Artificially synthesizing genomes has broad prospects in medical research and industrial strains. From the synthesis of the artificial life JCVI-syn1.0 by Craig Venter's team in 2010, to the rewriting and synthesis of the prokaryotic E. coli genome, and the Sc2.0 project's artificial synthesis of the yeast genome, researchers are constantly advancing in the depth and breadth of genome design and synthesis. However, there are still difficulties in synthesizing specific gene segments, ultimately leading to the inability to complete artificial chromosomes, which limits the application and promotion of artificial genome synthesis technology. To address this issue, the team of Professor Yingjin Yuan from Tianjin University in China has developed an interpretable machine learning framework (Figure 1) that can predict and quantify the difficulty of chromosome synthesis, guiding optimizing chromosome design and synthesis processes. 

The research team designed an efficient feature selection method by analyzing data from many known chromosome fragments and identified six key sequence features that cover energy and structural information during DNA chemical synthesis and assembly. Based on these results, the team developed an eXtreme Gradient Boosting (XGBoost) model that can effectively predict the synthesis difficulties of chromosome fragments. The model achieved an AUC (area under the receiver operating characteristic curves) of 0.895 in cross-validation and an AUC of 0.885 on an independent test set in collaboration with a DNA synthesis company, demonstrating a high accuracy and predictive ability.

The research team proposed a Synthesis difficulty Index (S-index) based on the SHAP algorithm to evaluate and interpret the synthesis difficulties of chromosomes. The study found that there were significant differences in the synthesis difficulties of different chromosomes, and the S-index could quantitatively explain the causes of synthesis difficulties for some gene fragments (Figure 2), providing a basis for chromosome sequence design and synthesis and improving the efficiency and success rate of designer chromosome synthesis. This achievement provides a practical tool for researchers in chromosome engineering and genome rewriting and is expected to provide more comprehensive guidance and support for chromosome design and synthesis. 

“We’re just seeing the tip of the AI iceberg. What’s coming is going to be exciting or terrifying, depending on your perspective.”

Last month, OpenAI launched its newest AI chatbot product, GPT-4. According to OpenAI, the bot, which uses machine learning to generate natural language text, passed the bar exam with a score in the 90^th percentile, passed 13 of 15 AP exams, and got a nearly perfect score on the GRE Verbal test.

Inquiring minds at BYU and 186 other universities wanted to know how OpenAI’s tech would fare on accounting exams. So, they put the original version, ChatGPT, to the test. The researchers say that while it still has work to do in the realm of accounting, it’s a game changer that will change how everyone teaches and learns — for the better.

“When this technology first came out, everyone was worried that students could now use it to cheat,” said lead study author David Wood, a BYU professor of accounting. “But opportunities to cheat have always existed. So for us, we’re trying to focus on what we can do with this technology now that we couldn’t do before to improve the teaching process for faculty and the learning process for students. Testing it out was eye-opening.”

Since its debut in November 2022, ChatGPT has become the fastest-growing technology platform ever, reaching 100 million users in under two months. In response to intense debate about how models like ChatGPT should factor into education, Wood decided to recruit as many professors as possible to see how the AI fared against actual university accounting students.

His co-author recruiting pitch on social media exploded: 327 co-authors from 186 educational institutions in 14 countries participated in the research, contributing 25,181 classroom accounting exam questions. They also recruited undergrad BYU students (including Wood’s daughter, Jessica) to feed another 2,268 textbook test bank questions to ChatGPT. The questions covered accounting information systems (AIS), auditing, financial accounting, managerial accounting, and tax, and varied in difficulty and type (true/false, multiple choice, short answer, etc.).

Although ChatGPT’s performance was impressive, the students performed better. Students scored an overall average of 76.7%, compared to ChatGPT’s score of 47.4%. On 11.3% of questions, ChatGPT scored higher than the student average, doing particularly well on AIS and auditing. But the AI bot did worse on tax, financial, and managerial assessments, possibly because ChatGPT struggled with the mathematical processes required for the latter type.

When it came to question type, ChatGPT did better on true/false questions (68.7% correct) and multiple-choice questions (59.5%), but struggled with short-answer questions (between 28.7% and 39.1%). In general, higher-order questions were harder for ChatGPT to answer. In fact, sometimes ChatGPT would provide authoritative written descriptions for incorrect answers, or answer the same question differently.

“It’s not perfect; you’re not going to be using it for everything,” said Jessica Wood, currently a freshman at BYU. “Trying to learn solely by using ChatGPT is a fool’s errand.”

The researchers also uncovered some other fascinating trends through the study, including:

• ChatGPT doesn’t always recognize when it is doing math and makes nonsensical errors such as adding two numbers in a subtraction problem or dividing numbers incorrectly.
• ChatGPT often provides explanations for its answers, even if they are incorrect. Other times, ChatGPT’s descriptions are accurate, but it will then proceed to select the wrong multiple-choice answer.
• ChatGPT sometimes makes up facts. For example, when providing a reference, it generates a real-looking reference that is completely fabricated. The work and sometimes the authors do not even exist.

That said, authors fully expect GPT-4 to improve exponentially on the accounting questions posed in their study, and the issues mentioned above. What they find most promising is how the chatbot can help improve teaching and learning, including the ability to design and test assignments, or perhaps be used for drafting portions of a project.

“It’s an opportunity to reflect on whether we are teaching value-added information or not,” said study coauthor and fellow BYU accounting professor Melissa Larson. “This is a disruption, and we need to assess where we go from here. Of course, I’m still going to have TAs, but this is going to force us to use them in different ways.”