This article was published as a part of the Data Science Blogathon.
Introduction
In the current scenario of the pandemic COVID-19 situation, biopharmaceuticals is an emerging and demanding field of life science, and data science is equally another popular discipline. Abundant literature is available on data science and biopharmaceutical industries with their achievements for public health benefits. Despite that, the author emphasizes using data science skills in developing problem-solving tools in the biopharmaceutical industry. Because there is litter literature available on combined studies on data science and the biopharmaceutical industry. This article provides a new opportunity for academic and industrial professionals about the newly combined discipline of data science and biopharmaceutical. The professionals may develop new applications by applying data science as a tool in biopharmaceutical industries.
A Brief Account of Data Science and Biopharmaceutical
Presently, data science uses as a tool for the collection, preparation, analysis, visualization, management, and preservation of an abundant amount of information in the form of data. Data science is the only way to extract knowledge and insights from structured/unstructured data by employing various scientific methods, processes, algorithms, and systems in an automated manner. Data science is a progressive, sequential, and upward tool to solve task-specific problems described in figure 1.
Data scientists are acquainted with statistical and computational competencies, paired with domain knowledge, to analyze and interpret raw data and assist in decision-making. In the current scenario, data science is an interdisciplinary field. Due to this interdisciplinary collaborative work, the new discipline has a broad range of applications in the academic (Medical, Biomedical, Physics, Chemistry, & Biology) and industries (Biotechnology, Clinical, and Biopharmaceuticals). A formula created for a better understanding of the interdisciplinary collaboration work with novel and innovative applications as described below:
Graduate, Master’s, and doctoral degree qualified professionals in Biology, Medical science, Biomedical science, Biotechnology, Microbiology, Biochemistry, Bio-static, Biophysics, Vaccine biology, Pharmaceutical science, and Healthcare. They are actively engaged in the industrial production of life-saving drugs, preventive medicines, and therapeutic drugs & vaccines for human purposes. Author stamps that biopharmaceutical industries play a dynamic role in this field of health care for humans and animals.
The continued rapid growth in data science, generation of big data sets, and advancement in algorithms have increased the demand for data science tools (such as machine learning, artificial intelligence, etc.) in biopharmaceutical industries. This progress has also triggered a wave of start-ups that employ artificial intelligence for drug discovery, most of them using it to identify patterns hidden in large volumes of data. On 30th May 2018, Nic Fleming reported in Nature journal that machine learning and other technologies are expected to begin a hunt for new pharmaceuticals quicker, cheaper, and more effective, especially in drug discovery research.
I have selected one article as an example for better discussion and understanding purpose. On 09th July 2020, Huang published a research article on “Drug Discovery with Deep Learning, Under 10 Lines of Codes” and presented an example mentioned below:
For example, An application and code-base example are described with two objectives for ease of understanding the purpose.
Objective 1 – Repurposing/Screening from a set of antiviral drugs for a COVID-19 target 3CL protease.
Data – Corresponding data in the data set as given below:
Output–Automatic generated list of the drug candidate in printout form.
Objective 2 – virtual screening on a sample of data from the BindingDB data set and then using the virtual_screening function to generate a list of drug-target pairs with high binding affinities.
Data – Corresponding data in the data set as given below:
If no drug/target names are selected, the list of the drug/target is used instead of the expected result. A similar-looking ranked list would generate.
Applications of Data Science in Industries
Data science is a well-established field and plays a crucial role in different industries because each industry has unprocessed, un-utilized, and unstructured/semi-structured data. According to a study, 2.5 quintillion bytes of data has generated in a single day. There is a need to process the massive amount of the data for information in systematic algorithms. The data should be used and then analyzed to develop new findings and applications to nourish the industrial outcome. In the present situation, data science is the only way of utilizing data and developing possible applications through applying data analysis for structure, statistical and mathematical techniques on collected data to detect underlying patterns and make predictions. Data science professionals can improve efficiency and control risks in the industries and are also crucial in the cost cuttings. Apart from this, the professional can help in various ways like Data Architect, Applications Architect, Infrastructure Architect, Enterprise Architect, Data Analyst, and Scientist.
Data science professionals should be acquainted with a broad range of qualities, which may be helpful in different industries. Therefore, the professionals have more chances to get a job in various industries for their services and job responsibilities described in table 1.
Table 1: Jobs of data science professionals in Industries
| S. No. |
Jobs of data science professionals in Industries |
| 1 | Banking services |
| 2 | Financial services |
| 3 | Energy and Utilities |
| 4 | Pharmaceuticals and Healthcare |
| 5 | E-commerce |
| 6 | Media and Entertainment |
| 7 | Telecommunication |
| 8 | Automobile |
| 9 | Retail |
| 10 | Travels |
| 11 | Hospitality |
Out of these industries, the only healthcare industry has been selected and discussed for this article. Based on available literature on various website portals, it has been proved that data science has been used to extract information from daily data generated in healthcare institutions and industries. The healthcare industry is being used the data science as a tool for exploiting data for decision-making and meaningful information as data science applications in healthcare like Medical Image Analytics, Quantified Health, Data Science for Post-care Monitoring, Diagnosis, and Disease Prevention, Data Science for Drug Discovery, Natural Language Processing (NLP) for Electronic Health Records, and Bio-metrics in Healthcare.
Data Science Tools in the Biopharmaceutical Industries
Literature is available on data science and biopharmaceutical product-based industries on the internet, which can be asses through available search engines. The biopharmaceutical field is directly concerned with public health and human or animal life. Based on available literature on the internet, data science is a need of various sectors of the biopharmaceutical industry, summarized in table 2.
