An Update: Artificial intelligence in Pharmaceutical/Chemical Process Development, Manufacturing & Net Zero [Post of March, 31, 2023]

In recent years talk of AI (artificial intelligence) ^(1,2) has picked up speed and progressively been touted as the methodology/technology to go to for new products, manufacturing process technology development, quality, supply chain, and inventory management etc. for the active pharmaceutical ingredients (API) and fine/specialty chemicals. When fully developed and incorporated, it is suggested and expected to be the salvation of almost every current shortcoming. I have not heard much about the use of AI based applications in the pharmaceutical products and fine specialty chemicals, if it is happening. 

 

This post is an update on my last post on the subject ⁽³⁾. There is no financial relationship with any “for profit” and non-profit” organization. We all know that API and fine/specialty chemicals are organic chemicals that have similar skeletal structures and manufacturing processes. The only difference is that one set enhance life style and the other extends/prolongs life. Many are suggesting value of AI in the new pharmaceuticals discovery and/or their manufacturing. I wonder how much of own monies has been invested or spent in R&D and manufacturing by who are suggesting the perceived/resulting benefits. Are there verifiable examples? If any of the pharmaceutical companies are exploring AI applications, they are not being discussed in open forums. 

 

Application/inclusion of AI in pharmaceuticals is possible and it can happen by taking one step at a time. Since the pharmaceutical manufacturing is regulated, my conjecture is that what all is being practiced today and is in the pipeline will not change for the brand as well as the generic drugs. Related expense is too high and no business is going to absorb it and/or pass it on to the patients. Potential application of AI to process quality and manufacturing process control is suggestive that our universities have done an inadequate job of training process designers. Every AI proposed manufacturing specific application will have to be ROI justified and tested especially if it impacts manufacturing. Regulatory approval could be a deterrent. 

 

New Product/Drug Identification: 

AI based new drug product scouting for a disease is a possibility. Someone has to pay for the effort. No one knows the time or the investment AI route will take. Time and expense for AI based effort has to be lower that the current effort. Someone will have to take a leap of faith. If it takes same as the current time and money, AI based effort will fizzle out. 

 

Product Manufacturing Process:

 

Once a potential product is suggested/selected by AI or a current method, the real task of taking the identified product to commercialization begins. If the companies stay with their current practices and methods ⁽⁴⁾ nothing will change and companies will not achieve Net ZERO ⁽⁵⁾. AI recommended methods will have to be better and economic.  

 

I thought it would be a great idea to ask ChatGPT ⁽¹⁾ what does it know about sociochemicology ^(5,6,7). It could not give any answer. On sharing a video link ⁽⁶⁾ that briefly explains sociochemicology, it was very quick to understand and share its value in development of efficient chemical processes and achieving “Net Zero ⁽⁵⁾ ” in pharmaceutical and specialty chemicals. Its search capabilities are impressive.

 

I decided to check out what AI can suggest for process chemistry and manufacturing routes for few chemicals I am very familiar with. I tested ChatGPT ⁽¹⁾ and Perplexity ⁽²⁾ by asking my credentials. “Results were interesting. They accurately identified few things but could not give details. I was told by others that AI it is constantly learning and it becomes better by answering questions. I asked additional questions and it cited some of my work.  

 

I queried ChatGPT ⁽¹⁾ about the following chemicals.

 

Saccharin:

 

I asked ChatGPT ⁽¹⁾ about the manufacture of saccharin. It gave me a process practiced by Monsanto which was abandoned in late sixties. When reminded that there is an alternate process starting with phthalic anhydride, it gave me its process details. It was significantly different and complex chemistry compared to what we practiced which was phthalic anhydride based also. It surprised me as I was involved with scale-up and manufacture of our chemistry, a continuous process that operated year round with scheduled shut downs for maintenance etc.. 

 

Omeprazole:

 

I asked about Omeprazole chemistry. ChatGPT ⁽¹⁾ does not suggest how to execute the its chemistry. Chemistry outlined in USP 7,227,024 ^(8,9) is an alternate process. Compared to ChatGPT ⁽¹⁾ suggested process ‘024 based process’s execution is very simple and can be produced using a continuous process. It includes some of the sociochemicology ^(6,7) based teachings. 

