That’s why we are in constant, open dialogue with biochemists and laboratory researchers—engaging directly with the scientific community to understand the true pain points and daily challenges faced in modern research labs.

By speaking the language of working scientists, we ensure our AI platform is not only technologically advanced, but also genuinely relevant and practical for everyday laboratory needs.
At BinomLabs, we believe the best innovation
starts with listening.
Pitch Deck (PDF or secure link)
  • Visual summary of the problem, solution, market, team, business model, traction, competition, and financials.
Product/Platform Overview
  • Explaining AI product, technology, workflow, and main differentiators (with diagrams).

Technical Whitepaper or Science Appendix
For BioTech: a more detailed document on your technology, methods, experimental validation, patents

Traction & Validation Data
Evidence of lab/clinical results, user testimonials, pilots, publications, or peer review (PDF, slides)

Financial Model

Contacts/CVs
Product/Platform Overview
"As the founder of BinomLabs, I have personally overseen every aspect of our platform’s development—especially when it comes to the accuracy of our calculations and the reliability of the correlations we provide to experimental laboratories. I take full responsibility for the quality of every result our platform delivers. For our clients—whether in academia or pharma—this means reduced experimental costs, faster project turnaround, and far greater confidence in the data driving their innovation. "
Tatiana Koshlan
Founder, BinomLabs

1. Title & Tagline

Name of your product/platform, a one-liner of what it does.
The BinomLabs startup was founded by two academic researchers with extensive interdisciplinary experience in the field of experimental biochemistry, mathematical physics, polymer physics, mathematical statistics, more details can be found in SV.

We have developed and passed the Proof of Concept of an AI platform for predicting experimental data, mainly in vitro experiments, and partially in vivo experiments.

The goal of our AI platform is to reduce preliminary and clarifying biochemical experiments conducted in "wet" laboratories by obtaining a preliminary forecast of experimental data
Detailed description:

2. Core Problem & Solution

What problem are you solving? What’s your solution/product?

In real laboratory studies, experimental errors can reach as high as 70%. Different laboratories often obtain inconsistent results when studying the same scientific problem. This variability, caused by random errors, leads to wasted resources and unreliable outcomes.

AI-Platform Solution:
Our AI-platform leverages predictive algorithms to dramatically reduce experimental errors and optimize experimental design. By integrating machine learning into the planning and execution of in vitro studies, our platform enables researchers to consistently obtain more reliable results, regardless of location or team.

Impact on Cost and Efficiency:
The left-hand slides show that, without AI, achieving 100% effectiveness typically requires a large number of experiments, each with varying success rates.

In contrast, AI-guided experiments reach optimal effectiveness with fewer trials, saving time and effort.
On the right, real-world cost comparisons for both academic and pharma projects illustrate the dramatic financial impact:
  • Academic projects: Costs drop from $50,000 (10 experiments, no AI) to $15,000 (3 experiments, with AI).
  • Pharma projects: Costs fall from $300,000 to $90,000 using AI-driven prediction and planning.
Detailed description:

3. How It Works / Workflow

Step-by-step: How does a user interact with your product?

optimization of biochemical experiments by obtaining a preliminary forecast of experimental data for selected molecules, this will increase efficiency and reduce costs of biochemical experiments by eliminating intermediate clarifying in-vitro experiments
Usefulness and benefits of the product provided to researchers:
using the following experimental techniques:
  • Affinity electrophoresis,
  • Isothermal Calorimetry,
  • Gel Electrophoresis,
  • Surface plasmon resonance,
  • Spectroscopic assays.
Predicting experimental results allows reducing the consumption of biological material, labor costs, increasing the useful output of high-tech experiments.

AI platform, where the user can independently select the
necessary molecules and experimental conditions

List of experimental methods for which the researcher can obtain a prediction of experimental data with good accuracy
List of experimental data for which the researcher can obtain a high level of prediction
List of calculation data provided by the AI platform
correlation graphs between experimental and calculated data
List of molecules under study for which a prediction of experimental data will be obtained.
Additional experimental data for which the researcher can obtain a good level of correlation with the calculated data in the form of a forecast

4. Key Features

Main capabilities, modules, or unique tools.

