_2025_06_17_14_16_55.jpg&w=3840&q=100)
UP researchers use AI models to predict antimicrobial resistance
Researchers from the University of the Philippines have tapped artificial intelligence to predict antimicrobial resistance, particularly in agricultural environments.
UP researchers used Escherichia coli (E. coli) for testing antimicrobial resistance since it can easily develop resistance to antibiotics.
E. coli is a common bacterium that inhabits the intestines of animals and humans and is often used to identify fecal contamination.
UP researchers tested AI prediction models to determine the antimicrobial resistance of E. coli using genetic data and laboratory test results from the National Center for Biotechnology Information (NCBI) database.
These AI models are Random Forest (RF), Support Vector Machine (SVM), and two ensemble methods—Adaptive Boosting (AB) and Extreme Gradient Boosting (XGB).
'We selected the models based on their strengths in handling biological and imbalanced data,' said Dr. Pierangeli Vital of UP Diliman College of Science's Natural Sciences Research Institute.
'These models were chosen to compare performance across different learning strategies and to identify which is most suitable for predicting antibiotic resistance,' she added.
The study showed that the AI models most accurately predicted resistance to streptomycin and tetracycline, both types of antibiotics.
However, ciprofloxacin, another type of antibiotic, was the most challenging to predict due to the limited number of resistant samples in the data (only 4%), which led to difficulty in identifying resistance and poor sensitivity.
The study noted that AB and XGB consistently delivered good results, even when tested on imbalanced antimicrobial resistance data.
'We think that this strategy has great potential for real-time monitoring of antimicrobial resistance, particularly in agriculture,' Vital said.
'As DNA sequencing becomes faster and cheaper, prediction models such as ours can pick up resistant bacteria early—before they lead to outbreaks. This can facilitate better decision-making in food safety, agriculture, and public health programs,' she added.
The researchers recommend including more diverse sample types and data sources to better understand and predict how bacteria develop resistance.
The study titled 'Prediction models for the antimicrobial resistance of Escherichia coli in an agricultural setting around Metro Manila, Philippines' was published in the Malaysian Journal of Microbiology. —VBL, GMA Integrated News
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
GMA Network
3 days ago
- GMA Network
Smuggled onions in Paco market tested positive for E.coli —DA
The Department of Agriculture (DA) on Wednesday warned the public against buying smuggled or illegally imported onions after samples collected last week from the Paco Public Market in Manila tested positive for E. coli bacteria. 'This is a food safety issue and a clear threat to public health,' Agriculture Secretary Francisco Tiu Laurel Jr. said in a statement. 'We will order the confiscation of those onions as required under the Food Safety Act of 2013,' he added. Bureau of Plant Industry (BPI) Director Gerald Glenn Panganiban said he has formally informed the Manila local government unit about the test results from the Paco market samples, which indicated possible fecal contamination and poor sanitation in the handling and processing of the red onions. According to Mayo Clinic, E. coli can cause diarrhea, nausea, and vomiting. These symptoms may appear three or four days after exposure to the bacteria. 'To protect the public and consumers from food-borne illnesses and unsanitary conditions, we recommend the confiscation of the said commodities,' Panganiban wrote in his letter to the Manila LGU. The DA has not issued any permits for onion imports, in line with President Ferdinand Marcos Jr.'s directive to safeguard local farmers, who have just completed their harvest. Tiu Laurel also instructed the BPI and other DA units monitoring public markets to be on alert for suspected smuggled onions and to immediately submit any samples for testing. Last week, Tiu Laurel asked the assistance of the Philippine National Police in gathering intelligence to apprehend onion smugglers. Meanwhile, a separate shipment of 25 metric tons of red onions, intercepted by the BPI and the Bureau of Customs (BOC) at the Mindanao International Container Terminal in Misamis Oriental, will also be tested for contaminants—including heavy metals, pesticide residues, and harmful bacteria. The DA will ask the BOC to turn them over for government redistribution if they are determined to be safe for consumption. — VBL, GMA Integrated News
GMA Network
19-06-2025
- GMA Network
PH-Japan educational ties strengthen 'Golden Age' relations — envoy