 

Metformin Hydrochloride:

 

ChatGPT ⁽¹⁾ suggests a process chemistry. It does not suggest its manufacturing process. A quick review of this chemistry suggests it can be a challenge to commercialize. An alternate chemistry and method ^{(10, 12)} suggest a safer continuous manufacturing processing. 

 

AI suggested chemistries for the above three products are not economic as better and economic processes were/are commercial. Use of sociochemicology ^(6,7) is profusely incorporated in each of the above actual and suggested processes ^(8,9,10,12) . 

 

Future Path:

 

Considering pharma’s current commercialization and manufacturing practices, about 60+ years old ^{(10, 11, 12)}, each of the following that could be AI based will have to be considered and evaluated for their economic and commercial merit. 

 

·       If the drug discovery is going to take same/similar time like the current time and path, my speculation is that all the euphoria and the related investment in AI could be lost. It can provide chemistries for the identified product but I am not sure it can generate and economic processes. This observation is based on the three chemistries I inquired about. Would AI be able to suggest the most optimum chemistry and manufacturing processes for the new molecules is not known? Even if it does, each would need a thorough review and it will have to be tested.  

 

·       For inclusion of AI each company will have to decide its commercial details e.g. business model, economics, investment, operating strategies etc.. One would expect that village’s (chemists, chemical engineers, purchasing, maintenance, accounting) journey to “net Zero” ^{(6, 12,13)} would begin when a chemical molecule is identified and/or speculated as a potential drug candidate. If a pharma company decides to fit the process in its available equipment ⁽⁴⁾, its manufacturing methods will stay 60+ years old ^{(10, 11, 12, 13)} and it will not achieve “net zero ⁽⁵⁾”. 

 

·       If companies want economic “net zero” ⁽⁵⁾ processes they will have to exploit mutual behavior of chemicals, sociochemicology ^{(6, 7)} and Real Information/Intelligence (RI) ^{(5, 6, 7, 10, 11, 12, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23)} and exploit capabilities of the processing equipment that are available and being used in other manufacturing industries ⁽⁵⁾. It is interesting to note that each process chemistry tells us about the chemicals used and produced. Their sociochemicological behavior can be capitalize on to create excellent manufacturing processes ^{(10, 11, 12, 23)}. It seems somehow pharma industry has not been capitalizing on this information. Their inclusion and consideration along with use of modular processes ^{(10, 11, 12, 23)} can deliver excellent Net Zero ⁽⁵⁾ processes.  

·       Many are suggesting application of AI for e.g. inventory control, quality control, manufacturing efficiencies, process control and supply chain etc. in pharma. It is difficult to postulate the impact of new applications. I don’t know whether if any of the AI based application suggesters have invested their own money to test their applications in pharma’s current manufacturing operations and received regulatory approval. Considering regulatory challenges this could be hard. 

If pharma companies decide to bring their manufacturing from antiquity to today and move forward, AI might be of value. However, each company will have to decide their incorporation based on cost, value and regulatory interference. Let us see where does AI lead pharma in the next two years. It would be worth re-visiting the topic.  

 

Girish Malhotra, PE

 

EPCOT International

 

1.     ChatGPT https://chatgpt.com

2.     Perplexity https://www.perplexity.ai

3.     Malhotra, Girish: Artificial intelligence in Chemical Process Development, Manufacturing & Net Zero, Profitability through Simplicity, March 31, 2023

4.     Malhotra, Girish: Square Plug In A Round Hole: Does This Scenario Exist in Pharmaceuticals? Profitability through Simplicity, August 17, 2010 

5.     Malhotra, Girish: NET ZERO for Active Pharmaceutical Ingredient & Fine/Specialty Chemicals: Nondestructive Creation, Profitability through Simplicity, November 7, 2024

6.     Malhotra, Girish: Sociochemicology , May 30, 2013

7.     Malhotra, Girish: Focus on Physical Properties To Improve Processes: Chemical Engineering, Vol. 119 No. 4 April 2012, pgs. 63-66

8.     Malhotra, Girish: Alphabet Shuffle: Moving From QbA to QbD - An Example of Continuous Processing, Pharmaceutical Processing, February 2009 pg. 12-13

9.     Malhotra, Girish: Analysis of API (Omeprazole): My perspective, Poster Session: Pharmaceutical AIChE Annual Meeting, November 11, 2009, Nashville, TN