Correlation between stability value lg(cond(W)) and experimental Kd value:
R=0.869
Binding affinities of peptides to Bcl-xL. Residues of Bak peptide substituted with alanine are in boldface.
lg (Kd)
Calculated
Experiment
[Structure of Bcl-xL–Bak Peptide Complex: Recognition Between Regulators of Apoptosis]
Сorrelation graphs between experimental and calculated data
Contribution of the charged residues of BAX to the binding affinity. BAX peptides (36-mer) with the alanine substitution of the indicated charged residues were titrated into BCL-2, and the deduced KD values are listed in the table. Shown in the bottom is the ITC run for the titration of the BAX peptide with the triple substitutions.
Calculated data
Experiment data
The correlation between calculated and experimental parameters reaches 93%
[Evidence that inhibition of BAX activation by BCL-2 involves its tight and preferential interaction with the BH3 domain of BAX]
The results of the experimental IC50 (a) and (b)
and calculated values of lg(cond(W)) (c) and (d));

the top graphs present the experimental results for MCL-1–Bax-BH3 (a)

and Bcl-xL–Bax-BH3 (b) complexes,


while the bottom graphs show the results of numerical calculations for the same biological complexes namely MCL-1–Bax-BH3 (c) and Bcl-xL–Bax-BH3 (d).

[A Paradigm Shift in Experimental Biochemistry: A Priori Estimation of Physical Parameters of Biomolecules]
c)
d)
Figure processed calculated data for the negative and positive data sets for the calculated value of lg[Kd] , blue and red indicate the results for the positive set of mutations and black indicates the results for the negative data set. Note that negative values of the lg[Kd] value correspond to a Kd value less than 1, so we are talking here about the values of the dissociation constant corresponding to values less than 1 mol in the positive range of values.
Method for Predicting the Oncogenicity of Mutant Proteins
Correspondence of mutation numbers to their names for the positive and negative sets of p53 mutations
Negative mutation type = absence of observed incidence of cancer
Positive mutation type= registered cases of cancer
The AI platform allows predicting the results of experimental data for molecular complexes of any complexity
Calculated data
[A Paradigm Shift in Experimental Biochemistry: A Priori Estimation of Physical Parameters of Biomolecules]
Prediction of experimental data for large molecular complexes
Experiment data IC50
Calculated Data for next following cases:
Scheme of chemical reaction pathways on the assembly of a hexamer, taking into account
the change in the calculated thermodynamic quantities TΔS, lg(Kd), Δ(ΔW), and lg(cond(W)).
The order of formation of a hexameric complex involving three proteins and three peptides, taking into account various modifications in the peptides
The arrows indicate the paths of hexamer formation, and the "dead-end" formations are also marked in red. The Experimental Kd data are given for each hexamer.

5. Differentiators

What sets you apart from competitors or current solutions?

  • The tasks and problems in biochemical research are our direct tasks, as well as finding a direct, understandable correlation between calculated and experimental data

  • High correlation level up to 93% between experimental and calculated data

  • Real conditions of biochemical laboratories are embedded in our AI platform, molecular structures of any complexity, as well as the ability to set such conditions as
Temperature, concentration of reagents, denaturants
  • The main barrier between AI developers of software for biochemical laboratories and experimental laboratories is the lack of a common professional language for designating experimental problems.

  • Each group of developers has its own spectrum of scientific interests, which hardly intersect with each other.

  • For bioinformaticians, the value of free energy still occupies a dominant position, which, however, poorly reflects experimental results
Problem description:
Binomlabs Benefits:
6. Technical Highlights
A few sentences about core technology, methods, or AI/ML involved.

The calculation of the physical quantities for molecules interaction characterize the formation of each complex reveals the direction of the passage of biochemical reactions depending on the affinity and concentration of active elements, thus the platform will help determine stable and transient biological formations with the participation of the studied drugs.

At the same time, the use of AI-platform allows you to introduce many factors into the system under study, making direct measurements of changes in chemical reactions.
Get acquainted with technical information, a lot of calculations, proofs, mathematical formulas:

7. Use Cases / User Types

Example(s) of how real customers (labs, pharma, researchers) use AI-platform product.

The following section contains information on the share of in vitro experiments in large pharmaceutical companies in 2024.
All customers can be divided into two large groups: academic researchers and commercial companies.
An example of fine-tuning the affinity of an antibody to an antigen, bypassing expensive experimental techniques, giving a prediction for the most effective antibodies in terms of affinity
AI platform include:

  • modification of antibody flexible chains,
  • stepwise testing of each antibody to antigen,
  • determination of key amino acid residues,
  • range of affinity changes,
  • analysis of redistribution of interaction energy,
  • influence of temperature on aggregation and unfolding
Stages of formation and selection for 15 antibody modifications by BinomLabs platform, saving laboratory funds at each set up stage and the cost price of the BinomLabs research platform.
Table present a comparison of the main experimental techniques and comparable BinomLabs methods using an automated platform
This chart contains information about the Israeli consumer market, including academic, pharmaceutical and commercial companies.

Investor Update: Financial Model & CEO Search

At BinomLabs, our current financial model is intentionally based on the most modest and conservative growth milestones. We believe in setting realistic expectations for our investors and building a solid foundation for sustainable success.