Japan underscored the significance of educational cooperation in strengthening the "Golden Age" of bilateral relations with the Philippines. In a press release issued on Thursday, Japanese Ambassador to the Philippines Endo Kazuya said a deeper educational partnership between Manila and Tokyo advances and strengthens their "Golden Age" of bilateral relations. Kazuya also stressed that such collaboration could establish long-term trust and people-to-people connections, which will later support the nation's lasting diplomatic ties. Japan is currently engaged in a number of educational partnerships with the Philippines including trainings, scholarship grants, and student exchanges. Last year, the Department of Education (DepEd) partnered with a Japanese company in a bid to improve the math proficiency of public school learners. The DepEd signed a memorandum of agreement with Japan-based firm Sprix, Inc. to provide public school students free access to the Test of Fundamental Skills (TOFAS). According to DepEd, TOFAS allows teachers to assess students' calculation and problem-solving skills "accurately, providing valuable data to tailor instruction according to each student's needs." To recall, Kazuya welcomed distinguished Japan Studies professors from the University of the Philippines (UP) in April, and De La Salle University (DLSU) and Ateneo de Manila University (ADMU) in May to his residence in Makati City. Among those who visited him include UP Asian Center Professor Dr. Matthew M. Santamaria, Associate Professor Dr. Jocelyn Celero, Assistant Professor Dr. Karl Ian U. Cheng Chua, retired professor and former Center for International Studies (CIS) director Dr. Cynthia Neri Zayas, and UP CIS Professor Dr. Amparo Adelina Umali III. In a separate meeting, Kazuya also met with DLSU's Department of International Studies Professor Dr. Dennis Trinidad, Associate Professor Dr. Ron Bridget Vilog and ADMU's Japanese Studies Program, Assistant Professors Dr. Kristine Michelle L. Santos and Dr. Hiroko Nagai-Yabut. Also on Thursday, Ferdinand "Bongbong" Marcos Jr. flew to Osaka, Japan for a working visit. Last April, Japan said the opening of its new visa processing center in Manila shows the deeper people-to-people relations between the Philippines and Japan. The event was hailed as an "indicator and proof" of the "Golden Age" of the two countries' relations. — VDV, GMA Integrated News
GMA Network
17-06-2025
- GMA Network
UP researchers use AI models to predict antimicrobial resistance
Researchers from the University of the Philippines have tapped artificial intelligence to predict antimicrobial resistance, particularly in agricultural environments. UP researchers used Escherichia coli (E. coli) for testing antimicrobial resistance since it can easily develop resistance to antibiotics. E. coli is a common bacterium that inhabits the intestines of animals and humans and is often used to identify fecal contamination. UP researchers tested AI prediction models to determine the antimicrobial resistance of E. coli using genetic data and laboratory test results from the National Center for Biotechnology Information (NCBI) database. These AI models are Random Forest (RF), Support Vector Machine (SVM), and two ensemble methods—Adaptive Boosting (AB) and Extreme Gradient Boosting (XGB). 'We selected the models based on their strengths in handling biological and imbalanced data,' said Dr. Pierangeli Vital of UP Diliman College of Science's Natural Sciences Research Institute. 'These models were chosen to compare performance across different learning strategies and to identify which is most suitable for predicting antibiotic resistance,' she added. The study showed that the AI models most accurately predicted resistance to streptomycin and tetracycline, both types of antibiotics. However, ciprofloxacin, another type of antibiotic, was the most challenging to predict due to the limited number of resistant samples in the data (only 4%), which led to difficulty in identifying resistance and poor sensitivity. The study noted that AB and XGB consistently delivered good results, even when tested on imbalanced antimicrobial resistance data. 'We think that this strategy has great potential for real-time monitoring of antimicrobial resistance, particularly in agriculture,' Vital said. 'As DNA sequencing becomes faster and cheaper, prediction models such as ours can pick up resistant bacteria early—before they lead to outbreaks. This can facilitate better decision-making in food safety, agriculture, and public health programs,' she added. The researchers recommend including more diverse sample types and data sources to better understand and predict how bacteria develop resistance. The study titled 'Prediction models for the antimicrobial resistance of Escherichia coli in an agricultural setting around Metro Manila, Philippines' was published in the Malaysian Journal of Microbiology. —VBL, GMA Integrated News