Table 2: Top sectors of data science
| S. No. | Engaged sectors |
| 1 | Media & Entertainment |
| 2 | Healthcare |
| 3 | Retail |
| 4 | Telecommunications |
| 5 | Automotive |
| 6 | Digital Marketing |
| 7 | Professional Services |
After that, researchers concluded that data science could play a crucial role in developing novel and innovative application-based tools for professionals in biopharmaceutical industries. In the current situation, data science has required qualities for application in pharmaceutical industries like drug discovery, marketing and sales, and gene editing. Apart from that author summarized here other possible ways where data science may play a significant role in the industries as point-wise described in table 3.
Table 3: Investigated points list for application of data science in biopharmaceuticals industries
| S. No. | Application of data science in biopharmaceuticals industries |
| 1 | Generation, management, and preservation of the parameter-base data and the process-based data for further use |
| 2 | Analyze the data inter-and intra-parameters. |
| 3 | Retrieve and analyze the laboratory quality management system. |
| 4 | Optimization and standardization of the production. Production process steps through preserving data in the database. |
| 5 | Validation of the process steps based on available data set of the specific instrument or equipment used in the industries |
| 6 | Management of the data generated from clinical trials |
| 7 | Preserved data use and analysis parameter-wise / process-wise / product-wise / other requirement basis. |
| 8 | Inventory Management and Demand forecasting. |
| 9 | Predictive analytics or Real-time data of performance and quality. |
| 10 | Preventive maintenance and fault prediction. |
| 11 | Price optimization. |
| 12 | Optimization of the supply chain. |
| 13 | Designing and development of the product. |
| 14 | Automation and Robotization in the factory. |
| 15 | Efficiency and Computer Vision Applications. |
| 16 | Work required to investigate the other aspects |
The points mentioned above are not the limits of data science applications as a tool in the industries. I attended one webinar on “The Blueprint for Enterprise Data Management in Life Sciences” in March 2022. In this event, the expert mentioned that the top 10 global life sciences companies are spending more than $100 million per year to harness healthcare data with implications for discovery, clinical development, and commercialization. This investment helps in the complexity of managing data security, governance, and compliance to streamline global operations and digital transformation efforts. Apart from that author has gone through various websites to find out about the biopharmaceuticals industries, where data science will use to develop applications and utilized as a problem-solving tool in the industry. Out of this, I am summarizing only the top five industrial examples in below table 4.
Table 4: Description of the top five biopharmaceuticals industries in data science
| S. No. | Field of data science | Company name and application in biopharmaceuticals industries |
| 1 | Artificial Intelligence (AI) | M/s Pfizer – For the advancement in Precision Oncology using AI and real-world data. |
| 2 | Artificial Intelligence (AI) | M/s Janssen Pharmaceutica – An AI-powered used to develop a new drug design system |
| 3 | Artificial Intelligence (AI) | M/s Sanofi – Automation in medical literature review with minimum time (01 Second per article). |
| 4 | Artificial Intelligence (AI) | M/s Novartis – Establishment of a new AI Empowerment lab for leveraging data and Artificial Intelligence to transform the developed medicines discovered, developed, and commercialised. |
| 5 | Artificial Intelligence (AI) | M/s Bayer – Digital transformation with digital technologies like AI in Research and Development to make simple, effective, and speed up the discovery and development of new drugs for patients to treat noncommunicable diseases like cardiovascular and oncological diseases |
Data science has a broad range of tools, which can help in various ways to the biopharmaceuticals industries like Artificial Intelligence (AI), Machine Learning (ML), etc. The selection of the tool depends on a data source, data nature, data source, and output needed from the data. Presently, the following data sources require the attention of data science in biopharmaceuticals industries as described below:
1. Collection of patient data through electronic health and medical records.
2. Capturing information from customer feedback, patient disease monitoring, and device assistance from social media.
3. Real-time data collection of medical devices and sensors from patients related to disease progression.
4. Medicines records indicate the difference between prescribed and the purchase by the patient to find out the adverse events.
5. Sequencing data of genomics and proteomics.
6. Data from medical imaging of patients.
7. Data from epidemiological studies.
Conclusion
Biopharmaceutical and Data Science are the fastest growing and most demanding industries due to their need, problem-solving, and knowledge gaps. The author wants to torch new integration and combination of these two disciplines. At present, there is no integrated course between these two disciplines. Based on available literature on different web portals, there is a need to carry out studies related to problem-solving and application development for biopharmaceutical industries by scientists. The scientists work in data science and biopharmaceutical domains, and they can work jointly and develop data science tools for biopharmaceutical industries. Both professionals have an independent role in developing the data science tool for the biopharmaceutical industry. The biopharmaceutical professionals will work on the identification of the problem-based gaps. After that, the data scientists will start working to develop suitable, reliable, and specific problem-solving tools with their application for filling the gaps. At the end of this article, the author strongly recommends that the new combined disciplines will play a crucial role in filling the gaps and demands of biopharmaceutical industries through newly developed data science tools for novel applications as a new beginning.
The author expects the readers to enjoy the article and nourish their knowledge domain. I am happy if any reader will get motivated to start work in this field after reading the article, and I am always open to discussing the content of this article.
Please contact for a discussion on my e.mail ID: [email protected].
The media shown in this article is not owned by Analytics Vidhya and is used at the Author’s discretion.