10.   Malhotra, Girish: Chemical Process Simplification: Improving Productivity and Sustainability John Wiley & Sons, February 2011 

11.   Malhotra, Girish: Chapter 4 “Simplified Process Development and Commercialization” in “ Quality by Design-Putting Theory into Practice” co-published by Parenteral Drug Association and DHI Publishing© February 2011

12.   Malhotra, Girish: Active Pharmaceutical Ingredient Manufacturing: Nondestructive Creation De Gruyter April 2022

13.   Schrader, Ulf: McKinsey & Co. Operations can launch blockbuster in pharma, February 16, 2021

14.   Malhotra, Girish: Profitability through Simplicity

15.   Malhotra, Girish: Focus on Physical Properties To Improve Processes: Chemical Engineering, Vol. 119 No. 4 April 2012, pgs. 63-66

16.  Shreve, R. N. Unit Processes in Chemical Engineering, Industrial and Engineering Chemistry,1954, 46, 4, pg., 672, Accessed June 22, 2020. 

17.  McCabe W. L & Smith J. M. Unit Operations of Chemical Engineering McGraw-Hill Book Company Second Edition 1967 

18.  McGraw Hill Chemical engineering Series https://www.book-info.com/series/McGraw-Hill+chemical+engineering+series.mobi.htm

19.  Malhotra, Girish: Process Simplification and Net Zero: Capitalizing on Physical and Chemical Properties of Reactants and Intermediate, Profitability through Simplicity, August 20, 2024

20.  Gasteiger J.: Chemistry in Times of Artificial Intelligence ChemPhysChem 2020, 21, 2233– 2242 Accessed March 21, 2023

21.  Perry, J. H. et.al. Chemical Engineer’s Handbook Fourth Edition: McGraw-Hill Chemical Engineering Series, 1963 

22.  Levenspiel, O: Chemical Reaction Engineering, John Wiley & Sons 1999

23.  Malhotra, Girish: Process Simplification: Is the Best Answer: New Terminologies or the Application of Fundamentals? Profitability through Simplicity, December 14, 2024

Process Simplification and The Art of Exploiting Physical Properties

Chemical additives, petrochemicals, plastics and pharmaceuticals are different reacted forms and formulations of organic (fine/specialty) and inorganic chemicals. We have mastered their use and continue to develop new uses to make our lives easier.

We are also familiar with or can find chemical and physical properties of the chemicals that are used in these applications. However, many of us have not totally understood or mastered their mutual behavior and/or how their mutual behavior can be used/manipulated/modified/exploited to simplify processes, especially the reactive processes. To some extent it is an art that can significantly improve profitability.  

Simpler processes streamline manufacturing. They are sustainable and assist in many other ways e.g. lower costs, higher profit, improve supply chain, give competitive edge through better product quality.

We have to ask ourselves a question “are we exploiting physical and chemical properties to their fullest extent?” If we are not, then the question is why not? Answer is very simple, at least to me. Values and virtues of physical and chemical are taught. However, we generally are not taught how to exploit them. I learnt from my mentors and colleagues. Shortcomings have been discussed in the past ^(1,2,3,4) and in many other publications. If we can understand and manipulate their mutual social behavior “sociochemicology” we should be able to create, design and simplify many of the reactive or formulation processes.

Collectively fault lies with us. Why? When developing a new process we don’t have the time to exploit these properties.

Opportunities are tremendous, however, getting from studying to practicing may not be the simplest. We do practice what we are taught, but not to the extent we could. Traditions also come in the way of exploitation. Most of the time textbook methods and laboratory practices are followed.

Everything has to be done yesterday and the pressure to have the process ready to be scaled up day before yesterday is omnipresent. With such constraints even the best, creative and imaginative chemists and chemical engineers can falter. Processes are commercialized and they may not be the most optimum. Generally such processes are accepted in the chemical industry. Continuous improvement opportunities allow us to better these processes. However, there are applications where commercializing a perfect process that has very stringent tolerances and meet certain regulatory needs are a must. Electronic chemicals and pharmaceuticals fit the higher tolerance regimen with pharmaceuticals due to regulations being even more demanding. Second chances in these areas can cost significant time and money.