It’s important to note that we are actively searching for a high-impact CEO to join our leadership team. Once this key executive is in place, we anticipate that our financial trajectory will accelerate significantly.

All projections presented today reflect our “base case” scenario; with the right CEO, we fully expect our business metrics—including revenue, customer acquisition, and market penetration—to at least double.

This approach ensures that BinomLabs remains a low-risk, high-upside opportunity for our early investors. We are committed to updating our forecasts and sharing an enhanced growth roadmap as soon as the CEO appointment is finalized.

1. Customer Growth (per month/quarter, by segment)

Month/Quarter Academic Enterprise Pharma Total Customers
Q1 2025 1 0 0 1
Q2 2025 2 0 0 2
Q3 2025 2 1 0 3
Q4 2025 3 1 0 4
Q1 2026 4 1 1 6
Q2 2026 5 2 1 8
Q3 2026 6 3 1 10
Q4 2026 7 4 2 13

2. Pricing Tiers

Tier Monthly Price Annual Price Typical Customer Type
Academic $500 $5,000 Universities, research labs
Enterprise $2,000 $20,000 CROs, core facilities
Pharma $5,000 $50,000 Biotech, pharma companies

3. Monthly Revenue Calculation Example

Month Academic Customers Academic MRR Enterprise Customers Enterprise MRR Pharma Customers Pharma MRR Total MRR
Jan 2026 1 $500 0 $0 0 $0 $500
Feb 2026 2 $1,000 0 $0 0 $0 $1,000
Mar 2026 2 $1,000 0 $0 0 $0 $1,000
Apr 2026 2 $1,000 1 $2,000 0 $0 $3,000
May 2026 3 $1,500 1 $2,000 0 $0 $3,500

4. Quarterly Totals (Auto-calculated in spreadsheet)

Quarter Total Customers Total Revenue (all tiers)
Q1 2026 1 $2,500
Q2 2026 4 $10,000
Q3 2026 5 $15,500
Q4 2026 7 $24,000

8. Founder's Contacts

St. Petersburg State University/
Ben-Gurion University
St. Petersburg State University/
Ariel University
Kirill Kulikov
kulikov.kirill.g@gmail.com
Postdoc,
Machine learning field,
PhD in biological
and physical sciences
Doctor of Habilitation,
Mathematical Physics,
Software developer, specialist in mathematical and statistics
Tatiana Koshlan
koshlan.tetiana@gmail.com
Founder
Founder
Postdoctoral Fellow, Medical Faculty of Computer Science;
PhD in Molecular Physics;
Master of Science in Biophysics;Postdoctoral thesis:
“The Role of Electrostatic Interactions in the Formation of Protein Complexes.”

My interdisciplinary research lies at the intersection of biological and physical sciences. I focus on studying the interactions of biological molecules using physical methods, and applying advanced mathematical tools to develop new technologies and software for systematic measurement and analysis of diverse biological interaction datasets.
Doctor of Habilitation, Mathematical Physics;
Ph.D. in Physics and Mathematics,
thesis title: «Mathematical Modeling of the Optical Properties of Multilayer Biological Systems and Structures in their Heterogeneous Conjugation» (2004)

The Doctor of Science, thesis title «Analytical models of interaction of laser radiation with complex heterogeneous biological tissues» (2014).

Research interests are theory diffraction theory, electrodynamics, physics of lasers, tissue optical methods of mathematical modeling in biological tissue optics and numerical method, biophysics.
in

Features of BinomLabs for the pharmaceutical industry

Implementation of AI algorithms to achieve 90% correlation with real-experimental data
  • Continuous Improvement
    Our algorithms are continuously tested and validated in collaboration with real-biochemistry research labs and academic partners.
  • Built for modern biology
    Our core strength lies in our highly qualified development team. Our team’s expertise spans mathematical physics, statistics, linear systems, integration, modeling, and programming
  • Security and Data Integrity
    We implement robust security protocols to ensure your data is always safe and confidential.
  • Task-Specific Customization:
    Our platform adjusts its analytical approach based on the parameters and goals of your experiment. The tasks and issues set by the customer are the central aspect for our developers.
  • User-Centric Flexibility
    We are in constant, open dialogue with biochemists and laboratory researchers—engaging directly with the scientific community to understand the true pain points faced in modern research labs.
  • Supports Diverse Experimental Setups
    Our algorithms allow us to set such experimental parameters as temperature, salt concentration, and denaturant.

Leave your request and our specialists will contact you shortly on all issues

|

Meet the group, explore the school, and get a free consultation
I have a question about the study of molecules
list of molecules:
I would like to study the following properties of these molecules
List of properties:
Made on
Tilda