English.
CONTACT
Contact / free first consultation
Enquiries about the mentoring program and a free first consultation are welcome. We usually reply within 2–3 business days.
SERVICES
Other services
For research involving three or more tools, see collaborative research. For introducing one tool for use within a company or laboratory, see technology adoption and consulting.