Process Development Opportunities:

Process development is done in the laboratory and at times circumstances are not helpful to think BIG. By BIG, I mean how we will deal with commercial quantities of raw materials and intermediates. Our “Imagineering” falters somewhere when we are scaling up from the lab to a commercial process. We pay a price via higher product cost and at times with lack of first time product quality because we have not spent the time needed to create an efficient economic process.

Exploitation and imagineering of physical and chemical properties of the chemicals to create an economic process can be an art which depends on “eye of the designer”. Individual imprints come from our experiences and understanding of unit processes and unit operations.

I have used one of the physical properties as an example to illustrate how we can master/exploit sociochemicalogy to create and commercialize excellent and sustainable processes.

Liquids are Developer’s Best Friend: 

Every chemical comes in its natural state in one of the three forms: gas, solid and liquid.

At room temperature gas cannot be held in hand where as solid and liquid can be handled. When it comes to handling gases in the lab they are a challenge. Liquefied gas handling has use constraints in the lab. They can be a challenge in plants also. Special equipment would be needed if liquefied gas were to be handled. Since many labs are not equipped, gases are dissolved in a liquid and used in process development. Use of ammonia as ammonium hydroxide is an example. Process productivity can be lost when dilute gas solutions are used. Commercial handling of liquefied gases requires special attention and is product volume dependent.

In laboratory, solids are generally dissolved in appropriate solvent and used as a dissolved solution. Depending on solubility at room temperature process productivity can be significantly impacted. On commercial scale if the solid raw material can be used as a melt, it would be ideal, as the process will have high productivity. Again process economics and product demand come into play.

Raw materials, reaction intermediates and products as liquid are easiest to handle. Our ability to recognize the differences in density, mutual solubility, boiling point differences and other physical properties and exploit them to our advantage generally results in an economic and sustainable process ^(4,5,6). Exploitation of physical and chemical properties is not a cookie cutter exercise but is more like a precision surgery for each process, especially for the reactive processes.

There are many chemical reactions that can be commercially done in all liquid phase when the raw materials are solid or gas at room temperature. With sufficient residence time and using fundamental of chemistry and chemical engineering the produced product can be purified to produce global needs from a single plant. Latent advantages of such processes are very high productivity with minimal use of diluting solvents that are necessary in conventional processes. One has to imagine, explore and look. As explained earlier reason and rational for not looking in the lab is that we do not have the necessary equipment to explore such reactions. Many times such opportunities are never explored even after commercial success of such products.

Many books can be written about how sociochemicology of the chemicals can be used and improved to commercial advantage. It is best that such methods be left to the imagination of chemists and chemical engineers. Given a chance they are extremely creative, imaginative and resourceful and the results would magnificent.

Girish Malhotra, PE

EPCOT International

1. Malhotra, Girish: A Radical Approach to Fine/Specialty API Manufacturing, Profitability Through Simplicity January 20, 2010
2. Malhotra, Girish: Focus on Physical Properties To Improve Processes: Chemical Engineering, Vol. 119 No. 4 April 2012, pgs 63-66
3.  Malhotra, Girish: Industry 4.0 (Digitization): Its Benefits to Pharma and Other Chemical Industries, Profitability through Simplicity, November 11, 2016
4.  Malhotra, Girish: Chemical Process Simplification: Improving Productivity and Sustainability, ISBN: 978-0-470-48754-9, January 2011, John Wiley & Sons Inc.
5.  US patents: 3,928,457; 4,945,184; 5,004,839; 3,564,001; 4,363,914
6. McCabe, W. L. and Smith, J.C. Unit Operations of Chemical Engineering, McGraw-Hill, Inc. 1956; 40

Industry 4.0 (Digitization): Its Benefits to Pharma and Other Chemical Industries

Digital transformation ⁽¹⁾, Industry 4.0, is being touted as the manufacturing’s next act and it might as well be. BASF is an aggressive player in the chemical arena. Others are considering their options. McKinsey ⁽²⁾ and PriceWaterhouseCooper ⁽³⁾ are bullish on industries incorporating digital transformation. Virtues of digitization are being discussed. The concept is in its infancy. However, I strongly believe that the chemical industry that includes pharmaceuticals, specialty/fine chemicals, coating, additive, polymers producing companies will benefit significantly from digitization.  

With respect to digitization, my focus is on chemical and physical property information. Benefit of the generated information when diligently used in process development, commercialization and manufacturing could be higher than the EBIDTA suggested in McKinsey report ⁽²⁾.  

I would like to share my perspective of why and how digitization of physical and chemical properties can immensely help process development, scale up and commercialization of every product that is chemicals based. Till Internet came along essentially every supplier company shared physical and chemical properties of the raw materials. If the chemical and physical property data was not readily available much of it could be calculated using thermodynamic principles ^{(4, 5)}. Chemical and physical behavior postulated using thermodynamics had to be reconfirmed at times in the laboratory but was extremely helpful in developing and designing rather quite efficient processes. Solubilities and mutual behavior could be extrapolated. If the mutual behavior of chemicals was not available it was generated in the lab.

Value of the generated data was enormous as it reduced process development and commercialization time. It also assisted in evaluating and considering different process design parameters and operating conditions to create very near an optimum process that produced quality products from the get go. Due to differences in equipment size and behavior, physical and chemical property data assisted in transitioning from laboratory to pilot plant to commercial scale. All of the property data assisted in troubleshooting and optimizing processes.

As the Internet developed companies stopped sharing physical and chemical properties. Companies did offer Material Safety Data Sheets. Contained information was for safety compliance and had minimum information that could be used for process design. In order to get the necessary data for project feasibility one had to reveal and share significant product and process information. There was hesitation on both sides. Lack of reliable and useful physical and chemical properties meant delays in process development and commercialization ⁽⁶⁾.

I still recall Exxon’s Blue Book that we used in process design. Data Book of Hydrocarbons by J.B. Maxwell [D. Van Nostrand Company] based on Exxon’s Blue Book was an excellent source in public domain. In mid sixties Hydrocarbon Processing magazine published physical properties of hydrocarbons. All these were of great value.

If the physical and chemical properties and mutual behavior can be digitized and readily available through a central depository, chemists and chemical engineers would be developing best of the best processes and producing quality products. Doing it right the first time would mean significant financial savings from better processes and elimination of waste that requires remediation investment. Commercialization time would also be reduced. For brand pharma, digitization could mean patent life extension. Generics could consider taking advantage of economies of scale to make many drugs affordable.

Mr. Christoph Schmitz, senior partner at McKinsey ⁽¹⁾ correctly points that the right kind of talent (combination of chemists and chemical engineers and IT) would be needed for digitization. Chemists and chemical engineers would be assisted by IT personnel to digitize the needed data. It is time for everyone associated with any form of chemical producing and handling company to support Industry 4.0.

Digitized data would assist chemists and chemical engineers to develop and commercialize processes that will have comparatively higher process yield and productivity. Processes would be economic and more sustainable that the current processes. Pharmaceutical could become affordable. Global healthcare costs could be lowered.  

I can imagine improving process yield of the active pharmaceutical ingredient by 20% or more, reducing batch cycle time, using a single solvent instead of multiple solvents and producing a single active isomer if the product had two isomers. Additional benefits will come from significant improvements in inventory turns, asset utilization and product quality management.    

Additives, coatings, resins, polymers and petrochemicals will also benefit from digitized data. Global chemical and chemical engineering associations along with universities and government think tanks could join forces to digitize chemical and physical property data. All said and done digitization has value that has been proven over and over again within the companies who have used it. If the benefits more than trillion dollars value ⁽¹⁾ can be realized Digitization, Industry 4.0, is worth the effort.

Girish Malhotra, PE
President

EPCOT International

1. Westervelt, Rob, Digital Transformation, Chemical Week, October 17, 2016 pgs. 17-22
   
   
2. Baur, Cornelius, Wee, and Dominik: Manufacturing’s next act, McKinsey & Co. June 2015, accessed November 3, 2016
   
   

3.     Industry 4.0: Building the digital enterprise, PriceWaterhouseCooper, accessed November 3, 2016
 

4. Dodge, B.F., Chemical Engineering Thermodynamics, McGraw-Hill Book Company, 1944
   
   
5. National Institute of Science and Technology
   
   
6. Malhotra, Girish, Information Challenges for Product, Process Development and Process Design: A Reality Check, Profitability through Simplicity, April 10, 2011